HOLDS: Efficient Fall Detection through Accelerometers and Computer Vision

Fern'ndez-Caballero, Antonio; Sokolova, Marina V.; Serrano-Cuerda, Juan; Castillo, José Carlos; Moreno, Verónica Díaz; Castiñeira, Rodrigo; Redondo, Luis

doi:10.1109/ie.2012.11

Cited by 7 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve fall detection, some have suggested using at least two tri-axial accelerometers at separate body locations and additional gyroscope to measure body orientation before and after fall-like events. It has been shown in experiments that detection accuracy of over 80% can be achieved with different combinations of methods [69][70][71][72][73]. In one study which used Hidden Markov Models (HMM), fall could be predicted a few hundred milliseconds before the person collided with the floor.…”

Section: Fall Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Ubiquitous Health Monitoring: Integration of Wearable Sensors, Novel Sensing Techniques, and Body Sensor Networks

2015

View full text Add to dashboard Cite

Abstract. Emergence of the Internet and widespread use of mobile computing have brought traditional eHealth beyond the boundary of the clinical setting, evolving to mHealth which is patient-centered and ubiquitous. Faced with the world's rapidly ageing population and its burden on the healthcare system, one of the intense areas of development in mHealth is continuous patient monitoring. It requires careful integration of wearable sensors and wireless body sensor networks. Unlike traditional ambulatory monitors, sensors for mHealth may appear in various forms, such as watches, jewelry, eyewear, and even smart garments. Recent work have focused on design for wearability, alternative sensing techniques, and mHealth-specific network topologies.

show abstract

Section: Fall Detectionmentioning

confidence: 99%

“…Most fall detection techniques are either image-based with computer vision or sensor-based [69] [70].…”

Section: Fall Detectionmentioning

confidence: 99%

Ubiquitous Health Monitoring: Integration of Wearable Sensors, Novel Sensing Techniques, and Body Sensor Networks

2015

View full text Add to dashboard Cite

show abstract

“…The most traditional approach to identify specific human events by analysing images is the identification of the human's posture [29][30][31]. This can be achieved by analysing the silhouette of the person [16,25], obtaining the skeleton [32][33][34], processing the complete information of the person's image, which is the approach used in this work, or even a combination of techniques [35].…”

Section: Related Workmentioning

confidence: 99%

Heart Attack Detection in Colour Images Using Convolutional Neural Networks

et al. 2019

View full text Add to dashboard Cite

Cardiovascular diseases are the leading cause of death worldwide. Therefore, getting help in time makes the difference between life and death. In many cases, help is not obtained in time when a person is alone and suffers a heart attack. This is mainly due to the fact that pain prevents him/her from asking for help. This article presents a novel proposal to identify people with an apparent heart attack in colour images by detecting characteristic postures of heart attack. The method of identifying infarcts makes use of convolutional neural networks. These have been trained with a specially prepared set of images that contain people simulating a heart attack. The promising results in the classification of infarcts show 91.75% accuracy and 92.85% sensitivity.

show abstract

“…Doukas and Maglogiannis [2011] and Yu et al [2010] leverage on the combination of audio and video information, known as multimodal processing, using a speech recognition system to double check a possible fall by also analyzing the extracted voice. Fernández-Caballero et al [2012] "mix accelerometer-based fall detection and computer-visionbased (visible and infrared) fall detection".…”

Section: Applications For Carementioning

confidence: 99%

Information Technology for Active Ageing: A Review of Theory and Practice

Parra¹

2014

View full text Add to dashboard Cite

Active Ageing (AA) aims to foster a physically, mentally and socially active lifestyle as a person ages. It is a complex, multi-faceted problem that involves a variety of different actors, such as policy makers, doctors, care givers, family members, friends and, of course, older adults. This survey aims to understand the role of a new actor, which increasingly plays the role of enabler and facilitator, i.e., that of the technology provider. The survey specifically focuses on Information Technology (IT), with a particular emphasis on software applications, and on how IT can prevent decline, compensate for lost capabilities, aid care, and enhance existing capabilities. The analysis confirms the crucial role of IT in AA, shows that AA requires a multidisciplinary approach, and identifies the need for better integration of hardware, software, the environment and the involved actors.

show abstract

HOLDS: Efficient Fall Detection through Accelerometers and Computer Vision

Cited by 7 publications

References 6 publications

Ubiquitous Health Monitoring: Integration of Wearable Sensors, Novel Sensing Techniques, and Body Sensor Networks

Ubiquitous Health Monitoring: Integration of Wearable Sensors, Novel Sensing Techniques, and Body Sensor Networks

Heart Attack Detection in Colour Images Using Convolutional Neural Networks

Information Technology for Active Ageing: A Review of Theory and Practice

Contact Info

Product

Resources

About