Optimal Recurrent Neural Network Research Articles

Design of Network Security Assessment and Prediction Model Based on Improved K-means Clustering and Intelligent Optimization Recurrent Neural Network

Design of Network Security Assessment and Prediction Model Based on Improved K-means Clustering and Intelligent Optimization Recurrent Neural Network

Opt-RNN-DBFSVM: Optimal recurrent neural network density based fuzzy support vector machine

Two major problems are encountered when using fuzzy SVM: (a) the number of local minima increases exponentially with the number of samples and (b) the quantity of required computer storage, required for a regular quadratic programming solver, increases by an exponential magnitude as the problem size expands. The Kernel-Adatron family of algorithms gaining attention lately which has allowed to handle very large classification and regression problems. However, these methods treat different types of samples (Noise, border, and core) with the same manner, which causes searches in unpromising areas and increases the number of iterations. In this work, we introduce a hybrid method to overcome these shortcoming, namely Optimal Recurrent Neural Network Density Based fuzzy Support Vector Machine (Opt-RNN-DBFSVM). This method consists of four steps: (a) characterization of different samples, (b) elimination of samples with a low probability of being a support vector, (c) construction of an appropriate recurrent neural network based on an original energy function, and (d) solution of the system of differential equations, managing the dynamics of the RNN, using the Euler–Cauchy method involving an optimal time step. Thanks to its recurrent architecture, the RNN remembers the regions explored during the search process. We demonstrated that RNN-FSVM converges to feasible support vectors and Opt-RNN-DBFSVM has a very low time complexity compared to RNN-FSVM with constant time step, and KAs-FSVM. Several experiments were performed on academic data sets. We used several classification performance measures to compare Opt-RNN-DBFSVM to different classification methods and the results obtained show the good performance of the proposed method.

OPT-RNN-DBSVM: OPTimal Recurrent Neural Network and Density-Based Support Vector Machine

When implementing SVMs, two major problems are encountered: (a) the number of local minima of dual-SVM increases exponentially with the number of samples and (b) the computer storage memory required for a regular quadratic programming solver increases exponentially as the problem size expands. The Kernel-Adatron family of algorithms, gaining attention recently, has allowed us to handle very large classification and regression problems. However, these methods treat different types of samples (i.e., noise, border, and core) in the same manner, which makes these algorithms search in unpromising areas and increases the number of iterations as well. This paper introduces a hybrid method to overcome such shortcomings, called the Optimal Recurrent Neural Network and Density-Based Support Vector Machine (Opt-RNN-DBSVM). This method consists of four steps: (a) the characterization of different samples, (b) the elimination of samples with a low probability of being a support vector, (c) the construction of an appropriate recurrent neural network to solve the dual-DBSVM based on an original energy function, and (d) finding the solution to the system of differential equations that govern the dynamics of the RNN, using the Euler–Cauchy method involving an optimal time step. Density-based preprocessing reduces the number of local minima in the dual-SVM. The RNN’s recurring architecture avoids the need to explore recently visited areas. With the optimal time step, the search moves from the current vectors to the best neighboring support vectors. It is demonstrated that RNN-SVM converges to feasible support vectors and Opt-RNN-DBSVM has very low time complexity compared to the RNN-SVM with a constant time step and the Kernel-Adatron algorithm–SVM. Several classification performance measures are used to compare Opt-RNN-DBSVM with different classification methods and the results obtained show the good performance of the proposed method.

Drug–Target Interaction Prediction Model Using Optimal Recurrent Neural Network

Drug-target interactions prediction (DTIP) remains an important requirement in the field of drug discovery and human medicine. The identification of interaction among the drug compound and target protein plays an essential process in the drug discovery process. It is a lengthier and complex process for predicting the drug target interaction (DTI) utilizing experimental approaches. To resolve these issues, computational intelligence based DTIP techniques were developed to offer an efficient predictive model with low cost. The recently developed deep learning (DL) models can be employed for the design of effective predictive approaches for DTIP. With this motivation, this paper presents a new drug target interaction prediction using optimal recurrent neural network (DTIP-ORNN) technique. The goal of the DTIP-ORNN technique is to predict the DTIs in a semi-supervised way, i.e., inclusion of both labelled and unlabelled instances. Initially, the DTIP-ORNN technique performs data preparation process and also includes class labelling process, where the target interactions from the database are used to determine the final label of the unlabelled instances. Besides, drug-to-drug (D-D) and target-to-target (T-T) interactions are used for the weight initiation of the RNN based bidirectional long short term memory (BiLSTM) model which is then utilized to the prediction of DTIs. Since hyperparameters significantly affect the prediction performance of the BiLSTM technique, the Adam optimizer is used which mainly helps to improve the DTI prediction outcomes. In order to ensure the enhanced predictive outcomes of the DTIP-ORNN technique, a series of simulations are implemented on four benchmark datasets. The comparative result analysis shows the promising performance of the DTIP-ORNN method on the recent approaches.

Research on Default Prediction Model of Corporate Credit Risk Based on Big Data Analysis Algorithm

In recent years, with the rise of many technologies such as big data and artificial intelligence, the digitalization and information transformation of enterprises have gradually penetrated into the financial industry. Based on different big data analysis algorithms, we aim to establish a default prediction model for corporate credit risk, further optimize different models, compare the model performance, and analyze the robustness of the optimal model. We collect 21 items of financial and non-financial index data from more than 1,000 listed companies, standardize, balance and normalize the data, use correlation coefficient to screen the index, and establish two in-depth learning models, convolutional neural network model and recurrent neural network model, based on Pytorch framework of Spark platform, to complete the model optimization, and compare them with two traditional machine learning models: random forest model and logistic regression model. Finally, the comparison experiment shows that the recurrent neural network is the optimal model with an accuracy rate of 0.93, a recall rate of 0.96 and a F1 value of 0.93. For the optimal recurrent neural network model, the robustness of the model is analyzed by modifying the number of indicators, changing the number of samples and eliminating non-financial factors. The results show that the evaluation indicators of the model do not change much under the three conditions, and the model has a good robustness.

An automatic selection of optimal recurrent neural network architecture for processes dynamics modelling purposes

A problem related to the development of algorithms designed to find the structure of artificial neural network used for behavioural (black-box) modelling of selected dynamic processes has been addressed in this paper. The research has included four original proposals of algorithms dedicated to neural network architecture search. Algorithms have been based on well-known optimisation techniques such as evolutionary algorithms and gradient descent methods. In the presented research an artificial neural network of recurrent type has been used, whose architecture has been selected in an optimised way based on the above-mentioned algorithms. The optimality has been understood as achieving a trade-off between the size of the neural network and its accuracy in capturing the response of the mathematical model under which it has been learnt. During the optimisation, original specialised evolutionary operators have been proposed. The research involved an extended validation study based on data generated from a mathematical model of the fast processes occurring in a pressurised water nuclear reactor.

Anomaly Detection of Operating Equipment in Livestock Farms Using Deep Learning Techniques

In order to establish a smart farm, many kinds of equipment are built and operated inside and outside of a pig house. Thus, the environment for livestock (limited to pigs in this paper) in the barn is properly maintained for its growth conditions. However, due to poor environments such as closed pig houses, lack of stable power supply, inexperienced livestock management, and power outages, the failure of these environment equipment is high. Thus, there are difficulties in detecting its malfunctions during equipment operation. In this paper, based on deep learning, we provide a mechanism to quickly detect anomalies of multiple equipment (environmental sensors and controllers, etc.) in each pig house at the same time. In particular, environmental factors (temperature, humidity, CO2, ventilation, radiator temperature, external temperature, etc.) to be used for learning were extracted through the analysis of data accumulated for the generation of predictive models of each equipment. In addition, the optimal recurrent neural network (RNN) environment was derived by analyzing the characteristics of the learning RNN. In this way, the accuracy of the prediction model can be improved. In this paper, the real-time input data (only in the case of temperature) was intentionally induced above the threshold, and 93% of the abnormalities were detected to determine whether the equipment was abnormal.

Optimal Controllers for Grid Connected Re System and their Challenges: A Brief Review

A conquest for Science and also Technology and also the ever-growing planet of innovation trigger numerous innovations. Currently India demandingly picking to beat non-renewable fuel sources sparsity issues along with Renewable Energy Sources (RES). Renewable Energy Sources needs intricate innovations for the usage. Renewable resource resources and also modern technologies possess prospective to supply options to the enduring electricity troubles being actually experienced due to the establishing nations. The renewable resource resources like wind power, solar power, geothermal power, electricity, biomass electricity and also energy tissue innovation may be made use of to get over electricity lack in India. To overcome the power demand for such a fast-growing economic climate, India will certainly need an ensured source of 3- 4 times extra power than the overall power consumed today. This work reviews different control techniques and proposes a new control technique Optimal Recurrent Neural Networks (ORNN) based Controller to mitigate the power quality (PQ) disturbances of power system. In the proposed approach, optimal weight selection is employed for enhancing the learning procedure of RNN (ORNN). Here, ORNN technique is utilized for selecting the ideal control signal of grid inverter through optimal adjustments of the control variables in the power system. The proposed strategy creates the ideal control of the grid inverter which tries to enhance the power quality of a power system and manage the line voltage by providing reactive power compensation. This paper reviews several papers with different control strategies applied to the grid connected inverter.

Predicting death by suicide using administrative health care system data: Can recurrent neural network, one-dimensional convolutional neural network, and gradient boosted trees models improve prediction performance?

BackgroundSuicide is a leading cause of death, particularly in younger persons, and this results in tremendous years of life lost. ObjectiveTo compare the performance of recurrent neural networks, one-dimensional convolutional neural networks, and gradient boosted trees, with logistic regression and feedforward neural networks. MethodsThe modeling dataset contained 3548 persons that died by suicide and 35,480 persons that did not die by suicide between 2000 and 2016. 101 predictors were selected, and these were assembled for each of the 40 quarters (10 years) prior to the quarter of death, resulting in 4040 predictors in total for each person. Model configurations were evaluated using 10-fold cross-validation. ResultsThe optimal recurrent neural network model configuration (AUC: 0.8407), one-dimensional convolutional neural network configuration (AUC: 0.8419), and XGB model configuration (AUC: 0.8493) all outperformed logistic regression (AUC: 0.8179). In addition to superior discrimination, the optimal XGB model configuration also achieved superior calibration. ConclusionsAlthough the models developed in this study showed promise, further research is needed to determine the performance limits of statistical and machine learning models that quantify suicide risk, and to develop prediction models optimized for implementation in clinical settings. It appears that the XGB model class is the most promising in terms of discrimination, calibration, and computational expense. LimitationsMany important predictors are not available in administrative data and this likely places a limit on how well prediction models developed with administrative data can perform.

An Efficient Optimized Probabilistic Neural Network Based Kidney Stone Detection and Segmentation over Ultrasound Images

Locating renal calculus in the ultrasound image is a demanding requirement in the field of medical imaging. For accurate detection of kidney stone, in this paper, optimal recurrent neural network (OPNN) is adopted. The proposed work undergoes pre-processing, feature extraction, classification, and segmentation. Initially, the noise present in input images is removed with the median filter because noises impact the accuracy of the classification. Then, compute features of this image. In the classification stage, features are used to classify defects through optimal probabilistic NeuralNetwork (OPNN). OPNN is a combination of PNN and spider monkey optimization (SMO). The parameter of PNN is optimized with the help of SMO. Then, the stone region from the abnormal image is segmented using probabilistic fuzzy c-means clustering (PFCM). The proposed methodology performance can be analyzed by using Sensitivity, Accuracy, and Specificity.

Effective features to classify ovarian cancer data in internet of medical things

Ovarian Cancer (OC) is a type of cancer that affects ovaries in women, and is difficult to detect at initial stage resulting to increased mortality rate. The OC data generated from the Internet of Medical Things (IoMT) can be used to identify distinguish the OC. To achieve this, we utilize Self Organizing Maps (SOM) and Optimal Recurrent Neural Networks (ORNN) to classify OC. SOM algorithm was utilized for better feature subset selection and was also utilized for separating profitable, understood and intriguing data from huge measures of medical data. In addition, an optimal classifier named optimal recurrent neural network (ORNN) is also employed. The classification rate of OC detection process can be improved by optimizing the weights of RNN structure using Adaptive Harmony Search Optimization (AHSO) algorithm. A set of experimentation is carried out using the data collected from women who have a high danger of OC because of familial or individual history of cancer. The proposed method attains a maximum accuracy of 96.27 with the sensitivity and specificity rate of 85.2 respectively when compared to recurrent neural networks (RNN), feedforward neural networks (FFNN) and so on. The experimental results verified that the proposed model can be used to detect cancer at early stages with high accuracy, sensitivity, specificity and low root mean square error (RMSE).

A genetic algorithm to obtain the optimal recurrent neural network

Selecting the optimal topology of a neural network for a particular application is a difficult task. In the case of recurrent neural networks, most methods only induce topologies in which their neurons are fully connected. In this paper, we present a genetic algorithm capable of obtaining not only the optimal topology of a recurrent neural network but also the least number of connections necessary. Finally, this genetic algorithm is applied to a problem of grammatical inference using neural networks, with very good results.