Semi-supervised fall detection algorithm using fall indicators in smartphone

Fahmi, P.N. Ali; Viet, Vo Quang; Choi, Deokjai

doi:10.1145/2184751.2184890

Cited by 24 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most common examples about prevention is accident detection (e.g. falls) that has been addressed using sensors and algorithms [9]. Furthermore, self-monitoring of health parameters, as part of primary prevention, has been tightly coupled with health promotion and challenges related to lifestyle and behavior changes [20].…”

Section: Preventive Self-monitoring Technologymentioning

confidence: 99%

Understanding challenges and opportunities of preventive blood pressure self-monitoring at home

Grönvall

Verdezoto

2013

Proceedings of the 31st European Conference on Cognitive Ergonomics

View full text Add to dashboard Cite

Self-monitoring activities are increasingly parts of people's everyday lives. Some of these measurements are performed voluntary rather than being referred by a physician, and conducted because of either a preventive health interest, or to better understand the body and its functions (so-called 'Quantified Self'). In this article, we explore socio-technical complexities that may occur when introducing preventive health-measurement technologies into older adults' daily routines and everyday lives. In particular, the original study investigated blood pressure (BP) measurement in non-clinical settings, to understand existing challenges, and uncover opportunities for self-monitoring technologies to support preventive healthcare activities among older adults. From our study, several aspects emerged that are important to consider when designing preventive self-monitoring technology, such as the complexity of guidelines for self-measuring, the importance of interpretation, understanding and health awareness, sharing self-monitoring information for prevention, various motivational factors, the role of the doctor in prevention, the home as a distributed information space, and so on. An awareness of these aspects may help designers to develop better support tools for people's preventive self-monitoring needs, compared to existing solutions. Supporting the active and informed individual may improve their self-care, awareness, and implementation of preventive care. Based on our study, we reflect on the findings to illustrate how these aspects may also inform both people engaged in Quantified Self activities and designers alike, and the tools and approaches that have sprung from the so-called 'Quantified Self' movement.

show abstract

Section: Preventive Self-monitoring Technologymentioning

confidence: 99%

Understanding challenges and opportunities of preventive blood pressure self-monitoring at home

Grönvall

Verdezoto

2013

Proceedings of the 31st European Conference on Cognitive Ergonomics

View full text Add to dashboard Cite

show abstract

“…Zhao et al [26] implemented three machine-learning algorithms-namely C4.5 DTC, NB, and SVM and compared their performances based on recognition accuracy. Fahmi et al [27] designed a semisupervised algorithm to detect a genuine fall event with smartphone. He and Li [28] employed a combined algorithm of Fisher's discriminant ratio (FDR) criterion and J3 criterion for feature selection and hierarchical classifiers to recognize 15 activities including fall events.…”

Section: Smartphone-based Systemsmentioning

confidence: 99%

“…The outcomes are often represented by four possible situations [24,30]: TP, a fall occurred and was correctly detected; FP, the system declared a fall that did not occur; true negative (TN), a fall-like event was not misclassified as a fall event; false negative (FN), a fall occurred, but the system missed it. The reliability of systems is usually evaluated based on the following parameters: sensitivity (SE) = TP/(TP+FN), which is the ratio of fallers correctly classified as fall event [27,[31][32][33][34]; specificity (SP) = TN/(TP+FN), which is the ratio of fall-like events correctly classified as nonfallers [35][36][37][38]; accuracy = (TP+TN)/(TP+FP+FN+TN), which is the ratio of true results in the whole data set [26,28,29,39]. Some works measured the performance in a different way; they utilized precision = (∩)/and recall-namely, the number of correct results divided by the total outputs-as the performance indexes [40][41][42].…”

Section: Performance Evaluationsmentioning

confidence: 99%

The Emerging Wearable Solutions in mHealth

Zhao¹,

Li²,

Tsien³

2016

Mobile Health Technologies - Theories and Applications

View full text Add to dashboard Cite

The marriage of wearable sensors and smartphones have fashioned a foundation for mobile health technologies that enable healthcare to be unimpeded by geographical boundaries. Sweeping efforts are under way to develop a wide variety of smartphonelinked wearable biometric sensors and systems. This chapter reviews recent progress in the field of wearable technologies with a focus on key solutions for fall detection and prevention, Parkinson's disease assessment and cardiac disease, blood pressure and blood glucose management. In particular, the smartphone-based systems, without any external wearables, are summarized and discussed.

show abstract

“…To achieve this goal we can use learning techniques like the semi-supervised algorithm used by Ali Fahmi et al in [19]. Each user moves differently, for this reason, the system should have adjusted the classification parameters to the particular movements of the user.…”

mentioning

confidence: 99%

Smart Collaborative Mobile System for Taking Care of Disabled and Elderly People

et al. 2013

View full text Add to dashboard Cite

Official statistics data show that in many countries the population is aging. In addition, there are several illnesses and disabilities that also affect a small sector of the population. In recent years, researchers and medical foundations are working in order to develop systems based on new technologies and enhance the quality of life of them. One of the cheapest ways is to take advantage of the features provided by the smartphones. Nowadays, the development of reduced size smartphones, but with high processing capacity, has increased dramatically. We can take profit of the sensors placed in smartphones in order to monitor disabled and elderly people. In this paper, we propose a smart collaborative system based on the sensors embedded in mobile devices, which permit us to monitor the status of a person based on what is happening in the environment, but comparing and taking decisions based on what is happening to its neighbors. The proposed protocol for the mobile ad hoc network and the smart system algorithm are described in detail. We provide some measurements showing the decisions taken for several common cases and we also show the performance of our proposal when there is a medium size group of disabled or elderly people. Our proposal can also be applied to take care of children in several situations.

show abstract

Semi-supervised fall detection algorithm using fall indicators in smartphone

Cited by 24 publications

References 11 publications

Understanding challenges and opportunities of preventive blood pressure self-monitoring at home

Understanding challenges and opportunities of preventive blood pressure self-monitoring at home

The Emerging Wearable Solutions in mHealth

Smart Collaborative Mobile System for Taking Care of Disabled and Elderly People

Contact Info

Product

Resources

About