A Multi-sensor Fall Detection System Based on Multivariate Statistical Process Analysis

Yue, Wu; Su, Yi-Wen; Hu, Yachao; Yu, Ning; Ran, Feng

doi:10.1007/s40846-018-0404-z

Cited by 16 publications

(9 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dynamic or adaptive threshold-based fall detection and prevention methods have been proposed to solve these problems. Wu et al [127] proposed an adaptive threshold method to detect falls based on a multivariate control chart. This adaptive threshold method had high detection performance as it considered individual historical data, that is to say, this constructed fall detection was a person-specific method.…”

Section: ) Threshold-based Fall Detection and Fall Preventionmentioning

confidence: 99%

“…Statistics process can also be used to detect or prevent falls. Wu et al [127] applied Hotelling's T2 statistic to detect falls, while Hu and Qu [153] proposed ARIMA-based statistical process-based pre-impact fall detector. Actually, both machine learning and statistics-based fall detection/prevention algorithms have been widely studied, as they can achieve high accuracy than threshold-based fall detection/prevention methods.…”

Section: ) Non-threshold-based Fall Detection and Fall Preventionmentioning

confidence: 99%

See 1 more Smart Citation

Research of Fall Detection and Fall Prevention Technologies: A Systematic Review

2019

View full text Add to dashboard Cite

Falls are abnormal activity events that occur infrequently; however, they are serious health problems among elderly individuals. With the advancements of technologies, falls have been widely studied by scientific researchers to minimize serious consequences and negative impacts. Fall detection and fall prevention are two strategies to tackle fall issues with a variety of sensing techniques and classifier models. Currently, many reviews on fall-related technologies have been presented and analyzed; however, most of them give surveys on the subfield of fall-related systems, while others are not extensive and comprehensive reviews. In fact, the latest researches have a new trend of fusion-based methods to improve the performance of the fall-related systems based on a combination of different sensors or classifier models. Adaptive threshold and radio frequency-based systems are also researched and proposed recently, which are seldom mentioned in other reviews. Therefore, a global taxonomy for current fall-related studies from four aspects, including current literature reviews, fall detection, and prevention systems based on different sensor apparatus and analytic algorithm, low power techniques, and sensor placements for fall-related systems are conducted in this paper. Several research challenges and issues in the fall-related field are also discussed and analyzed. The objective of this review paper is to conclude and provide a good position of current fall-related studies to inspire researchers in this field. INDEX TERMSAdaptive algorithm, classification algorithms, fall detection, fall prevention, low power techniques, sensing techniques. LINGMEI REN received the Ph.D. degree from the

show abstract

Section: ) Threshold-based Fall Detection and Fall Preventionmentioning

confidence: 99%

Section: ) Non-threshold-based Fall Detection and Fall Preventionmentioning

confidence: 99%

Research of Fall Detection and Fall Prevention Technologies: A Systematic Review

2019

View full text Add to dashboard Cite

show abstract

“…e adaptive threshold value-based fall event detection and prevention methods are devised to overcome fixed threshold value-based methods' pitfalls. In a study, researchers devised an adaptive threshold approach to detect fall events relying on a multivariate control chart [27]. is adaptive threshold approach showed high detection accuracy with an individual's historical data, which can be considered a person-specific method.…”

Section: Related Workmentioning

confidence: 99%

Falling and Drowning Detection Framework Using Smartphone Sensors

Alqahtani

Alsubai

Sha

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Advancements in health monitoring using smartphone sensor technologies have made it possible to quantify the functional performance and deviations in an individual’s routine. Falling and drowning are significant unnatural causes of silent accidental deaths, which require an ambient approach to be detected. This paper presents the novel ambient assistive framework Falling and Drowning Detection (FaDD) for falling and drowning detection. FaDD perceives input from smartphone sensors, such as accelerometer, gyroscope, magnetometer, and GPS, that provide accurate readings of the movement of an individual’s body. FaDD hierarchically recognizes the falling and drowning actions by applying the machine learning model. The approach activates embedding, in a smartphone application, to notify emergency alerts to various stakeholders (i.e., guardian, rescue, and close circle community) about drowning of an individual. FaDD detects falling, drowning, and routine actions with good accuracy of 98%. Furthermore, the FaDD framework enhances coordination to provide more efficient and reliable healthcare services to people.

show abstract

“…Adaptive thresholds can be dynamically calculated based on history and processing of individual data movement and motion information [75]- [77] or based on clustering of people according to their gender, height, weight and age [78]. In [79] pretested reference templates for each type of fall using comparison between the angles and angular velocities of the thigh segment between falls and normal activities are used for fall detection.…”

Section: ) Fall Detection and Preventionmentioning

confidence: 99%

Wearables and the Internet of Things (IoT), Applications, Opportunities, and Challenges: A Survey

2020

View full text Add to dashboard Cite

Smart wearables collect and analyze data, and in some scenarios make a smart decision and provide a response to the user and are finding more and more applications in our daily life. In this paper, we comprehensively survey the most recent and important research works conducted in the area of wearable Internet of Things (IoT) and classify the wearables into four major clusters: (i) health, (ii) sports and daily activity, (iii) tracking and localization, and (iv) safety. The fundamental differences of the algorithms associated within each cluster are grouped and analyzed and the research challenges and open issues in each cluster are discussed. This survey reveals that although Cellular IoT (CIoT) has many advantages and can bring enormous applications to IoT wearables, it has been rarely studied by the researchers. This article also addresses the opportunities and challenges related to implementing CIoT-enabled wearables.INDEX TERMS Smart wearables, Internet of Things, cellular IoT.

show abstract

A Multi-sensor Fall Detection System Based on Multivariate Statistical Process Analysis

Cited by 16 publications

References 55 publications

Research of Fall Detection and Fall Prevention Technologies: A Systematic Review

Research of Fall Detection and Fall Prevention Technologies: A Systematic Review

Falling and Drowning Detection Framework Using Smartphone Sensors

Wearables and the Internet of Things (IoT), Applications, Opportunities, and Challenges: A Survey

Contact Info

Product

Resources

About