Abstract: Abstract Deep Neural Networks (DNN) are nothing but neural networks with many hidden layers. DNNs are becoming popular in automatic speech recognition tasks which combines a good acoustic with a language model. Standard feedforward neural networks cannot handle speech data well since they do not have a way to feed information from a later layer back to an earlier layer. Thus, Recurrent Neural Networks (RNNs) have been introduced to take temporal dependencies into account. However, the shortcoming of RNNs is that long-term dependencies due to the vanishing/exploding gradient problem cannot be handled. Therefore, Long Short-Term Memory (LSTM) networks were introduced, which are a special case of RNNs, that takes long-term dependencies in a speech in addition to short-term dependencies into account. Similarily, GRU (Gated Recurrent Unit) networks are an improvement of LSTM networks also taking long-term dependencies into consideration. Thus, in this paper, we evaluate RNN, LSTM, and GRU to compare their performances on a reduced TED-LIUM speech data set. The results show that LSTM achieves the best word error rates, however, the GRU optimization is faster while achieving word error rates close to LSTM.

Abstract: Aiming at the problem that the most existing fault diagnosis methods could not effectively recognize the early faults in the rotating machinery, the empirical mode decomposition, fuzzy information entropy, improved particle swarm optimization algorithm and least squares support vector machines are introduced into the fault diagnosis to propose a novel intelligent diagnosis method, which is applied to diagnose the faults of the motor bearing in this paper. In the proposed method, the vibration signal is decomposed into a set of intrinsic mode functions (IMFs) by using empirical mode decomposition method. The fuzzy information entropy values of IMFs are calculated to reveal the intrinsic characteristics of the vibration signal and considered as feature vectors. Then the diversity mutation strategy, neighborhood mutation strategy, learning factor strategy and inertia weight strategy for basic particle swarm optimization (PSO) algorithm are used to propose an improved PSO algorithm. The improved PSO algorithm is used to optimize the parameters of least squares support vector machines (LS-SVM) in order to construct an optimal LS-SVM classifier, which is used to classify the fault. Finally, the proposed fault diagnosis method is fully evaluated by experiments and comparative studies for motor bearing. The experiment results indicate that the fuzzy information entropy can accurately and more completely extract the characteristics of the vibration signal. The improved PSO algorithm can effectively improve the classification accuracy of LS-SVM, and the proposed fault diagnosis method outperforms the other mentioned methods in this paper and published in the literature. It provides a new method for fault diagnosis of rotating machinery.

Abstract: In this paper, a membrane evolutionary artificial potential field (memEAPF) approach for solving the mobile robot path planning problem is proposed, which combines membrane computing with a genetic algorithm (membrane-inspired evolutionary algorithm with one-level membrane structure) and the artificial potential field method to find the parameters to generate a feasible and safe path. The memEAPF proposal consists of delimited compartments where multisets of parameters evolve according to rules of biochemical inspiration to minimize the path length. The proposed approach is compared with artificial potential field based path planning methods concerning to their planning performance on a set of twelve benchmark test environments, and it exhibits a better performance regarding path length. Experiments to demonstrate the statistical significance of the improvements achieved by the proposed approach in static and dynamic environments are shown. Moreover, the implementation results using parallel architectures proved the effectiveness and practicality of the proposal to obtain solutions in considerably less time.

Abstract: This paper proposes an improved epsilon constraint-handling mechanism and combines it with a decomposition-based multi-objective evolutionary algorithm (MOEA/D) to solve constrained multi-objective optimization problems (CMOPs). The proposed constrained multi-objective evolutionary algorithm (CMOEA) is named MOEA/D-IEpsilon. It adjusts the epsilon level dynamically according to the ratio of feasible to total solutions in the current population. In order to evaluate the performance of MOEA/D-IEpsilon, a new set of CMOPs with two and three objectives is designed, having large infeasible regions (relative to the feasible regions), and they are called LIR-CMOPs. Then, the 14 benchmarks, including LIR-CMOP1-14, are used to test MOEA/D-IEpsilon and four other decomposition-based CMOEAs, including MOEA/D-Epsilon, MOEA/D-SR, MOEA/D-CDP and CMOEA/D. The experimental results indicate that MOEA/D-IEpsilon is significantly better than the other four CMOEAs on all of the test instances, which shows that MOEA/D-IEpsilon is more suitable for solving CMOPs with large infeasible regions. Furthermore, a real-world problem, namely the robot gripper optimization problem, is used to test the five CMOEAs. The experimental results demonstrate that MOEA/D-IEpsilon also outperforms the other four CMOEAs on this problem.

Abstract: Evolutionary algorithms are widely used for solving multiobjective optimization problems but are often criticized because of a large number of function evaluations needed. Approximations, especially function approximations, also referred to as surrogates or metamodels are commonly used in the literature to reduce the computation time. This paper presents a survey of 45 different recent algorithms proposed in the literature between 2008 and 2016 to handle computationally expensive multiobjective optimization problems. Several algorithms are discussed based on what kind of an approximation such as problem, function or fitness approximation they use. Most emphasis is given to function approximation-based algorithms. We also compare these algorithms based on different criteria such as metamodeling technique and evolutionary algorithm used, type and dimensions of the problem solved, handling constraints, training time and the type of evolution control. Furthermore, we identify and discuss some promising elements and major issues among algorithms in the literature related to using an approximation and numerical settings used. In addition, we discuss selecting an algorithm to solve a given computationally expensive multiobjective optimization problem based on the dimensions in both objective and decision spaces and the computation budget available.

Abstract: This paper proposes a new hybrid stochastic training algorithm using the recently proposed grasshopper optimization algorithm (GOA) for multilayer perceptrons (MLPs) neural networks. The GOA algorithm is an emerging technique with a high potential in tackling optimization problems based on its flexible and adaptive searching mechanisms. It can demonstrate a satisfactory performance by escaping from local optima and balancing the exploration and exploitation trends. The proposed GOAMLP model is then applied to five important datasets: breast cancer, parkinson, diabetes, coronary heart disease, and orthopedic patients. The results are deeply validated in comparison with eight recent and well-regarded algorithms qualitatively and quantitatively. It is shown and proved that the proposed stochastic training algorithm GOAMLP is substantially beneficial in improving the classification rate of MLPs.

Abstract: Dempster–Shafer evidence theory is widely used in the information fusion field for its effectivity in representing and handling uncertain information. However, applications of Dempster rule in combining multiple conflicting evidence often cause counterintuitive results. One of the existing researches on conflict is based on the similarity of evidence. However, due to the fact that computational complexity of the existing methods is large, it is difficult to meet the real-time requirements of systems. Therefore, new effective methods with acceptable expense should be explored. In this article, following the idea of modifying the source model of evidence, a new method based on DEMATEL is proposed to take the weight of each evidence into consideration. First, the total-relation matrix is determined by the similarity among evidence. Second, prominence and importance are calculated. Finally, the weighted average combination result can be obtained based on Dempster’s rule of combination. Numerical examples are used to demonstrate that the proposed model is efficient to both deals with conflicting evidence and reduce computational complexity.

Abstract: The existing grey wolf optimization algorithm has some disadvantages, such as slow convergence speed, low precision and so on. So this paper proposes a grey wolf optimization algorithm combined with particle swarm optimization (PSO_GWO). In this new algorithm, the Tent chaotic sequence is used to initiate the individuals’ position, which can increase the diversity of the wolf pack. And the nonlinear control parameter is used to balance the global search and local search ability of the algorithm and improve the convergence speed of the algorithm. At the same time, the idea of PSO is introduced, which utilize the best value of the individual and the best value of the wolf pack to update the position information of each grey wolf. This method preserves the best position information of the individual and avoids the algorithm falling into a local optimum. To verify the performance of this algorithm, the proposed method is tested on 18 benchmark functions and compared with some other improved algorithms. The simulation results show that the proposed algorithm can better search global optimal solution and better robustness than other algorithm.

Abstract: Particle swarm optimizer is a well-known efficient population and control parameter-based algorithm for global optimization of different problems. This paper focuses on a new and primary sample for PSO, which is named phasor particle swarm optimization (PPSO) and is based on modeling the particle control parameters with a phase angle (θ), inspired from phasor theory in the mathematics. This phase angle (θ) converts PSO algorithm to a self-adaptive, trigonometric, balanced, and nonparametric meta-heuristic algorithm. The performance of PPSO is tested on real-parameter optimization problems including unimodal and multimodal standard test functions and traditional benchmark functions. The optimization results show good and efficient performance of PPSO algorithm in real-parameter global optimization, especially for high-dimensional optimization problems compared with other improved PSO algorithms taken from the literature. The phasor model can be used to expand different types of PSO and other algorithms. The source codes of the PPSO algorithms are publicly available at https://github.com/ebrahimakbary/PPSO .

Abstract: This paper proposes a hybrid algorithm based on Water Cycle and Moth-Flame Optimization algorithms for solving numerical and constrained engineering optimization problems. The spiral movement of moths in Moth-Flame Optimization algorithm is introduced into the Water Cycle Algorithm to enhance its exploitation ability. In addition, to increase randomization in the new hybrid method, the streams in the Water Cycle Algorithm are allowed to update their position using a random walk (Levy flight). The random walk significantly improves the exploration ability of the Water Cycle Algorithm. The performance of the new hybrid Water Cycle–Moth-Flame Optimization algorithm (WCMFO) is investigated in 23 benchmark functions such as unimodal, multimodal and fixed-dimension multimodal benchmark functions. The results of the WCMFO are compared to the other state-of-the-art metaheuristic algorithms. The results show that the hybrid method is able to outperform the other state-of-the-art metaheuristic algorithms in majority of the benchmark functions. To evaluate the efficiency of the WCMFO in solving complex constrained engineering and real-life problems, three well-known structural engineering problems are solved using WCMFO and the results are compared with the ones of the other metaheuristics in the literature. The results of the simulations revealed that the WCMFO is able to provide very competitive and promising results comparing to the other hybrid and metaheuristic algorithms.

Abstract: In this work, the Synthetic Minority Over-sampling Technique (SMOTE) approach is adapted for high-dimensional binary settings. A novel distance metric is proposed for the computation of the neighborhood for each minority sample, which takes into account only a subset of the available attributes that are relevant for the task. Three variants for the distance metric are explored: Euclidean, Manhattan, and Chebyshev distances, and four different ranking strategies: Fisher Score, Mutual Information, Eigenvector Centrality, and Correlation Score. Our proposal was compared with various oversampling techniques on low- and high-dimensional datasets with the presence of class-imbalance, including a case study on Natural Language Processing (NLP). The proposed oversampling strategy showed superior results on average when compared with SMOTE and other variants, demonstrating the importance of selecting the right attributes when defining the neighborhood in SMOTE-based oversampling methods.

Abstract: The evaluation and precise prediction of safety factor (SF) of slopes can be useful in designing/analyzing these important structures. In this study, an attempt has been made to evaluate/predict SF of many homogenous slopes in static and dynamic conditions through applying various hybrid intelligent systems namely imperialist competitive algorithm (ICA)-artificial neural network (ANN), genetic algorithm (GA)-ANN, particle swarm optimization (PSO)-ANN and artificial bee colony (ABC)-ANN. In fact, ICA, PSO, GA and ABC were used to adjust weights and biases of ANN model. In order to achieve the aim of this study, a database composed of 699 datasets with 5 model inputs including slope gradient, slope height, friction angle of soil, soil cohesion and peak ground acceleration and one output (SF) was established. Several parametric investigations were conducted in order to determine the most effective factors of GA, ICA, ABC and PSO algorithms. The obtained results of hybrid models were check considering two performance indices, i.e., root-mean-square error and coefficient of determination $$(R^{2})$$ . To evaluate capability of all hybrid models, a new system of ranking, i.e., the color intensity rating, was developed. As a result, although all predictive models are able to approximate slope SF values, PSO-ANN predictive model can perform better compared to others. Based on $$R^{2}$$ , values of (0.969, 0.957, 0.980 and 0.920) were found for testing of ICA-ANN, ABC-ANN, PSO-ANN and GA-ANN predictive models, respectively, which show higher efficiency of the PSO-ANN model in predicting slope SF values.

Abstract: The nonlinear regression estimation issues are solved by successful application of a novel neural network technique termed as support vector machines (SVMs). Evaluation of recurrent neural networks (RNNs) can assist in pattern recognition of several real-time applications and reduce the pattern mismatch. This paper provides a robust prediction model for multiple applications. Traditionally, back-propagation algorithms were used for training RNN. This paper predict system reliability by applying SVM learning algorithm to RNN. Comparison of the proposed model is done with the existing systems for analysis of prediction performance. These results indicate that the performance of proposed system exceeds that of the existing ones.

Abstract: Open-shop scheduling problem (OSSP) is a well-known topic with vast industrial applications which belongs to one of the most important issues in the field of engineering. OSSP is a kind of NP problems and has a wider solution space than other basic scheduling problems, i.e., Job-shop and flow-shop scheduling. Due to this fact, this problem has attracted many researchers over the past decades and numerous algorithms have been proposed for that. This paper investigates the effects of crossover and mutation operator selection in Genetic Algorithms (GA) for solving OSSP. The proposed algorithm, which is called EGA_OS, is evaluated and compared with other existing algorithms. Computational results show that selection of genetic operation type has a great influence on the quality of solutions, and the proposed algorithm could generate better solutions compared to other developed algorithms in terms of computational times and objective values.

Abstract: Most of the existing image steganographic approaches embed the secret information imperceptibly into a cover image by slightly modifying its content. However, the modification traces will cause some distortion in the stego-image, especially when embedding color image data that usually contain thousands of bits, which makes successful steganalysis possible. In this paper, we propose a novel coverless steganographic approach without any modification for transmitting secret color image. In our approach, instead of modifying a cover image to generate the stego-image, steganography is realized by using a set of proper partial duplicates of a given secret image as stego-images, which are retrieved from a natural image database. More specifically, after dividing each database image into a number of non-overlapping patches and indexing those images based on the features extracted from these patches, we search for the partial duplicates of the secret image in the database to obtain the stego-images, each of which shares one or several visually similar patches with the secret image. At the receiver end, by using the patches of the stego-images, our approach can approximately recover the secret image. Since the stego-images are natural ones without any modification traces, our approach can resist all of the existing steganalysis tools. Experimental results and analysis prove that our approach not only has strong resistance to steganalysis, but also has desirable security and high hiding capability.

Abstract: Feature selection (FS) can be defined as the problem of finding the minimal number of features from an original set with the minimum information loss. Since FS problems are known as NP-hard problems, it is necessary to investigate a fast and an effective search algorithm to tackle this problem. In this paper, two incremental hill-climbing techniques (QuickReduct and CEBARKCC) are hybridized with the binary ant lion optimizer in a model called HBALO. In the proposed approach, a pool of solutions (ants) is generated randomly and then enhanced by embedding the most informative features in the dataset that are selected by the two filter feature selection models. The resultant population is then used by BALO algorithm to find the best solution. The proposed binary approaches are tested on a set of 18 well-known datasets from UCI repository and compared with the most recent related approaches. The experimental results show the superior performance of the proposed approaches in searching the feature space for optimal feature combinations.

Abstract: The intuitionistic fuzzy set (IFS), as a generation of Zadeh’s fuzzy set, can express and process uncertainty much better. Similarity measures between IFSs are used to indicate the similarity degree between the information carried by IFSs. Although several similarity measures for IFSs have been proposed in previous studies, some of them cannot satisfy the axioms of similarity, or provide counterintuitive cases. In this paper, we first review several widely used similarity measures and then propose a new similarity measures. As the consistency of two IFSs, the proposed similarity measure is defined based on the direct operation on the membership function, non-membership function, hesitation function and the upper bound of membership function of two IFS, rather than based on the distance measure or the relationship of membership and non-membership functions. It proves that the proposed similarity measure satisfies the properties of the axiomatic definition for similarity measures. Comparison between the previous similarity measures and the proposed similarity measure indicates that the proposed similarity measure does not provide any counterintuitive cases. Moreover, it is demonstrated that the proposed similarity measure is capable of discriminating difference between patterns. Experiments on medical diagnosis and cluster analysis are carried out to illustrate the applicability of the proposed similarity measure in practice.

Abstract: In the recent decades, credit scoring has become a very important analytical resource for researchers and financial institutions around the world. It helps to boost both profitability and risk control since bank credits plays a significant role in the banking industry. In this study, a novel approach based on deep genetic cascade ensemble of different support vector machine (SVM) classifiers (called Deep Genetic Cascade Ensembles of Classifiers (DGCEC)) is applied to the Statlog Australian data. The proposed approach is a hybrid model which merges the benefits of: (a) evolutionary computation, (b) ensemble learning, and (c) deep learning. The proposed approach comprises of a novel 16-layer genetic cascade ensemble of classifiers, having: two types of SVM classifiers, normalization techniques, feature extraction methods, three types of kernel functions, parameter optimizations, and stratified 10-fold cross-validation method. The general architecture of the proposed approach consists of ensemble learning, deep learning, layered learning, supervised training, feature (attributes) selection using genetic algorithm, optimization of parameters for all classifiers by using genetic algorithm, and a new genetic layered training technique (for selection of classifiers). Our developed model achieved the highest prediction accuracy of 97.39%. Hence, our proposed approach can be employed in the banking system to evaluate the bank credits of the applicants and aid the bank managers in making correct decisions.

Abstract: Optimal power flow (OPF) is one of the most important tools in power system operation and control, which determines the minimum operating cost and retains the control variables in their secure boundaries. This paper takes into account several unbridled practical constraints in the OPF problem, three of which – that is – valve-point effect, multi-fuel option, and, above all, prohibited operating zone are the most conspicuous ones. Further, the flexible alternating current transmission systems (FACTS) devices are considered, as well, which have several merits such as decreasing the active power transmission loss, controlling the power flow, and improving the voltage stability/profile, to name but a few. Accordingly, thyristor controlled series capacitor (TCSC) – the most popular and common component of the FACTS equipment’s category – is utilized in this study. As a result, the OPF problem integrated with such practical constraints referred to above as well as FACTS devices becomes a highly nonlinear-nonconvex optimization problem and to solve it, a reliable and efficient evolutionary algorithm such as fuzzy-based improved comprehensive-learning particle swarm optimization (FBICLPSO) algorithm is introduced. The proposed approach is scrutinized on IEEE 30-bus test system, which is a commonly used test system for solving the non-smooth and non-convex versions of the OPF problem. Comparing the obtained results by the proposed algorithm with the available alternatives in the literature corroborate the potential and effectiveness of the proposed approach.

Abstract: Multi-criteria decision making (MCDM) has attracted wide interest due to its extensive applications in practice. In our previous study, a method called D-AHP (AHP method extended by D numbers preference relation) was proposed to study the MCDM problems based on a D numbers extended fuzzy preference relation, and a solution for the D-AHP method has been given to obtain the weights and ranking of alternatives from the decision data, in which the results obtained by using the D-AHP method are influenced by the credibility of information. However, in previous study the impact of information’s credibility on the results is not sufficiently investigated, which becomes an unsolved issue in the D-AHP. In this paper, we focus on the credibility of information within the D-AHP method and study its impact on the results of a MCDM problem. Information with different credibilities including high, medium and low, respectively, is taken into consideration. The results show that the credibility of information in the D-AHP method slightly impacts the ranking of alternatives, but the priority weights of alternatives are influenced in a relatively obvious extent.

Abstract: Brain tumor diagnosis is a challenging and difficult process in view of the assortment of conceivable shapes, regions, and image intensities. The pathological detection and identification of brain tumor and comparison among normal and abnormal tissues need grouped scientific techniques for features extraction, displaying, and measurement of the disease images. Our study shows an improved automated brain tumor segmentation and identification approach using ANN from MR images without human mediation by applying the best attributes toward preparatory brain tumor case revelation. To obtain the exact district region of brain tumor from MR images, we propose a brain tumor segmentation technique that has three noteworthy improvement focuses. To begin with, K-means clustering will be utilized as a part of the principal organization in the process of improving the MR image to be marked in the districts regions in light of their gray scale. Second, ANN is utilized to choose the correct object in view of training phase. Third, texture feature of brain tumor area will be extracted to the division stage. With respect to the brain tumor identification, the grayscale features are utilized to analyze and diagnose the brain tumor to differentiate the benign and malignant cases. According to the study results demonstrated that: (1) enhancement adaptive strategy was utilized as post-processing in brain tumor identification; (2) identify and build an assessment foundation of automated segmentation and identification for brain tumor cases; (3) highlight the methods based on region growing method and K-means clustering technique to select the best region; and (4) evaluate the proficiency of the foreseen outcomes by comparing ANN and SVM segmentation outcomes, and brain tumor cases classification. The ANN approach classifier recorded accuracy of 94.07% with line assumption (brain tumor cases classification) and sensitivity of 90.09% and specificity of 96.78%.

Abstract: In this paper, a conscious neighborhood-based crow search algorithm (CCSA) is proposed for solving global optimization and engineering design problems. It is a successful improvement to tackle the imbalance search strategy and premature convergence problems of the crow search algorithm. CCSA introduces three new search strategies called neighborhood-based local search (NLS), non-neighborhood based global search (NGS) and wandering around based search (WAS) in order to improve the movement of crows in different search spaces. Moreover, a neighborhood concept is defined to select the movement strategy between NLS and NGS consciously, which enhances the balance between local and global search. The proposed CCSA is evaluated on several benchmark functions and four applied problems of engineering design. In all experiments, CCSA is compared by other state-of-the-art swarm intelligence algorithms: CSA, BA, CLPSO, GWO, EEGWO, WOA, KH, ABC, GABC, and Best-so-far ABC. The experimental and statistical results show that CCSA is very competitive especially for large-scale optimization problems, and it is significantly superior to the compared algorithms. Furthermore, the proposed algorithm also finds the best optimal solution for the applied problems of engineering design.

Abstract: Multi-criteria decision-making (MCDM) methods are susceptible to the subjectivity of experts when especially they use linguistic terms for assessment. This subjectivity and vagueness in the evaluation process have been handled by the recent extensions of ordinary fuzzy sets such as type-2 fuzzy sets, hesitant fuzzy sets, intuitionistic fuzzy sets, Pythagorean fuzzy sets and neutrosophic sets. Pythagorean fuzzy sets are superior to the other extensions with a more flexible definition of membership function. A novel Pythagorean fuzzy AHP method has been developed for MCDM. The developed method has been applied to a landfill site selection problem for the city of Istanbul in Turkey. The proposed method has successfully evaluated the landfill location alternatives with respect to the considered criteria. The results are compared with ordinary fuzzy AHP, and it is revealed that the proposed method produces consistent and informative outcomes better representing the uncertainty of decision-making environment. Robustness of the decision given by the proposed method is ensured by conducting one-at-a-time sensitivity analysis.

Abstract: Coronary artery disease is a common chronic disease, also known as ischemic heart disease, which is a cardiac dysfunction caused by the insufficient blood supply to the heart and kills countless people every year. In recent years, coronary artery disease ranks first among the world’s top ten causes of death. Cardiac auscultation is still an important examination for diagnosing heart diseases. Many heart diseases can be diagnosed effectively by auscultation. However, cardiac auscultation relies on the subjective experience of physicians. To provide an objective diagnostic means and assist physicians in the diagnosis of heart sounds at a clinic, this study uses phonocardiograms to build an automatic classification model. This study proposes an automatic classification approach for phonocardiograms using deep learning and ensemble learning with a Savitzky–Golay filter. The experimental results showed that the proposed method is very competitive, and showed that the performance of the phonocardiogram classification model in hold out testing was 86.04% MAcc (86.46% sensitivity, 85.63% specificity), and in ten-fold cross validation it was 89.81% MAcc (91.73% sensitivity, 87.91% specificity). These two experimental results are all better than two state-of-art algorithms and show the potential to apply in real clinic situation.

Abstract: In this paper, we propose a method of phishing website detection that utilizes a meta-heuristic-based nonlinear regression algorithm together with a feature selection approach. In order to validate the proposed method, we used a dataset comprised of 11055 phishing and legitimate webpages, and select 20 features to be extracted from the mentioned websites. This research utilizes two feature selection methods: decision tree and wrapper to select the best feature subset, while the latter incurred the detection accuracy rate as high as 96.32%. After the feature selection process, two meta-heuristic algorithms are successfully implemented to predict and detect the fraudulent websites: harmony search (HS) which was deployed based on nonlinear regression technique and support vector machine (SVM). The nonlinear regression approach was used to classify the websites, where the parameters of the proposed regression model were obtained using HS algorithm. The proposed HS algorithm uses dynamic pitch adjustment rate and generated new harmony. The nonlinear regression based on HS led to accuracy rates of 94.13 and 92.80% for train and test processes, respectively. As a result, the study finds that the nonlinear regression-based HS results in better performance compared to SVM.

Abstract: We set out in this study to review a vast amount of recent literature on machine learning (ML) approaches to predicting financial distress (FD), including supervised, unsupervised and hybrid supervised–unsupervised learning algorithms. Four supervised ML models including the traditional support vector machine (SVM), recently developed hybrid associative memory with translation (HACT), hybrid GA-fuzzy clustering and extreme gradient boosting (XGBoost) were compared in prediction performance to the unsupervised classifier deep belief network (DBN) and the hybrid DBN-SVM model, whereby a total of sixteen financial variables were selected from the financial statements of the publicly-listed Taiwanese firms as inputs to the six approaches. Our empirical findings, covering the 2010–2016 sample period, demonstrated that among the four supervised algorithms, the XGBoost provided the most accurate FD prediction. Moreover, the hybrid DBN-SVM model was able to generate more accurate forecasts than the use of either the SVM or the classifier DBN in isolation.

Abstract: Over years, natural calamities like drought have taken a huge toll on human life and resources. As the prediction methods increase, the effects of natural calamities can be reduced to an extent by preplanning and providing warnings to the people. Metrological drought indices like standardized precipitation index and standardized precipitation evapotranspiration index are used to identify drought and its severity level. By forecasting these indices, the occurrences of drought are predicted using the prediction models which help the society to take preventive measures due to the effect of drought. Many research works on prediction majorly focused on statistical methods such as Holt–Winters and ARIMA, but these methods lack accuracy to provide long-term forecasts. However, with advances in the area of machine learning especially artificial neural networks and deep neural networks, there seems to be a method to predict drought in the long term with a good accuracy. Long short-term memory is used in recurrent neural network to predict the drought indices which handle the real-time nonlinear data well and good that can help authorities better prepare and mitigate natural disasters. In this paper, we compare the 1-, 6- and 12-month prediction of the ARIMA statistical model with LSTM using multivariate input in hopes of bettering said performance.

Abstract: Prioritization of watersheds for conservation measures is essential for a variety of functions, such as flood control projects for which determining areas of top priority is a managerial decision that should be based on physical, social, and economic characteristic of the region of interest and the outcome of past operations. The objective of this study therefore was to investigate morphological characteristics and identify critical sub-watersheds which are liable to be damaged, using remote sensing/geographical information systems and multi-criteria decision-making methods AHP/FAHP. Fourteen morphometric parameters were selected to prioritize sub-watersheds using an analytical hierarchical process (AHP) and a fuzzy analytical hierarchical process (FAHP). Based on the FAHP approach, sub-watersheds, as vulnerable zones, were categorized in five priority levels (very high, high, medium, low, and very low levels). The conservation and management measures are essential in the high to very high levels categories. Thus, the FAHP approach is a practical and convenient method to show potential zones in order to implement effective management strategies, especially in areas where data availability is low and soil diversity is high. Finally, without having to encounter high cost and a waste of time, sub-watersheds can be categorized using morphometric parameters for implementing conservational measures to simultaneously conserve soil and the environment.

Abstract: The intermittent feature of renewable energy sources leads to the mismatch between supply and load demand on microgrids. In such circumstance, the system experiences large fluctuations, if the secondary load frequency control (LFC) mechanism is unable to compensate the mismatch. In this issue, this paper presents a well-structured combination of the fuzzy PD and cascade PI-PD controllers named FPD/PI-PD controller as a supplementary (secondary) controller for the secondary load frequency control in the islanded multi-microgrid (MMG). Additionally, two modifications to the JAYA algorithm are made to enhance the diversity of the initial population and ameliorate the global searching ability in the iterative process. Afterward, the improved JAYA algorithm, referred to as IJAYA, is employed for fine-tuning the proposed structured controller installed in areas of the studied MMG. The superiority of the proposed IJAYA is validated by comparative analysis with genetic algorithm and basic JAYA in a similar structure of the PID controller. Furthermore, it will be shown that the proposed FPD/PI-PD controller employing IJAYA provides a higher degree of stability in suppressing the responses deviations as compared with the conventional PID and FPID controller structures. Finally, the novel optimal proposed approach is validated and implemented in the hardware-in-the-loop (HIL) based on OPAL-RT to integrate the fidelity of physical simulation and the flexibility of numerical simulation.