Toxic Comment Classification Based on Bidirectional Gated Recurrent Unit and Convolutional Neural Network

For English toxic comment classification, this paper presents the model that combines Bi-GRU and CNN optimized by global average pooling (BG-GCNN) based on the bidirectional gated recurrent unit (Bi-GRU) and global pooling optimized convolution neural network (CNN) . The model treats each type of toxic comment as a binary classification. First, Bi-GRU is used to extract the time-series features of the comment and then the dimensionality is reduced through global pooling optimized convolution neural network. Finally, the classification result is output by Sigmoid function. Comparative experiments show the BG-GCNN model has a better classification effect than Text-CNN, LSTM, Bi-GRU, and other models. The Macro-F1 value of the toxic comment dataset on the Kaggle competition platform is 0.62. The F1 values of the three toxic label classification results (toxic, obscene, and insult label) are 0.81, 0.84, and 0.74, respectively, which are the highest values in the comparative experiment.

Comparative Study of Forecasting Models for Forex Predictions with the Impact of Different Currencies

- Foreign Exchange (Forex) is the exchange / trading of currencies from different countries with the aim of making profit. Exchange rates on Forex markets are always changing and it is hard to predict. Many factors affect exchange rates of certain currency pairs like inflation rates, interest rates, government debt, term of trade, political stability of certain countries, recession and many more. Uncertainty in Forex prediction can be reduced with the help of technology by using machine learning. There are many machine learning methods that can be used when predicting Forex. The methods used in this paper are Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Support Vector Regression (SVR). XGBOOST, and ARIMA. The outcome of this paper will be comparison results that show how other major currency pairs have influenced the performance and accuracy of different methods. From the results, it was proven that XGBoost outperformed other models by 0.36% compared to ARIMA model, 4.4% compared to GRU model, 8% compared to LSTM model, 9.74% compared to SVR model. Keywords— Forex Forecasting, Long Short Term Memory, Gated Recurrent Unit, Support Vector Regression, ARIMA, Extreme Gradient Boosting

Age Estimation from fMRI Data Using Recurrent Neural Network

Finding a biomarker that indicates the subject’s age is one of the most important topics in biology. Several recent studies tried to extract a biomarker from brain imaging data including fMRI data. However, most of them focused on MRI data, which do not provide dynamics and lack attempts to apply recently proposed deep learning models. We propose a deep neural network model that estimates the age of a subject from fMRI images using a recurrent neural network (RNN), more precisely, a gated recurrent unit (GRU). However, applying neural networks is not trivial due to the high dimensional nature of fMRI data. In this work, we propose a novel preprocessing technique using the Automated Anatomical Labeling (AAL) atlas, which significantly reduces the input dimension. The proposed dimension reduction technique allows us to train our model with 640 training and validation samples from different projects under mean squared error (MSE). Finally, we obtain the correlation value of 0.905 between the predicted age and the actual age on 155 test samples. The proposed model estimates the age within the range of ±12 on most of the test samples. Our model is written in Python and is freely available for download.

AN ARTIFICIAL INTELLIGENCE APPROACH TO PREDICTION OF EXTREME EVENTS: THE CASE OF STORMS IN WESTERN FRANCE

Storms represent an increased source of risk that affects human life, property, and the environment. Prediction of these events, however, is challenging due to their low frequency of occurrence. This paper proposed an artificial intelligence approach to address this challenge and predict storm characteristics and occurrence using a gated recurrent unit (GRU) neural network and a support vector machine (SVM). Historical weather and marine measurements collected from buoy data, as well as a database of storms containing all the extreme events that occurred in Brittany and Pays de la Loire regions, Western France, since 1996, were used. Firstly, GRU was used to predict the characteristics of storms (wind speed, pressure, humidity, temperature, and wave height). Then, SVM was introduced to identify storm-specific patterns and predict storm occurrence. The approach adopted leads to the prediction of storms and their characteristics, which could be used widely to reduce the awful consequences of these natural disasters by taking preventive measures.

A CNN-ABiGRU method for Gearbox Fault Diagnosis

As a key part of modern industrial machinery, there has been a lot of fault diagnosis methods for gearbox. However, traditional fault diagnosis methods suffer from dependence on prior knowledge. This paper proposed an end-to-end method based on convolutional neural network (CNN), Bidirectional gated recurrent unit (BiGRU), and Attention Mechanism. Among them, the application of BiGRU not only made perfect use of the time sequence of signal, but also saved computing resources more than the same type of networks because of the low amount of calculation. In order to verify the effectiveness and generalization performance of the proposed method, experiments are carried out on two datasets, and the accuracy is calculated by the ten-fold crossvalidation. Compared with the existing fault diagnosis methods, the experimental results show that the proposed model has higher accuracy.

Session interest model for CTR prediction based on self-attention mechanism

Click-through rate prediction, which aims to predict the probability of the user clicking on an item, is critical to online advertising. How to capture the user evolving interests from the user behavior sequence is an important issue in CTR prediction. However, most existing models ignore the factor that the sequence is composed of sessions, and user behavior can be divided into different sessions according to the occurring time. The user behaviors are highly correlated in each session and are not relevant across sessions. We propose an effective model for CTR prediction, named Session Interest Model via Self-Attention (SISA). First, we divide the user sequential behavior into session layer. A self-attention mechanism with bias coding is used to model each session. Since different session interest may be related to each other or follow a sequential pattern, next, we utilize gated recurrent unit (GRU) to capture the interaction and evolution of user different historical session interests in session interest extractor module. Then, we use the local activation and GRU to aggregate their target ad to form the final representation of the behavior sequence in session interest interacting module. Experimental results show that the SISA model performs better than other models.