Evaluation of Hand Action Classification Performance Using Machine Learning Based on Signals from Two sEMG Electrodes

Sensors, Journal Year: 2024, Volume and Issue: 24(8), P. 2383 - 2383

Published: April 9, 2024

Classification-based myoelectric control has attracted significant interest in recent years, leading to prosthetic hands with advanced functionality, such as multi-grip hands. Thus far, high classification accuracies have been achieved by increasing the number of surface electromyography (sEMG) electrodes or adding other sensing mechanisms. While many prescribed still adopt two-electrode sEMG systems, detailed studies on signal processing and performance are lacking. In this study, nine able-bodied participants were recruited perform six typical hand actions, from which signals two acquired using a Delsys Trigno Research+ acquisition system. Signal machine learning algorithms, specifically, linear discriminant analysis (LDA), k-nearest neighbors (KNN), support vector machines (SVM), used study accuracies. Overall accuracy 93 ± 2%, action-specific 97 F1-score 87 7% achieved, comparable those reported multi-electrode systems. The highest SVM algorithm compared LDA KNN algorithms. A logarithmic relationship between features was revealed, plateaued at five features. These comprehensive findings may potentially contribute strategies for commonly systems further improve functionality.

Language: Английский

---

Metaheuristic integrated machine learning classification of colon cancer using STFT LASSO and EHO feature extraction from microarray gene expressions

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 17, 2024

Abstract The microarray gene expression data poses a tremendous challenge due to their curse of dimensionality problem. sheer volume features far surpasses available samples, leading overfitting and reduced classification accuracy. Thus the must be with efficient feature extraction methods reduce extract meaningful information enhance accuracy interpretability. In this research, we discover uniqueness applying STFT (Short Term Fourier Transform), LASSO (Least Absolute Shrinkage Selection Operator), EHO (Elephant Herding Optimisation) for extracting significant from lung cancer reducing database. is performed using following classifiers: Gaussian Mixture Model (GMM), Particle Swarm Optimization (PSO) GMM, Detrended Fluctuation Analysis (DFA), Naive Bayes classifier (NBC), Firefly Support Vector Machine Radial Basis Kernel (SVM-RBF) Flower Pollination (FPO) GMM. FPO-GMM attained highest in range 96.77, an F1 score 97.5, MCC 0.92 Kappa 0.92. reported results underline significance utilizing STFT, LASSO, data. These methodologies also help improved early diagnosis enhanced

Language: Английский

---

WGCNA and Machine Learning-based Integrative Bioinformatics Analysis for Identifying Key Genes of Colorectal Cancer

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 144350 - 144363

Published: Jan. 1, 2024

Language: Английский

---

An Optimized Two Stage U-Net Approach for Segmentation of Pancreas and Pancreatic Tumor.

MethodsX, Journal Year: 2024, Volume and Issue: 13, P. 102995 - 102995

Published: Oct. 4, 2024

Language: Английский

---

Ant-based feature and instance selection for multiclass imbalanced data

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 133952 - 133968

Published: Jan. 1, 2024

Language: Английский

---

An Optimized Two Stage U-Net Approach for Segmentation of Pancreas and Pancreatic Tumor

Published: Jan. 1, 2024

Language: Английский

---

Evaluating classification tools for the prediction of in-vitro microbial pyruvate yield from organic carbon sources

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(7), P. e0306987 - e0306987

Published: July 11, 2024

The laboratory-scale ( in-vitro ) microbial fermentation based on screening of process parameters (factors) and statistical validation (responses) using regression analysis. recent trends have shifted from full factorial design towards more complex response surface methodology designs such as Box-Behnken design, Central Composite design. Apart the optimisation methodologies, listed are not flexible enough in deducing properties terms class variables. Machine learning algorithms unique visualisations for dataset presented with appropriate algorithms. classification cannot be applied all datasets selection classifier is essential this regard. To resolve issue, factor-response relationship needs to evaluated subsequent preprocessing could lead results. aim current study was investigate data-mining accuracy developed pyruvate production organic sources first time. attributes were subjected comparative various classifiers accuracy, multilayer perceptron (neural network algorithm) selected classifier. As per results, model showed significant results prediction classes a good fit. curve also converging linearly separable.

Language: Английский

---

Optimization of Gene Selection for Cancer Classification in High-Dimensional Data Using an Improved African Vultures Algorithm

Algorithms, Journal Year: 2024, Volume and Issue: 17(8), P. 342 - 342

Published: Aug. 6, 2024

This study presents a novel method, termed RBAVO-DE (Relief Binary African Vultures Optimization based on Differential Evolution), aimed at addressing the Gene Selection (GS) challenge in high-dimensional RNA-Seq data, specifically rnaseqv2 lluminaHiSeq un edu Level 3 RSEM genes normalized dataset, which contains over 20,000 genes. RNA Sequencing (RNA-Seq) is transformative approach that enables comprehensive quantification and characterization of gene expressions, surpassing capabilities micro-array technologies by offering more detailed view expression data. Quantitative analysis can be pivotal identifying differentiate normal from malignant tissues. However, managing these dense matrix data significant challenges. The algorithm designed to meticulously select most informative dataset comprising than assess their relevance across twenty-two cancer datasets. To determine effectiveness selected genes, this employs Support Vector Machine (SVM) k-Nearest Neighbor (k-NN) classifiers. Compared binary versions widely recognized meta-heuristic algorithms, demonstrates superior performance. According Wilcoxon’s rank-sum test, with 5% significance level, achieves up 100% classification accuracy reduces feature size 98% datasets examined. advancement underscores potential enhance precision selection for research, thereby facilitating accurate efficient identification key genetic markers.

Language: Английский

---

Accuracy is not enough: a heterogeneous ensemble model versus FGSM attack

Complex & Intelligent Systems, Journal Year: 2024, Volume and Issue: 10(6), P. 8355 - 8382

Published: Aug. 28, 2024

Abstract In this paper, based on facial landmark approaches, the possible vulnerability of ensemble algorithms to FGSM attack has been assessed using three commonly used models: convolutional neural network-based antialiasing (A_CNN), Xc_Deep2-based DeepLab v2, and SqueezeNet (Squ_Net)-based Fire modules. Firstly, individual deep learning classifier-based Facial Emotion Recognition (FER) classifications have developed; predictions from all classifiers are then merged majority voting develop HEM_Net-based model. Following that, an in-depth investigation their performance in case attack-free carried out terms Jaccard coefficient, accuracy, precision, recall, F1 score, specificity. When applied benchmark datasets, ensemble-based method (HEM_Net) significantly outperforms precision reliability while also decreasing dimensionality input data, with accuracy 99.3%, 87%, 99% for Extended Cohn-Kanade (CK+), Real-world Affective Face (RafD), Japanese female expressions (Jaffee) respectively. Further, a comprehensive analysis drop every model affected by is over range epsilon values (the perturbation parameter). The results experiments show that advised HEM_Net declined drastically 59.72% CK + 42.53% RafD images, 48.49% Jaffee dataset when increased A E (attack levels). This demonstrated successful Fast Gradient Sign Method (FGSM) can reduce prediction increase levels. However, due voting, proposed could improve its robustness against attacks, indicating lessen deception adversarial instances. generally holds even as level increases.

Language: Английский

---

Revolutionizing Colon Histopathology Glandular Segmentation Using an Ensemble Network With Watershed Algorithm

International Journal of Imaging Systems and Technology, Journal Year: 2024, Volume and Issue: 34(5)

Published: Sept. 1, 2024

ABSTRACT Colorectal adenocarcinoma, the most prevalent form of colon cancer, originates in glandular structures intestines, presenting histopathological abnormalities affected tissues. Accurate gland segmentation is crucial for identifying these potentially fatal abnormalities. While recent methodologies have shown success segmenting glands benign tissues, their efficacy diminishes when applied to malignant tissue segmentation. This study aims develop a robust learning algorithm using convolutional neural network (CNN) segment histology images. The methodology employs CNN based on U‐Net architecture, augmented by weighted ensemble that integrates DenseNet 169, Inception V3, and Efficientnet B3 as backbone models. Additionally, segmented boundaries are refined watershed algorithm. Evaluation Warwick‐QU dataset demonstrates promising results model, achieving an F1 score 0.928 0.913, object dice coefficient 0.923 0.911, Hausdorff distances 38.97 33.76 test sets A B, respectively. These compared with outcomes from GlaS challenge (MICCAI 2015) existing research findings. Furthermore, our model validated publicly available named LC25000, visual inspection reveals results, further validating approach. proposed underscores advantages amalgamating diverse models, highlighting potential techniques enhance tasks beyond individual capabilities.

Language: Английский

---