Independently Recurrent Neural Network Research Articles

Independent Random Recurrent Neural Networks for Infrared Spatial Point Targets Classification

Exo-atmospheric infrared (IR) point target discrimination is an important research topic of space surveillance systems. It is difficult to describe the characteristic information of the shape and micro-motion states of the targets and to discriminate different targets effectively by the characteristic information. This paper has constructed the infrared signature model of spatial point targets and obtained the infrared radiation intensity sequences dataset of different types of targets. This paper aims to design an algorithm for the classification problem of infrared radiation intensity sequences of spatial point targets. Recurrent neural networks (RNNs) are widely used in time series classification tasks, but face several problems such as gradient vanishing and explosion, etc. In view of shortcomings of RNNs, this paper proposes an independent random recurrent neural network (IRRNN) model, which combines independent structure RNNs with randomly weighted RNNs. Without increasing the training complexity of network learning, our model solves the problem of gradient vanishing and explosion, improves the ability to process long sequences, and enhances the comprehensive classification performance of the algorithm effectively. Experiments show that the IRRNN algorithm performs well in classification tasks and is robust to noise.

Open source software security vulnerability detection based on dynamic behavior features.

Open source software has been widely used in various industries due to its openness and flexibility, but it also brings potential security problems. Therefore, security analysis is required before using open source software. The current mainstream open source software vulnerability analysis technology is based on source code, and there are problems such as false positives, false negatives and restatements. In order to solve the problems, based on the further study of behavior feature extraction and vulnerability detection technology, a method of using dynamic behavior features to detect open source software vulnerabilities is proposed. Firstly, the relationship between open source software vulnerability and API call sequence is studied. Then, the behavioral risk vulnerability database of open source software is proposed as a support for vulnerability detection. In addition, the CNN-IndRNN classification model is constructed by improving the Independently Recurrent Neural Net-work (IndRNN) algorithm and applies to open source software security vulnerability detection. The experimental results verify the effectiveness of the proposed open source software security vulnerability detection method based on dynamic behavior features.

Intelligent pulse analysis of high-speed electrical discharge machining using different RNNs

High-speed electrical discharge machining (EDM) is a nontraditional machining method using high electric energy to efficiently remove materials. In this paper, a novel pulse classification method was proposed based on the recurrent neural network (RNN) for high-speed EDM pulse analysis. This study is the first time that an RNN has been applied in high-speed EDM pulse analysis. Different from traditional EDM, discharge pulses of high-speed EDM were classified into five types during the machining process: open, spark, arc, partially short and short. Models based on three different RNNs including the traditional RNN, LSTM (long short-term memory) and IndRNN (independently recurrent neural network) with different activation functions were built to analyze the discharge pulses in the research. A new input data structure based on the minimum signal change period was proposed in the classification method to simplify the model structure and improve accuracy at the same time. Without setting thresholds, the highest classification accuracy of the proposed model is up to 97.85%, which can simultaneously classify discharge pulses based on 10,000 orders of magnitude including various current values. The proposed method was effectively adapted to the complicated machining conditions and the compound power source of the high-speed EDM. The optimal model was used to analyze the distribution of discharge pulses during the machining process under different currents, fluxes and feeding speeds. The proportion of the discharge pulses was clearly predicted. Through analyzing the discharge pulses of long machining time, the regulation of discharge under different machining parameters was revealed more reliably, providing valuable information for the improvement of high-speed EDM servo systems.

A novel hybrid model on the prediction of time series and its application for the gold price analysis and forecasting

Gold, as a dominant ingredient in financial market, has gripped a large quantities of the financiers and scholars to research the formation mechanism of its price. Academic circles spring up plenty of methods to analyze and predict the gold price, such techniques are based on linear regression (MLR), support vector machine (SVM), artificial neural network (ANN), respectively. However, the existing methods cannot track the random and nonlinear features of the gold price well. The accurate and effective estimation models are acceptable for researching the temporal sequence, at the same time, it will be a powerful tool for governments and investors to formulate strategies.In this paper, a novel combination technique is put forward based on independent component analysis (ICA) and gate recurrent unit neural network (GRUNN) methods, which called ICA-GRUNN. In the first place, due to the ICA is multichannel mixed-signal analysis technique, variational mode decomposition (VMD) technique is utilized to decompose the original temporal series into virtual multichannel mixed-signal. Next, statistically independent components (ICs) are separated out from the time sequence via ICA, and then, the influence factors of the gold price are analyzed from the aspect of ICs. The results demonstrate that the fluctuation of the gold price will be interrupted by long-term trends, cyclic recurrent factors and random events. Thirdly, applying GRUNN on ICs to acquire the prediction series of independent components (ICPs) and the forecasting result of the gold price is the combination of the ICPs. Finally, comparison experiments indicate that ICA-GRUNN provides prediction with high accuracy and outperforms the benchmark methods, autoregressive integrated moving average (ARIMA), radial basis function neural network (RBFNN), long short term memory neural network (LSTM), GRUNN and ICA-LSTM.

Bidirectional LSTM Malicious webpages detection algorithm based on convolutional neural network and independent recurrent neural network

This paper proposes a bidirectional LSTM algorithm (CBIR) based on convolutional neural network and independent recurrent neural network. The algorithm extracts the “texture fingerprint” feature used to express the similarity of the content of the URL binary file of the malicious webpages, and uses the word vector tool word2vec to train the URL word vector feature and extract the URL static vocabulary feature. The “texture fingerprint” feature, the URL word vector feature and the URL static vocabulary feature are merged, and the malicious webpages is analyzed and detected based on the CBIR algorithm model. Experimental results show that compared with other methods, the proposed CBIR algorithm has improved the accuracy of malicious webpages detection.

A Hybrid Auto scaling for Cloud applications using an Efficient Predictive technique in Private Cloud

Background/Objective: To provide an efficient predictive technique to foresee future workload as well as to handle the resources efficiently by performing hybrid auto scaling for Cloud applications. Cloud applications might expertise completely different workload at different times, automatic provisioning has to work with efficiency at any point of time. Auto scaling is a feature of cloud computing that potentially scale the resources in line on demand. Considering this expectation, they are generally categorized into Reactive scaling which adds or reduces resources based on a fixed threshold value. The predictive scaling is used provide necessary scaling actions beforehand. Methods/Statistical Analysis: To perform the hybrid auto scaling (reactive plus predictive auto scaling), a time series technique should be used. Auto-regressive Moving Average (ARMA) model, the Exponential Smoothing (ES) model, the Autoregressive model (AR), the Moving Average model (MA) and the Trend- Adjusted Exponential Smoothing (TAES), Auto Regressive Integrated Moving Average (ARIMA) Time-series model, Naïve bayes algorithm, Recurrent Neural Network- Long Short Term Memory (RNN-LSTM), Independent Recurrent Neural Network (IndRNN) are time series techniques used to foresee the future workload. To find the effectiveness of predictive techniques, Mean Absolute Error (MAE), Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) performance metrics are evaluated. Findings: Based on the evaluation, IndRNN gives the minimum error rate. IndRNN is used to predict the future resource requisites in order to ascertain adequate resource are available ahead of time. Application: The predicted result from IndRNN method is integrated on private cloud to autoscale the resources for cloud applications. Keywords: Cloud Applications, Hybrid Autoscaling, Independent Recurrent Neural Network (IndRNN), Private Cloud, Workload

Cloud based health monitoring and abnormality detection using smart mirror

Background/Objective: To provide an efficient predictive technique to foresee future workload as well as to handle the resources efficiently by performing hybrid auto scaling for Cloud applications. Cloud applications might expertise completely different workload at different times, automatic provisioning has to work with efficiency at any point of time. Auto scaling is a feature of cloud computing that potentially scale the resources in line on demand. Considering this expectation, they are generally categorized into Reactive scaling which adds or reduces resources based on a fixed threshold value. The predictive scaling is used provide necessary scaling actions beforehand. Methods/Statistical Analysis: To perform the hybrid auto scaling (reactive plus predictive auto scaling), a time series technique should be used. Auto-regressive Moving Average (ARMA) model, the Exponential Smoothing (ES) model, the Autoregressive model (AR), the Moving Average model (MA) and the Trend- Adjusted Exponential Smoothing (TAES), Auto Regressive Integrated Moving Average (ARIMA) Time-series model, Naïve bayes algorithm, Recurrent Neural Network- Long Short Term Memory (RNN-LSTM), Independent Recurrent Neural Network (IndRNN) are time series techniques used to foresee the future workload. To find the effectiveness of predictive techniques, Mean Absolute Error (MAE), Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) performance metrics are evaluated. Findings: Based on the evaluation, IndRNN gives the minimum error rate. IndRNN is used to predict the future resource requisites in order to ascertain adequate resource are available ahead of time. Application: The predicted result from IndRNN method is integrated on private cloud to autoscale the resources for cloud applications. Keywords: Abnormality, Cloud, Health Monitoring, Raspberry Pi, Sensor, Smart Mirror, Two Way Mirror