Non-Linear Chaotic Features-Based Human Activity Recognition

Tu, Pengjia; Li, Junhuai; Cao, Ting; Wang, Kan

doi:10.3390/electronics10020111

Cited by 8 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different sEMG features can reflect various muscle statuses during movement. Moreover, as sEMG belongs to the nonlinear time series, here, six nonlinear features from sEMG, i.e., ApEn, SampEn, FuzzyEn, LZC, Lyapunov, and CD, are extracted [21]. Specifically, entropy could characterize the complexity of the signal series, and the greater the values are, the more complex the signal is.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Chaotic features. Motivated by our previous works [21], both CD and Lyapunov are extracted as the chaotic features, to reflect the complexity of sEMG signals.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Nevertheless, if all features are directly input into the classification model, it will not only increase the complexity and time of the training model, but also the recognition accuracy of the classifier. In addition, motivated by [21], due to the similarity between the features, there is a situation in which the accuracy decreases with the increase of dimension of multi-feature combination. Hence, it is necessary to discriminate and analyze the FS value of extracted features.…”

Section: Selection Of Musclesmentioning

confidence: 99%

See 2 more Smart Citations

Lower Limb Motion Recognition with Improved SVM Based on Surface Electromyography

Tu,

Li,

Wang

2024

Sensors

Self Cite

View full text Add to dashboard Cite

During robot-assisted rehabilitation, failure to recognize lower limb movement may efficiently limit the development of exoskeleton robots, especially for individuals with knee pathology. A major challenge encountered with surface electromyography (sEMG) signals generated by lower limb movements is variability between subjects, such as motion patterns and muscle structure. To this end, this paper proposes an sEMG-based lower limb motion recognition using an improved support vector machine (SVM). Firstly, non-negative matrix factorization (NMF) is leveraged to analyze muscle synergy for multi-channel sEMG signals. Secondly, the multi-nonlinear sEMG features are extracted, which reflect the complexity of muscle status change during various lower limb movements. The Fisher discriminant function method is utilized to perform feature selection and reduce feature dimension. Then, a hybrid genetic algorithm-particle swarm optimization (GA-PSO) method is leveraged to determine the best parameters for SVM. Finally, the experiments are carried out to distinguish 11 healthy and 11 knee pathological subjects by performing three different lower limb movements. Results demonstrate the effectiveness and feasibility of the proposed approach in three different lower limb movements with an average accuracy of 96.03% in healthy subjects and 93.65% in knee pathological subjects, respectively.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

“…Chaotic features. Motivated by our previous works [21], both CD and Lyapunov are extracted as the chaotic features, to reflect the complexity of sEMG signals.…”

Section: Feature Extractionmentioning

confidence: 99%

Section: Selection Of Musclesmentioning

confidence: 99%

See 1 more Smart Citation

Lower Limb Motion Recognition with Improved SVM Based on Surface Electromyography

Tu,

Li,

Wang

2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…This study included only four features-three numerical features (FL, AB_AD, and IN_EX) representing human activity time series sensor data, which are non-linear in character [45], and one categorical feature representing roof slope angles (S). Moreover, placing and nailing shingle phases (classes P2 and P5) had more observations than the others due to the relatively higher durations involved in these two specific phases, resulting in a non-uniform distribution of class labels and, hence, an imbalanced dataset.…”

Section: Selection Of Classifiersmentioning

confidence: 99%

Automated Classification of the Phases Relevant to Work-Related Musculoskeletal Injury Risks in Residential Roof Shingle Installation Operations Using Machine Learning

et al. 2023

View full text Add to dashboard Cite

Awkward kneeling in sloped shingle installation operations exposes roofers to knee musculoskeletal disorder (MSD) risks. To address the varying levels of risk associated with different phases of shingle installation, this research investigated utilizing machine learning to automatically classify seven distinct phases in a typical shingle installation task. The classification process relied on analyzing knee kinematics data and roof slope information. Nine participants were recruited and performed simulated shingle installation tasks while kneeling on a sloped wooden platform. The knee kinematics data were collected using an optical motion capture system. Three supervised machine learning classification methods (i.e., k-nearest neighbors (KNNs), decision tree (DT), and random forest (RF)) were selected for evaluation. The KNN classifier provided the best performance for overall accuracy. The results substantiated the feasibility of applying machine learning in classifying shingle installation phases from workers’ knee joint rotation and roof slope angles, which may help facilitate method and tool development for automated knee MSD risk surveillance and assessment among roofers.

show abstract

“…However, the quality of reconstruction depends on the choice of reconstruction parameters, size and delay. Now, with the reconstructed phase space [16][17][18], it is possible to analyze the dynamics of nonlinear systems using the recurrence plot method, which is a two-dimensional representation of the recurrences of the states of a system [19][20][21]. This method can highlight hidden correlations in the system through the presence of textures that are related to typical behaviors in terms of system dynamics [22,23].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Time Series Analysis in Unstable Periodic Orbits Identification-Control Methods of Nonlinear Systems

Ivan

Arva

2022

Electronics

View full text Add to dashboard Cite

The main purpose of this paper is to present a solution to the well-known problems generated by classical control methods through the analysis of nonlinear time series. Among the problems analyzed, for which an explanation has been sought for a long time, we list the significant reduction in control power and the identification of unstable periodic orbits (UPOs) in chaotic time series. To accurately identify the type of behavior of complex systems, a new solution is presented that involves a method of two-dimensional representation specific to the graphical point of view, and in particular the recurrence plot (RP). An example of the issue studied is presented by applying the recurrence graph to identify the UPO in a chaotic attractor. To identify a certain type of behavior in the numerical data of chaotic systems, nonlinear time series will be used, as a novelty element, to locate unstable periodic orbits. Another area of use for the theories presented above, following the application of these methods, is related to the control of chaotic dynamical systems by using RP in control techniques. Thus, the authors’ contributions are outlined by using the recurrence graph, which is used to identify the UPO from a chaotic attractor, in the control techniques that modify a system variable. These control techniques are part of the closed loop or feedback strategies that describe control as a function of the current state of the UPO stabilization system. To exemplify the advantages of the methods presented above, the use of the recurrence graph in the control of a buck converter through the application of a phase difference signal was analyzed. The study on the command of a direct current motor using a buck converter shows, through a final concrete application, the advantages of using these analysis methods in controlling dynamic systems.

show abstract

Non-Linear Chaotic Features-Based Human Activity Recognition

Cited by 8 publications

References 20 publications

Lower Limb Motion Recognition with Improved SVM Based on Surface Electromyography

Lower Limb Motion Recognition with Improved SVM Based on Surface Electromyography

Automated Classification of the Phases Relevant to Work-Related Musculoskeletal Injury Risks in Residential Roof Shingle Installation Operations Using Machine Learning

Nonlinear Time Series Analysis in Unstable Periodic Orbits Identification-Control Methods of Nonlinear Systems

Contact Info

Product

Resources

About