SmartSwim: An Infrastructure-Free Swimmer Localization System Based on Smartphone Sensors

Xiao, Dong; Yu, Zhiwen; Yi, Fei; Wang, Liang; Tan, Chiu C.; Guo, Bin

doi:10.1007/978-3-319-39601-9_20

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the noises among the motion data always have significant effect on fall detection accuracy, it is necessary to filter the noises [ 30 ]. Xiao et al [ 31 ] used the mean filter, the moving average filter, and the Prewitt horizontal edge-emphasizing filter to filter noise in the swimming recognition. The experiments proved that the moving average filter has the best effect on filtering noise.…”

Section: Experiments and Evaluationmentioning

confidence: 99%

An Energy-Efficient Fall Detection Method Based on FD-DNN for Elderly People

Liu

Hou

Jian

et al. 2020

Sensors

View full text Add to dashboard Cite

A fall detection module is an important component of community-based care for the elderly to reduce their health risk. It requires the accuracy of detections as well as maintains energy saving. In order to meet the above requirements, a sensing module-integrated energy-efficient sensor was developed which can sense and cache the data of human activity in sleep mode, and an interrupt-driven algorithm is proposed to transmit the data to a server integrated with ZigBee. Secondly, a deep neural network for fall detection (FD-DNN) running on the server is carefully designed to detect falls accurately. FD-DNN, which combines the convolutional neural networks (CNN) with long short-term memory (LSTM) algorithms, was tested on both with online and offline datasets. The experimental result shows that it takes advantage of CNN and LSTM, and achieved 99.17% fall detection accuracy, while its specificity and sensitivity are 99.94% and 94.09%, respectively. Meanwhile, it has the characteristics of low power consumption.

show abstract

Section: Experiments and Evaluationmentioning

confidence: 99%

An Energy-Efficient Fall Detection Method Based on FD-DNN for Elderly People

Liu

Hou

Jian

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Another study looked at using location information to keep track of swimmers in a pool and provide information on their current status (e.g., swimming stroke being performed, walking, not moving). Such a system could be used by lifeguards to help keep track of all swimmers in order to quickly notice a need for the lifeguard to step in [11].…”

Section: Introductionmentioning

confidence: 99%

Wrist-Based Survival Swimming Activity Recognition System

Tandon,

Powell,

Polsley

et al.

2023 ASEE GSW Proceedings

View full text Add to dashboard Cite

According to the World Health Organization, over 300,000 drowning deaths occur worldwide each year. One of the main contributors is lack of survival swimming knowledge; for example, the Redcross indicates that 50% of the population in the United States does not know how to swim. In this work, we explore the potential of using wearable technology to help address the lack of swimming training. Wearable technology like Fitbit or Apple Watch are smart devices that recognize people's activities and are increasingly integral to tracking one's health and well-being. When it comes to swimming or other aquatic activities, wearables have focused on professional and elite swimmers where devices support lap swimming strokes (backstroke, breaststroke, butterfly, freestyle) which are common in Olympic competitions. Our research expands lap swimming activity recognition by incorporating two survival swimming activities: treading water and sidestroke. We present a study which collects all six stroke types from a wrist-worn device, and we develop a machine learning algorithm that classifies activities with an F-measure of 0.94.

show abstract