commit fcbea99d0187033c128764301d91689dc14b87cd Author: 魏遇卿 <358614401@qq.com> Date: Tue Mar 7 21:18:12 2023 +0800 Initial commit diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dfe0770 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,2 @@ +# Auto detect text files and perform LF normalization +* text=auto diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..d9005f2 --- /dev/null +++ b/.gitignore @@ -0,0 +1,152 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintainted in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ diff --git a/.idea/.gitignore b/.idea/.gitignore new file mode 100644 index 0000000..13566b8 --- /dev/null +++ b/.idea/.gitignore @@ -0,0 +1,8 @@ +# Default ignored files +/shelf/ +/workspace.xml +# Editor-based HTTP Client requests +/httpRequests/ +# Datasource local storage ignored files +/dataSources/ +/dataSources.local.xml diff --git a/.idea/ECG_by_Diffenert_CNN_Test.iml b/.idea/ECG_by_Diffenert_CNN_Test.iml new file mode 100644 index 0000000..dc26ab5 --- /dev/null +++ b/.idea/ECG_by_Diffenert_CNN_Test.iml @@ -0,0 +1,11 @@ + + + + + + + + + + \ No newline at end of file diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml new file mode 100644 index 0000000..105ce2d --- /dev/null +++ b/.idea/inspectionProfiles/profiles_settings.xml @@ -0,0 +1,6 @@ + + + + \ No newline at end of file diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..f8d7d56 --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,4 @@ + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..3443cb7 --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/other.xml b/.idea/other.xml new file mode 100644 index 0000000..640fd80 --- /dev/null +++ b/.idea/other.xml @@ -0,0 +1,7 @@ + + + + + \ No newline at end of file diff --git a/main.py b/main.py new file mode 100644 index 0000000..d0294e6 --- /dev/null +++ b/main.py @@ -0,0 +1,159 @@ +import wfdb +import pywt +import seaborn +# import torch +import numpy as np +import matplotlib;matplotlib.use('TkAgg') +import tensorflow as tf +import matplotlib.pyplot as plt +from sklearn.metrics import confusion_matrix + +# 测试集在数据集中所占的比例 +RATIO = 0.2 + + +# 小波去噪预处理 +def denoise(data): + # 小波变换 + coeffs = pywt.wavedec(data=data, wavelet='db5', level=9) + cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs + # 阈值去噪 + threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1)))) + cD1.fill(0) + cD2.fill(0) + for i in range(1, len(coeffs) - 2): + coeffs[i] = pywt.threshold(coeffs[i], threshold) + # 小波反变换,获取去噪后的信号 + rdata = pywt.waverec(coeffs=coeffs, wavelet='db5') + return rdata + + +# 读取心电数据和对应标签,并对数据进行小波去噪 +def getDataSet(number, X_data, Y_data): + ecgClassSet = ['N', 'A', 'V', 'L', 'R'] + # 读取心电数据记录 + print("正在读取 " + number + " 号心电数据...") + # 读取MLII导联的数据 + record = wfdb.rdrecord('W:/MIT-BIT/mit-bih-arrhythmia-database-1.0.0/' + number, channel_names=['MLII']) + data = record.p_signal.flatten() + rdata = denoise(data=data) + # 获取心电数据记录中R波的位置和对应的标签 + annotation = wfdb.rdann('W:/MIT-BIT/mit-bih-arrhythmia-database-1.0.0/' + number, 'atr') + Rlocation = annotation.sample + Rclass = annotation.symbol + # 去掉前后的不稳定数据 + start = 10 + end = 5 + i = start + j = len(annotation.symbol) - end + # 因为只选择NAVLR五种心电类型,所以要选出该条记录中所需要的那些带有特定标签的数据,舍弃其余标签的点 + # X_data在R波前后截取长度为300的数据点 + # Y_data将NAVLR按顺序转换为01234 + while i < j: + try: + # Rclass[i] 是标签 + lable = ecgClassSet.index(Rclass[i]) + # 基于经验值，基于R峰向前取100个点，向后取200个点 + x_train = rdata[Rlocation[i] - 100:Rlocation[i] + 200] + X_data.append(x_train) + Y_data.append(lable) + i += 1 + except ValueError: + i += 1 + return + + +# 加载数据集并进行预处理 +def loadData(): + numberSet = ['100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', + '116', '117', '119', '121', '122', '123', '124', '200', '201', '202', '203', '205', '208', + '210', '212', '213', '214', '215', '217', '219', '220', '221', '222', '223', '228', '230', + '231', '232', '233', '234'] + dataSet = [] + lableSet = [] + for n in numberSet: + getDataSet(n, dataSet, lableSet) + # 转numpy数组,打乱顺序 + dataSet = np.array(dataSet).reshape(-1, 300) + lableSet = np.array(lableSet).reshape(-1, 1) + train_ds = np.hstack((dataSet, lableSet)) + np.random.shuffle(train_ds) + # 数据集及其标签集 + X = train_ds[:, :300].reshape(-1, 300, 1) + Y = train_ds[:, 300] + # 测试集及其标签集 + shuffle_index = np.random.permutation(len(X)) + # 设定测试集的大小 RATIO是测试集在数据集中所占的比例 + test_length = int(RATIO * len(shuffle_index)) + # 测试集的长度 + test_index = shuffle_index[:test_length] + # 训练集的长度 + train_index = shuffle_index[test_length:] + X_test, Y_test = X[test_index], Y[test_index] + X_train, Y_train = X[train_index], Y[train_index] + return X_train, Y_train, X_test, Y_test + + +# 构建CNN模型 +def buildModel(): + newModel = tf.keras.models.Sequential([ + tf.keras.layers.InputLayer(input_shape=(300, 1)), + # 第一个卷积层, 4 个 21x1 卷积核 + tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='SAME', activation='tanh'), + # 第一个池化层, 最大池化,4 个 3x1 卷积核, 步长为 2 + tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='SAME'), + # 第二个卷积层, 16 个 23x1 卷积核 + tf.keras.layers.Conv1D(filters=16, kernel_size=23, strides=1, padding='SAME', activation='relu'), + # 第二个池化层, 最大池化,4 个 3x1 卷积核, 步长为 2 + tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='SAME'), + # 第三个卷积层, 32 个 25x1 卷积核 + tf.keras.layers.Conv1D(filters=32, kernel_size=25, strides=1, padding='SAME', activation='tanh'), + # 第三个池化层, 平均池化,4 个 3x1 卷积核, 步长为 2 + tf.keras.layers.AvgPool1D(pool_size=3, strides=2, padding='SAME'), + # 第四个卷积层, 64 个 27x1 卷积核 + tf.keras.layers.Conv1D(filters=64, kernel_size=27, strides=1, padding='SAME', activation='relu'), + # 打平层,方便全连接层处理' + tf.keras.layers.Flatten(), + # 全连接层,128 个节点 转换成128个节点 + tf.keras.layers.Dense(128, activation='relu'), + # Dropout层,dropout = 0.2 + tf.keras.layers.Dropout(rate=0.2), + # 全连接层,5 个节点 + tf.keras.layers.Dense(5, activation='softmax') + ]) + return newModel + + +def plotHeatMap(Y_test, Y_pred): + con_mat = confusion_matrix(Y_test, Y_pred) + # 绘图 + fig=plt.figure(figsize=(4, 5)) + seaborn.heatmap(con_mat, annot=True, fmt='.20g', cmap='Blues') + plt.ylim(0, 5) + plt.xlabel('Predicted labels') + plt.ylabel('True labels') + plt.show(fig) + + +def main(): + # X_train,Y_train为所有的数据集和标签集 + # X_test,Y_test为拆分的测试集和标签集 + X_train, Y_train, X_test, Y_test = loadData() + print(X_train.shape) + + model = buildModel() + model.compile(optimizer='adam', + loss='sparse_categorical_crossentropy', metrics=['accuracy'] + # metrics: 列表，包含评估模型在训练和测试时的性能的指标，典型用法是metrics=[‘accuracy’]。 + ) + model.summary() + + # 训练与验证 + model.fit(X_train, Y_train, epochs=30, batch_size=128, validation_split=RATIO) # validation_split 训练集所占比例 + # 预测 + Y_pred = model.predict(X_test) + print(Y_pred) + plotHeatMap(Y_test,Y_pred) + +if __name__ == '__main__': + main() diff --git a/testpltshow.py b/testpltshow.py new file mode 100644 index 0000000..c544fea --- /dev/null +++ b/testpltshow.py @@ -0,0 +1,19 @@ +## read_img.py + +import cv2 +import os +import matplotlib.pyplot as plt +from PIL import Image + +source_path='E:/CToE/Pictures' + +def show_pic(): + # img=cv2.imread(os.path.join(source_path,'t1.png')) + img=Image.open(os.path.join(source_path,'1.png')) + # plt.imshow(img) + info = plt.imshow(img) + print(info) + plt.show() + +if __name__ == '__main__': + show_pic() \ No newline at end of file