Search results
1 – 10 of over 1000The purpose of this paper is to investigate the existence and global exponential stability of periodic solution of memristor-based recurrent neural networks with time-varying…
Abstract
Purpose
The purpose of this paper is to investigate the existence and global exponential stability of periodic solution of memristor-based recurrent neural networks with time-varying delays and leakage delays.
Design/methodology/approach
The differential inequality theory and some novel mathematical analysis techniques are applied.
Findings
A set of sufficient conditions which guarantee the existence and global exponential stability of periodic solution of involved model is derived.
Practical implications
It plays an important role in designing the neural networks.
Originality/value
The obtained results of this paper are new and complement some previous studies. The innovation of this paper concludes two aspects: the analysis on the existence and global exponential stability of periodic solution of memristor-based recurrent neural networks with time-varying delays and leakage delays is first proposed; and it is first time to establish the sufficient criterion which ensures the existence and global exponential stability of periodic solution of memristor-based recurrent neural networks with time-varying delays and leakage delays.
Details
Keywords
Junfei Qiao, Gaitang Han, Honggui Han and Wei Chai
The purpose of this paper is to present an on-line modeling and controlling scheme based on the dynamic recurrent neural network for wastewater treatment system.
Abstract
Purpose
The purpose of this paper is to present an on-line modeling and controlling scheme based on the dynamic recurrent neural network for wastewater treatment system.
Design/methodology/approach
A control strategy based on rule adaptive recurrent neural network (RARFNN) is proposed in this paper to control the dissolved oxygen (DO) concentration and nitrate nitrogen (SNo) concentration. The structure of the RARFNN is self-organized by a rule adaptive algorithm, and the rule adaptive algorithm considers the overall information processing ability of neural network. Furthermore, a stability analysis method is given to prove the convergence of the proposed RARFNN.
Findings
By application in the control problem of wastewater treatment process (WWTP), results show that the proposed control method achieves better performance compared to other methods.
Originality/value
The proposed on-line modeling and controlling method uses the RARFNN to model and control the dynamic WWTP. The RARFNN can adjust its structure and parameters according to the changes of biochemical reactions and pollutant concentrations. And, the rule adaptive mechanism considers the overall information processing ability judgment of the neural network, which can ensure that the neural network contains the information of the biochemical reactions.
Details
Keywords
B. Cannas, S. Cincotti, A. Fanni, M. Marchesi, F. Pilo and M. Usai
Many practical applications of neural networks require the identification of non‐linear deterministic systems or chaotic systems. In these cases the use of a network architecture…
Abstract
Many practical applications of neural networks require the identification of non‐linear deterministic systems or chaotic systems. In these cases the use of a network architecture known as locally recurrent neural network (LRNN) is often preferable in place of standard feedforward multi‐layer perceptron (MLP) networks, or of globally recurrent neural network. In this paper locally recurrent networks are used to simulate the behaviour of the Chua’s circuit that can be considered a paradigm for studying chaos. It is shown that such networks are able to identify the underlying link among the state variables of the Chua’s circuit. Moreover, they are able to behave like an autonomous Chua’s double scroll, showing a chaotic behaviour of the state variables obtainable through a suitable circuit elements choice.
Details
Keywords
K.C. LAM, TIESONG HU, S.O. CHEUNG, R.K.K. YUEN and Z.M. DENG
Modelling of the multiproject cash flow decisions in a contracting firm facilitates optimal resource utilization, financial planning, profit forecasting and enables the inclusion…
Abstract
Modelling of the multiproject cash flow decisions in a contracting firm facilitates optimal resource utilization, financial planning, profit forecasting and enables the inclusion of cash‐flow liquidity in forecasting. However, a great challenge for contracting firm to manage his multiproject cash flow when large and multiple construction projects are involved (manipulate large amount of resources, e.g. labour, plant, material, cost, etc.). In such cases, the complexity of the problem, hence the constraints involved, renders most existing regular optimization techniques computationally intractable within reasonable time frames. This limit inhibits the ability of contracting firms to complete construction projects at maximum efficiency through efficient utilization of resources among projects. Recently, artificial neural networks have demonstrated its strength in solving many optimization problems efficiently. In this regard a novel recurrent‐neural‐network model that integrates multi‐objective linear programming and neural network (MOLPNN) techniques has been developed. The model was applied to a relatively large contracting company running 10 projects concurrently in Hong Kong. The case study verified the feasibility and applicability of the MOLPNN to the defined problem. A comparison undertaken of two optimal schedules (i.e. risk‐avoiding scheme A and risk‐seeking scheme B) of cash flow based on the decision maker's preference is described in this paper.
Details
Keywords
Soheil Ganjefar and Mojtaba Alizadeh
The power system is complex multi‐component dynamic system with many operational levels made up of a wide range of energy sources with many interaction points. Low frequency…
Abstract
Purpose
The power system is complex multi‐component dynamic system with many operational levels made up of a wide range of energy sources with many interaction points. Low frequency oscillations are observed when large power systems are interconnected by relatively weak tie lines. These oscillations may sustain and grow to cause system separation if no adequate damping is available. The present paper aims to propose an on‐line self‐learning PID (OLSL‐PID) controller in order to damp the low frequency power system oscillations in a single‐machine system.
Design/methodology/approach
The proposed OLSL‐PID is used as a controller in order to damp the low frequency power system oscillations. It has a local nature because of its powerful adaption process based on back‐propagation (BP) algorithm that is implemented through an adaptive self‐recurrent wavelet neural network identifier (ASRWNNI). In fact PID controller parameters are updated in on‐line mode, using BP algorithm based on the information provided by the ASRWNNI which is a powerful fast‐acting identifier because of its local nature, self‐recurrent structure and stable training algorithm with ALRs based on discrete lyapunov stability theorem.
Findings
The proposed control scheme is applied to a single machine infinite bus power system under different operating conditions and disturbances. The nonlinear time‐domain simulation results are promising and show the effectiveness and robustness of the proposed controller and also reveal that: because of the high adaptability, the local behavior and high flexibility of the OLSL‐PID controller, it can be damp the low frequency oscillations in the best possible manner and significantly improves the stability performance of the system.
Originality/value
The proposed controller adaption process is done in each sampling period using a powerful adaption law based on BP algorithm. Also during the process the system sensitivity is provided by a powerful fast‐acting identifier. As an alternative to multi‐layer perceptron neural network, self‐recurrent wavelet neural networks (SRWNNs) which combine the properties such as attractor dynamics of recurrent neural network and the fast convergence of the wavelet neural network were proposed to identify synchronous generator. Also to help the OLSL‐PID stability first, PID parameters tuning problem under a wide range of operating conditions is converted to an optimization problem which solved by a chaotic optimization algorithm (COA), and afterwards PID controller is hooked up in the system and on‐line tuning is done in each sampling period.
Details
Keywords
The purpose of this paper is to propose an accurate product reliability prediction model in order to enhance product quality and reduce product costs.
Abstract
Purpose
The purpose of this paper is to propose an accurate product reliability prediction model in order to enhance product quality and reduce product costs.
Design/methodology/approach
This study proposes a new method for predicting the reliability of repairable systems. The novel method employed constructs a predictive model by integrating neural networks and genetic algorithms. Findings – The novel method employed constructs a predictive model by integrating neural networks and genetic algorithms. Genetic algorithms are used to globally optimize the number of neurons in the hidden layer, the learning rate and momentum of neural network architecture. Research limitations/implications – This study only adopts real failure data from an electronic system to verify the feasibility and effectiveness of the proposed method. Future research may use other product's failure data to verify the proposed method. The proposed method is superior to ARIMA and neural network model prediction techniques in the reliability of repairable systems. Practical implications – Based on the more accurate analytical results achieved by the proposed method, engineers or management authorities can take follow‐up actions to ensure that products meet quality requirements, provide logistical support and correct product design. Originality/value – The proposed method is superior to other prediction techniques in predicting the reliability of repairable systems.
Details
Keywords
Yasuhide Shinohara, Yasuhiko Nishio, Tadashi Dohi and Shunji Osaki
The determination of the release schedule for a new software product is the most important issue for designing and controlling a software development process. In fact, the optimal…
Abstract
The determination of the release schedule for a new software product is the most important issue for designing and controlling a software development process. In fact, the optimal software release problem based on some software reliability growth models has been studied by many authors. In this paper, we propose a new method to estimate the optimal software release time under an alternative cost criterion. More precisely, two kinds of artificial neural networks are used to estimate the fault‐detection time observed in both testing and operation phases. As a cost criterion, we adopt the expected cost rate (the expected total software cost per unit testing time). Then, it is shown that the optimization problem to obtain the optimal release time can be reduced to a graphical one to minimize the tangent slope from a point to an (estimated) empirical curve in two‐dimensional space. Through numerical examples using actual fault‐detection time data, it is illustrated that the method proposed is a very useful device to estimate the optimal software release time precisely.
Details
Keywords
Wei Feng, Yuqin Wu and Yexian Fan
The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations (NSS). Because the conventional methods for the…
Abstract
Purpose
The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations (NSS). Because the conventional methods for the prediction of NSS, such as support vector machine, particle swarm optimization, etc., lack accuracy, robustness and efficiency, in this study, the authors propose a new method for the prediction of NSS based on recurrent neural network (RNN) with gated recurrent unit.
Design/methodology/approach
This method extracts internal and external information features from the original time-series network data for the first time. Then, the extracted features are applied to the deep RNN model for training and validation. After iteration and optimization, the accuracy of predictions of NSS will be obtained by the well-trained model, and the model is robust for the unstable network data.
Findings
Experiments on bench marked data set show that the proposed method obtains more accurate and robust prediction results than conventional models. Although the deep RNN models need more time consumption for training, they guarantee the accuracy and robustness of prediction in return for validation.
Originality/value
In the prediction of NSS time-series data, the proposed internal and external information features are well described the original data, and the employment of deep RNN model will outperform the state-of-the-arts models.
Details
Keywords
Isaac Chairez, Israel Alejandro Guarneros-Sandoval, Vlad Prud, Olga Andrianova, Sleptsov Ernest, Viktor Chertopolokhov, Grigory Bugriy and Arthur Mukhamedov
There are common problems in the identification of uncertain nonlinear systems, nonparametric approximation, state estimation, and automatic control. Dynamic neural network (DNN…
Abstract
Purpose
There are common problems in the identification of uncertain nonlinear systems, nonparametric approximation, state estimation, and automatic control. Dynamic neural network (DNN) approximation can simplify the development of all the aforementioned problems in either continuous or discrete systems. A DNN is represented by a system of differential or recurrent equations defined in the space of vector activation functions with weights and offsets that are functionally associated with the input data.
Design/methodology/approach
This study describes the version of the toolbox, that can be used to identify the dynamics of the black box and restore the laws underlying the system using known inputs and outputs. Depending on the completeness of the information, the toolbox allows users to change the DNN structure to suit specific tasks.
Findings
The toolbox consists of three main components: user layer, network manager, and network instance. The user layer provides high-level control and monitoring of system performance. The network manager serves as an intermediary between the user layer and the network instance, and allows the user layer to start and stop learning, providing an interface to indirectly access the internal data of the DNN.
Research limitations/implications
Control capability is limited to adjusting a small number of numerical parameters and selecting functional parameters from a predefined list.
Originality/value
The key feature of the toolbox is the possibility of developing an algorithmic semi-automatic selection of activation function parameters based on optimization problem solutions.
Details
Keywords
Femi Emmanuel Ayo, Olusegun Folorunso, Friday Thomas Ibharalu and Idowu Ademola Osinuga
Hate speech is an expression of intense hatred. Twitter has become a popular analytical tool for the prediction and monitoring of abusive behaviors. Hate speech detection with…
Abstract
Purpose
Hate speech is an expression of intense hatred. Twitter has become a popular analytical tool for the prediction and monitoring of abusive behaviors. Hate speech detection with social media data has witnessed special research attention in recent studies, hence, the need to design a generic metadata architecture and efficient feature extraction technique to enhance hate speech detection.
Design/methodology/approach
This study proposes a hybrid embeddings enhanced with a topic inference method and an improved cuckoo search neural network for hate speech detection in Twitter data. The proposed method uses a hybrid embeddings technique that includes Term Frequency-Inverse Document Frequency (TF-IDF) for word-level feature extraction and Long Short Term Memory (LSTM) which is a variant of recurrent neural networks architecture for sentence-level feature extraction. The extracted features from the hybrid embeddings then serve as input into the improved cuckoo search neural network for the prediction of a tweet as hate speech, offensive language or neither.
Findings
The proposed method showed better results when tested on the collected Twitter datasets compared to other related methods. In order to validate the performances of the proposed method, t-test and post hoc multiple comparisons were used to compare the significance and means of the proposed method with other related methods for hate speech detection. Furthermore, Paired Sample t-Test was also conducted to validate the performances of the proposed method with other related methods.
Research limitations/implications
Finally, the evaluation results showed that the proposed method outperforms other related methods with mean F1-score of 91.3.
Originality/value
The main novelty of this study is the use of an automatic topic spotting measure based on naïve Bayes model to improve features representation.
Details