zhaoxiaomian's starred repositories
IDDs_EEG_ML_classification
Classification of intellectual and developmental disorder subjects and healthy controls using EEG signals
Comparison-of-Hybrid-Neural-Network-Methodologies-for-Sentiment-Emotion-Analysis
Twitter tweets play an important role in every organisation. This project is based on analysing the English tweets and categorizing the tweets based on the sentiment and emotions of the user. The literature survey conducted showed promising results of using hybrid methodologies for sentiment and emotion analysis. Four different hybrid methodologies have been used for analysing the tweets belonging to various categories. A combination of classification and regression approaches using different deep learning models such as Bidirectional LSTM, LSTM and Convolutional neural network (CNN) are implemented to perform sentiment and behaviour analysis of the tweets. A novel approach of combining Vader and NRC lexicon is used to generate the sentiment and emotion polarity and categories. The evaluation metrics such as accuracy, mean absolute error and mean square error are used to test the performance of the model. The business use cases for the models applied here can be to understand the opinion of customers towards their business to improve their service. Contradictory to the suggestions of Google’s S/W ratio method, LSTM models performed better than using CNN models for categorical as well as regression problems.
German-Traffic-Sign-Classification
This project aims to bring out an in depth comparison among existing image classification models on German Traffic Sign benchmark (GTSRB) images. In this project famous machine learning algorithms like Logistic Regression, SVMs, MLPs etc. and deep learning models like ResNet and CNNs have been implemented. Apart from this we also employed ensemble learning algorithm like Random Forest to get clear comparsion based on evaluation metrics like ROC Curves, Precision, Accuracies etc. Transfer Learning has also been implemented by extracting features of CNN and using them in other models.
Mental-Emotional-Sentiment-Classification
EEG emotional sentiment classification
Human-Activity-Recognition-using-wearable-sensors-and-machine-learning
A human activity recognition model is developed using accelerometer data extracted from sensors and a machine learning approach is used for multi-label activity recognition
CNN_LSTM_HAR_Pytorch
Reproduce Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition in pytorch
microsleep-detection
Code for microsleep (drowsiness) detection in EEG data
Classification-Performance-Standard
Classification performance standards such as accuracy, precision, recall, confusion matrix, F1, ROC, AUC. Take MNIST as example.
AttCNN-with-Focal-Loss
This repository includes ATTCnn code implementation of this paper: https://www.cs.umd.edu/~emhand/Papers/AAAI2018_SelectiveLearning.pdf
focalloss4keras
Keras implementation of focal loss.
focal-loss-keras
Binary and Categorical Focal loss implementation in Keras.
Attention-Based-BiLSTM-relation-extraction
Tensorflow Implementation of "Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification" (ACL 2016)
Chinese-Text-Classification-Pytorch
中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。
EEG_classification
EEG multi-classification task with DL models (CNN, LSTM)
Deep-Learning-BCI-IV-2a
Clasificacion de imagenes motoras en señales EEG con CNN, LSTM y otros clasificadores
LSTM_for_EEG
my first LSTM for EEG Analysis and visualization
keras-focal-loss
Implementation of binary and categorical/multiclass focal loss using Keras with TensorFlow backend
focal-loss-implementation-in-keras
Binary and Categorical Focal loss implementation in Keras.
Focal_Loss_Keras
Multi-class classification with focal loss for imbalanced datasets
focal-loss
Tensorflow version implementation of focal loss for binary and multi classification
linear-regression
Ordinary Least Squres, Batch Gradient Descent and Hyperparameters analysis
Spatial_Data_Analysis
Spatial Data Analysis using different statistical methods
time-series-prophet
Time Series Analysis & Forecasting of Rossmann Sales with Python. EDA, TSA and seasonal decomposition, Forecasting with Prophet and XGboost modeling for regression.
Prediction-of-Alcoholism
The Kaggle dataset contained EEG correlates of genetic predisposition to alcoholism. Performed Exploratory Data analysis, Data cleaning and predicted if a person is more likely to develop alcohol use disorder or not. As the data was uniform, Classification Models like Logistic Regression and Decision Tree were used.