A Wavelet-Based Approach to Fall Detection

Palmerini, Luca; Bagalà, Fabio; Zanetti, Andrea; Klenk, Jochen; Becker, Clemens; Cappello, Angelo

doi:10.3390/s150511575

Cited by 44 publications

(47 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Droghini et al (24) proposed fall and nonfall detection systems using an acoustic signal similar to that described in Ref. 25. Guan et al (26) presented a novel method of detecting a fall using a pyroelectric infrared (PIR) sensor network similar to that of Yun and Song.…”

Section: Devices and Wearablesmentioning

confidence: 99%

Recognizing Falls, Daily Activities, and Health Monitoring by Smart Devices

Sukreep¹,

Elgazzar²,

Chu³

et al. 2019

Sensors and Materials

View full text Add to dashboard Cite

One of the biggest challenges in ageing societies is to improve life, health, safety, and support of the elderly population in their daily life. Currently, the number of elderly people living alone is increasing every year. Living alone allows more freedom but raises the risk of serious injuries or fatal accidents. Falls are the key cause of significant health problems, especially for an elderly person who lives alone. Moreover, vital signs such as heart rate, balancing activities, and environmental context are crucial in relation to the user's condition. To assist people living alone and improve their health quality, we firmly believe that the advances in Smart Devices, Smart Environment, and Internet of Things paradigms are very helpful for developing a fall and activity recognition system. We propose a system using an unobtrusive device consisting of a smartwatch and a smartphone to identify falls and thirteen daily activities (e.g., walking, running, typing, and waving the hand). The events leading to a fall, the speed of falling down, the heart rate while doing an activity, and the time passed since the fall are important data that we store to help a doctor diagnose and rehabilitate a patient. Environment sensors are used to indicate the indices of ambient conditions such as temperature, humidity, brightness, and motion detected. Suitable machine learning techniques are used for daily activity recognition, and the processing time for classification was compared on the basis of a smartwatch and an Amazon Web Services (AWS) cloud server. Threshold-based health risk analysis models are utilized for abnormal activity recognition and heart rate and heat index (temperature and humidity) determination. The system issues different types of notifications such as warning messages, sounding alarms, and phone calls to related persons such as family members, caregivers, or doctors. Various easy-to-understand visualizations are presented to track and monitor the subjects in real time, including heart rate, daily activity summary, health risk status, and environmental information.

show abstract

Section: Devices and Wearablesmentioning

confidence: 99%

Recognizing Falls, Daily Activities, and Health Monitoring by Smart Devices

Sukreep¹,

Elgazzar²,

Chu³

et al. 2019

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…Ref. [7] created a prototype wavelet of typical fall pattern by using the average acceleration sum vector. The degree of similarity of the signal to the prototype was then computed though wavelet analysis.…”

Section: Corresponding Authormentioning

confidence: 99%

Fall Detection using Lifting Wavelet Transform and Support Vector Machine

Liang

Usaha

2017

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-Frequency domain features of inertial movement enables multi-resolution analysis for fall detection, yet they are computationally intensive. This paper proposes a computationally light frequency domain feature extraction method based on lifting wavelet transform (LWT) which provides computational efficiency suitable for real-time low power devices such as wearable sensors for human fall detection. LWT is combined with support vector machine (SVM) to identify falls from activities of daily living. Performance of the Haar and Biorthogonal 2.2 wavelets were compared with the time domain feature of root-mean square acceleration using a human fall dataset. Results show that the first level detail coefficients features for both Haar and Biorthogonal 2.2 wavelets achieve good overall fall detection accuracy, sensitivity and specificity.

show abstract

“…(1) Abnormal gait behavior is detected by video frames. In [3][4][5][6][7][8][9], gait silhouette features of human body or movement trajectory features are extracted from the surveillance videos. And they are used for abnormal gait behavior detection and analysis.…”

Section: Introductionmentioning

confidence: 99%

Abnormal Gait Behavior Detection for Elderly Based on Enhanced Wigner-Ville Analysis and Cloud Incremental SVM Learning

Luo¹,

Tang²,

Xiao

2016

Journal of Sensors

View full text Add to dashboard Cite

A cloud based health care system is proposed in this paper for the elderly by providing abnormal gait behavior detection, classification, online diagnosis, and remote aid service. Intelligent mobile terminals with triaxial acceleration sensor embedded are used to capture the movement and ambulation information of elderly. The collected signals are first enhanced by a Kalman filter. And the magnitude of signal vector features is then extracted and decomposed into a linear combination of enhanced Gabor atoms. The Wigner-Ville analysis method is introduced and the problem is studied by joint time-frequency analysis. In order to solve the large-scale abnormal behavior data lacking problem in training process, a cloud based incremental SVM (CI-SVM) learning method is proposed. The original abnormal behavior data are first used to get the initial SVM classifier. And the larger abnormal behavior data of elderly collected by mobile devices are then gathered in cloud platform to conduct incremental training and get the new SVM classifier. By the CI-SVM learning method, the knowledge of SVM classifier could be accumulated due to the dynamic incremental learning. Experimental results demonstrate that the proposed method is feasible and can be applied to aged care, emergency aid, and related fields.

show abstract

A Wavelet-Based Approach to Fall Detection

Cited by 44 publications

References 30 publications

Recognizing Falls, Daily Activities, and Health Monitoring by Smart Devices

Recognizing Falls, Daily Activities, and Health Monitoring by Smart Devices

Fall Detection using Lifting Wavelet Transform and Support Vector Machine

Abnormal Gait Behavior Detection for Elderly Based on Enhanced Wigner-Ville Analysis and Cloud Incremental SVM Learning

Contact Info

Product

Resources

About