Grupo de investigación "Domótica y Ambientes Inteligentes"

14/12/2023

Hoy, he participado en la Jornada «Sistemas Tecnológicos de Apoyo a las Personas Mayores», organizada por la Cátedra UNESCO de Educación, Investigación e Inclusión Digital; el Robotics & Tridimensional Vision Research Group (RoViT) de - UA - Universitat d'Alacant / Universidad de Alicante; y la Fundación ICAR “Centro Internacional para la Investigación del Envejecimiento”.

He hablado sobre video-monitorización ética de personas mayores y el trabajo que el Grupo de Investigación en Entornos Inteligentes para un Envejecimiento Activo y Saludable de la UA - Universitat d'Alacant / Universidad de Alicante realiza dentro de los proyectos internacionales visuAAL MSCA Innovative Training Network y GoodBrother COST Action.

Un evento muy interesante.

12/12/2013

Dentro de un par de proyectos de investigación que estamos acabando actualmente, estamos realizando una "Encuesta sobre monitorización de personas y privacidad en el hogar". Aunque originalmente estaba pensada para ser contestada únicamente por personas mayores y dependientes, la encuesta es dinámica y se adapta a diferentes perfiles. Puede ser contestada por cualquiera, lo que nos permitirá tener una visión más amplia sobre esta cuestión.

Por favor, ayúdanos con estos proyectos completando la encuesta. Si tienes alguna persona mayor a la que le puedas pasar la encuesta, te agradecería que lo hicieras.

Puedes acceder a la encuesta en http://shanon.iuii.ua.es/survey/index.php/165112.

Te agradecería que compartieras esta encuesta para que llegara a un mayor número de personas y tener un mayor número de respuestas.

Se está realizando un estudio sobre la monitorización de personas en espacios privados dentro de los proyectos "Caring4U - A study on people activity in private spaces: towards a multisensor network that meets privacy requirements" ("Caring4U - Un estudio de la actividad de personas en espacios priv...

14/06/2013

Postdoctoral position (Research Associate) in computer vision, human behaviour understanding and ambient assisted living

Applications are invited for a position as a Research Associate in the Faculty of Science, Engineering and Computing/Digital Imaging Research Centre at Kingston University, United Kingdom. This is a fixed contract until 31st October 2015. Applications until midnight 30th June 2013. More information at http://www.jobs.ac.uk/job/AGS492/research-associate/

The researcher will work on the BREATHE research project funded by European Union's Ambient Assisted Living programme. BREATHE will provide an ICT-based solution for the caregiver and the elderly in order to mitigate these problems and impact at three levels: personal, by increasing quality of life and care; local and regional, by providing a tool usable by different stakeholders to effectively manage the reality of the informal care, and by opening opportunities of new business models and employment; and European, by reducing health system costs as a consequence of effective management of informal care. The individual solution is based on a strong server side system that maintains updated models of both caregiver and assisted person and offer strategic support for the informal caregivers during long term care.

The project is a multi-disciplinary research programme and Kingston University responsibility is to develop algorithmic solutions for improved understanding of daily activities in an assisted living environment by analysing multisensory information captured by an array of video and other sensors.

The RoleFree-thinking, collaborative, innovative, Kingston University is yours to discover. This is a unique opportunity to explore the growing...

27/05/2013

Engineers on the are being invited to develop an intelligent solution for people living with cognitive impairments and other long term conditions that could change their lives.

Project Nocturne, run in conjunction with the Bath Institute of Medical Engineering and Armley Helping Hands in Leeds, UK, hopes to find a reliable solution that will alert a relative or carer if their loved one is not safely in bed at night, or fails to get up in the morning.

http://www.element14.com/community/groups/bime

BIME (Bath Institute of Medical Engineering) is a design and development charity working in the fields of medicine, health care and assistive technology for disabled people. The Bath Institute of Medical Engineering is an independent charity, working to develop new technologies to support people wit...

27/03/2013

"Silhouette-based Human Action Recognition using Sequences of Key Poses" publicado en Pattern Recognition Letters (http://www.sciencedirect.com/science/article/pii/S0167865513000342). Abstract: In this paper, a human action recognition method is presented in which pose representation is based on the contour points of the human silhouette and actions are learned by making use of sequences of multi-view key poses. Our contribution is twofold. Firstly, our approach achieves state-of-the-art success rates without compromising the speed of the recognition process and therefore showing suitability for online recognition and real-time scenarios. Secondly, dissimilarities among different actors performing the same action are handled by taking into account variations in shape (shifting the test data to the known domain of key poses) and speed (considering inconsistent time scales in the classification). Experimental results on the publicly available Weizmann, MuHAVi and IXMAS datasets return high and stable success rates, achieving, to the best of our knowledge, the best rate so far on the MuHAVi Novel Actor test.

In this paper, a human action recognition method is presented in which pose representation is based on the contour points of the human silhouette and actions are learned by making use of sequences of multi-view key poses. Our contribution is twofold. Firstly, our approach achieves state-of-the-art s...

25/03/2013

MetalTIC, Hogar Digital valida nuevos sistemas inteligentes para la gestión y distribución eléctrica
http://www.fempa.es/webcms/index.php?menu=noticias&submenu=ver_noticia&id_noticia=2734

“MetalTIC está al servicio de las empresas del metal innovadoras ya que pueden utilizarla como planta piloto a escala real y certificado de resultados además de como herramienta de demostración y promoción de nuevas tecnologías”, recordaba Baena

22/03/2013

http://web.ua.es/es/actualidad-universitaria/2013/marzo2013/marzo2013-11-17/investigadores-de-la-universidad-de-alicante-desarrollan-un-sistema-inteligente-de-distribucion-de-energia-electrica.html

Actualidad Universitaria. Investigadores de la Universidad de Alicante desarrollan un sistema inteligente de distribución de energía eléctrica

26/02/2013

II Encuentro sobre responsabilidad Social Tecnológica http://fts.org.es/encuentro-erst13/ #.USzaxjCeD2Y

Encuentro para la reflexión activa acerca de la tecnología social, la responsabilidad social tecnológica y los factores humanos en las TIC.

21/11/2012

"Optimal Feature Selection for Skeletal Data from RGB-D Devices using a Genetic Algorithm" presentado en The 11th Mexican International Conference on Artificial Intelligence. Esperemos que esté pronto disponible la versión electrónica en Springer. Ya avisaremos. Abstract: The growth in interest in RGB-D devices (e.g. MicrosoftKinect or ASUS Xtion Pro) is based on their low price, as well as thewide range of possible applications. These devices can provide skeletaldata consisting of 3D position, as well as orientation data, which can befurther used for pose or action recognition. Data for 15 or 20 joints canbe retrieved, depending on the libraries used. Recently, many datasetshave been made available which allow the comparison of dierent actionrecognition approaches for diverse applications (e.g. gaming, Ambient-Assisted Living, etc.). In this work, a genetic algorithm is used to de-termine the contribution of each of the skeleton's joints to the accuracyof an action recognition algorithm, thus using or ignoring the data fromeach joint depending on its relevance. The proposed method has beenvalidated using a k-means-based action recognition approach and usingthe MSR-Action3D dataset for test. Results show the presented algo-rithm is able to improve the recognition rates while reducing the feature size

05/11/2012

"An Efficient Approach for Multi-view Human Action Recognition Based on Bag-of-Key-Poses" presentado por Alexandros Andre Chaaraoiu en el 3rd International Workshop on Human Behavior Understanding http://www.springerlink.com/content/wh12htlt27t43n0v/

06/10/2012

Control of a smart home with the Kinect