Human Postures Recognition Based on D-S Evidence Theory and Multi-sensor Data Fusion

  title={Human Postures Recognition Based on D-S Evidence Theory and Multi-sensor Data Fusion},
  author={Wenfeng Li and Junrong Bao and Xiuwen Fu and Giancarlo Fortino and Stefano Galzarano},
  journal={2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)},
  • Wenfeng LiJunrong Bao S. Galzarano
  • Published 13 May 2012
  • Computer Science
  • 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)
Body Sensor Networks (BSNs) are conveying notable attention due to their capabilities in supporting humans in their daily life. In particular, real-time and noninvasive monitoring of assisted livings is having great potential in many application domains, such as health care, sport/fitness, e-entertainment, social interaction and e-factory. And the basic as well as crucial feature characterizing such systems is the ability of detecting human actions and behaviors. In this paper, a novel approach… 

Figures and Tables from this paper

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

An automatic fall detection system using multiple wearable sensors and finding optimal sensor attachment locations is designed and three sensors fixed on the waist, arm and thigh were able to efficiently distinguish falls from non-falls.

Sitting Posture Recognition Based on Data Fusion on Pressure Cushion

The body pressure collection system is built; it is explored the relationship between the pressure distributions and sitting posture; based on daily sitting posture of disabled and older people , the eight states is summarized that people sit on the wheelchair, and using density-based clustering methods establish the evaluation model of difference sitting postures.

Study on Fear Emotion Recognition Based on Traditional Chinese Medicine and Body Sensor Network

Body sensor network is used to perceive human physiological parameters, especially human skin resistance in and out of adjacent fingers and the pulse information in ulnar-sided position on the right hand and it perceives psychological states of the human objectively and directly, which will provide a prototype model to obtain human physiological and psychological indexes objectively.

A Survey of Body Sensor Networks

The research status of BSNs, the analysis of hotspots, and future development trends are introduced, and the discussion of major challenges and technical problems facing currently are discussed.


The proposed framework consists in the combination of the events’ uncertainty computation with the trained database and the fusion method based on the conflict management of evidences, and the inference of DempsterShafer theory resembles human perception and fits for uncertainty and conflict management with incomplete information.

Collaborative Body Sensor Networks

The paper presents C-SPINE, an enhancement of the SPINE middleware for CBSN applications, and a collaborative emotion detection system, integrating heart rate sensing with handshake detection, is developed through C- SPINE and experimentally analyzed.

A novel bio-kinematic encoder for human exercise representation and decomposition - Part 2: Robustness and optimisation

Bio-kinematic characterisations of human exercises constitute dealing with parameters such as velocity, acceleration, joint angles, etc. A majority of these are measured directly from various sensors



Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring

Results demonstrate the feasibility of implementing an accelerometry-based, real-time movement classifier using embedded intelligence.

Ambient and Wearable Sensor Fusion for Activity Recognition in Healthcare Monitoring Systems

A robust framework for enhanced activity recognition is introduced by integrating an ear-worn activity recognition (e-AR) sensor with ambient blob-based vision sensors by using a Gaussian Mixture Model Bayes classifier.

From Modeling to Implementation of Virtual Sensors in Body Sensor Networks

A multi-layer task model based on the concept of Virtual Sensors to improve architecture modularity and design reusability is presented and results confirm that great effectiveness can be achieved in designing and implementing BSN applications through the Virtual Sensor approach while maintaining high efficiency and accuracy.

Interfacing human and computer with wireless body area sensor networks: the WiMoCA solution

This paper demonstrates the flexibility of a custom-designed WBASN called WiMoCA with respect to a wide range of posture and activity recognition applications by means of practical implementation and on-the-field testing.

A Practical Approach to Recognizing Physical Activities

This paper presents an approach to building a system that exhibits these properties and provides evidence based on data for 8 different activities collected from 12 different subjects, and indicates that the system has an accuracy rate of approximately 90% while meeting the requirements.

Activity monitoring from real-time triaxial accelerometer data using sensor network

Methodologies and parameters used for chest case worn sensor as well as for wrist worn sensor are presented and compare and results shows chest is better position to activity monitoring and fall detection.

Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly

The ambulatory system showed a very high accuracy (> 99%) in identifying the 62 transfers or rolling out of bed, as well as 144 different posture changes to the back, ventral, right and left sides, in both first and second studies.

An active vision system for fall detection and posture recognition in elderly healthcare

An active vision system for the automatic detection of falls and the recognition of several postures for elderly homecare applications using a wall-mounted Time-Of-Flight camera with high performances in terms of efficiency and reliability on a large real dataset.

Analyzing features for activity recognition

This paper presents a systematic analysis of features computed from a real-world data set and shows how the choice of feature and the window length over which the feature is computed affects the recognition rates for different activities.

Activity recognition and monitoring using multiple sensors on different body positions

The design of an activity recognition and monitoring system based on the eWatch, multi-sensor platform worn on different body positions, is presented and the tradeoff between recognition accuracy and computational complexity is analyzed.