Electrocardiogram (ECG) signals are used to identify cardiovascular disease. The availability of signal processing and neural networks techniques for processing ECG signals has inspired us to do research that consists...Electrocardiogram (ECG) signals are used to identify cardiovascular disease. The availability of signal processing and neural networks techniques for processing ECG signals has inspired us to do research that consists of extracting features of an ECG signals to identify types of cardiovascular diseases. We distinguish between normal and abnormal ECG data using signal processing and neural networks toolboxes in Matlab. Data, which are downloaded from an ECG database, Physiobank, are used for training and testing the neural network. To distinguish normal and abnormal ECG with the significant accuracy, pattern recognition tools with NN is used. Feature Extraction method is also used to identify specific heart diseases. The diseases that were identified include Tachycardia, Bradycardia, first-degree Atrioventricular (AV), and second-degree Atrioventricular. Since ECG signals are very noisy, signal processing techniques are applied to remove the noise contamination. The heart rate of each signal is calculated by finding the distance between R-R intervals of the signal. The QRS complex is also used to detect Atrioventricular blocks. The algorithm successfully distinguished between normal and abnormal data as well as identifying the type of disease.展开更多
Large amount of data has been generated by Organizations. Different Analytical Tools are being used to handle such kind of data by Data Scientists. There are many tools available for Data processing, Visualisations, P...Large amount of data has been generated by Organizations. Different Analytical Tools are being used to handle such kind of data by Data Scientists. There are many tools available for Data processing, Visualisations, Predictive Analytics and so on. It is important to select a suitable Analytic Tool or Programming Language to carry out the tasks. In this research, two of the most commonly used Programming Languages have been compared and contrasted which are Python and R. To carry out the experiment two data sets have been collected from Kaggle and combined into a single Dataset. This study visualizes the data to generate some useful insights and prepare data for training on Artificial Neural Network by using Python and R language. The scope of this paper is to compare the analytical capabilities of Python and R. An Artificial Neural Network with Multilayer Perceptron has been implemented to predict the severity of accidents. Furthermore, the results have been used to compare and tried to point out which programming language is better for data visualization, data processing, Predictive Analytics, etc.展开更多
Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the...Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.展开更多
在R-λ帧内码控中,提出基于卷积神经网络(Convolutional Neural Networks,CNN)的最佳比特分配和最优拉格朗日因子λ选择。首先,探索编码树单元(Coding Tree Unit,CTU)的码率与失真(Rate-Distortion,R-D)及码率与拉格朗日因子λ(Rate-λ...在R-λ帧内码控中,提出基于卷积神经网络(Convolutional Neural Networks,CNN)的最佳比特分配和最优拉格朗日因子λ选择。首先,探索编码树单元(Coding Tree Unit,CTU)的码率与失真(Rate-Distortion,R-D)及码率与拉格朗日因子λ(Rate-λ,R-λ)的关系特性,设计具有四输出的CNN预测R-D和R-λ曲线的关键参数;然后,建立帧级λ和目标码率的优化方程,反演得到最佳CTU码率分配;最后,根据CTU码率分配和先知的R-λ曲线,得到最优CTU级λ。实验表明,算法在保持4.76%控制精度下,比VTM13.0默认码控算法提高0.31 dB的编码质量。展开更多
文摘Electrocardiogram (ECG) signals are used to identify cardiovascular disease. The availability of signal processing and neural networks techniques for processing ECG signals has inspired us to do research that consists of extracting features of an ECG signals to identify types of cardiovascular diseases. We distinguish between normal and abnormal ECG data using signal processing and neural networks toolboxes in Matlab. Data, which are downloaded from an ECG database, Physiobank, are used for training and testing the neural network. To distinguish normal and abnormal ECG with the significant accuracy, pattern recognition tools with NN is used. Feature Extraction method is also used to identify specific heart diseases. The diseases that were identified include Tachycardia, Bradycardia, first-degree Atrioventricular (AV), and second-degree Atrioventricular. Since ECG signals are very noisy, signal processing techniques are applied to remove the noise contamination. The heart rate of each signal is calculated by finding the distance between R-R intervals of the signal. The QRS complex is also used to detect Atrioventricular blocks. The algorithm successfully distinguished between normal and abnormal data as well as identifying the type of disease.
文摘Large amount of data has been generated by Organizations. Different Analytical Tools are being used to handle such kind of data by Data Scientists. There are many tools available for Data processing, Visualisations, Predictive Analytics and so on. It is important to select a suitable Analytic Tool or Programming Language to carry out the tasks. In this research, two of the most commonly used Programming Languages have been compared and contrasted which are Python and R. To carry out the experiment two data sets have been collected from Kaggle and combined into a single Dataset. This study visualizes the data to generate some useful insights and prepare data for training on Artificial Neural Network by using Python and R language. The scope of this paper is to compare the analytical capabilities of Python and R. An Artificial Neural Network with Multilayer Perceptron has been implemented to predict the severity of accidents. Furthermore, the results have been used to compare and tried to point out which programming language is better for data visualization, data processing, Predictive Analytics, etc.
基金Supported by the Shaanxi Province Key Research and Development Project (No. 2021GY-280)Shaanxi Province Natural Science Basic Research Program (No. 2021JM-459)the National Natural Science Foundation of China (No. 61772417)
文摘Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.
