This is a python package that contains different algorithm proposed in different research papers in order to perform EMG classification
The Algorithms currently implemented for classification of EMG are:
1. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders (DOI: https://doi.org/10.1016/j.compbiomed.2013.01.020)
2. IDENTIFYING THE MOTOR NEURON DISEASE IN EMG SIGNAL USING TIME AND FREQUENCY DOMAIN FEATURES WITH COMPARISON (DOI: 10.5121/sipij.2012.3207)
Files and Folders in the package:
1. Performance Metrics, Accuracy Graph and Table, Signal Preprocessing Graphs, Feature Array, etc. obtained from each
classification technique are included in '*_*_classification_output' folder of the base directory.
e.g. The classification outputs for Algorithm 1 are included in 'pso_svm_classification_output' folder and
the outputs for Algorithm 2 are included in 'time_freq_classification output folder'.
2. init.py is the default file of the package.
3. 'dataset_functions.py' contains the functions associated in retrieving data urls and labels from specified
data set directory.
4. 'muap_analysis_functions.py' contains the functions associated with extracting features from Muscle Unit Action
Potential(MUAP) waveforms generated from EMG Decomposition technique.
(N.B: The Algorithm for EMG Decomposition will be added later.)
5. 'particle_swarm_optimization.py' contains the functions associated with performing Particle Swarm Optimization(PSO)
technique in order to obtain best hyperparameters for a classifier or any other optimization task.
6. 'pso_svm_classification.py' is an obsolete file which will be later replaced by 'wavelet_transform_classification.py'.
7. 'signal_analysis_functions.py' contains the functions associated with Preprocessing and extracting features from
time and frequency domain of a signal.
8. 'test_area.py' is an additional file for testing code under development.
9. 'time_freq_classification.py' contains the functions associated with performing and evaluating classification of EMG
signals using Algorithm 2.
10. 'utility.py' is an additional file for manipulating data structure and organization e.g. copying dataset to a
different directory, renaming dataset, etc.
11. 'wavelet_transform_classification.py' contains the functions associated with performing and evaluating classification
of EMG signals using Algorithm 1.
Dataset Structure:
1. The main dataset directory consists of two folders (train and test) where the 'test' folder contains patient
records for testing the classifier and 'train' folder contains patient record for training the classifier.
2. Each of the train/test directory consists of three folders(myopathy, ALS and normal) where each folder contains
folders for different subjects who falls under the specified group. The record folders of each subject is stored in
a folder(patient folder) bearing a unique ID number(e.g. a01_patient, c01_patient, etc.) for each individual
patient. Each patient folder can have multiple EMG record folders obtained from the brachial biceps of the
subject. Each record folder contains information related to each signal recorded from the specific patient.
3. Each record folder of the subjects also bear a unique ID number(e.g. N2001A01BB05, N2001A01BB06, etc.) and each
folder contains three files. They are 'data.npy' and 'data.hea'.
4. data.npy: This file contains the EMG signal recorded from an electromyograph. The data is stored as a 'Numpy' one
dimensional array where the length of array indicates the number of samples obtained at a specific sampling frequency.
5. data.hea: This is a WFDB header file that contains all the information regarding subject under investigation and
recorded EMG signal from the subject. As for example it contains the sampling frequency and total number of
samples obtained from the signal, gender of the subject, period of diagnosis, duration of disease, location of
placement of electrode, filters used, level of insertion of needle, etc. The data is stored as a text file
(More documentation on WFDB header files: http://www.emglab.net/emglab/Tutorials/WFDB.html).
Preprocessing, Feature Extraction and Classification:
1. Performed according to the techniques mentioned in respective papers of each implemented EMG Classification
algorithm.
Performance Evaluation:
1. ROC Curve and Area Under the Curve for varying input size
2. Test & Validation accuracy, Sensitivity and Specificity Curve for each Feature Extraction technique
3. Average Performance Table for varying input size and each Feature Extraction Technique
4. Feature Output Curves and Tables
5. Signal preprocessing Curves.
没有合适的资源?快使用搜索试试~ 我知道了~
The Algorithms currently implemented for classification of EMG
共145个文件
png:75个
npy:27个
html:20个
需积分: 5 0 下载量 102 浏览量
2022-12-20
19:50:23
上传
评论
收藏 11.29MB ZIP 举报
温馨提示
This is a python package that contains different algorithm proposed in different research papers in order to perform EMG classification The Algorithms currently implemented for classification of EMG are: 1. Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders (DOI: https://doi.org/10.1016/j.compbiomed.2013.01.020) 2. IDENTIFYING THE MOTOR NEURON DISEASE IN EMG SIGNAL USING TIME AND FREQUENCY DOMAIN FEATURES WITH COMPARISON (DOI: 10.5121/sipij.2012.3207)
资源推荐
资源详情
资源评论
收起资源包目录
The Algorithms currently implemented for classification of EMG (145个子文件)
psosvm_performance_table.html 13KB
psosvm_accuracy_table.html 7KB
fft_performance_table.html 3KB
simulated_signal_spectral_peaks_table.html 2KB
spectral_peaks_table.html 2KB
simulated_signal_pso_knn_spectral_peaks_table.html 2KB
average_performance_graph_test_simulated_scaled.html 2KB
average_performance_graph_validation_simulated_scaled.html 2KB
average_performance_graph_validation_real_scaled.html 960B
average_performance_graph_validation_real_unscaled.html 959B
average_performance_graph_test_real_scaled.html 942B
average_performance_graph_test_real_unscaled.html 939B
average_performance_graph_validation_simulated_unscaled.html 915B
average_performance_graph_test_simulated_unscaled.html 904B
average_performance_real_scaled_validation.html 732B
average_performance_graph_validation_real_scaled.html 732B
average_performance_graph_test_real_scaled.html 708B
average_performance_real_scaled_test.html 706B
average_performance_graph_test_simulated_scaled.html 705B
average_performance_graph_validation_simulated_scaled.html 662B
config.json 5KB
README.md 5KB
features_real_scaled.npy 55KB
features_ZeroCrossingrate_real_scaled.npy 35KB
features_AverageSpectralAmplitude_real_unscaled.npy 35KB
features_ZeroLag_real_scaled.npy 35KB
features_AverageSpectralAmplitude_real_scaled.npy 35KB
features_ZeroLag_real_unscaled.npy 35KB
features_ZeroCrossingrate_real_unscaled.npy 35KB
features_MeanFrequency_real_unscaled.npy 35KB
features_MeanFrequency_real_scaled.npy 35KB
features_ZeroCrossingrate_simulated_unscaled.npy 19KB
features_ZeroLag_simulated_unscaled.npy 19KB
features_AverageSpectralAmplitude_simulated_unscaled.npy 19KB
features_MeanFrequency_simulated_unscaled.npy 19KB
features_ZeroCrossingrate_simulated_scaled.npy 19KB
features_AverageSpectralAmplitude_simulated_scaled.npy 19KB
features_MeanFrequency_simulated_scaled.npy 19KB
features_ZeroLag_simulated_scaled.npy 19KB
label__real_unscaled.npy 836B
label__real_scaled.npy 836B
labels_real_scaled.npy 832B
label__simulated_unscaled.npy 524B
label__simulated_scaled.npy 524B
label_map_real_scaled.npy 168B
label_map__real_scaled.npy 168B
label_map__real_unscaled.npy 168B
label_map__simulated_unscaled.npy 168B
label_map__simulated_scaled.npy 168B
roc_knn_performance_graph_zero_lag_autocorrelation_real_unscaled.png 200KB
roc_knn_performance_graph_avg_spectral_amplitude_real_scaled.png 198KB
roc_knn_performance_graph_mean_frequency_real_unscaled.png 194KB
roc_knn_performance_graph_zero_crossing_rate_real_unscaled.png 194KB
roc_knn_performance_graph_avg_spectral_amplitude_real_unscaled.png 192KB
roc_knn_performance_graph_mean_frequency_real_scaled.png 192KB
roc_knn_performance_graph_zero_lag_autocorrelation_real_scaled.png 187KB
all_graph_avg_spectral_amplitude.png 187KB
roc_knn_performance_graph_zero_crossing_rate_real_scaled.png 185KB
roc_knn_performance_graph_zero_crossing_rate_simulated_unscaled.png 182KB
roc_knn_performance_graph_zero_crossing_rate_simulated_scaled.png 178KB
roc_knn_performance_graph_avg_spectral_amplitude_simulated_unscaled.png 178KB
roc_knn_performance_graph_mean_frequency_simulated_scaled.png 177KB
roc_knn_performance_graph_zero_lag_autocorrelation_simulated_unscaled.png 177KB
roc_knn_performance_graph_avg_spectral_amplitude_simulated_scaled.png 175KB
roc_knn_poly_scaled.png 174KB
roc_graph_knn_real_scaled.png 173KB
roc_graph_knn_simulated_scaled.png 172KB
roc_knn_performance_graph_zero_lag_autocorrelation_simulated_scaled.png 166KB
muap_segmentation_normal_real.png 163KB
roc_knn_performance_graph_mean_frequency_simulated_unscaled.png 158KB
roc_graph_rfa_real_scaled.png 157KB
muap_classification_normal_real.png 153KB
feature_extraction_expanded_muap_waveforms_als_real.png 147KB
feature_extraction_actual_muap_waveforms_als_real.png 144KB
raw_emg_signal.png 143KB
roc_svm_rbf_poly_scaled.png 141KB
roc_svm_rbf_real_scaled.png 141KB
roc_graph_svm_poly_real_scaled.png 139KB
muap_classification_als_real.png 137KB
roc_svm_poly_real_scaled.png 137KB
filtered_emg_signal.png 133KB
filtered_emg_random_segments.png 133KB
roc_graph_svm_rbf_real_scaled.png 133KB
roc_graph_svm_poly_simulated_scaled.png 131KB
feature_extraction_baseline_corrected_muap_waveforms_als_real.png 131KB
muap_segmentation_als_real.png 129KB
roc_graph_svm_rbf_simulated_scaled.png 127KB
feature_extraction_baseline_corrected_muap_waveforms_other_real.png 127KB
autocorrelation_emg_random_segments.png 126KB
muap_decomposition_normal_real.png 124KB
cropped_emg_signal.png 124KB
muap_decomposition_als_real.png 114KB
feature_extraction_expanded_muap_waveforms_other_real.png 112KB
feature_extraction_actual_muap_waveforms_other_real.png 106KB
performance_graph_mean_frequency_real_unscaled.png 103KB
performance_graph_zero_crossing_rate_real_scaled.png 102KB
performance_graph_avg_spectral_peak_amplitude_real_scaled.png 102KB
performance_graph_zero_lag_autocorrelation_real_scaled.png 101KB
performance_graph_zero_crossing_rate_real_unscaled.png 100KB
performance_graph_knn_real_scaled.png 100KB
共 145 条
- 1
- 2
资源评论
eiurijkajk
- 粉丝: 0
- 资源: 64
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功