Granger-causality: An efficient single user movement recognition using a smartphone accelerometer sensor

Avilés‐Cruz, Carlos; Rodriguez-Martinez, Eduardo; Villegas-Cortéz, Juan; Ferreyra-Ramírez, Andrés

doi:10.1016/j.patrec.2019.06.029

Cited by 20 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the validity of the human activity model, another set of experiments was carried out as follows: First, the information gain of each sensor was calculated according to the Formulas (3)- (6). The training set (including the validation set) without sliding window processing was used to calculate the information gain.…”

Section: Experiments On Information Gain-based Human Activity Modelmentioning

confidence: 99%

“…Human activity recognition (HAR) technology [ 1 ] has been widely used in various areas, such as security monitoring [ 2 ], human-machine interaction [ 3 ], sports analysis [ 4 ], medical treatment [ 5 ], and health care [ 6 ], etc. According to the types of sensors used, HAR systems can be mainly divided into environmental sensor-based HAR, video-based HAR, and wearable sensor-based HAR [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

Liu

Jian

Ren

et al. 2021

Entropy

View full text Add to dashboard Cite

Wearable sensor-based HAR (human activity recognition) is a popular human activity perception method. However, due to the lack of a unified human activity model, the number and positions of sensors in the existing wearable HAR systems are not the same, which affects the promotion and application. In this paper, an information gain-based human activity model is established, and an attention-based recurrent neural network (namely Attention-RNN) for human activity recognition is designed. Besides, the attention-RNN, which combines bidirectional long short-term memory (BiLSTM) with attention mechanism, was tested on the UCI opportunity challenge dataset. Experiments prove that the proposed human activity model provides guidance for the deployment location of sensors and provides a basis for the selection of the number of sensors, which can reduce the number of sensors used to achieve the same classification effect. In addition, experiments show that the proposed Attention-RNN achieves F1 scores of 0.898 and 0.911 in the ML (Modes of Locomotion) task and GR (Gesture Recognition) task, respectively.

show abstract

Section: Experiments On Information Gain-based Human Activity Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

Liu

Jian

Ren

et al. 2021

Entropy

View full text Add to dashboard Cite

show abstract

“…A causality-induced hierarchical Bayesian model was suggested to deal with interaction AR [64]. In [43], a G-causality-based framework was presented for the recognition of single-user activity. Additionally, another study proposed a human-object interaction model that integrates the causal relationship between humans and objects based on the TE for video AR [39].…”

Section: A Temporal Dependency-based Feature Extractionmentioning

confidence: 99%

“…Studies on quantitative characterization while extracting causality on a given time series have been reported [42][43][44][45][46]. Among them, a well-known study analyzed Granger causality (G-causality) [42][43], which represents the causality between two time series using an auto-regression model. However, G-causality is limited in dealing with nonlinear relationships because it is based on a linear model.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Human Activity Recognition Based on Causality Feature Extraction

et al. 2021

View full text Add to dashboard Cite

We propose a novel data-driven feature extraction approach based on direct causality and fuzzy temporal windows (FTWs) to improve the precision of human activity recognition and mitigate the problems of easily-confused activities and unlabeled data, which significantly degrade classification performance owing to the correlation of labeled data. In recognizing activities, the proposed approach not only considers the importance of oncoming short-term sensor data but also considers the continuity from past activities of the preceding long-term sensor data. In terms of the oncoming data, the causality feature is extracted using the direct transfer entropy to determine the unique pattern of an activity, which represents the quantified causal relationship between sensor activations. In terms of the preceding data, several hours of historical data are compressed to fuzzy features based on FTWs. Subsequently, the causality and fuzzy features are fused by matrix multiplication to express distinct features of activities. To effectively learn the spatiotemporal dependencies of the fused feature, deep long short-term memory (LSTM), two-dimensional convolutional neural network (2D-CNN), and hybrid models composed of a combination of LSTM and CNN were used. Leave-one-day-out cross-validation was performed based on the CASAS open datasets, including Aruba, Cairo, and Milan. The results showed that the macro-F1-scores were improved by 16.4, 37.5, and 18.5%, respectively, compared with those of the FTW-only environments. In addition, the proposed approach could improve the precision of activity recognition and mitigate the problems associated with the environments containing unlabeled data.INDEX TERMS activity of daily living, activity recognition, causality, convolutional neural network, deep learning, fuzzy feature, long short-term memory.

show abstract

“…Data can come from different sources. Many researchers [12,13,14] use only sensors embedded in a smartphone to classify user activities. Radio-based activity recognition is less popular, but provides lower power consumption and lower cost of production of the sensors [15].…”

Section: Introductionmentioning

confidence: 99%

Improving state estimation through projection post-processing for activity recognition in football

Ciszewski¹,

Söhl²,

Jongbloed³

2021

Preprint

View full text Add to dashboard Cite

The past decade has seen an increased interest in human activity recognition. Most commonly, the raw data coming from sensors attached to body parts are unannotated, which creates a need for fast labelling method. Part of the procedure is choosing or designing an appropriate performance measure. We propose a new performance measure, the Locally Time-Shifted Measure, which addresses the issue of timing uncertainty of state transitions in the classification result. Our main contribution is a novel post-processing method for binary activity recognition. It improves the accuracy of the classification methods, by correcting for unrealistically short activities in the estimate.

show abstract

Granger-causality: An efficient single user movement recognition using a smartphone accelerometer sensor

Cited by 20 publications

References 25 publications

An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

Deep Learning for Human Activity Recognition Based on Causality Feature Extraction

Improving state estimation through projection post-processing for activity recognition in football

Contact Info

Product

Resources

About