Showing papers in "Neural Computing and Applications in 2019"

Monarch butterfly optimization

Abstract: In nature, the eastern North American monarch population is known for its southward migration during the late summer/autumn from the northern USA and southern Canada to Mexico, covering thousands of miles. By simplifying and idealizing the migration of monarch butterflies, a new kind of nature-inspired metaheuristic algorithm, called monarch butterfly optimization (MBO), a first of its kind, is proposed in this paper. In MBO, all the monarch butterfly individuals are located in two distinct lands, viz. southern Canada and the northern USA (Land 1) and Mexico (Land 2). Accordingly, the positions of the monarch butterflies are updated in two ways. Firstly, the offsprings are generated (position updating) by migration operator, which can be adjusted by the migration ratio. It is followed by tuning the positions for other butterflies by means of butterfly adjusting operator. In order to keep the population unchanged and minimize fitness evaluations, the sum of the newly generated butterflies in these two ways remains equal to the original population. In order to demonstrate the superior performance of the MBO algorithm, a comparative study with five other metaheuristic algorithms through thirty-eight benchmark problems is carried out. The results clearly exhibit the capability of the MBO method toward finding the enhanced function values on most of the benchmark problems with respect to the other five algorithms. Note that the source codes of the proposed MBO algorithm are publicly available at GitHub ( https://github.com/ggw0122/Monarch-Butterfly-Optimization , C++/MATLAB) and MATLAB Central ( http://www.mathworks.com/matlabcentral/fileexchange/50828-monarch-butterfly-optimization , MATLAB).

Accurate photovoltaic power forecasting models using deep LSTM-RNN

Abstract: Photovoltaic (PV) is one of the most promising renewable energy sources. To ensure secure operation and economic integration of PV in smart grids, accurate forecasting of PV power is an important issue. In this paper, we propose the use of long short-term memory recurrent neural network (LSTM-RNN) to accurately forecast the output power of PV systems. The LSTM networks can model the temporal changes in PV output power because of their recurrent architecture and memory units. The proposed method is evaluated using hourly datasets of different sites for a year. We compare the proposed method with three PV forecasting methods. The use of LSTM offers a further reduction in the forecasting error compared with the other methods. The proposed forecasting method can be a helpful tool for planning and controlling smart grids.

An approach toward decision-making and medical diagnosis problems using the concept of spherical fuzzy sets

Abstract: Human opinion cannot be restricted to yes or no as depicted by conventional fuzzy set (FS) and intuitionistic fuzzy set (IFS) but it can be yes, abstain, no and refusal as explained by picture fuzzy set (PFS). In this article, the concept of spherical fuzzy set (SFS) and T-spherical fuzzy set (T-SFS) is introduced as a generalization of FS, IFS and PFS. The novelty of SFS and T-SFS is shown by examples and graphical comparison with early established concepts. Some operations of SFSs and T-SFSs along with spherical fuzzy relations are defined, and related results are conferred. Medical diagnostics and decision-making problem are discussed in the environment of SFSs and T-SFSs as practical applications.

Feature selection via a novel chaotic crow search algorithm

Abstract: Crow search algorithm (CSA) is a new natural inspired algorithm proposed by Askarzadeh in 2016. The main inspiration of CSA came from crow search mechanism for hiding their food. Like most of the optimization algorithms, CSA suffers from low convergence rate and entrapment in local optima. In this paper, a novel meta-heuristic optimizer, namely chaotic crow search algorithm (CCSA), is proposed to overcome these problems. The proposed CCSA is applied to optimize feature selection problem for 20 benchmark datasets. Ten chaotic maps are employed during the optimization process of CSA. The performance of CCSA is compared with other well-known and recent optimization algorithms. Experimental results reveal the capability of CCSA to find an optimal feature subset which maximizes the classification performance and minimizes the number of selected features. Moreover, the results show that CCSA is superior compared to CSA and the other algorithms. In addition, the experiments show that sine chaotic map is the appropriate map to significantly boost the performance of CSA.

A novel image encryption scheme based on DNA sequence operations and chaotic systems

Abstract: In the paper, a novel image encryption algorithm based on DNA sequence operations and chaotic systems is proposed. The encryption architecture of permutation and diffusion is adopted. Firstly, 256-bit hash value of the plain image is gotten to calculate the initial values and system parameters of the 2D Logistic-adjusted-Sine map (2D-LASM) and a new 1D chaotic system; thus, the encryption scheme highly depends on the original image. Next, the chaotic sequences from 2D-LASM are used to produce the DNA encoding/decoding rule matrix, and the plain image is encoded into a DNA matrix according to it. Thirdly, DNA level row permutation and column permutation are performed on the DNA matrix of the original image, inter-DNA-plane permutation and intra-DNA-plane permutation can be attained simultaneously, and then, DNA XOR operation is performed on the permutated DNA matrix using a DNA key matrix, and the key matrix is produced by the combination of two 1D chaotic systems. Finally, after decoding the confused DNA matrix, the cipher image is obtained. Experimental results and security analyses demonstrate that the proposed scheme not only has good encryption effect, but also is secure enough to resist against the known attacks.

Chaotic grasshopper optimization algorithm for global optimization

Abstract: Grasshopper optimization algorithm (GOA) is a new meta-heuristic algorithm inspired by the swarming behavior of grasshoppers. The present study introduces chaos theory into the optimization process of GOA so as to accelerate its global convergence speed. The chaotic maps are employed to balance the exploration and exploitation efficiently and the reduction in repulsion/attraction forces between grasshoppers in the optimization process. The proposed chaotic GOA algorithms are benchmarked on thirteen test functions. The results show that the chaotic maps (especially circle map) are able to significantly boost the performance of GOA.

Epileptic seizure detection using hybrid machine learning methods

Abstract: The aim of this study is to establish a hybrid model for epileptic seizure detection with genetic algorithm (GA) and particle swarm optimization (PSO) to determine the optimum parameters of support vector machines (SVMs) for classification of EEG data. SVMs are one of the robust machine learning techniques and have been extensively used in many application areas. The kernel parameter’s setting for SVMs in training process effects the classification accuracy. We used GA- and PSO-based approach to optimize the SVM parameters. Compared to the GA algorithm, the PSO-based approach significantly improves the classification accuracy. It is shown that the proposed Hybrid SVM can reach a classification accuracy of up to 99.38% for the EEG datasets. Hence, the proposed Hybrid SVM is an efficient tool for neuroscientists to detect epileptic seizure in EEG.

Detection of phishing websites using an efficient feature-based machine learning framework

Abstract: Phishing is a cyber-attack which targets naive online users tricking into revealing sensitive information such as username, password, social security number or credit card number etc. Attackers fool the Internet users by masking webpage as a trustworthy or legitimate page to retrieve personal information. There are many anti-phishing solutions such as blacklist or whitelist, heuristic and visual similarity-based methods proposed to date, but online users are still getting trapped into revealing sensitive information in phishing websites. In this paper, we propose a novel classification model, based on heuristic features that are extracted from URL, source code, and third-party services to overcome the disadvantages of existing anti-phishing techniques. Our model has been evaluated using eight different machine learning algorithms and out of which, the Random Forest (RF) algorithm performed the best with an accuracy of 99.31%. The experiments were repeated with different (orthogonal and oblique) random forest classifiers to find the best classifier for the phishing website detection. Principal component analysis Random Forest (PCA-RF) performed the best out of all oblique Random Forests (oRFs) with an accuracy of 99.55%. We have also tested our model with the third-party-based features and without third-party-based features to determine the effectiveness of third-party services in the classification of suspicious websites. We also compared our results with the baseline models (CANTINA and CANTINA+). Our proposed technique outperformed these methods and also detected zero-day phishing attacks.

Self-compacting concrete strength prediction using surrogate models

Abstract: Despite the extensive use of self-compacting concrete in constructions over the last decades, there is not yet a robust quantitative method, available in the literature, which can reliably predict its strength based on its mix components. Τhis limitation is due to the highly nonlinear relation between the self-compacting concrete’s compressive strength and the mixed components. In this paper, the application of artificial neural networks for predicting the mechanical characteristics of self-compacting concrete has been investigated. Specifically, surrogate models (such as artificial neural network models and a new proposed normalization method) have been used for predicting the 28-day compressive strength of admixture-based self-compacting concrete (based on experimental data available in the literature). The comparison of the derived results with the experimental findings demonstrates the ability of artificial neural networks to approximate the compressive strength of self-compacting concrete in a reliable and robust manner. Furthermore, the proposed formula for the normalization of data has been proven effective and robust compared to available ones.

Adapting weather conditions based IoT enabled smart irrigation technique in precision agriculture mechanisms

Abstract: Precision agriculture is the mechanism which controls the land productivity and maximizes the revinue and minimizes the impact on sorroundings by automating the complete agriculture processes. This projected work relies on independent internet of things (IoT) enabled wireless sensor network (WSN) framework consisting of soil moisture (MC) probe, soil temperature measuring device, environmental temperature sensor, environmental humidity sensing device, CO2 sensor, daylight intensity device (light dependent resistor) to acquire real-time farm information through multi-point measurement. The projected observance technique consists of all standalone IoT-enabled WSN nodes used for timely data acquisitions and storage of agriculture information. The farm history is additionally stored for generating necessary action throughout the whole course of farming. The work summarizes the optimum usage of irrigation by the precise management of water valve using neural network-based prediction of soil water requirement in 1 h ahead. Our proposed irrigation control scheme utilizes structural similarity (SSIM)-based water valve management mechanism which is used to locate farm regions having water deficiency. Moreover, a close comparative study of optimization techniques, like variable learning rate gradient descent, gradient descent for feedforward neural network-based pattern classification, is performed and the best practice is employed to forecast soil MC on hourly basis together with interpolation method for generating soil moisture content (MC) distribution map. Finally, SSIM index-based soil MC deficiency is calculated to manipulate the specified valves for maintaining uniform water requirement through the entire farm area. The valve control commands are again processed using fuzzy logic-based weather condition modeling system to manipulate control commands by considering different weather conditions.

A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system

Abstract: Dockless bike-sharing is becoming popular all over the world, and short-term spatiotemporal distribution forecasting on system state has been further enlarged due to its dynamic spatiotemporal characteristics. We employ a deep learning approach, named the convolutional long short-term memory network (conv-LSTM), to address the spatial dependences and temporal dependences. The spatiotemporal variables including number of bicycles in area, distribution uniformity, usage distribution, and time of day as a spatiotemporal sequence in which both the input and the prediction target are spatiotemporal 3D tensors within one end-to-end learning architecture. Experiments show that conv-LSTM outperforms LSTM on capturing spatiotemporal correlations.

A chaotic image encryption algorithm based on 3-D bit-plane permutation

Abstract: There are two shortcomings existing in the current color image encryption. One is that high correlation between R, G, B components of the original image may be neglected, the other is that the encryption has little relationship with the plain image, and then it is vulnerable to be broken. In order to solve these two problems and present secure and effective image encryption scheme, we introduce a novel chaos-based image encryption algorithm for color images based on three-dimensional (3-D) bit-plane permutation. In the proposed algorithm, the color plain image is firstly converted to 24 bit planes by RGB splitting and bit plane decomposition, next three-dimensional bit-plane permutation is performed on bit planes, position sequences for permutation are obtained from the 3D Chen chaotic system, and then the three confused components are gotten. Secondly, three key matrices are generated by a 1D chaotic system and a multilevel discretization method, and finally, the color cipher image is obtained by diffusing the confused components using key matrices. The SHA 256 hash function value of the plain image is obtained and combined with the given parameters to calculate the parameters and initial values of the chaotic system, so that the proposed scheme highly depends on the plain image and it may effectively withstand known-plaintext and chosen-plaintext attacks. Simulation results and security analyses demonstrate that our algorithm not only has good encryption effect, but can also resist against common attacks, so it is reliable to be applied for image secure communications.

A novel method for solving the fully neutrosophic linear programming problems

Abstract: The most widely used technique for solving and optimizing a real-life problem is linear programming (LP), due to its simplicity and efficiency. However, in order to handle the impreciseness in the data, the neutrosophic set theory plays a vital role which makes a simulation of the decision-making process of humans by considering all aspects of decision (i.e., agree, not sure and disagree). By keeping the advantages of it, in the present work, we have introduced the neutrosophic LP models where their parameters are represented with a trapezoidal neutrosophic numbers and presented a technique for solving them. The presented approach has been illustrated with some numerical examples and shows their superiority with the state of the art by comparison. Finally, we conclude that proposed approach is simpler, efficient and capable of solving the LP models as compared to other methods.

Artificial bee colony-based neural network for the prediction of the fundamental period of infilled frame structures

Abstract: The artificial bee colony (ABC) algorithm is a recently introduced swarm intelligence algorithm for optimization, which has already been successfully applied for the training of artificial neural network (ANN) models. This paper thoroughly explores the performance of the ABC algorithm for optimizing the connection weights of feed-forward (FF) neural network models, aiming to accurately determine one of the most critical parameters in reinforced concrete structures, namely the fundamental period of vibration. Specifically, this study focuses on the determination of the vibration period of reinforced concrete infilled framed structures, which is essential to earthquake design, using feed-forward ANNs. To this end, the number of storeys, the number of spans, the span length, the infill wall panel stiffness, and the percentage of openings within the infill panel are selected as input parameters, while the value of vibration period is the output parameter. The accuracy of the FF–ABC model is verified through comparison with available formulas in the literature. The results indicate that the artificial neural network, the weights of which had been optimized via the ABC algorithm, exhibits greater ability, flexibility and accuracy in comparison with statistical models.

Real-time prediction of online shoppers’ purchasing intention using multilayer perceptron and LSTM recurrent neural networks

Abstract: In this paper, we propose a real-time online shopper behavior analysis system consisting of two modules which simultaneously predicts the visitor’s shopping intent and Web site abandonment likelihood. In the first module, we predict the purchasing intention of the visitor using aggregated pageview data kept track during the visit along with some session and user information. The extracted features are fed to random forest (RF), support vector machines (SVMs), and multilayer perceptron (MLP) classifiers as input. We use oversampling and feature selection preprocessing steps to improve the performance and scalability of the classifiers. The results show that MLP that is calculated using resilient backpropagation algorithm with weight backtracking produces significantly higher accuracy and F1 Score than RF and SVM. Another finding is that although clickstream data obtained from the navigation path followed during the online visit convey important information about the purchasing intention of the visitor, combining them with session information-based features that possess unique information about the purchasing interest improves the success rate of the system. In the second module, using only sequential clickstream data, we train a long short-term memory-based recurrent neural network that generates a sigmoid output showing the probability estimate of visitor’s intention to leave the site without finalizing the transaction in a prediction horizon. The modules are used together to determine the visitors which have purchasing intention but are likely to leave the site in the prediction horizon and take actions accordingly to improve the Web site abandonment and purchase conversion rates. Our findings support the feasibility of accurate and scalable purchasing intention prediction for virtual shopping environment using clickstream and session information data.

Sustainable closed-loop supply chain network design with discount supposition

Abstract: Supply chain network design (SCND) is one of the important, primary and strategic decisions affecting competitive advantages and all other decisions in supply chain management. Although most of papers in SCND focus only on the economic performance, this study considers simultaneously economic, social and environmental aspects. In this study, a new mixed integer nonlinear programming model is developed to formulate a multi-objective sustainable closed-loop supply chain network design problem by considering discount supposition in the transportation costs for the first time. In order to address the problem, not only traditional and recent metaheuristics are utilized, but also the algorithms are hybridized according to their strengths especially in intensification and diversification. To evaluate the efficiency and effectiveness of these algorithms, they are compared with each other by four assessment metrics for Pareto optimal analyses. Although the results indicate the performance of three proposed new hybridization algorithms, KAGA achieves better solutions compared with the others, but it needs more time. At the end, we introduced a real industrial example in glass industry to verify the proposed model and the algorithms.

Maize leaf disease classification using deep convolutional neural networks

Abstract: Crop diseases are a major threat to food security. Identifying the diseases rapidly is still a difficult task in many parts of the world due to the lack of the necessary infrastructure. The accurate identification of crop diseases is highly desired in the field of agricultural information. In this study, we propose a deep convolutional neural network (CNN)-based architecture (modified LeNet) for maize leaf disease classification. The experimentation is carried out using maize leaf images from the PlantVillage dataset. The proposed CNNs are trained to identify four different classes (three diseases and one healthy class). The learned model achieves an accuracy of 97.89%. The simulation results for the classification of maize leaf disease show the potential efficiency of the proposed method.

Fault diagnosis of gearbox based on RBF-PF and particle swarm optimization wavelet neural network

Abstract: The gear cracks of gear box are one of most common failure forms affecting gear shaft drive. It has become significant for practice and economy to diagnose the situation of gearbox rapidly and accurately. The extracted signal is filtered first to eliminate noise, which is pretreated for the diagnostic classification based on the particle filter of radial basis function. As traditional error back-propagation of wavelet neural network with falling into local minimum easily, slow convergence speed and other shortcomings, the particle swarm optimization algorithm is proposed in this paper. This particle swarm algorithm that optimizes the weight values of wavelet neural network (scale factor) and threshold value (the translation factor) was developed to reduce the iteration times and improve the convergence precision and rapidity so that the various parameters of wavelet neural network can be chosen adaptively. Experimental results demonstrate that the proposed method can accurately and quickly identify the damage situation of the gear crack, which is more robust than traditional back-propagation algorithm. It provides guidances and references for the maintenance of the gear drive system schemes.

On the exploration and exploitation in popular swarm-based metaheuristic algorithms

Abstract: It is obvious from wider spectrum of successful applications that metaheuristic algorithms are potential solutions to hard optimization problems. Among such algorithms are swarm-based methods like particle swarm optimization and ant colony optimization which are increasingly attracting new researchers. Despite popularity, the core questions on performance issues are still partially answered due to limited insightful analyses. Mere investigation and comparison of end results may not reveal the reasons behind poor or better performance. This study, therefore, performed in-depth empirical analysis by quantitatively analyzing exploration and exploitation of five swarm-based metaheuristic algorithms. The analysis unearthed explanations the way algorithms performed on numerical problems as well as on real-world application of classification using adaptive neuro-fuzzy inference system (ANFIS) trained by selected metaheuristics. The outcome of empirical study suggested that coherence and consistency in the swarm individuals throughout iterations is the key to success in swarm-based metaheuristic algorithms. The analytical approach adopted in this study may be employed to perform component-wise diversity analysis so that the contribution of each component on performance may be determined for devising efficient search strategies.

Chaotic multi-verse optimizer-based feature selection

Abstract: The multi-verse optimizer (MVO) is a new evolutionary algorithm inspired by the concepts of multi-verse theory namely, the white/black holes, which represents the interaction between the universes. However, the MVO has some drawbacks, like any other evolutionary algorithms, such as slow convergence and getting stuck in local optima (maximum or minimum). This paper provides a novel chaotic MVO algorithm (CMVO) to avoid these drawbacks, where chaotic maps are used to improve the performance of MVO algorithm. The CMVO algorithm is applied to solve the feature selection problem, in which five benchmark datasets are used to evaluate the performance of CMVO algorithm. The results of CMVO is compared with standard MVO and two other swarm algorithms. The experimental results show that logistic chaotic map is the best chaotic map that increases the performance of MVO, and also the MVO is better than other swarm algorithms.

An Automatic Tamil Speech Recognition system by using Bidirectional Recurrent Neural Network with Self-Organizing Map

Abstract: Speech recognition is one of the entrancing fields in the zone of computer science. Exactness of speech recognition framework may decrease because of the nearness of noise exhibited by the speech signal. Consequently, noise removal is a fundamental advance in automatic speech recognition (ASR) system. ASR is researched for various languages in light of the fact that every language has its particular highlights. Particularly, the requirement for ASR framework in Tamil language has been expanded broadly over the most recent couple of years. In this work, bidirectional recurrent neural network (BRNN) with self-organizing map (SOM)-based classification scheme is suggested for Tamil speech recognition. At first, the input speech signal is pre-prepared by utilizing Savitzky–Golay filter keeping in mind the end goal to evacuate the background noise and to improve the signal. At that point, Multivariate Autoregressive based highlights by presenting discrete cosine transformation piece to give a proficient signal investigation. And in addition, perceptual linear predictive coefficients likewise separated to enhance the classification accuracy. The feature vector is shifted in measure, for picking the right length of feature vector SOM utilized. At long last, Tamil digits and words are ordered by utilizing BRNN classifier where the settled length feature vector from SOM is given as input, named as BRNN-SOM. The experimental analysis demonstrates that the suggested conspire accomplished preferable outcomes looked at over exist deep neural network–hidden Markov model algorithm regarding signal-to-noise ratio, classification accuracy, and mean square error.

An artificial neural network approach for under-reamed piles subjected to uplift forces in dry sand

Abstract: The present study is about under-reamed pile subjected to uplift forces. They are known to be very effective especially against uplift forces. The objective is to develop a simple design formula ba...

Research on prediction model of geotechnical parameters based on BP neural network

Abstract: With the vigorous development of the national economy, the pace and scale of urban construction have been unfolded at an unprecedented speed. A large number of construction projects have made the urban engineering geological exploration activities reach a considerable scale in depth and breadth. The survey results of these projects are very valuable information resources, which not only played an important role in urban planning and construction at that time, but also had high reuse value. Based on BP neural network theory, this paper uses engineering geological database as the research and development platform. Based on the theory of BP neural network and the engineering geological database as the research and development platform, this paper establishes the prediction of geotechnical parameters based on the analysis of the characteristics of geotechnical materials and the distribution of geotechnical sediments and geotechnical parameters. Based on the survey data and specific engineering information, the prediction model of the project was established, and the distribution of the stratum and the relevant geotechnical parameters were predicted. Based on the study of geotechnical properties and BP neural network, a new parameter prediction model is established. Taking the engineering geological database as the platform, using the programming language such as MATLAB, the preliminary research and construction of this prediction system were carried out. The results show that the generalization ability of the prediction model meets the requirements.

Multi-objective sine-cosine algorithm (MO-SCA) for multi-objective engineering design problems

Abstract: This paper proposes a novel and an effective multi-objective optimization algorithm named multi-objective sine-cosine algorithm (MO-SCA) which is based on the search technique of sine-cosine algorithm (SCA). MO-SCA employs the elitist non-dominated sorting and crowding distance approach for obtaining different non-domination levels and to preserve the diversity among the optimal set of solutions, respectively. The effectiveness of the method is measured by implementing it on multi-objective benchmark problems that have various characteristics of Pareto front such as convex, non-convex and discrete. This proposed algorithm is also checked for the multi-objective engineering design problems with distinctive features. Furthermore, we show the proposed algorithm effectively generates the Pareto front and is easy to implement and algorithmically simple.

The naked mole-rat algorithm

Abstract: This work proposes a new swarm intelligent nature-inspired algorithm called naked mole-rat (NMR) algorithm. This NMR algorithm mimics the mating patterns of NMRs present in nature. Two types of NMRs called workers and breeders are found to depict these patterns. Workers work continuously in the endeavor to become breeders, while breeders compete among themselves to mate with the queen. Those breeders who become sterile are pushed back to the worker’s group, and the fittest worker becomes a new breeder. This phenomenon has been adapted to develop the NMR algorithm. The algorithm has been benchmarked on 27 well-known test functions, and its performance is evaluated by a comparative study with particle swarm optimization (PSO), grey wolf optimization (GWO), whale optimization algorithm (WOA), differential evolution (DE), gravitational search algorithm (GSA), fast evolutionary programming (FEP), bat algorithm (BA), flower pollination algorithm (FPA), and firefly algorithm (FA). The experimental results and statistical analysis prove that NMR algorithm is very competitive as compared to other state-of-the-art algorithms. The matlab code for NMR algorithm is avaliable at https://github.com/rohitsalgotra/Naked-Mole-Rat-Algorithm .

A novel efficient substitution-box design based on firefly algorithm and discrete chaotic map

Abstract: Substitution boxes are essential nonlinear components responsible to impart strong confusion and security in most of modern symmetric ciphers. Constructing efficient S-boxes has been a prominent topic of interest for security experts. With an aim to construct cryptographically efficient S-box, a novel scheme based on firefly (FA) optimization and chaotic map is proposed in this paper. The anticipated approach generates initial S-box using chaotic map. The meta-heuristic FA is applied to find notable configuration of S-box that satisfies the criterions by guided search for near-optimal features by minimizing fitness function. The performance of proposed approach is assessed through well-established criterions such as bijectivity, nonlinearity, strict avalanche criteria, bit independence criteria, differential uniformity, and linear approximation probability. The obtained experimental results are compared with some recently investigated S-boxes to demonstrate that the proposed scheme has better proficiency of constructing efficient S-boxes.

Malware detection based on deep learning algorithm

Abstract: In this study we represent malware as opcode sequences and detect it using a deep belief network (DBN). Compared with traditional shallow neural networks, DBNs can use unlabeled data to pretrain a multi-layer generative model, which can better represent the characteristics of data samples. We compare the performance of DBNs with that of three baseline malware detection models, which use support vector machines, decision trees, and the k-nearest neighbor algorithm as classifiers. The experiments demonstrate that the DBN model provides more accurate detection than the baseline models. When additional unlabeled data are used for DBN pretraining, the DBNs perform better than the other detection models. We also use the DBNs as an autoencoder to extract the feature vectors of executables. The experiments indicate that the autoencoder can effectively model the underlying structure of input data and significantly reduce the dimensions of feature vectors.

Combined heat and power economic dispatch problem solution by implementation of whale optimization method

Abstract: Combined heat and power economic dispatch (CHPED) is introduced as a difficult optimization problem, which provides optimal generation scheduling of heat and power units. The CHPED problem aims to minimize the fuel cost of CHP units with the consideration of operational constraints. In this paper, whale optimization algorithm (WOA) is employed to solve CHPED problem. WOA is a new meta-heuristic optimization technique, which is introduced recently for solving optimization problems. Social behavior of humpback whales is the basic idea of proposal of WOA, where the bubble-net hunting strategy inspires this optimization procedure. Three test systems are considered for evaluation of the performance of the WOA in solving the non-convex nonlinear CHPED problem. The first test instance, which includes 24 units, is studied for evaluating WOA performance in finding the optimal solution of CHPED problem. 84-Unit and 96-unit test systems are introduced for the first time in this paper to show the superiority of WOA in solving non-convex CHPED optimization problem. The second test system contains 40 power-only units, 24 CHP units, and 20 heat-only units. Additionally, the third test instance contains 52 power-only units, 24 CHP units, and 20 heat-only units. The obtained optimal solutions represent WOA efficiency and feasibility and capability of obtaining better solutions with respect to other optimization techniques in terms of operational cost and ability of implementation of WOA on large systems.

Novel applications of intelligent computing paradigms for the analysis of nonlinear reactive transport model of the fluid in soft tissues and microvessels

Abstract: This article presents a methodology to solve a one-dimensional steady-state nonlinear reactive transport model (RTM) that is meant for fluid and solute transport model of soft tissues and microvessels. The methodology integrates the artificial neural network (ANN), genetic algorithms (GAs), and pattern search (PS) aided by active-set technique (AST) and interior-point technique (IPT). The RTM is represented with nonlinear second-order system based on the boundary value problem of ordinary differential equation. The ANN modeling is used for governing expression of RTM to form a fitness function in mean square sense, and optimization solvers based on the GA, PS, GA-AST, GA-IPT, PS-AST, PS-IPT are used for viable learning of weights. Proposed techniques are applied to different nonlinear RTMs based on variation in the characteristic reaction rate and half-saturation concentration. The proposed stochastic numerical solutions are compared with state-of-the-art solvers in order to check the accuracy and convergence based on sufficient large multiple runs of the algorithms.

Extreme learning machine model for water network management

Abstract: A novel failure rate prediction model is developed by the extreme learning machine (ELM) to provide key information needed for optimum ongoing maintenance/rehabilitation of a water network, meaning the estimated times for the next failures of individual pipes within the network. The developed ELM model is trained using more than 9500 instances of pipe failure in the Greater Toronto Area, Canada from 1920 to 2005 with pipe attributes as inputs, including pipe length, diameter, material, and previously recorded failures. The models show recent, extensive usage of pipe coating with cement mortar and cathodic protection has significantly increased their lifespan. The predictive model includes the pipe protection method as pipe attributes and can reflect in its predictions, the effect of different pipe protection methods on the expected time to the next pipe failure. The developed ELM has a superior prediction accuracy relative to other available machine learning algorithms such as feed-forward artificial neural network that is trained by backpropagation, support vector regression, and non-linear regression. The utility of the models provides useful inputs when planning and budgeting for watermain inspection, maintenance, and rehabilitation.