Predicting Complex Activities from Ongoing Multivariate Time Series

Abstract

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.

RETRACTED ARTICLE: Human activity recognition with deep learning: overview, challenges and possibilities

“…In this way, the mutual profound extractor uses the priori of basic tasks which are components of a composite operation. In comparison to joint research, [125] uses two conditional probabilistic models to infers a series of basic events and their resulting composite operation. The authors used an approximate sequence of acts to infer the composite behavior where time differences between single activities are drawn for the classification of the composite behavior.…”

Approaches and Applications of Early Classification of Time Series: A Review

“…Literature indicates large number of early classification approaches for time series data. These approaches addressed the problems from wide range of research areas including healthcare [46]- [48], [61]- [63], human activity recognition [8], [43], [44], industry [34], [51], [64], and so on. After making comprehensive survey, we found that UTS has attracted more researchers than MTS.…”

“…3) Model based early classification: Another set of early classification approaches [34], [42], [44], [49], [55], [58], [69] proposed mathematical models based on conditional probabilities. The approaches obtain these conditional probabilities by either fitting a discriminative classifier or using generative classifiers on training.…”

“…Using discriminative classifier [34], [49], [51], [74]- [77] Using generative classifier [42]- [44], [56]- [58], [69]…”

“…These conditional probabilities are either generated by generative classifiers or computed by fitting a discriminative classifier on training dataset. Further, there exist some approaches [42]- [44], [69] which do not incorporate the reliability parameter in the model but still provided significant earliness.…”