Comparative study of machine learning algorithms for activity recognition with data sequence in home-like environment

Fan, Xiangyu; Zhang, Huiguo; Leung, Cyril; Miao, Chunyan

doi:10.1109/mfi.2016.7849484

Cited by 10 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decade, a large body of work has studied recognition of simple human activities [Yang, 2009;Krishnan and Cook, 2014;Yang et al, 2015;Fan et al, 2016;Hammerla et al, 2016]. Recently, the rapid development of sensor networks enables the recognition of complex activities (CAs) from multivariate time series (MTS).…”

Section: Related Workmentioning

confidence: 99%

“…There are a few works targeting on early classification of time series data [Xing et al, 2009;Ghalwash and Obradovic, 2012]. Xing et al [2009] develop a 1-nearest neighbor classification model for an early prediction on univariate time series.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, early recognition of human activities based on sensor MTS data incurs substantial challenges. There are a few studies for early classification on time series data [Xing et al, 2009;Ghalwash and Obradovic, 2012;Anderson et al, 2012;Lin et al, 2015;Dachraoui et al, 2015]. However, the task of these methods is finding one optimal early stage to classify a time series, thus they are not suitable for predicting CAs at any specific early stage.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Complex Activities from Ongoing Multivariate Time Series

Cheng

Erfani

Zhang

et al. 2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

The rapid development of sensor networks enables recognition of complex activities (CAs) using multivariate time series. However, CAs are usually performed over long periods of time, which causes slow recognition by models based on fully observed data. Therefore, predicting CAs at early stages becomes an important problem. In this paper, we propose Simultaneous Complex Activities Recognition and Action Sequence Discovering (SimRAD), an algorithm which predicts a CA over time by mining a sequence of multivariate actions from sensor data using a Deep Neural Network. SimRAD simultaneously learns two probabilistic models for inferring CAs and action sequences, where the estimations of the two models are conditionally dependent on each other. SimRAD continuously predicts the CA and the action sequence, thus the predictions are mutually updated until the end of the CA. We conduct evaluations on a real-world CA dataset consisting of a rich amount of sensor data, and the results show that SimRAD outperforms state-of-the-art methods by average 7.2% in prediction accuracy with high confidence.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Complex Activities from Ongoing Multivariate Time Series

Cheng

Erfani

Zhang

et al. 2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…For example, Fan et al [26] studied three neural network structures (Gated Recurrent Unit, Long Short-Term Memory, Recurrent Neural Network) and showed that a simple structure that remembers history as meta-layers outperformed recurrent networks. The sensors they used include grid-eye infrared array, force and noise sensors as well as electrical current detectors.…”

Section: Related Workmentioning

confidence: 99%

“…Dynamic Bayesian Networks (e.g., [23]), Hidden Markov Models (e.g., [24]) and Conditional Random Fields (e.g., [25]) are popular methods due to their ability to recognise latent random variables in observing sequences of sensor-generated data. Other approaches rely on Artificial Neural Networks (e.g., [26]). A more detailed discussion will be given in Section 2.…”

Section: Introductionmentioning

confidence: 99%

Using Sensors to Study Home Activities

Jiang

Pozza

Gunnarsdóttir

et al. 2017

JSAN

View full text Add to dashboard Cite

Abstract:Understanding home activities is important in social research to study aspects of home life, e.g., energy-related practices and assisted living arrangements. Common approaches to identifying which activities are being carried out in the home rely on self-reporting, either retrospectively (e.g., interviews, questionnaires, and surveys) or at the time of the activity (e.g., time use diaries). The use of digital sensors may provide an alternative means of observing activities in the home. For example, temperature, humidity and light sensors can report on the physical environment where activities occur, while energy monitors can report information on the electrical devices that are used to assist the activities. One may then be able to infer from the sensor data which activities are taking place. However, it is first necessary to calibrate the sensor data by matching it to activities identified from self-reports. The calibration involves identifying the features in the sensor data that correlate best with the self-reported activities. This in turn requires a good measure of the agreement between the activities detected from sensor-generated data and those recorded in self-reported data. To illustrate how this can be done, we conducted a trial in three single-occupancy households from which we collected data from a suite of sensors and from time use diaries completed by the occupants. For sensor-based activity recognition, we demonstrate the application of Hidden Markov Models with features extracted from mean-shift clustering and change points analysis. A correlation-based feature selection is also applied to reduce the computational cost. A method based on Levenshtein distance for measuring the agreement between the activities detected in the sensor data and that reported by the participants is demonstrated. We then discuss how the features derived from sensor data can be used in activity recognition and how they relate to activities recorded in time use diaries.

show abstract

A Comparative Study on Classifying Human Activities Using Classical Machine and Deep Learning Methods

Bozkurt

2021

Arab J Sci Eng

View full text Add to dashboard Cite

Comparative study of machine learning algorithms for activity recognition with data sequence in home-like environment

Cited by 10 publications

References 23 publications

Predicting Complex Activities from Ongoing Multivariate Time Series

Predicting Complex Activities from Ongoing Multivariate Time Series

Using Sensors to Study Home Activities

A Comparative Study on Classifying Human Activities Using Classical Machine and Deep Learning Methods

Contact Info

Product

Resources

About