Mining from Time Series Human Movement Data

Tseng, Chiu-Che; Cook, Diane J.

doi:10.1109/icsmc.2006.384617

Cited by 9 publications

(2 citation statements)

References 5 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-Layer Perceptron (MLP) neural networks are used to identify the movements data collected from a WSN [15] [16]. For instance, the authors in [17] have applied different algorithms to recognize the age categories of data representing waking pattern and to identify the change in volunteers behaviour change.…”

Section: Related Workmentioning

confidence: 99%

Behavioural pattern identification and prediction in intelligent environments

Mahmoud

Lotfi

Langensiepen

2013

Applied Soft Computing

View full text Add to dashboard Cite

In this paper, the application of soft computing techniques in prediction of an occupant's behaviour in an inhabited intelligent environment is addressed. In this research, daily activities of elderly people who live in their own homes suffering from dementia are studied. Occupancy sensors are used to extract the movement patterns of the occupant. The occupancy data is then converted into temporal sequences of activities which are eventually used to predict the occupant behaviour. To build the prediction model, different dynamic recurrent neural networks are investigated. Recurrent neural networks have shown a great ability in finding the temporal relationships of input patterns. The experimental results show that non-linear autoregressive network with exogenous inputs model correctly extracts the long term prediction patterns of the occupant and outperformed the Elman network. The results presented here are validated using data generated from a simulator and real environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Behavioural pattern identification and prediction in intelligent environments

Mahmoud

Lotfi

Langensiepen

2013

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…The authors of [126] used MLP as the prediction technique to anticipate the subject's next movement. The authors of [127] have applied different learning algorithms to recognize the age categories and to detect possible changes in individual's health condition based on walking data patterns. The used algorithms were MLP, decision tree, support vector classifier, Naive Bayes and Bayesnet.…”

Section: Computational Intelligence Techniquesmentioning

confidence: 99%

A survey on health monitoring systems for health smart homes

Mshali

Lemlouma

Moloney

et al. 2018

International Journal of Industrial Ergonomics

193

View full text Add to dashboard Cite

Aging population ratios are rising significantly. Health monitoring systems (HMS) in smart environments have evolved rapidly to become a viable alternative to traditional healthcare solutions. The aim of HMS is to not only reduce costs but to also provide timely e-health services to individuals wishing to maintain their independence. In this way, elderly people can avoid, for as long as possible, any interaction with healthcare institutions (e.g. nursing homes and hospitals), which in turn reduces pressure on the health system. To fully realise this vision of seamless e-health services supporting people in need of them, a number of challenges that need further investigation still exist. To this end, we provide an overview of the current state of the art for smart health monitoring systems. We review HMS in smart environments from a general perspective and with a particular focus on systems for the elderly and dependent people. We look at the challenges for these systems from the perspective of developing the technology itself, system requirements, system design and modelling. We present a consolidated picture of the most important functions and services offered by HMS for monitoring and detecting human behaviour including its concepts, approaches, and processing techniques. Moreover, we provide an extensive, in-depth analysis and evaluation of the existing research findings in the area of e-health systems. Finally, we present challenges and open issues facing the smart HMS field and we make recommendations on how to improve future systems.

show abstract

Body Sensor Networks for Activity and Gesture Recognition

Krishnan

Panchanathan

2013

The Art of Wireless Sensor Networks

View full text Add to dashboard Cite

Mining from Time Series Human Movement Data

Cited by 9 publications

References 5 publications

Behavioural pattern identification and prediction in intelligent environments

Behavioural pattern identification and prediction in intelligent environments

A survey on health monitoring systems for health smart homes

Body Sensor Networks for Activity and Gesture Recognition

Contact Info

Product

Resources

About