2022
Santoyo-Ramón, José Antonio
Contribuciones al estudio y análisis de sistemas vestibles de detección de caídas PhD Thesis
Universidad de Málaga, 2022.
@phdthesis{TesiSantoyo22,
title = {Contribuciones al estudio y análisis de sistemas vestibles de detección de caídas},
author = {José Antonio Santoyo-Ramón},
url = {https://riuma.uma.es/xmlui/handle/10630/24216},
year = {2022},
date = {2022-02-11},
address = {Casilari E.},
school = {Universidad de Málaga},
abstract = {Las caídas son la segunda causa mundial de muerte por lesiones accidentales o no intencionales según la Organización Mundial de la Salud. En este contexto, cabe destacar que las personas mayores de
65 años tienen un mayor riesgo de sufrir este tipo de accidentes. Estos datos, unidos al envejecimiento de la población, convierten las caídas en uno de los mayores problemas de salud pública actuales, por tanto, resulta de vital importancia encontrar soluciones que ayuden a paliar los graves problemas originados por estas. El avance de los dispositivos ¿vestibles¿ y su incorporación en nuestro día a día convierte a esta tecnología en una solución interesante para aplicarla al ámbito de estudio de las caídas. En el presente trabajo se realiza un estudio y análisis de sistemas vestibles de detección de caídas, describiendo las diferentes contribuciones científicas aportadas a este campo de manera temática y cronológica. En concreto, se expone en primer lugar la creación de un repositorio público, que incluye movimientos de la vida cotidiana y caídas, con el objetivo de proveer a la comunidad científica de una herramienta con la que poder analizar sistemáticamente diferentes aspectos y técnicas relacionados con la detección. Posteriormente, debido a la aparición de diferentes repositorios en la literatura, se revisan estas bases de datos y se investigan los problemas originados por la heterogeneidad existente y la inexistencia de una normalización a la hora de crear este tipo de datasets. Consecutivamente, se analizan y evalúan diferentes procedimientos de detección de caídas de menor a mayor complejidad, tales como algoritmos de detección de caídas basados en umbrales, algoritmos de aprendizaje automático, tanto de aprendizaje supervisado (considerando las estrategias más comunes de machine learning) como detectores de anomalías, así como técnicas de aprendizaje profundo como las redes neuronales convolucionales, demostrando que existen arquitecturas de clasificación que proporcionan un gran rendimiento a la hora de discernir entre caídas y movimientos cotidianos. Asimismo, se estudia el efecto que provoca la posición y número de sensores utilizados, los estadísticos utilizados como características de entrada de los algoritmos u otros factores como los rasgos físicos de los sujetos que participan en los repositorios, la frecuencia de muestreo o la tipología de los movimientos que se utilizan a la hora de entrenar y testear los algoritmos, así como las prestaciones obtenidas al entrenar y testear con bases de datos cruzadas, esto es, con trazas de movimientos provenientes de repositorios diferentes.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Las caídas son la segunda causa mundial de muerte por lesiones accidentales o no intencionales según la Organización Mundial de la Salud. En este contexto, cabe destacar que las personas mayores de
65 años tienen un mayor riesgo de sufrir este tipo de accidentes. Estos datos, unidos al envejecimiento de la población, convierten las caídas en uno de los mayores problemas de salud pública actuales, por tanto, resulta de vital importancia encontrar soluciones que ayuden a paliar los graves problemas originados por estas. El avance de los dispositivos ¿vestibles¿ y su incorporación en nuestro día a día convierte a esta tecnología en una solución interesante para aplicarla al ámbito de estudio de las caídas. En el presente trabajo se realiza un estudio y análisis de sistemas vestibles de detección de caídas, describiendo las diferentes contribuciones científicas aportadas a este campo de manera temática y cronológica. En concreto, se expone en primer lugar la creación de un repositorio público, que incluye movimientos de la vida cotidiana y caídas, con el objetivo de proveer a la comunidad científica de una herramienta con la que poder analizar sistemáticamente diferentes aspectos y técnicas relacionados con la detección. Posteriormente, debido a la aparición de diferentes repositorios en la literatura, se revisan estas bases de datos y se investigan los problemas originados por la heterogeneidad existente y la inexistencia de una normalización a la hora de crear este tipo de datasets. Consecutivamente, se analizan y evalúan diferentes procedimientos de detección de caídas de menor a mayor complejidad, tales como algoritmos de detección de caídas basados en umbrales, algoritmos de aprendizaje automático, tanto de aprendizaje supervisado (considerando las estrategias más comunes de machine learning) como detectores de anomalías, así como técnicas de aprendizaje profundo como las redes neuronales convolucionales, demostrando que existen arquitecturas de clasificación que proporcionan un gran rendimiento a la hora de discernir entre caídas y movimientos cotidianos. Asimismo, se estudia el efecto que provoca la posición y número de sensores utilizados, los estadísticos utilizados como características de entrada de los algoritmos u otros factores como los rasgos físicos de los sujetos que participan en los repositorios, la frecuencia de muestreo o la tipología de los movimientos que se utilizan a la hora de entrenar y testear los algoritmos, así como las prestaciones obtenidas al entrenar y testear con bases de datos cruzadas, esto es, con trazas de movimientos provenientes de repositorios diferentes.
65 años tienen un mayor riesgo de sufrir este tipo de accidentes. Estos datos, unidos al envejecimiento de la población, convierten las caídas en uno de los mayores problemas de salud pública actuales, por tanto, resulta de vital importancia encontrar soluciones que ayuden a paliar los graves problemas originados por estas. El avance de los dispositivos ¿vestibles¿ y su incorporación en nuestro día a día convierte a esta tecnología en una solución interesante para aplicarla al ámbito de estudio de las caídas. En el presente trabajo se realiza un estudio y análisis de sistemas vestibles de detección de caídas, describiendo las diferentes contribuciones científicas aportadas a este campo de manera temática y cronológica. En concreto, se expone en primer lugar la creación de un repositorio público, que incluye movimientos de la vida cotidiana y caídas, con el objetivo de proveer a la comunidad científica de una herramienta con la que poder analizar sistemáticamente diferentes aspectos y técnicas relacionados con la detección. Posteriormente, debido a la aparición de diferentes repositorios en la literatura, se revisan estas bases de datos y se investigan los problemas originados por la heterogeneidad existente y la inexistencia de una normalización a la hora de crear este tipo de datasets. Consecutivamente, se analizan y evalúan diferentes procedimientos de detección de caídas de menor a mayor complejidad, tales como algoritmos de detección de caídas basados en umbrales, algoritmos de aprendizaje automático, tanto de aprendizaje supervisado (considerando las estrategias más comunes de machine learning) como detectores de anomalías, así como técnicas de aprendizaje profundo como las redes neuronales convolucionales, demostrando que existen arquitecturas de clasificación que proporcionan un gran rendimiento a la hora de discernir entre caídas y movimientos cotidianos. Asimismo, se estudia el efecto que provoca la posición y número de sensores utilizados, los estadísticos utilizados como características de entrada de los algoritmos u otros factores como los rasgos físicos de los sujetos que participan en los repositorios, la frecuencia de muestreo o la tipología de los movimientos que se utilizan a la hora de entrenar y testear los algoritmos, así como las prestaciones obtenidas al entrenar y testear con bases de datos cruzadas, esto es, con trazas de movimientos provenientes de repositorios diferentes.
Picinali, Lorenzo; Katz, Brian FG; Geronazzo, Michele; Majdak, Piotr; Reyes-Lecuona, Arcadio; Vinciarelli, Alessandro
The SONICOM Project: Artificial Intelligence-Driven Immersive Audio, From Personalization to Modeling [Applications Corner] Journal Article
In: IEEE Signal Processing Magazine, vol. 39, no. 6, pp. 85-88, 2022.
@article{9931551,
title = {The SONICOM Project: Artificial Intelligence-Driven Immersive Audio, From Personalization to Modeling [Applications Corner]},
author = {Lorenzo Picinali and Brian FG Katz and Michele Geronazzo and Piotr Majdak and Arcadio Reyes-Lecuona and Alessandro Vinciarelli},
url = {https://ieeexplore.ieee.org/document/9931551},
doi = {10.1109/MSP.2022.3182929},
year = {2022},
date = {2022-01-01},
journal = {IEEE Signal Processing Magazine},
volume = {39},
number = {6},
pages = {85-88},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Santoyo-Ramón, Jose Antonio; Casilari, Eduardo; Cano-Garc’ıa, Jose Manuel
A Cross-Dataset Evaluation of Wearable Fall Detection Systems Proceedings Article
In: Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments, pp. 1–6, Association for Computing Machinery, Corfu, Greece, 2022, ISBN: 9781450396318.
@inproceedings{10.1145/3529190.3529191,
title = {A Cross-Dataset Evaluation of Wearable Fall Detection Systems},
author = {Jose Antonio Santoyo-Ramón and Eduardo Casilari and Jose Manuel Cano-Garc'ıa},
url = {https://doi.org/10.1145/3529190.3529191},
doi = {10.1145/3529190.3529191},
isbn = {9781450396318},
year = {2022},
date = {2022-01-01},
booktitle = {Proceedings of the 15th International Conference on PErvasive Technologies Related to Assistive Environments},
pages = {1–6},
publisher = {Association for Computing Machinery},
address = {Corfu, Greece},
series = {PETRA '22},
abstract = {The popularity of wearables and their seamless integration into our daily lives have transformed these devices into an appealing resource to deploy automatic fall detection systems. During last years, a massive literature on new methods and algorithms for these wearable detectors has been produced. However, in most cases these algorithms are tested against one single (or at best two) datasets containing signals captured from falls and conventional movements. This work evaluates the behavior of a fall detection system based on a convolutional neural network when different public repositories of movements are alternatively used for training and testing the model. After a systematic cross-dataset evaluation involving four well-known datasets, we show the difficulty of extrapolating the results achieved by a certain classifier for a particular database when another dataset is considered. Results seem to indicate that classification methods tend to overlearn the particular conditions (typology of movements, characteristics of the employed sensor, experimental subjects) under which the training samples were generated.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The popularity of wearables and their seamless integration into our daily lives have transformed these devices into an appealing resource to deploy automatic fall detection systems. During last years, a massive literature on new methods and algorithms for these wearable detectors has been produced. However, in most cases these algorithms are tested against one single (or at best two) datasets containing signals captured from falls and conventional movements. This work evaluates the behavior of a fall detection system based on a convolutional neural network when different public repositories of movements are alternatively used for training and testing the model. After a systematic cross-dataset evaluation involving four well-known datasets, we show the difficulty of extrapolating the results achieved by a certain classifier for a particular database when another dataset is considered. Results seem to indicate that classification methods tend to overlearn the particular conditions (typology of movements, characteristics of the employed sensor, experimental subjects) under which the training samples were generated.
Castillo-Sánchez, José-Borja; Casilari, Eduardo; Cano-García, Jose Manuel; González-Parada, Eva; González-Cañete, Francisco J.
A Low-cost Home Monitoring Architecture for Human Activity Recognition Using Smartwatches Proceedings Article
In: 2022 IEEE International Mediterranean Conference on Communications and Networking (MeditCom), pp. 172-177, 2022.
@inproceedings{9928697,
title = {A Low-cost Home Monitoring Architecture for Human Activity Recognition Using Smartwatches},
author = {José-Borja Castillo-Sánchez and Eduardo Casilari and Jose Manuel Cano-García and Eva González-Parada and Francisco J. González-Cañete},
doi = {10.1109/MeditCom55741.2022.9928697},
year = {2022},
date = {2022-01-01},
booktitle = {2022 IEEE International Mediterranean Conference on Communications and Networking (MeditCom)},
pages = {172-177},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Santoyo-Ramón, José Antonio; Casilari, Eduardo; Cano-García, José Manuel
A study of the influence of the sensor sampling frequency on the performance of wearable fall detectors Journal Article
In: Measurement, vol. 193, pp. 110945, 2022, ISSN: 0263-2241.
@article{ANTONIOSANTOYORAMON2022110945,
title = {A study of the influence of the sensor sampling frequency on the performance of wearable fall detectors},
author = {José Antonio Santoyo-Ramón and Eduardo Casilari and José Manuel Cano-García},
url = {https://www.sciencedirect.com/science/article/pii/S0263224122002226},
doi = {https://doi.org/10.1016/j.measurement.2022.110945},
issn = {0263-2241},
year = {2022},
date = {2022-01-01},
journal = {Measurement},
volume = {193},
pages = {110945},
abstract = {Last decade has witnessed a major research interest on wearable fall detection systems. Sampling rate in these detectors strongly affects the power consumption and required complexity of the employed wearables. This study investigates the effect of the sampling frequency on the efficacy of the detection process. For this purpose, we train a convolutional neural network to directly discriminate falls from conventional activities based on the raw acceleration signals captured by a transportable sensor. Then, we analyze the changes in the performance of this classifier when the sampling rate is progressively reduced. In contrast with previous studies, the detector is tested against a wide set of public repositories of benchmarking traces. The quality metrics achieved for the different frequencies and the analysis of the spectrum of the signals reveal that a sampling rate of 20 Hz can be enough to maximize the effectiveness of a fall detector.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Last decade has witnessed a major research interest on wearable fall detection systems. Sampling rate in these detectors strongly affects the power consumption and required complexity of the employed wearables. This study investigates the effect of the sampling frequency on the efficacy of the detection process. For this purpose, we train a convolutional neural network to directly discriminate falls from conventional activities based on the raw acceleration signals captured by a transportable sensor. Then, we analyze the changes in the performance of this classifier when the sampling rate is progressively reduced. In contrast with previous studies, the detector is tested against a wide set of public repositories of benchmarking traces. The quality metrics achieved for the different frequencies and the analysis of the spectrum of the signals reveal that a sampling rate of 20 Hz can be enough to maximize the effectiveness of a fall detector.
Casilari, Eduardo; Silva, Carlos A.
An analytical comparison of datasets of Real-World and simulated falls intended for the evaluation of wearable fall alerting systems Journal Article
In: Measurement, vol. 202, pp. 111843, 2022, ISSN: 0263-2241.
@article{CASILARI2022111843,
title = {An analytical comparison of datasets of Real-World and simulated falls intended for the evaluation of wearable fall alerting systems},
author = {Eduardo Casilari and Carlos A. Silva},
url = {https://www.sciencedirect.com/science/article/pii/S0263224122010429},
doi = {https://doi.org/10.1016/j.measurement.2022.111843},
issn = {0263-2241},
year = {2022},
date = {2022-01-01},
journal = {Measurement},
volume = {202},
pages = {111843},
abstract = {Automatic fall detection is one of the most promising applications of wearables in the field of mobile health. The characterization of the effectiveness of wearable fall detectors is hampered by the inherent difficulty of testing these devices with real-world falls. In fact, practically all the proposals in the literature assess the detection algorithms with ‘scripted’ falls that are simulated in a controlled laboratory environment by a group of volunteers (normally young and healthy participants). Aiming at appraising the adequacy of this method, this work systematically compares the statistical characteristics of the acceleration signals from two databases with real falls and those computed from the simulated falls provided by 18 well-known repositories commonly employed by the related works. The results show noteworthy differences between the dynamics of emulated and real-life falls, which undermines the testing procedures followed to date and forces to rethink the strategies for evaluating wearable fall detectors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Automatic fall detection is one of the most promising applications of wearables in the field of mobile health. The characterization of the effectiveness of wearable fall detectors is hampered by the inherent difficulty of testing these devices with real-world falls. In fact, practically all the proposals in the literature assess the detection algorithms with ‘scripted’ falls that are simulated in a controlled laboratory environment by a group of volunteers (normally young and healthy participants). Aiming at appraising the adequacy of this method, this work systematically compares the statistical characteristics of the acceleration signals from two databases with real falls and those computed from the simulated falls provided by 18 well-known repositories commonly employed by the related works. The results show noteworthy differences between the dynamics of emulated and real-life falls, which undermines the testing procedures followed to date and forces to rethink the strategies for evaluating wearable fall detectors.
Romero-Jerez, Juan M.; Lopez-Martinez, F. Javier; Peña-Martín, Juan P.; Abdi, Ali
Stochastic Fading Channel Models With Multiple Dominant Specular Components Journal Article
In: IEEE Transactions on Vehicular Technology, vol. 71, no. 3, pp. 2229-2239, 2022.
@article{9678061,
title = {Stochastic Fading Channel Models With Multiple Dominant Specular Components},
author = {Juan M. Romero-Jerez and F. Javier Lopez-Martinez and Juan P. Peña-Martín and Ali Abdi},
doi = {10.1109/TVT.2022.3141949},
year = {2022},
date = {2022-01-01},
journal = {IEEE Transactions on Vehicular Technology},
volume = {71},
number = {3},
pages = {2229-2239},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Olyaee, Maryam; Peña-Martín, Juan P.; Lopez-Martinez, F. Javier; Romero-Jerez, Juan M.
Statistical Characterization of the Multicluster Two-Wave Fading Model Proceedings Article
In: 2022 5th International Conference on Advanced Communication Technologies and Networking (CommNet), pp. 1-7, 2022.
@inproceedings{9993838,
title = {Statistical Characterization of the Multicluster Two-Wave Fading Model},
author = {Maryam Olyaee and Juan P. Peña-Martín and F. Javier Lopez-Martinez and Juan M. Romero-Jerez},
doi = {10.1109/CommNet56067.2022.9993838},
year = {2022},
date = {2022-01-01},
booktitle = {2022 5th International Conference on Advanced Communication Technologies and Networking (CommNet)},
pages = {1-7},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
del Carmen Doblas, María; Cáceres-Cansino, Ana Mª; Heredia-Sánchez, Fernando; Peña-Martín, Juan Pedro; García-Berdonés, Carmen; Trujillo-Aguilera, Davinia
Colaboración entre PAS y PDI para el desarrollo de competencias genéricas: primeros resultados y lecciones aprendidas Proceedings Article
In: XXIX Congreso Universitario de Innovación Educativa en las Enseñanzas Técnicas (CUIEET’29), Valencia 19-22 de julio de 2022, pp. 285-290, 2022.
@inproceedings{8108225,
title = {Colaboración entre PAS y PDI para el desarrollo de competencias genéricas: primeros resultados y lecciones aprendidas},
author = {María del Carmen Doblas and Ana Mª Cáceres-Cansino and Fernando Heredia-Sánchez and Juan Pedro Peña-Martín and Carmen García-Berdonés and Davinia Trujillo-Aguilera},
doi = {https://hdl.handle.net/10630/24777},
year = {2022},
date = {2022-01-01},
booktitle = {XXIX Congreso Universitario de Innovación Educativa en las Enseñanzas Técnicas (CUIEET’29), Valencia 19-22 de julio de 2022},
pages = {285-290},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Peña-Martín, Juan P.; García-Berdonés, Carmen; del Carmen Doblas Navarro, Mª; Cansino, Ana Mª Cáceres; Heredia-Sánchez, Fernando; Trujillo-Aguilera, Davinia
Una experiencia para introducir la competencia de Planificación y Gestión del Tiempo en un grado de ingeniería Proceedings Article
In: XXIX Congreso Universitario de Innovación Educativa en las Enseñanzas Técnicas (CUIEET’29), Valencia 19-22 de julio de 2022, pp. 251-256, 2022.
@inproceedings{8108226,
title = {Una experiencia para introducir la competencia de Planificación y Gestión del Tiempo en un grado de ingeniería},
author = {Juan P. Peña-Martín and Carmen García-Berdonés and Mª del Carmen Doblas Navarro and Ana Mª Cáceres Cansino and Fernando Heredia-Sánchez and Davinia Trujillo-Aguilera},
doi = {https://hdl.handle.net/10630/24770},
year = {2022},
date = {2022-01-01},
booktitle = {XXIX Congreso Universitario de Innovación Educativa en las Enseñanzas Técnicas (CUIEET’29), Valencia 19-22 de julio de 2022},
pages = {251-256},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Z., Sharifian; Barekatain,; B., Ariza Quintana
LOADng-AT: a novel practical implementation of hybrid AHP-TOPSIS algorithm in reactive routing protocol for intelligent IoT-based networks Journal Article
In: The Journal of Supercomputing, vol. 78, pp. 9521–9569, 2022, ISSN: 1573-0484.
@article{SHARIFIAN2022,
title = {LOADng-AT: a novel practical implementation of hybrid AHP-TOPSIS algorithm in reactive routing protocol for intelligent IoT-based networks},
author = {Sharifian Z. and Barekatain and Ariza Quintana B.},
url = {https://link.springer.com/article/10.1007/s11227-021-04256-8},
doi = {https://doi.org/10.1007/s11227-021-04256-8},
issn = {1573-0484},
year = {2022},
date = {2022-01-01},
journal = {The Journal of Supercomputing},
volume = {78},
pages = {9521–9569},
abstract = {Despite that IoT technology provides a promising future for human life, some significant challenges such as routing, security, low-cost equipment, energy consumption, privacy, and reliability can considerably affect its performance. In recent studies, routing has been considered as one of the most critical challenges in IoT due to many existing IoT devices in a network. Selecting a non-optimal path increases collision probability and packet latency which sharply reduces the network performance. Hence, a novel flexible, scalable, and efficient routing protocol named LOADng-AT has been introduced in this study to overcome this challenge. Using LOADng-AT, firstly, taking advantage of the hello message, information about link quality parameters up to two hops is exchanged among nodes. This information includes various parameters such as bi-/unidirectional links, ETX, number of neighbors, link stability, received and residual energy, and SINR, gathered by hello message. Secondly, considering those parameters simultaneously, LOADng-AT efficiently chooses the best possible route based on the hybrid AHP-TOPSIS algorithm. The proposed protocol considerably decreases the RREQ broadcast storm. Moreover, it supports an error recovery path without rerunning a new routing process that noticeably decreases the network routing delay. LOADng-AT can be easily adapted to any QoS parameter with very low complexity which is very important for a delay-sensitive IoT-based network. Finally, in case of noisy condition, the proposed protocol can be efficiently used in low-quality links. Simulation results based on several scenarios in the OMNET ++ simulator show that end-to-end delay (EED) and packet delivery ratio (PDR) parameters significantly improved in the proposed method compared to other similar methods. In other words, using LOADng-AT, the mean values of PDR parameter were 98.64 and 82 percent for network sizes 400 × 200 and 800 × 400 m2, respectively, while the mean values of EED were 0.001 and 0.018 for network sizes 400 × 200 and 800 × 400 m2, respectively. The overall improvement for PDR and EED parameters in all 60 considered scenarios compared to similar methods were 82.26 and 16.6 percent, respectively.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Despite that IoT technology provides a promising future for human life, some significant challenges such as routing, security, low-cost equipment, energy consumption, privacy, and reliability can considerably affect its performance. In recent studies, routing has been considered as one of the most critical challenges in IoT due to many existing IoT devices in a network. Selecting a non-optimal path increases collision probability and packet latency which sharply reduces the network performance. Hence, a novel flexible, scalable, and efficient routing protocol named LOADng-AT has been introduced in this study to overcome this challenge. Using LOADng-AT, firstly, taking advantage of the hello message, information about link quality parameters up to two hops is exchanged among nodes. This information includes various parameters such as bi-/unidirectional links, ETX, number of neighbors, link stability, received and residual energy, and SINR, gathered by hello message. Secondly, considering those parameters simultaneously, LOADng-AT efficiently chooses the best possible route based on the hybrid AHP-TOPSIS algorithm. The proposed protocol considerably decreases the RREQ broadcast storm. Moreover, it supports an error recovery path without rerunning a new routing process that noticeably decreases the network routing delay. LOADng-AT can be easily adapted to any QoS parameter with very low complexity which is very important for a delay-sensitive IoT-based network. Finally, in case of noisy condition, the proposed protocol can be efficiently used in low-quality links. Simulation results based on several scenarios in the OMNET ++ simulator show that end-to-end delay (EED) and packet delivery ratio (PDR) parameters significantly improved in the proposed method compared to other similar methods. In other words, using LOADng-AT, the mean values of PDR parameter were 98.64 and 82 percent for network sizes 400 × 200 and 800 × 400 m2, respectively, while the mean values of EED were 0.001 and 0.018 for network sizes 400 × 200 and 800 × 400 m2, respectively. The overall improvement for PDR and EED parameters in all 60 considered scenarios compared to similar methods were 82.26 and 16.6 percent, respectively.
Velasco-Álvarez, Francisco; Fernández-Rodríguez, Álvaro; Ron-Angevin, Ricardo
Brain-computer interface (BCI)-generated speech to control domotic devices Journal Article
In: Neurocomputing, vol. 509, pp. 121 – 136, 2022, ISSN: 09252312.
@article{Velasco-Álvarez2022121,
title = {Brain-computer interface (BCI)-generated speech to control domotic devices},
author = {Francisco Velasco-Álvarez and Álvaro Fernández-Rodríguez and Ricardo Ron-Angevin},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136557263&doi=10.1016%2fj.neucom.2022.08.068&partnerID=40&md5=fba9dd6b2ed7f2cb922271d1c20d8d7b},
doi = {10.1016/j.neucom.2022.08.068},
issn = {09252312},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Neurocomputing},
volume = {509},
pages = {121 – 136},
publisher = {Elsevier B.V.},
abstract = {A brain-computer interface (BCI) is a type of technology that establishes a communication channel between a user and certain devices in the environment via the brain signals of the user. The UMA-BCI Speller tool allows for easy configuration of a BCI, permitting it to be manipulated without the need for much technical knowledge. However, adapting a BCI system so that it can communicate with devices is a challenging task. A simpler technology that is increasingly used to enable communication with devices in the environment is based on voice commands. The aim of the present work is therefore to create a system to facilitate communication between a BCI and devices in the environment using voice commands. Twelve healthy participants and three amyotrophic lateral sclerosis (ALS) patients were asked to control a BCI home automation system. The devices to be controlled were a television, an air conditioner, a smart light bulb, a smart plug, and the WhatsApp and Spotify apps. Performance measures were recorded, and subjective measures were collected based on the System usability scale, NASA-TLX and ad hoc questionnaires. The results of this study validate the proposed system as a suitable option to facilitate communication between a BCI and commercial devices that have been previously adapted to operate based on voice commands. © 2022 The Authors},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
A brain-computer interface (BCI) is a type of technology that establishes a communication channel between a user and certain devices in the environment via the brain signals of the user. The UMA-BCI Speller tool allows for easy configuration of a BCI, permitting it to be manipulated without the need for much technical knowledge. However, adapting a BCI system so that it can communicate with devices is a challenging task. A simpler technology that is increasingly used to enable communication with devices in the environment is based on voice commands. The aim of the present work is therefore to create a system to facilitate communication between a BCI and devices in the environment using voice commands. Twelve healthy participants and three amyotrophic lateral sclerosis (ALS) patients were asked to control a BCI home automation system. The devices to be controlled were a television, an air conditioner, a smart light bulb, a smart plug, and the WhatsApp and Spotify apps. Performance measures were recorded, and subjective measures were collected based on the System usability scale, NASA-TLX and ad hoc questionnaires. The results of this study validate the proposed system as a suitable option to facilitate communication between a BCI and commercial devices that have been previously adapted to operate based on voice commands. © 2022 The Authors
Fernández-Rodríguez, Álvaro; Darves-Bornoz, Aube; Velasco-Álvarez, Francisco; Ron-Angevin, Ricardo
Effect of Stimulus Size in a Visual ERP-Based BCI under RSVP Journal Article
In: Sensors, vol. 22, no. 23, 2022, ISSN: 14248220.
@article{Fernández-Rodríguez2022,
title = {Effect of Stimulus Size in a Visual ERP-Based BCI under RSVP},
author = {Álvaro Fernández-Rodríguez and Aube Darves-Bornoz and Francisco Velasco-Álvarez and Ricardo Ron-Angevin},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85143730939&doi=10.3390%2fs22239505&partnerID=40&md5=0a44f83566fe3574ffbb67f6f865e9c5},
doi = {10.3390/s22239505},
issn = {14248220},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Sensors},
volume = {22},
number = {23},
publisher = {MDPI},
abstract = {Rapid serial visual presentation (RSVP) is currently one of the most suitable paradigms for use with a visual brain–computer interface based on event-related potentials (ERP-BCI) by patients with a lack of ocular motility. However, gaze-independent paradigms have not been studied as closely as gaze-dependent ones, and variables such as the sizes of the stimuli presented have not yet been explored under RSVP. Hence, the aim of the present work is to assess whether stimulus size has an impact on ERP-BCI performance under the RSVP paradigm. Twelve participants tested the ERP-BCI under RSVP using three different stimulus sizes: small (0.1 × 0.1 cm), medium (1.9 × 1.8 cm), and large (20.05 × 19.9 cm) at 60 cm. The results showed significant differences in accuracy between the conditions; the larger the stimulus, the better the accuracy obtained. It was also shown that these differences were not due to incorrect perception of the stimuli since there was no effect from the size in a perceptual discrimination task. The present work therefore shows that stimulus size has an impact on the performance of an ERP-BCI under RSVP. This finding should be considered by future ERP-BCI proposals aimed at users who need gaze-independent systems. © 2022 by the authors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Rapid serial visual presentation (RSVP) is currently one of the most suitable paradigms for use with a visual brain–computer interface based on event-related potentials (ERP-BCI) by patients with a lack of ocular motility. However, gaze-independent paradigms have not been studied as closely as gaze-dependent ones, and variables such as the sizes of the stimuli presented have not yet been explored under RSVP. Hence, the aim of the present work is to assess whether stimulus size has an impact on ERP-BCI performance under the RSVP paradigm. Twelve participants tested the ERP-BCI under RSVP using three different stimulus sizes: small (0.1 × 0.1 cm), medium (1.9 × 1.8 cm), and large (20.05 × 19.9 cm) at 60 cm. The results showed significant differences in accuracy between the conditions; the larger the stimulus, the better the accuracy obtained. It was also shown that these differences were not due to incorrect perception of the stimuli since there was no effect from the size in a perceptual discrimination task. The present work therefore shows that stimulus size has an impact on the performance of an ERP-BCI under RSVP. This finding should be considered by future ERP-BCI proposals aimed at users who need gaze-independent systems. © 2022 by the authors.
Velasco-Álvarez, Francisco; Fernández-Rodríguez, Álvaro; Ron-Angevin, Ricardo
Home Automation System Controlled Through Brain Activity Proceedings Article
In: Miesenberger, Klaus; Kouroupetroglou, Georgios; Mavrou, Katerina; Manduchi, Roberto; Rodriguez, Mario Covarrubias; Penáz, Petr (Ed.): Computers Helping People with Special Needs, pp. 105–112, Springer International Publishing, Cham, 2022, ISBN: 978-3-031-08645-8.
@inproceedings{10.1007/978-3-031-08645-8_13,
title = {Home Automation System Controlled Through Brain Activity},
author = {Francisco Velasco-Álvarez and Álvaro Fernández-Rodríguez and Ricardo Ron-Angevin},
editor = {Klaus Miesenberger and Georgios Kouroupetroglou and Katerina Mavrou and Roberto Manduchi and Mario Covarrubias Rodriguez and Petr Penáz},
isbn = {978-3-031-08645-8},
year = {2022},
date = {2022-01-01},
booktitle = {Computers Helping People with Special Needs},
pages = {105–112},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Brain-computer interface (BCI) technology allows brain activity to be used as a communication channel without the need for muscle activity. Therefore, this technology could be suitable for patients with severe muscular impairments. However, BCI systems have not been easily adapted to control external devices. Therefore, the aim of the present work is to control a home automation system through a BCI that allows the construction of voice commands. Six healthy users have tested the proposed system. The controlled appliances were: WhatsApp, Spotify, Google Nest, smart light bulb, smart plug (to turn on/off a radio) and an infrared controller (to control a TV and an air conditioner). Participants controlled the system for approximately 32 min, with an accuracy of about 80%. In definitive, it has been successfully demonstrated that the use of a BCI system for home automation control could be implemented in a flexible way and could be adapted to the needs of a user.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Brain-computer interface (BCI) technology allows brain activity to be used as a communication channel without the need for muscle activity. Therefore, this technology could be suitable for patients with severe muscular impairments. However, BCI systems have not been easily adapted to control external devices. Therefore, the aim of the present work is to control a home automation system through a BCI that allows the construction of voice commands. Six healthy users have tested the proposed system. The controlled appliances were: WhatsApp, Spotify, Google Nest, smart light bulb, smart plug (to turn on/off a radio) and an infrared controller (to control a TV and an air conditioner). Participants controlled the system for approximately 32 min, with an accuracy of about 80%. In definitive, it has been successfully demonstrated that the use of a BCI system for home automation control could be implemented in a flexible way and could be adapted to the needs of a user.
Arrebola, F.; Gonzalez-Toledo, D.; Garcia-Jimenez, P; Molina-Tanco, L.; Cuevas-Rodriguez, M.; Reyes-Lecuona, A.
Simulación en tiempo real de las reflexiones tempranas mediante el método de las imágenes Proceedings Article
In: 53 Congreso Español de Acústica -TECNIACUSTICA 2022., 2022.
@inproceedings{arrebola2022simulacion,
title = {Simulación en tiempo real de las reflexiones tempranas mediante el método de las imágenes},
author = {F. Arrebola and D. Gonzalez-Toledo and P Garcia-Jimenez and L. Molina-Tanco and M. Cuevas-Rodriguez and A. Reyes-Lecuona},
url = {https://documentacion.sea-acustica.es/publicaciones/Elche22/ID-99.pdf},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {53 Congreso Español de Acústica -TECNIACUSTICA 2022.},
abstract = {Se presenta una herramienta de código abierto para simular las reflexiones tempranas de una sala mediante el método de las imágenes. Para ello, el orden de reflexión y la distancia máxima de las fuentes espejo son controlables por el usuario. Asimismo, son configurables la geometría y los perfiles de absorción de las paredes. Se trata de una extensión del 3D Tune-In Toolkit, en la que se ha añadido la simulación del retardo de propagación y la implementación del método de las imágenes. Esta simulación de reverberación se puede completar con otros renderizadores mediante una aproximación hibrida.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Se presenta una herramienta de código abierto para simular las reflexiones tempranas de una sala mediante el método de las imágenes. Para ello, el orden de reflexión y la distancia máxima de las fuentes espejo son controlables por el usuario. Asimismo, son configurables la geometría y los perfiles de absorción de las paredes. Se trata de una extensión del 3D Tune-In Toolkit, en la que se ha añadido la simulación del retardo de propagación y la implementación del método de las imágenes. Esta simulación de reverberación se puede completar con otros renderizadores mediante una aproximación hibrida.
Olyaee, Maryam; Romero-Jerez, Juan M; Lopez-Martinez, F Javier; Goldsmith, Andrea J
Alternative Formulations for the Fluctuating Two-Ray Fading Model Journal Article
In: IEEE Transactions on Wireless Communications, vol. 21, no. 11, pp. 9404–9416, 2022.
@article{olyaee2022alternative,
title = {Alternative Formulations for the Fluctuating Two-Ray Fading Model},
author = {Maryam Olyaee and Juan M Romero-Jerez and F Javier Lopez-Martinez and Andrea J Goldsmith},
year = {2022},
date = {2022-01-01},
journal = {IEEE Transactions on Wireless Communications},
volume = {21},
number = {11},
pages = {9404–9416},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Olyaee, Maryam; Cortés, José A; Lopez-Martinez, F Javier; Paris, José F; Romero-Jerez, Juan M
The Fluctuating Two-Ray Fading Model with Independent Specular Components Journal Article
In: IEEE Transactions on Vehicular Technology, vol. 72, no. 5, pp. 5533–5545, 2022.
@article{olyaee2022fluctuating,
title = {The Fluctuating Two-Ray Fading Model with Independent Specular Components},
author = {Maryam Olyaee and José A Cortés and F Javier Lopez-Martinez and José F Paris and Juan M Romero-Jerez},
year = {2022},
date = {2022-01-01},
journal = {IEEE Transactions on Vehicular Technology},
volume = {72},
number = {5},
pages = {5533–5545},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Olyaee, Maryam; Romero-Jerez, Juan M; López-Martínez, F Javier; Goldsmith, Andrea J
Composite IG/FTR channel performance in wireless communication systems Proceedings Article
In: Proc. 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Sep., pp. 1314–1319, 2022.
@inproceedings{olyaee2022composite,
title = {Composite IG/FTR channel performance in wireless communication systems},
author = {Maryam Olyaee and Juan M Romero-Jerez and F Javier López-Martínez and Andrea J Goldsmith},
year = {2022},
date = {2022-01-01},
booktitle = {Proc. 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Sep.},
pages = {1314–1319},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Lopez, Jose J.; Gutierrez-Parera, Pablo; Cobos, Maximo
Compensating first reflections in non-anechoic head-related transfer function measurements Journal Article
In: Applied Acoustics, vol. 188, pp. 108523, 2022, ISSN: 0003-682X.
@article{Lopez2022,
title = {Compensating first reflections in non-anechoic head-related transfer function measurements},
author = {Jose J. Lopez and Pablo Gutierrez-Parera and Maximo Cobos},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0003682X21006174},
doi = {10.1016/j.apacoust.2021.108523},
issn = {0003-682X},
year = {2022},
date = {2022-01-01},
journal = {Applied Acoustics},
volume = {188},
pages = {108523},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cuevas-Rodriguez, Maria
3D Binaural Spatialisation for Virtual Reality and Psychoacoustics PhD Thesis
Universidad de Málaga, 2022.
@phdthesis{TesisMaria,
title = {3D Binaural Spatialisation for Virtual Reality and Psychoacoustics},
author = {Maria Cuevas-Rodriguez},
url = {https://hdl.handle.net/10630/25570},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
publisher = {UMA Editorial},
address = {Reyes-Lecuona, A and Molina-Tanco, L.},
school = {Universidad de Málaga},
abstract = {The 3DTI Toolkit-BS is designed to manage complex, dynamic acoustic scenes that change in real time. Smooth transitions for moving sources and/or listener were developed to avoid audible artefacts. The library has been evaluated with a battery of tests demonstrating its good dynamic behaviour and performance. The applications of the 3DTI Toolkit-BS library are not limited to Virtual Reality; the library aims to become a reference tool for the execution of psychoacoustics experiments, as it brings together in a single tool several techniques and functionalities developed and evaluated of spatial audio research in the last 20 years. The 3DTI Toolkit-BS tool was tested in a psychoacoustics experiment, a study on the influence of non-individual HRTF on speech intelligibility. It is known that HRTF signals have an impact on speech intelligibility in a Cocktail Party scenario (where the listener tries to focus attention on a particular acoustic stimulus, filtering out all other stimuli). In the experiment, the Speech Reception Threshold (SRT) was measured, showing significant global and individual differences between the SRTs measured using different HRTFs. These results confirmed that for these Cocktail Party situations, the choice of HRTF should be carefully considered for each individual.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
The 3DTI Toolkit-BS is designed to manage complex, dynamic acoustic scenes that change in real time. Smooth transitions for moving sources and/or listener were developed to avoid audible artefacts. The library has been evaluated with a battery of tests demonstrating its good dynamic behaviour and performance. The applications of the 3DTI Toolkit-BS library are not limited to Virtual Reality; the library aims to become a reference tool for the execution of psychoacoustics experiments, as it brings together in a single tool several techniques and functionalities developed and evaluated of spatial audio research in the last 20 years. The 3DTI Toolkit-BS tool was tested in a psychoacoustics experiment, a study on the influence of non-individual HRTF on speech intelligibility. It is known that HRTF signals have an impact on speech intelligibility in a Cocktail Party scenario (where the listener tries to focus attention on a particular acoustic stimulus, filtering out all other stimuli). In the experiment, the Speech Reception Threshold (SRT) was measured, showing significant global and individual differences between the SRTs measured using different HRTFs. These results confirmed that for these Cocktail Party situations, the choice of HRTF should be carefully considered for each individual.
2021
Santoyo-Ramón, José Antonio; Casilari, Eduardo; Cano-García, José Manuel
A study on the impact of the users’ characteristics on the performance of wearable fall detection system Journal Article
In: Scientific Reports, vol. 11, no. 23011, 2021, ISSN: 2045-2322.
@article{Ast/2021,
title = {A study on the impact of the users' characteristics on the performance of wearable fall detection system},
author = {José Antonio Santoyo-Ramón and Eduardo Casilari and José Manuel Cano-García},
url = {https://rdcu.be/cB5NF},
doi = {10.1038/s41598-021-02537-z},
issn = {2045-2322},
year = {2021},
date = {2021-11-01},
journal = {Scientific Reports},
volume = {11},
number = {23011},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Santoyo-Ramón, Jose Antonio; Casilari, Eduardo; Cano-García, José Manuel
A Study of One-Class Classification Algorithms for Wearable Fall Sensors Journal Article
In: Biosensors, vol. 11, no. 8, pp. 284, 2021, ISSN: 2079-6374.
@article{Jos/ASt/2021,
title = {A Study of One-Class Classification Algorithms for Wearable Fall Sensors},
author = {Jose Antonio Santoyo-Ramón and Eduardo Casilari and José Manuel Cano-García},
url = {https://www.mdpi.com/2079-6374/11/8/284},
doi = {10.3390/bios11080284},
issn = {2079-6374},
year = {2021},
date = {2021-08-01},
journal = {Biosensors},
volume = {11},
number = {8},
pages = {284},
abstract = {In recent years, the popularity of wearable devices has fostered the investigation of automatic fall detection systems based on the analysis of the signals captured by transportable inertial sensors. Due to the complexity and variety of human movements, the detection algorithms that offer the best performance when discriminating falls from conventional Activities of Daily Living (ADLs) are those built on machine learning and deep learning mechanisms. In this regard, supervised machine learning binary classification methods have been massively employed by the related literature. However, the learning phase of these algorithms requires mobility patterns caused by falls, which are very difficult to obtain in realistic application scenarios. An interesting alternative is offered by One-Class Classifiers (OCCs), which can be exclusively trained and configured with movement traces of a single type (ADLs). In this paper, a systematic study of the performance of various typical OCCs (for diverse sets of input features and hyperparameters) is performed when applied to nine public repositories of falls and ADLs. The results show the potentials of these classifiers, which are capable of achieving performance metrics very similar to those of supervised algorithms (with values for the specificity and the sensitivity higher than 95%). However, the study warns of the need to have a wide variety of types of ADLs when training OCCs, since activities with a high degree of mobility can significantly increase the frequency of false alarms (ADLs identified as falls) if not considered in the data subsets used for training},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In recent years, the popularity of wearable devices has fostered the investigation of automatic fall detection systems based on the analysis of the signals captured by transportable inertial sensors. Due to the complexity and variety of human movements, the detection algorithms that offer the best performance when discriminating falls from conventional Activities of Daily Living (ADLs) are those built on machine learning and deep learning mechanisms. In this regard, supervised machine learning binary classification methods have been massively employed by the related literature. However, the learning phase of these algorithms requires mobility patterns caused by falls, which are very difficult to obtain in realistic application scenarios. An interesting alternative is offered by One-Class Classifiers (OCCs), which can be exclusively trained and configured with movement traces of a single type (ADLs). In this paper, a systematic study of the performance of various typical OCCs (for diverse sets of input features and hyperparameters) is performed when applied to nine public repositories of falls and ADLs. The results show the potentials of these classifiers, which are capable of achieving performance metrics very similar to those of supervised algorithms (with values for the specificity and the sensitivity higher than 95%). However, the study warns of the need to have a wide variety of types of ADLs when training OCCs, since activities with a high degree of mobility can significantly increase the frequency of false alarms (ADLs identified as falls) if not considered in the data subsets used for training
Silva, Carlos A.; García-Bermúdez, Rodolfo; Casilari, Eduardo
Features Selection for Fall Detection Systems Based on Machine Learning and Accelerometer Signals Conference
Advances in Computational Intelligence 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, LNCS Springer Nature Switzerland, 2021.
@conference{Fea/2021,
title = {Features Selection for Fall Detection Systems Based on Machine Learning and Accelerometer Signals},
author = {Carlos A. Silva and Rodolfo García-Bermúdez and Eduardo Casilari},
url = {https://link.springer.com/chapter/10.1007%2F978-3-030-85099-9_31},
doi = {10.1007/978-3-030-85099-9_31},
year = {2021},
date = {2021-06-01},
booktitle = {Advances in Computational Intelligence 16th International Work-Conference on Artificial Neural Networks, IWANN 2021},
pages = {380–391},
publisher = {Springer Nature Switzerland},
series = {LNCS},
abstract = {Fall among older people is a major medical concern. Fall Detection Systems (FDSs) have been actively investigated to solve this problem. In this sense, FDSs must effectively reduce both the rates of false alarms and unnoticed fall. In this work we carry out a systematic evaluation of the performance of one of the most widely used machine learning supervised algorithm (Support Vector Machine) when using different input features. To evaluate the impact of the feature selection, we use Area Under the Curve (AUC) of Receiver Operating Characteristic (ROC) Curve as the performance metric. The results showed that with four features it is possible to obtain acceptable values for the detection of falls using accelerometer signals obtained from the userrqs waist. In addition, we also investigate if the impact of selecting the features based on the analysis of a dataset different from the final application framework where the detector will be operative.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Fall among older people is a major medical concern. Fall Detection Systems (FDSs) have been actively investigated to solve this problem. In this sense, FDSs must effectively reduce both the rates of false alarms and unnoticed fall. In this work we carry out a systematic evaluation of the performance of one of the most widely used machine learning supervised algorithm (Support Vector Machine) when using different input features. To evaluate the impact of the feature selection, we use Area Under the Curve (AUC) of Receiver Operating Characteristic (ROC) Curve as the performance metric. The results showed that with four features it is possible to obtain acceptable values for the detection of falls using accelerometer signals obtained from the userrqs waist. In addition, we also investigate if the impact of selecting the features based on the analysis of a dataset different from the final application framework where the detector will be operative.
Cuevas-Rodríguez, María; González-Toledo, Daniel; Reyes-Lecuona, Arcadio; Picinali, Lorenzo
Impact of non-individualised head related transfer functions on speech-in-noise performances within a synthesised virtual environment Journal Article
In: The Journal of the Acoustical Society of America, vol. 149, no. 4, pp. 2573–2586, 2021, ISSN: 0001-4966.
@article{Imp/2021,
title = {Impact of non-individualised head related transfer functions on speech-in-noise performances within a synthesised virtual environment},
author = {María Cuevas-Rodríguez and Daniel González-Toledo and Arcadio Reyes-Lecuona and Lorenzo Picinali},
url = {https://asa.scitation.org/doi/10.1121/10.0004220},
doi = {10.1121/10.0004220},
issn = {0001-4966},
year = {2021},
date = {2021-04-01},
urldate = {2021-04-01},
journal = {The Journal of the Acoustical Society of America},
volume = {149},
number = {4},
pages = {2573–2586},
abstract = {When performing binaural spatialisation, it is widely accepted that the choice of the head related transfer functions (HRTFs), and in particular the use of individually measured ones, can have an impact on localisation accuracy, externalization, and overall realism. Yet the impact of HRTF choices on speech-in-noise performances in cocktail party-like scenarios has not been investigated in depth. This paper introduces a study where 22 participants were presented with a frontal speech target and two lateral maskers, spatialised using a set of non-individual HRTFs. Speech reception threshold (SRT) was measured for each HRTF. Furthermore, using the SRT predicted by an existing speech perception model, the measured values were compensated in the attempt to remove overall HRTF-specific benefits. Results show significant overall differences among the SRTs measured using different HRTFs, consistently with the results predicted by the model. Individual differences between participants related to their SRT performances using different HRTFs could also be found, but their significance was reduced after the compensation. The implications of these findings are relevant to several research areas related to spatial hearing and speech perception, suggesting that when testing speech-in-noise performances within binaurally rendered virtual environments, the choice of the HRTF for each individual should be carefully considered.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
When performing binaural spatialisation, it is widely accepted that the choice of the head related transfer functions (HRTFs), and in particular the use of individually measured ones, can have an impact on localisation accuracy, externalization, and overall realism. Yet the impact of HRTF choices on speech-in-noise performances in cocktail party-like scenarios has not been investigated in depth. This paper introduces a study where 22 participants were presented with a frontal speech target and two lateral maskers, spatialised using a set of non-individual HRTFs. Speech reception threshold (SRT) was measured for each HRTF. Furthermore, using the SRT predicted by an existing speech perception model, the measured values were compensated in the attempt to remove overall HRTF-specific benefits. Results show significant overall differences among the SRTs measured using different HRTFs, consistently with the results predicted by the model. Individual differences between participants related to their SRT performances using different HRTFs could also be found, but their significance was reduced after the compensation. The implications of these findings are relevant to several research areas related to spatial hearing and speech perception, suggesting that when testing speech-in-noise performances within binaurally rendered virtual environments, the choice of the HRTF for each individual should be carefully considered.
González-Cañete, Francisco J.; Casilari, Eduardo
A Feasibility Study of the Use of Smartwatches in Wearable Fall Detection Systems Journal Article
In: Sensors, vol. 21, no. 6, pp. 2254, 2021, ISSN: 1424-8220.
@article{AFe/2021,
title = {A Feasibility Study of the Use of Smartwatches in Wearable Fall Detection Systems},
author = {Francisco J. González-Cañete and Eduardo Casilari},
url = {https://www.mdpi.com/1424-8220/21/6/2254},
doi = {10.3390/s21062254},
issn = {1424-8220},
year = {2021},
date = {2021-03-01},
journal = {Sensors},
volume = {21},
number = {6},
pages = {2254},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Márquez-Moncada, Ana; Luis, Bottcher Hauke; González-Toledo, Daniel; Cuevas-Rodriguez, María; Molina-Tanco, Luis; Reyes-Lecuona, Arcadio
Influencia del Audio 3D en la Percepción de la Ganancia de Rotación en un Entorno Virtual . Un Estudio Piloto Journal Article
In: Interacción 20/21, 2021.
@article{Marquez-Moncada2021a,
title = {Influencia del Audio 3D en la Percepción de la Ganancia de Rotación en un Entorno Virtual . Un Estudio Piloto},
author = {Ana Márquez-Moncada and Bottcher Hauke Luis and Daniel González-Toledo and María Cuevas-Rodriguez and Luis Molina-Tanco and Arcadio Reyes-Lecuona},
url = {https://hdl.handle.net/10630/22942},
year = {2021},
date = {2021-01-01},
journal = {Interacción 20/21},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Reyes-Lecuona, Arcadio; Márquez-Moncada, Ana; Luis, Bottcher Hauke; González-Toledo, Daniel; Cuevas-Rodriguez, María; Molina-Tanco, Luis
Binaural Audio and Rotation Gain in Virtual Environments Journal Article
In: Interaccion – Revista Digital de AIPO, vol. 2, iss. 2, pp. 54-62, 2021.
@article{Reyes-Lecuona2021c,
title = {Binaural Audio and Rotation Gain in Virtual Environments},
author = {Arcadio Reyes-Lecuona and Ana Márquez-Moncada and Bottcher Hauke Luis and Daniel González-Toledo and María Cuevas-Rodriguez and Luis Molina-Tanco},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Interaccion - Revista Digital de AIPO},
volume = {2},
issue = {2},
pages = {54-62},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Reyes-Lecuona, Arcadio; Cuevas-Rodriguez, Maria; Gonzalez-Toledo, Daniel; Molina-Tanco, Luis; Picinali, Lorenzo
Speech perception in VR: do we need individual recordings? Proceedings Article
In: pp. 1-1, 2021.
@inproceedings{Reyes-Lecuona2021b,
title = {Speech perception in VR: do we need individual recordings?},
author = {Arcadio Reyes-Lecuona and Maria Cuevas-Rodriguez and Daniel Gonzalez-Toledo and Luis Molina-Tanco and Lorenzo Picinali},
doi = {10.1109/i3da48870.2021.9610938},
year = {2021},
date = {2021-01-01},
journal = {International Conference on Immersive and 3D Audio},
issue = {101017743},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
López-Fernández, Jesús; Espinosa, Pablo Ramírez; Romero-Jerez, Juan M; López-Martínez, F Javier
A fluctuating line-of-sight fading model with double-rayleigh diffuse scattering Journal Article
In: IEEE Transactions on Vehicular Technology, vol. 71, no. 1, pp. 1000–1003, 2021.
@article{lopez2021fluctuating,
title = {A fluctuating line-of-sight fading model with double-rayleigh diffuse scattering},
author = {Jesús López-Fernández and Pablo Ramírez Espinosa and Juan M Romero-Jerez and F Javier López-Martínez},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Vehicular Technology},
volume = {71},
number = {1},
pages = {1000–1003},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ahrens, Axel; Cuevas-Rodríguez, María; Brimijoin, W. Owen
Speech intelligibility with various head-related transfer functions: A computational modelling approach Journal Article
In: JASA Express Letters, vol. 1, no. 3, 2021.
@article{Spe/2021,
title = {Speech intelligibility with various head-related transfer functions: A computational modelling approach},
author = {Axel Ahrens and María Cuevas-Rodríguez and W. Owen Brimijoin},
url = {https://asa.scitation.org/doi/10.1121/10.0003618},
doi = {10.1121/10.0003618},
year = {2021},
date = {2021-01-01},
journal = {JASA Express Letters},
volume = {1},
number = {3},
abstract = {Speech intelligibility (SI) is known to be affected by the relative spatial position between target and interferers. The benefit of a spatial separation is, along with other factors, related to the head-related transfer function (HRTF). The HRTF is individually different and thus, the cues that affect SI might also be different. In the current study, an auditory model was employed to predict SI with various HRTFs and at different angles on the horizontal plane. The predicted SI threshold was found to be largely different across HRTFs. Thus, individual listeners might have different access to SI cues, dependent on their HRTF.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Speech intelligibility (SI) is known to be affected by the relative spatial position between target and interferers. The benefit of a spatial separation is, along with other factors, related to the head-related transfer function (HRTF). The HRTF is individually different and thus, the cues that affect SI might also be different. In the current study, an auditory model was employed to predict SI with various HRTFs and at different angles on the horizontal plane. The predicted SI threshold was found to be largely different across HRTFs. Thus, individual listeners might have different access to SI cues, dependent on their HRTF.
González-Cañete, Francisco Javier; López-Rodríguez, José Luís; Galdón, Pedro María; Diaz-Estrella, Antonio
Improving the Screen Exploration of Smartphones Using Haptic Icons for Visually Impaired Users Journal Article
In: Sensors, vol. 21, no. 15, 2021, ISSN: 1424-8220.
@article{s21155024,
title = {Improving the Screen Exploration of Smartphones Using Haptic Icons for Visually Impaired Users},
author = {Francisco Javier González-Cañete and José Luís López-Rodríguez and Pedro María Galdón and Antonio Diaz-Estrella},
url = {https://www.mdpi.com/1424-8220/21/15/5024},
doi = {10.3390/s21155024},
issn = {1424-8220},
year = {2021},
date = {2021-01-01},
journal = {Sensors},
volume = {21},
number = {15},
abstract = {We report the results of a study on the learnability of the locations of haptic icons on smartphones. The aim was to study the influence of the use of complex and different vibration patterns associated with haptic icons compared to the use of simple and equal vibrations on commercial location-assistance applications. We studied the performance of users with different visual capacities (visually impaired vs. sighted) in terms of the time taken to learn the icons locations and the icon recognition rate. We also took into consideration the users satisfaction with the application developed to perform the study. The experiments concluded that the use of complex and different instead of simple and equal vibration patterns obtains better recognition rates. This improvement is even more noticeable for visually impaired users, who obtain results comparable to those achieved by sighted users.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We report the results of a study on the learnability of the locations of haptic icons on smartphones. The aim was to study the influence of the use of complex and different vibration patterns associated with haptic icons compared to the use of simple and equal vibrations on commercial location-assistance applications. We studied the performance of users with different visual capacities (visually impaired vs. sighted) in terms of the time taken to learn the icons locations and the icon recognition rate. We also took into consideration the users satisfaction with the application developed to perform the study. The experiments concluded that the use of complex and different instead of simple and equal vibration patterns obtains better recognition rates. This improvement is even more noticeable for visually impaired users, who obtain results comparable to those achieved by sighted users.
Reyes-Lecuona, Arcadio; Moncada, Ana Marquez; Bottcher, Hauke Luis; González-Toledo, Daniel; Cuevas-Rodr’iguez, Mar’ia; Molina-Tanco, Luis
Audio Binaural y Ganancia de Rotación en Entornos Virtuales Journal Article
In: Revista de la Asociación Interacción Persona Ordenador (AIPO), vol. 2, no. 2, pp. 54–62, 2021.
@article{reyes2021audio,
title = {Audio Binaural y Ganancia de Rotación en Entornos Virtuales},
author = {Arcadio Reyes-Lecuona and Ana Marquez Moncada and Hauke Luis Bottcher and Daniel González-Toledo and Mar'ia Cuevas-Rodr'iguez and Luis Molina-Tanco},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Revista de la Asociación Interacción Persona Ordenador (AIPO)},
volume = {2},
number = {2},
pages = {54--62},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
Casilari, Eduardo; Santoyo-Ramón, Jose Antonio; Cano-García, José Manuel
On the Heterogeneity of Existing Repositories of Movements Intended for the Evaluation of Fall Detection Systems Journal Article
In: Journal of Healthcare Engineering, vol. 2020, pp. 6622285, 2020, ISSN: 2040-2295.
@article{Ont/2020,
title = {On the Heterogeneity of Existing Repositories of Movements Intended for the Evaluation of Fall Detection Systems},
author = {Eduardo Casilari and Jose Antonio Santoyo-Ramón and José Manuel Cano-García},
url = {https://www.hindawi.com/journals/jhe/2020/6622285/},
doi = {10.1155/2020/6622285},
issn = {2040-2295},
year = {2020},
date = {2020-12-01},
journal = {Journal of Healthcare Engineering},
volume = {2020},
pages = {6622285},
abstract = {Due to the serious impact of falls on the autonomy and health of older people, the investigation of wearable alerting systems for the automatic detection of falls has gained considerable scientific interest in the field of body telemonitoring with wireless sensors. Because of the difficulties of systematically validating these systems in a real application scenario, Fall Detection Systems (FDSs) are typically evaluated by studying their response to datasets containing inertial sensor measurements captured during the execution of labelled nonfall and fall movements. In this context, during the last decade, numerous publicly accessible databases have been released aiming at offering a common benchmarking tool for the validation of the new proposals on FDSs. This work offers a comparative and updated analysis of these existing repositories. For this purpose, the samples contained in the datasets are characterized by different statistics that model diverse aspects of the mobility of the human body in the time interval where the greatest change in the acceleration module is identified. By using one-way analysis of variance (ANOVA) on the series of these features, the comparison shows the significant differences detected between the datasets, even when comparing activities that require a similar degree of physical effort. This heterogeneity, which may result from the great variability of the sensors, experimental users, and testbeds employed to generate the datasets, is relevant because it casts doubt on the validity of the conclusions of many studies on FDSs, since most of the proposals in the literature are only evaluated using a single database.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Due to the serious impact of falls on the autonomy and health of older people, the investigation of wearable alerting systems for the automatic detection of falls has gained considerable scientific interest in the field of body telemonitoring with wireless sensors. Because of the difficulties of systematically validating these systems in a real application scenario, Fall Detection Systems (FDSs) are typically evaluated by studying their response to datasets containing inertial sensor measurements captured during the execution of labelled nonfall and fall movements. In this context, during the last decade, numerous publicly accessible databases have been released aiming at offering a common benchmarking tool for the validation of the new proposals on FDSs. This work offers a comparative and updated analysis of these existing repositories. For this purpose, the samples contained in the datasets are characterized by different statistics that model diverse aspects of the mobility of the human body in the time interval where the greatest change in the acceleration module is identified. By using one-way analysis of variance (ANOVA) on the series of these features, the comparison shows the significant differences detected between the datasets, even when comparing activities that require a similar degree of physical effort. This heterogeneity, which may result from the great variability of the sensors, experimental users, and testbeds employed to generate the datasets, is relevant because it casts doubt on the validity of the conclusions of many studies on FDSs, since most of the proposals in the literature are only evaluated using a single database.
Casilari, Eduardo; Lora-Rivera, Raúl; García-Lagos, Francisco
A Study on the Application of Convolutional Neural Networks to Fall Detection Evaluated with Multiple Public Datasets Journal Article
In: Sensors, vol. 20, no. 5, pp. 1466, 2020, ISSN: 1424-8220.
@article{ASt/2020,
title = {A Study on the Application of Convolutional Neural Networks to Fall Detection Evaluated with Multiple Public Datasets},
author = {Eduardo Casilari and Raúl Lora-Rivera and Francisco García-Lagos},
url = {https://www.mdpi.com/1424-8220/20/5/1466},
doi = {10.3390/s20051466},
issn = {1424-8220},
year = {2020},
date = {2020-03-01},
journal = {Sensors},
volume = {20},
number = {5},
pages = {1466},
abstract = {Due to the repercussion of falls on both the health and self-sufficiency of older people and on the financial sustainability of healthcare systems, the study of wearable fall detection systems (FDSs) has gained much attention during the last years. The core of a FDS is the algorithm that discriminates falls from conventional Activities of Daily Life (ADLs). This work presents and evaluates a convolutional deep neural network when it is applied to identify fall patterns based on the measurements collected by a transportable tri-axial accelerometer. In contrast with most works in the related literature, the evaluation is performed against a wide set of public data repositories containing the traces obtained from diverse groups of volunteers during the execution of ADLs and mimicked falls. Although the method can yield very good results when it is hyper-parameterized for a certain dataset, the global evaluation with the other repositories highlights the difficulty of extrapolating to other testbeds the network architecture that was configured and optimized for a particular dataset.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Due to the repercussion of falls on both the health and self-sufficiency of older people and on the financial sustainability of healthcare systems, the study of wearable fall detection systems (FDSs) has gained much attention during the last years. The core of a FDS is the algorithm that discriminates falls from conventional Activities of Daily Life (ADLs). This work presents and evaluates a convolutional deep neural network when it is applied to identify fall patterns based on the measurements collected by a transportable tri-axial accelerometer. In contrast with most works in the related literature, the evaluation is performed against a wide set of public data repositories containing the traces obtained from diverse groups of volunteers during the execution of ADLs and mimicked falls. Although the method can yield very good results when it is hyper-parameterized for a certain dataset, the global evaluation with the other repositories highlights the difficulty of extrapolating to other testbeds the network architecture that was configured and optimized for a particular dataset.
Casilari, Eduardo; Álvarez-Marco, Moisés; García-Lagos, Francisco
A Study of the Use of Gyroscope Measurements in Wearable Fall Detection Systems Journal Article
In: Symmetry, vol. 12, no. 4, pp. 649, 2020, ISSN: 2073-8994.
@article{AStgiroscopo/2020,
title = {A Study of the Use of Gyroscope Measurements in Wearable Fall Detection Systems},
author = {Eduardo Casilari and Moisés Álvarez-Marco and Francisco García-Lagos},
url = {https://www.mdpi.com/2073-8994/12/4/649/htm},
doi = {10.3390/sym12040649},
issn = {2073-8994},
year = {2020},
date = {2020-03-01},
journal = {Symmetry},
volume = {12},
number = {4},
pages = {649},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Delgado-Escaño, Rubén; Castro, Francisco M.; Cózar, Julián R.; Marín-Jiménez, Manuel J.; Guil, Nicolás; Casilari, Eduardo
A cross-dataset deep learning-based classifier for people fall detection and identification Journal Article
In: Computer Methods and Programs in Biomedicine, vol. 184, no. 105265, 2020, ISSN: 0169-2607.
@article{Acr/2020,
title = {A cross-dataset deep learning-based classifier for people fall detection and identification},
author = {Rubén Delgado-Escaño and Francisco M. Castro and Julián R. Cózar and Manuel J. Marín-Jiménez and Nicolás Guil and Eduardo Casilari},
url = {https://www.sciencedirect.com/science/article/pii/S0169260719311770},
doi = {10.1016/j.cmpb.2019.105265},
issn = {0169-2607},
year = {2020},
date = {2020-02-01},
journal = {Computer Methods and Programs in Biomedicine},
volume = {184},
number = {105265},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
González-Cañete, Francisco J.; Casilari, Eduardo
Consumption Analysis of Smartphone based Fall Detection Systems with Multiple External Wireless Sensors Journal Article
In: Sensors, vol. 20, no. 3, 2020, ISSN: 1424-8220.
@article{Con/2020,
title = {Consumption Analysis of Smartphone based Fall Detection Systems with Multiple External Wireless Sensors},
author = {Francisco J. González-Cañete and Eduardo Casilari},
url = {https://www.mdpi.com/1424-8220/20/3/622},
doi = {10.3390/s20030622},
issn = {1424-8220},
year = {2020},
date = {2020-01-01},
journal = {Sensors},
volume = {20},
number = {3},
crossref = {622;},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Reyes-Lecuona, Arcadio; Molina-Tanco, Luis; Cuevas-Rodríguez, María; González-Toledo, Daniel
Interacción 3D y Realidad Virtual en la Universidad de Málaga. Presentación del grupo 3DI-DIANA Journal Article
In: Interaccion – Revista Digital de AIPO, pp. 85–88, 2020.
@article{Reyes-Lecuona2020,
title = {Interacción 3D y Realidad Virtual en la Universidad de Málaga. Presentación del grupo 3DI-DIANA},
author = {Arcadio Reyes-Lecuona and Luis Molina-Tanco and María Cuevas-Rodríguez and Daniel González-Toledo},
year = {2020},
date = {2020-01-01},
journal = {Interaccion - Revista Digital de AIPO},
pages = {85–88},
abstract = {The 3DI-DIANA team is researching and developing technology in 3D interaction and user experience in Interactive Virtual Environments (IVE) since 2004. Their work has focused on 3D interaction techniques for Virtual Reality from a Human-Computer Interaction perspective. Their expertise and interests span binaural 3D audio spatialisation, 3D interaction with reduced degrees of freedom, and Virtual and Augmented Reality, including haptic Virtual Reality and Presence. The team have an important record in collaborative projects, both at national and European level. They are open to collaborations with other research teams, being able to contribute with their expertise in their described topics. More specifically, the 3DI-DIANA team can contribute in extending interactive virtual environments with 3D Audio and developing 3D interaction techniques which improve the user experience of handling and visualization of complex 3D objects.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The 3DI-DIANA team is researching and developing technology in 3D interaction and user experience in Interactive Virtual Environments (IVE) since 2004. Their work has focused on 3D interaction techniques for Virtual Reality from a Human-Computer Interaction perspective. Their expertise and interests span binaural 3D audio spatialisation, 3D interaction with reduced degrees of freedom, and Virtual and Augmented Reality, including haptic Virtual Reality and Presence. The team have an important record in collaborative projects, both at national and European level. They are open to collaborations with other research teams, being able to contribute with their expertise in their described topics. More specifically, the 3DI-DIANA team can contribute in extending interactive virtual environments with 3D Audio and developing 3D interaction techniques which improve the user experience of handling and visualization of complex 3D objects.
2019
Casilari, Eduardo; García-Lagos, Francisco
A comprehensive study on the use of artificial neural networks in wearable fall detection systems Journal Article
In: Expert Systems with Applications, vol. 138, no. 112811, 2019, ISSN: 0957-4174.
@article{Aco/2019,
title = {A comprehensive study on the use of artificial neural networks in wearable fall detection systems},
author = {Eduardo Casilari and Francisco García-Lagos},
url = {https://www.sciencedirect.com/science/article/pii/S095741741930507X},
doi = {10.1016/j.eswa.2019.07.028},
issn = {0957-4174},
year = {2019},
date = {2019-12-01},
journal = {Expert Systems with Applications},
volume = {138},
number = {112811},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Reyes-Lecuona, Arcadio
3DI-DIANA. Interacción 3D y Realidad Virtual Conference
Interacción2019, San Sebastián, 2019.
@conference{3DI/2019,
title = {3DI-DIANA. Interacción 3D y Realidad Virtual},
author = {Arcadio Reyes-Lecuona},
year = {2019},
date = {2019-09-01},
booktitle = {Interacción2019},
address = {San Sebastián},
abstract = {El equipo 3DI-DIANA desarrolla su labor de investigación en interacción 3D y experiencia de usuario en Entornos Virtuales (EV) desde 2004. Su trabajo se centra en el estudio de la interacción persona-máquina en el contexto de las técnicas de interacción 3D en Realidad Virtual. Más concretamente, su experiencia e intereses abarcan las siguientes áreas: espacialización de audio 3D binaural, interacción 3D con grados de libertad reducidos, Realidad Aumentada, interacción 3D en EV, interacción háptica, navegación en EV caminando y Presencia en EV.
En este artículo, se presenta brevemente la actividad desarrollada por el grupo 3DI-DIANA con especial atención a su trabajo más reciente.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
El equipo 3DI-DIANA desarrolla su labor de investigación en interacción 3D y experiencia de usuario en Entornos Virtuales (EV) desde 2004. Su trabajo se centra en el estudio de la interacción persona-máquina en el contexto de las técnicas de interacción 3D en Realidad Virtual. Más concretamente, su experiencia e intereses abarcan las siguientes áreas: espacialización de audio 3D binaural, interacción 3D con grados de libertad reducidos, Realidad Aumentada, interacción 3D en EV, interacción háptica, navegación en EV caminando y Presencia en EV.
En este artículo, se presenta brevemente la actividad desarrollada por el grupo 3DI-DIANA con especial atención a su trabajo más reciente.
En este artículo, se presenta brevemente la actividad desarrollada por el grupo 3DI-DIANA con especial atención a su trabajo más reciente.
Cuevas-Rodríguez, María; Alon, David Lou; Clapp, Samuel W; Robinson, Philip W
Evaluation of the effect of head-mounted display on individualized head-related transfer functions Conference
Proceeding of the 23rd International Congress on Acoustic, ICA2019, 2019.
@conference{Cuevas-Rodriguez,
title = {Evaluation of the effect of head-mounted display on individualized head-related transfer functions},
author = {María Cuevas-Rodríguez and David Lou Alon and Samuel W Clapp and Philip W Robinson},
url = {http://pub.dega-akustik.de/ICA2019/data/articles/000871.pdf},
year = {2019},
date = {2019-09-01},
booktitle = {Proceeding of the 23rd International Congress on Acoustic, ICA2019},
pages = {2635–2642},
institution = {Facebook Reality Lab},
abstract = {Head Mounted Displays (HMDs) have become popular for acoustic experiments, such as perceptual comparison of virtual and real sound sources, or Head Related Transfer Function (HRTF) measurement. However, wearing an HMD while listening to real sound sources modifies the sound waves that reaches the listener's ears. In this work, we study the effect of HMDs on individualized HRTFs. We have collected acoustic HRTF measurements, with and without the HMD, from 24 human participants and a manikin head, over 612 directions (including different azimuth and elevation angles). An objective evaluation indicates that, although there are frequency-dependent directional regions where the distortion caused by the HMD is higher, other regions are less affected by the HMD. A MUSHRA test with 15 subjects compares individualized HRTFs and a generic HRTF, measured with and without HMD. The perceptual evaluation reveals a significant effect of the HMD on the measured individualized HRTF, but it also shows that this effect is significantly smaller than the difference between individualized HRTFs and a generic HRTF, as indicated by the objective evaluation. This implies that, although distorted by the presence of the HMD, some of the individualized HRTF characteristics might be preserved when the HMD is worn.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Head Mounted Displays (HMDs) have become popular for acoustic experiments, such as perceptual comparison of virtual and real sound sources, or Head Related Transfer Function (HRTF) measurement. However, wearing an HMD while listening to real sound sources modifies the sound waves that reaches the listener’s ears. In this work, we study the effect of HMDs on individualized HRTFs. We have collected acoustic HRTF measurements, with and without the HMD, from 24 human participants and a manikin head, over 612 directions (including different azimuth and elevation angles). An objective evaluation indicates that, although there are frequency-dependent directional regions where the distortion caused by the HMD is higher, other regions are less affected by the HMD. A MUSHRA test with 15 subjects compares individualized HRTFs and a generic HRTF, measured with and without HMD. The perceptual evaluation reveals a significant effect of the HMD on the measured individualized HRTF, but it also shows that this effect is significantly smaller than the difference between individualized HRTFs and a generic HRTF, as indicated by the objective evaluation. This implies that, although distorted by the presence of the HMD, some of the individualized HRTF characteristics might be preserved when the HMD is worn.
Reyes-Lecuona, Arcadio; Cuevas-Rodríguez, María; González-Toledo, Daniel; del Olmo, Carlos Garre; Rubia-Cuestas, Ernesto J.; Molina-Tanco, Luis; Rodríguez-Rivero, Ángel; Picinali, Lorenzo
23rd International Congress on Acoustics, ICA2019, Aachen, 2019, ISBN: 9783939296157.
@conference{The/2019,
title = {The 3D Tune-In Toolkit: A C++ library for binaural spatialisation, and hearing loss / hearing aids emulation},
author = {Arcadio Reyes-Lecuona and María Cuevas-Rodríguez and Daniel González-Toledo and Carlos Garre del Olmo and Ernesto J. Rubia-Cuestas and Luis Molina-Tanco and Ángel Rodríguez-Rivero and Lorenzo Picinali},
url = {http://pub.dega-akustik.de/ICA2019/data/index.html},
isbn = {9783939296157},
year = {2019},
date = {2019-09-01},
booktitle = {23rd International Congress on Acoustics, ICA2019},
address = {Aachen},
abstract = {This contribution presents the 3D Tune-In (3DTI) Toolkit, an open source C++ library for binaural spatialisation which includes hearing loss and hearing aid emulators. Binaural spatialisation is performed through convolution with user-imported Head Related Transfer Functions (HRTFs) and Binaural Room Impulse Responses (BRIRs), including additional functionalities such as near- and far-field source simulation, customisation of Interaural Time Differences (ITDs), and Ambisonic-based binaural reverberation. Hearing loss is simulated through gammatone filters and multiband expanders/compressors, including advanced non-linear features such as frequency smearing and temporal distortion. A generalised hearing aid simulator is also included, with functionalities such as dynamic equalisation, calibration from user-inputted audiograms, and directional processing.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
This contribution presents the 3D Tune-In (3DTI) Toolkit, an open source C++ library for binaural spatialisation which includes hearing loss and hearing aid emulators. Binaural spatialisation is performed through convolution with user-imported Head Related Transfer Functions (HRTFs) and Binaural Room Impulse Responses (BRIRs), including additional functionalities such as near- and far-field source simulation, customisation of Interaural Time Differences (ITDs), and Ambisonic-based binaural reverberation. Hearing loss is simulated through gammatone filters and multiband expanders/compressors, including advanced non-linear features such as frequency smearing and temporal distortion. A generalised hearing aid simulator is also included, with functionalities such as dynamic equalisation, calibration from user-inputted audiograms, and directional processing.
Picinali, Lorenzo; Cuevas-Rodríguez, María; González-Toledo, Daniel; Reyes-Lecuona, Arcadio
23rd International Congress on Acoustics, ICA2019, 2019, ISBN: 9783939296157.
@conference{Spe/2019,
title = {Speech-in-noise performances in virtual cocktail party using different non-individual Head Related Transfer Functions},
author = {Lorenzo Picinali and María Cuevas-Rodríguez and Daniel González-Toledo and Arcadio Reyes-Lecuona},
url = {http://ica2019.org/technical-program/},
isbn = {9783939296157},
year = {2019},
date = {2019-09-01},
booktitle = {23rd International Congress on Acoustics, ICA2019},
pages = {2158–2159},
abstract = {Functions (HRTFs) can have an impact on localisation accuracy and, more in general, realism and sound sources externalisation. The impact of the HRTF choice on speech-in-noise performances in cocktail party scenarios has though not yet been investigated in depth. Within a binaurally-rendered virtual environment, Speech Reception Thresholds (SRTs) with frontal target speaker and lateral noise maskers were measured for 22 subjects several times across different sessions, and using different HRTFs. Results show that for the majority of the tested subjects, significant differences could be found between the SRTs measured using different HRTFs. Furthermore, the HRTFs leading to better or worse SRT performances were not the same across the subjects, indicating that the choice of the HRTF can indeed have an impact on speech-in-noise performances within the tested conditions.
These results suggest that when testing speech-in-noise performances within binaurally-rendered virtual environments, the choice of the HRTF should be carefully considered. Furthermore a recommendation should be made for future modelling of the speech-in-noise perception mechanisms to include monoaural spectral cues in addition to interaural differences.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Functions (HRTFs) can have an impact on localisation accuracy and, more in general, realism and sound sources externalisation. The impact of the HRTF choice on speech-in-noise performances in cocktail party scenarios has though not yet been investigated in depth. Within a binaurally-rendered virtual environment, Speech Reception Thresholds (SRTs) with frontal target speaker and lateral noise maskers were measured for 22 subjects several times across different sessions, and using different HRTFs. Results show that for the majority of the tested subjects, significant differences could be found between the SRTs measured using different HRTFs. Furthermore, the HRTFs leading to better or worse SRT performances were not the same across the subjects, indicating that the choice of the HRTF can indeed have an impact on speech-in-noise performances within the tested conditions.
These results suggest that when testing speech-in-noise performances within binaurally-rendered virtual environments, the choice of the HRTF should be carefully considered. Furthermore a recommendation should be made for future modelling of the speech-in-noise perception mechanisms to include monoaural spectral cues in addition to interaural differences.
These results suggest that when testing speech-in-noise performances within binaurally-rendered virtual environments, the choice of the HRTF should be carefully considered. Furthermore a recommendation should be made for future modelling of the speech-in-noise perception mechanisms to include monoaural spectral cues in addition to interaural differences.
Santoyo-Ramón, Jose-Antonio; Casilari, Eduardo; Cano-García, José Manuel
Study of the Detection of Falls Using the SVM Algorithm, Different Datasets of Movements and ANOVA Conference
Proceedings of IEEE IWBBIO: International Work-Conference on Bioinformatics and Biomedical Engineering, Springer, Granada (Spain), May 8-10, 2019, 2019, ISBN: 9783030179373.
@conference{Stu/2019,
title = {Study of the Detection of Falls Using the SVM Algorithm, Different Datasets of Movements and ANOVA},
author = {Jose-Antonio Santoyo-Ramón and Eduardo Casilari and José Manuel Cano-García},
url = {https://link.springer.com/chapter/10.1007/978-3-030-17938-0_37},
doi = {10.1007/978-3-030-17938-0_37},
isbn = {9783030179373},
year = {2019},
date = {2019-05-01},
booktitle = {Proceedings of IEEE IWBBIO: International Work-Conference on Bioinformatics and Biomedical Engineering},
publisher = {Springer},
address = {Granada (Spain), May 8-10, 2019},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Picinali, Lorenzo; Hrafnkelsson, Ragnar; Reyes-Lecuona, Arcadio
The 3D Tune-In Toolkit VST Binaural Audio Plugin Conference
Audio Engineering Society Conference: 2019 AES International Conference on Immersive and Interactive Audio, Audio Engineering Society 2019.
@conference{picinali20193d,
title = {The 3D Tune-In Toolkit VST Binaural Audio Plugin},
author = {Lorenzo Picinali and Ragnar Hrafnkelsson and Arcadio Reyes-Lecuona},
year = {2019},
date = {2019-01-01},
booktitle = {Audio Engineering Society Conference: 2019 AES International Conference on Immersive and Interactive Audio},
organization = {Audio Engineering Society},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Reyes-Lecuona, Arcadio; González-Toledo, Daniel; Cuevas-Rodríguez, María; Herruzo-Torrico, Maria Luna; Puyol, Ana García; Molina-Tanco, Luis
PLUGGY3D. Augmented Reality for cultural heritage Conference
Proceedings of the 16th Annual EuroVR Conference – 2019, Tallinn, Estonia, 2019.
@conference{ArcadioReyes-LecuonaDanielGonzalez-Toledo2019,
title = {PLUGGY3D. Augmented Reality for cultural heritage},
author = {Arcadio Reyes-Lecuona and Daniel González-Toledo and María Cuevas-Rodríguez and Maria Luna Herruzo-Torrico and Ana García Puyol and Luis Molina-Tanco},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 16th Annual EuroVR Conference - 2019},
pages = {103–106},
address = {Tallinn, Estonia},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Cuevas-Rodríguez, María; Picinali, Lorenzo; González-Toledo, Daniel; del Olmo, Carlos Garre; Rubia-Cuestas, Ernesto J.; Molina-Tanco, Luis; Reyes-Lecuona, Arcadio
3D Tune-In Toolkit: An open-source library for real-time binaural spatialisation Journal Article
In: PLOS ONE, vol. 14, no. 3, pp. 1–37, 2019.
@article{10.1371/journal.pone.0211899,
title = {3D Tune-In Toolkit: An open-source library for real-time binaural spatialisation},
author = {María Cuevas-Rodríguez and Lorenzo Picinali and Daniel González-Toledo and Carlos Garre del Olmo and Ernesto J. Rubia-Cuestas and Luis Molina-Tanco and Arcadio Reyes-Lecuona},
url = {https://doi.org/10.1371/journal.pone.0211899},
doi = {10.1371/journal.pone.0211899},
year = {2019},
date = {2019-01-01},
journal = {PLOS ONE},
volume = {14},
number = {3},
pages = {1–37},
publisher = {Public Library of Science},
abstract = {The 3D Tune-In Toolkit (3DTI Toolkit) is an open-source standard C++ library which includes a binaural spatialiser. This paper presents the technical details of this renderer, outlining its architecture and describing the processes implemented in each of its components. In order to put this description into context, the basic concepts behind binaural spatialisation are reviewed through a chronology of research milestones in the field in the last 40 years. The 3DTI Toolkit renders the anechoic signal path by convolving sound sources with Head Related Impulse Responses (HRIRs), obtained by interpolating those extracted from a set that can be loaded from any file in a standard audio format. Interaural time differences are managed separately, in order to be able to customise the rendering according the head size of the listener, and to reduce comb-filtering when interpolating between different HRIRs. In addition, geometrical and frequency-dependent corrections for simulating near-field sources are included. Reverberation is computed separately using a virtual loudspeakers Ambisonic approach and convolution with Binaural Room Impulse Responses (BRIRs). In all these processes, special care has been put in avoiding audible artefacts produced by changes in gains and audio filters due to the movements of sources and of the listener. The 3DTI Toolkit performance, as well as some other relevant metrics such as non-linear distortion, are assessed and presented, followed by a comparison between the features offered by the 3DTI Toolkit and those found in other currently available open- and closed-source binaural renderers.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The 3D Tune-In Toolkit (3DTI Toolkit) is an open-source standard C++ library which includes a binaural spatialiser. This paper presents the technical details of this renderer, outlining its architecture and describing the processes implemented in each of its components. In order to put this description into context, the basic concepts behind binaural spatialisation are reviewed through a chronology of research milestones in the field in the last 40 years. The 3DTI Toolkit renders the anechoic signal path by convolving sound sources with Head Related Impulse Responses (HRIRs), obtained by interpolating those extracted from a set that can be loaded from any file in a standard audio format. Interaural time differences are managed separately, in order to be able to customise the rendering according the head size of the listener, and to reduce comb-filtering when interpolating between different HRIRs. In addition, geometrical and frequency-dependent corrections for simulating near-field sources are included. Reverberation is computed separately using a virtual loudspeakers Ambisonic approach and convolution with Binaural Room Impulse Responses (BRIRs). In all these processes, special care has been put in avoiding audible artefacts produced by changes in gains and audio filters due to the movements of sources and of the listener. The 3DTI Toolkit performance, as well as some other relevant metrics such as non-linear distortion, are assessed and presented, followed by a comparison between the features offered by the 3DTI Toolkit and those found in other currently available open- and closed-source binaural renderers.
Jiménez, Álvaro Martín
Desarrollo de un sistema de seguridad de detección de presencia (Trabajo Fin de Grado, Grado en Ingeniería de Sistemas Electrónicos) Masters Thesis
Universidad de Málaga, Supervisors: Eduardo Casilari/Jose Manuel Cano-García, 2019.
@mastersthesis{Alv/Des/2019,
title = {Desarrollo de un sistema de seguridad de detección de presencia (Trabajo Fin de Grado, Grado en Ingeniería de Sistemas Electrónicos)},
author = {Álvaro Martín Jiménez},
year = {2019},
date = {2019-01-01},
address = {Supervisors: Eduardo Casilari/Jose Manuel Cano-García},
school = {Universidad de Málaga},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Marco, Moisés Álvarez
Estudio de sistemas de detección de caídas basados en redes neuronales profundas (Trabajo Fin de Grado, Grado en Ingeniería de Tecnologías de Telecomunicación) Masters Thesis
Universidad de Málaga, Supervisors: Eduardo Casilari/Francisco García Lagos, 2019.
@mastersthesis{Moi/Est/2019,
title = {Estudio de sistemas de detección de caídas basados en redes neuronales profundas (Trabajo Fin de Grado, Grado en Ingeniería de Tecnologías de Telecomunicación)},
author = {Moisés Álvarez Marco},
year = {2019},
date = {2019-01-01},
address = {Supervisors: Eduardo Casilari/Francisco García Lagos},
school = {Universidad de Málaga},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Casilari, Eduardo; Rivera, Raúl Lora; Lagos, Francisco García
Evaluation of a Fall Alerting System based on a Convolutional Deep Neural Network Conference
Proceedings of IEEE 2019 International Conference on Control, Decision and Information Technologies (CODIT’2019), París (France), April 23-26, 2019, 2019.
@conference{Eva/2019,
title = {Evaluation of a Fall Alerting System based on a Convolutional Deep Neural Network},
author = {Eduardo Casilari and Raúl Lora Rivera and Francisco García Lagos},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of IEEE 2019 International Conference on Control, Decision and Information Technologies (CODIT'2019)},
address = {París (France), April 23-26, 2019},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}