Neighborhood components analysis in sEMG signal dimensionality reduction for gait phase pattern recognition

Manit, Jirapong; Youngkong, Prakarnkiat

doi:10.1109/ib2com.2011.6217897

Cited by 13 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For all the supervised models used, NCA yielded better classification performance with a smaller number of features due to its capability of identifying the most discriminatory features. This classification improvement is in line with previous studies which applied NCA in their analysis and obtained superior results after its application using different features from electromyography (EMG) signals to classify different stages of Alzheimer's disease and electroencephalography (EEG) signals to classify epilepsy patients, respectively (Raghu and Sriraam, 2018;Youngkong, 2011). The present study is the first to apply the NCA algorithm in gait kinematics patterns and our findings, similarly to the prior studies, confirm its great potential for the recognition of features with high discriminatory power.…”

Section: Performance Of Approachessupporting

confidence: 88%

“…To address this, we utilized Neighbour Component Analysis (NCA), which is a relatively recently developed technique designed to provide insight into the information context of the feature space. NCA has been used previously to identify different stages of Alzheimer's disease (Jin and Deng, 2018) and has been used to classify phases of gait (Youngkong, 2011). In these studies, the use of NCA improved classification accuracy compared to traditional techniques.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Kinematic biomarkers of chronic neck pain measured during gait: A data-driven classification approach

Jiménez-Grande

Atashzar

Martinez‐Valdes

et al. 2021

Journal of Biomechanics

View full text Add to dashboard Cite

Section: Performance Of Approachessupporting

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Kinematic biomarkers of chronic neck pain measured during gait: A data-driven classification approach

Jiménez-Grande

Atashzar

Martinez‐Valdes

et al. 2021

Journal of Biomechanics

View full text Add to dashboard Cite

“…To date, several studies using NCA have been described in the literature. For instance, Manit and Youngkong 41 applied NCA at the feature extraction and classification stages for sEMG signal pattern recognition. Similarly, Raghu et al 42 used this method for the classification of EEG signals.…”

Section: Methodsmentioning

confidence: 99%

NCA‐GA‐SVM: A new two‐level feature selection method based on neighborhood component analysis and genetic algorithm in hepatocellular carcinoma fatality prognosis

Książek

Turza

Pławiak

2022

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Hepatocellular carcinoma (HCC) is one of the major challenges facing biomedical research. Despite the high lethality, methods to predict mortality for this type of aggressive malignant tumor are insufficient. Machine learning is recognized by many authors as a valuable, yet poorly studied tool in this field. Undoubtedly, searching for new feature selection methods is significant in building an effective machine-learning model. In this study, we propose the novel hybrid model using neighborhood components analysis, genetic algorithm and support vector machine classifier (NCA-GA-SVM). Because SVM works with default parameters characterized by low classification results, we decided to use GA for the proper optimization and feature selection. As reported in the available literature, NCA and GA obtain high classification results. Here, we decided to combine these approaches, building a two-level algorithm for HCC fatality prognosis. We used a well-known dataset collected from 165 patients at Coimbra's Hospital and University Center, Portugal. Our results revealed 96.36% classification accuracy and 95.52% F1-score. Additionally, we compared all data for these metrics published so far. We demonstrated that our algorithm achieved the highest accuracy and can be successfully applied for the assessment of hepatocellular carcinoma mortality in the future. Our findings bring methodological value for future HCC studies and emphasize the possibility of using machine-learning techniques to improve the quality of medical decisions.

show abstract

“…NCA is a nonparametric dimensionality reduction technique which learns the Mahalanobis distance used in the k-nearest neighbourhood classification algorithm [ 48 ]. NCA has been applied on kinematics, kinetics and physiological signals [ 49 , 50 , 51 , 52 , 53 ] and has been shown to outperform other conventional algorithms such as principle component analysis and reliefF [ 50 , 53 ]. This approach optimises the feature weights by minimising the objective function that measures the leave-one-out prediction loss over the training data.…”

Section: Methodsmentioning

confidence: 99%

Joint Torque Prediction via Hybrid Neuromusculoskeletal Modelling during Gait Using Statistical Ground Reaction Estimates: An Exploratory Study

Lam¹,

Vujaklija²

2021

Sensors

View full text Add to dashboard Cite

Joint torques of lower extremity are important clinical indicators of gait capability. This parameter can be quantified via hybrid neuromusculoskeletal modelling that combines electromyography-driven modelling and static optimisation. The simulations rely on kinematics and external force measurements, for example, ground reaction forces (GRF) and the corresponding centres of pressure (COP), which are conventionally acquired using force plates. This bulky equipment, however, hinders gait analysis in real-world environments. While this portability issue could potentially be solved by estimating the parameters through machine learning, the effect of the estimation errors on joint torque prediction with biomechanical models remains to be investigated. This study first estimated GRF and COP through feedforward artificial neural networks, and then leveraged them to predict lower-limb sagittal joint torques via (i) inverse dynamics and (ii) hybrid modelling. The approach was evaluated on five healthy subjects, individually. The predicted torques were validated with the measured torques, showing that hip was the most sensitive whereas ankle was the most resistive to the GRF/COP estimates for both models, with average metrics values being 0.70 < R2 < 0.97 and 0.069 < RMSE < 0.15 (Nm/kg). This study demonstrated the feasibility of torque prediction based on personalised (neuro)musculoskeletal modelling using statistical ground reaction estimates, thus providing insights into potential real-world mobile joint torque quantification.

show abstract

Neighborhood components analysis in sEMG signal dimensionality reduction for gait phase pattern recognition

Cited by 13 publications

References 13 publications

Kinematic biomarkers of chronic neck pain measured during gait: A data-driven classification approach

Kinematic biomarkers of chronic neck pain measured during gait: A data-driven classification approach

NCA‐GA‐SVM: A new two‐level feature selection method based on neighborhood component analysis and genetic algorithm in hepatocellular carcinoma fatality prognosis

Joint Torque Prediction via Hybrid Neuromusculoskeletal Modelling during Gait Using Statistical Ground Reaction Estimates: An Exploratory Study

Contact Info

Product

Resources

About