Search

Motivation: Renal biopsy is an irreplaceable diagnostic tool for kidney diseases. Glomeruli provide important information for an accurate disease diagnosis. This paper applies deep learning techniques to automate translation of renal pathology images and glomerulus detection to improve the efficiency and accuracy on pathological diagnoses. Methods: This paper first proposes a new method for automatic translation of different renal pathology staining styles using the cycle-consistent Generative Adversarial Network (GAN). This paper then proposes the combination of faster region-based convolutional neural network (R-CNN) with an aspect ratio filter to detect glomeruli in light microscopy images processed with four different stains at various optical magnifications. Finally, this paper improves glomerulus detection at different stains by using translated image stains from the CycleGAN. Results: To show the effectiveness of the translation and detection methods, in addition to quantitative analysis of the results, the involvement of assessment from four physicians is also performed. Experimental results show that the physicians fail to differentiate real and translated stains and the automatic glomerulus detection method outperforms that manually labeled by the physicians. Conclusion: The proposed method works well and improves the efficiency of renal pathological diagnosis. This work contributes in the area of automated medical diagnosis.

Modular neural network (MNN) has distinct advantage in many fields such as pattern recognition and pattern recognition. However it is still a challenge to dynamically adjust the MNN structure for dynamic nonlinear system modeling. This paper proposes a novel online self-organizing MNN (OSOMNN) for nonlinear system modeling. In OSOMNN, an online task decomposition algorithm and a self-organizing algorithm for subnetwork are introduced. Firstly, the task decomposition algorithm is implemented by the online clustering method based on distance and local density, which can online divide the original task into several simpler subtasks. Then subnetworks with single-layer feedforward neural network are built to learn the divided subtasks. Moreover, this paper develops a self-organizing algorithm for subnetwork, which can dynamically adjust its structure and is trained by the improved online gradient method with fixed memory mechanism (FMOGM). To demonstrate the effectiveness of OSOMNN for nonlinear system modeling, experimental investigations using four benchmark nonlinear systems and the monthly sunspots time series show that OSOMNN can automatically add or merge the subnetwork modules and optimize the structure of subnetworks for nonlinear system modeling with a better generalization performance than the established alternatives.

Due to the capacity of data representation, non-negative matrix factorization has been investigated widely by introducing a variety of constraints. The general processing of non-negative matrix factorization for image clustering consists of two steps: (i) achieving the r -dimensional non-negative image representations, where the rank r is set to the expected number of clusters; (ii) adopting the traditional clustering techniques to accomplish the clustering task. Nevertheless, the previous non-negative matrix factorization variants derive image representations from the original space which cannot handle the nonlinear structure of images. This paper focuses on the existing issues and proposes an elastic net regularized kernel non-negative matrix factorization algorithm for clustering guided image representation. In order to explore the nonlinear relations of images, this paper uses the kernel trick to extend original non-negative matrix factorization. A self-organized graph and elastic net regularization are incorporated into the proposed objective of kernel non-negative matrix factorization, besides, the rank is allowed to be larger than the expected number of clusters. By doing so, the graph defined in the feature space is more qualified to represent the intrinsic structure of images. As an accompanying advantage, the clusters of images can be determined using the graph directly without using the two-step trick. According to the proposed alternating update algorithm for solving the optimization problem, the image representation and clustering result can be obtained simultaneously. Extensive experiments on challenging data sets demonstrate the effectiveness of the proposed algorithm compared with the prominent non-negative matrix factorization variants for image clustering.

Due to the global financial crisis occurred in 2008, with a large amount of companies troubling in financial distress, the machine learning-based prediction of this dilemma has shown economic stakeholders’ great practicability. In the field of machine learning, most of the previous studies only focus on the improvement of the imbalanced datasets sampling methods or the introduction of multiple classifiers in the constructing stage for prediction model. In view of this, this paper attempts to improve the scope and depth of ensemble to achieve better prediction performance for a severely imbalanced dataset of financial data of Chinese listed companies. For the first time, this paper combines the clustering-based under-sampling (CUS) with the gradient boosting decision tree (GBDT) to construct the model, which is used along with the current widely used extreme gradient boosting (XGBoost) as heterogeneous classifier to build heterogeneous ensemble in financial distress prediction. In addition, based on the idea of ensemble, this paper uses five feature selection methods based on different theoretical backgrounds to select features, and introduces ensemble from the whole process of feature selection, data preprocessing and model construction. In the comparative experience, the method proposed by us achieves the best performance on the test set. This study demonstrates the broad application of CUS for financial data processing and the superior generalization performance of the ensemble model relative to individual learners.

COVID-19 is a buzz word nowadays. The deadly virus that started in China has spread worldwide. The fundamental principle is “if the disease can travel faster information has to travel even faster”. The sequence of events reveals the upheaval need to strengthen the ability of the early warning system, risk reduction, and management of national and global risks. Digital contact tracing apps like Aarogya setu (India) and Pan-European privacy preserving proximity tracing (German) has somehow helped but they are more effective in the initial stage and less relevant in the community spread phase. Thus, there is a need to devise a Decision Support System (DSS) based on machine learning algorithms. In this paper, we have attempted to propose an Additive Utility Assumption Approach for Criterion Comparison in Multi-criterion Intelligent Decision Support system for COVID-19. The dataset of Covid-19 has been taken from government link for validating the results. In this paper, an additive utility assumption-based approach for multi-criterion decision support system (MCDSS) with an accurate prediction of identified risk factors on certain well-defined input parameters is proposed and validated empirically using the standard SEIR model approach (Susceptible, Exposed, Infected and Recovered). The results includes comparative analysis in tabular form with already existing approaches to illustrate the potential of the proposed approach including the parameters such as Precision, Recall and F-Score. Other advanced parameters such as, MCC (Matthews Correlation Coefficient), ROC (Receiver Operating Characteristics) and PRC (Precision Recall) have also been considered for validation and the graphs are illustrated using Jupyter notebook. The statistical analysis of the most affected top eight states of India is undertaken effectively using the Weka software tool and IBM Cognos software to correctly predict the outbreak of pandemic situation due to Covid-19. Finally, the article has immense potential to contribute to the COVID-19 situation and may prove to be instrumental in propelling the research interest of researchers and providing some useful insights for the current pandemic situation., Graphical abstract, Highlights • Proposing a Multi-criterion Intelligent DSS • Epidemiology modeling of data using a SEIFR Model • Our approach applies data to get trained using multiple parameters to handle and serve significant challenges existing especially in healthcare.

Due to the flexibility of Genetic Programming (GP), GP has been used for feature construction, feature selection and classifier construction. In this paper, GP classifiers with feature selection and feature construction are investigated to obtain simple and effective classification rules. During the construction of a GP classifier, irrelevant and redundant features affect the search ability of GP, and make GP easily fall into local optimum. This paper proposes two new GP classifier construction methods to restrict bad impact of irrelevant and redundant features on GP classifier. The first is to use a multiple-objective fitness function that decreases both classification error rate and the number of selected features, which is named as GPMO. The second is to first use a feature selection method, i.e., linear forward selection (LFS) to remove irrelevant and redundant features and then use GPMO to construct classifiers, which is named as FSGPMO. Experiments on twelve datasets show that GPMO and FSGPMO have advantages over GP classifiers with a single-objective fitness function named GPSO in term of classification performance, the number of selected features, time cost and function complexity. The proposed FSGPMO can achieve better classification performance than GPMO on higher dimension datasets, however, FSGPMO may remove potential effective features for GP classifier and achieve much lower classification performance than GPMO on some datasets. Compared with two other GP-based classifiers, GPMO can significantly improve the classification performance. Comparisons with other classification algorithms show that GPMO can achieve better or comparable classification performance on most selected datasets. Our proposed GPMO can achieve better performance than wrapper-based feature construction methods using GP on applications with insufficient instances. Further investigations show that bloat phenomena exists in the process of GP evolution and overfitting phenomena is not obvious. Moreover, the benefits of GP over other machine learning algorithms are discussed.

Image segmentation is an essential part of image analysis, which has a direct impact on the quality of image analysis results. Thresholding is one of the simplest and widely used methods for image segmentation. Thresholding can be either bi-level, which involves partitioning of an image into two segments, or multilevel, which partitions an image into multiple segments using multiple thresholds values. This paper focuses on multilevel thresholding. A good segmentation scheme through multilevel thresholding identifies suitable threshold values to optimize between-class variance or entropy criterion. For such optimizations, nature inspired metaheuristic algorithms are commonly used. This paper presents a Kapur’s entropy based Crow Search Algorithm (CSA) to estimate optimal values of multilevel thresholds. Crow Search Algorithm is based on the intelligent behavior of crow flock. Crow Search Algorithm have shown better results because of less number of parameters, no premature convergence, and better exploration–exploitation balance in the search strategy. Kapur’s entropy is used as an objective function during the optimization process. The experiments have been performed on benchmarked images for different threshold values (i.e. 2, 4, 8, 16, 32 thresholds). The proposed method has been assessed and performance is compared with well-known metaheuristic optimization methods like Particle Swarm Optimization (PSO), Differential Evolution (DE), Grey Wolf Optimizer (GWO), Moth-Flame Optimization (MFO) and Cuckoo Search (CS). Experimental results have been evaluated qualitatively and quantitatively by using well-performed evaluation methods namely PSNR, SSIM, and FSIM. Computational time and Wilcoxon p-type value also compared. Experimental results show that proposed algorithm performed better than PSO, DE, GWO, MFO and CS in terms of quality and consistency.

International audience; Benchmarking of optimization solvers is an important and compulsory task for performance assessment that in turn can help in improving the design of algorithms. It is a repetitive and tedious task. Yet, this task has been greatly automatized in the past ten years with the development of the Comparing Continuous Optimizers platform (COCO). In this context, this paper presents a new testbed, called bbob-largescale, that contains functions ranging from dimension 20 to 640, compatible with and extending the well-known single-objective noiseless bbob test suite to larger dimensions. The test suite contains 24 single-objective functions in continuous domain, built to model well-known difficulties in continuous optimization and to test the scaling behavior of algorithms. To reduce the computational demand of the orthogonal search space transformations that appear in the bbob test suite, while retaining some desired properties, we use permuted block diagonal orthogonal matrices. The paper discusses implementation technicalities and presents a guide for using the test suite within the COCO platform and for interpreting the postprocessed output. The source code of the new test suite is available on GitHub as part of the open source COCO benchmarking platform.

As a branch of machine learning, deep learning has been used for tackling with the music auto-tagging problem. Deep learning methods, especially those with convolutional neural network (CNN) architecture, have exhibited good performance on this multi-label classification task. However, the feature extracting part and preprocessing part of this architecture need to be improved. In this paper, we propose a deep-learning model based on CNN with scattering transform and self-attention mechanism for music automatic tagging. To get a balance between information integrity and feature extraction in the preprocessing phase, we employ the scattering transform. Then, a multi-layer CNN is used to extract higher-level features from the scattering coefficients. In order to select better receptive fields of the CNN, self-attention sub-network is appended at the last layer of CNN. Experimental results on the MagnaTagATune dataset and Million Song Dataset (MSD) show the proposed model is a good choice for music auto-tagging task, since the scores of the area under the receiver operating characteristic curve (ROC-AUC) and the area under the precision–recall curve (PR-AUC) obtained in this paper surpass the state-of-the-art models. Furthermore, we visualize the distributions of attention weights, activations of the CNN and ROC-AUC scores on each tag for better understanding of the model.

Robots for rescue operations after a disaster are an interesting and challenging research problem that has the potential to save lives and reduce economic losses after a disaster. We developed TOPTWR, an extension of the popular TOPTW model, to model the issues in task allocation for teams of rescue robots. Our hybrid algorithm is based on a team of heterogeneous humanoid robots trying to optimize five objectives (task rewards, task completion time, total energy, maximum energy consumption for a single robot, and missed deadline penalties). A common approach to solve these kinds of problems are multi-objective evolutionary algorithms (MOEAs), but their major disadvantage is that they cannot deal with dynamic environments easily. This paper presents an efficient solution for TOPTWR by combining MOEAs with learning algorithms. A novel Extended Multi-Start Simulated Annealing Iterated Local Search (EMSAILS) operator using a modern state-of-the-art NSGA-III algorithm is proposed. In addition, we applied Q-Learning to learn the likely changes in the environment and how to react to them. This algorithm, HMO-TOPTWR-NSGA-III (HMO-N-L), uses an artificial neural network (ANN) as a function approximator to make the huge state and action spaces tractable. This paper includes a thorough empirical evaluation demonstrating the effectiveness of the multi-objective algorithm in both static and dynamic environments. The evaluation shows that the proposed algorithm reduces the error by up to 42% against three state-of-the-art approaches to TOPTW (HMO-N, MSA, and IPI).

Fuzzy inference systems (FISs) are a predictive modeling technique based on fuzzy sets that utilize approximate reasoning to mimic the decision-making process of human experts. There are several expert- and data-driven methods for developing FISs, among which fuzzy clustering algorithms are the most frequently used data-driven methods. This paper introduces a new fuzzy clustering algorithm for developing FISs in construction applications that addresses two limitations of existing fuzzy clustering algorithms: the lack of capacity to determine the number of clusters automatically from the characteristics of the data, and the poor performance in predictive modeling of highly dimensional problems. Existing fuzzy clustering algorithms are limited in construction applications since determining the number of clusters based on subjective expert judgment reduces the accuracy of the resulting FIS, and construction systems are often highly dimensional with a large number of inputs affecting the system outputs. The fuzzy clustering algorithm proposed in this paper determines the number of clusters automatically based on the characteristics of the data, specifically the non-linearity observed within clusters, and assigns weights to the rules of FISs to improve their accuracy in highly dimensional problems. This paper advances the state-of-the-art of fuzzy clustering and contributes to construction modeling by providing a new data-driven technique for developing FISs that suits the characteristics of construction problems.

Combinative Distance based ASsesment (CODAS) method aims to perform multi-criteria selection process according to the largest Euclidean and Taxicab distance with respect to negative ideal solutions. Recently, several CODAS methods have been applied to multi-criteria decision making problems with interval valued intuitionistic fuzzy sets. This paper demonstrates the weaknesses of using Euclidean and Taxicab distance on interval valued intuitionistic fuzzy sets and provides alternative strategies to model the vagueness and uncertainty in decision maker evaluations more effectively. The contribution of this paper is twofold. First, a new selection metric is defined in order to eliminate the disadvantages of using Euclidean and Taxicab distance in interval valued intuitionistic fuzzy CODAS. Second, a new fuzzy aggregation operator is proposed for aggregating decision maker evaluations by using fuzzy weights rather than using crisp weights. To show the effectiveness of the modified CODAS method, an application is given for multi-criteria selection of renewable energy alternatives in Turkey and the results are compared with two other interval valued intuitionistic fuzzy CODAS methods in the literature.

The Dynamic Time Warping (DTW) technique is widely used in time series data mining. However, it should be pointed out that the calculation complexity of DTW is very high. In this paper, we propose an accurate and fast DTW calculation algorithm on weak sparse time series (WSTS). The algorithm takes the advantage of the weak sparse property, and it shows a remarkable time saving in DTW calculation. In addition, it should be emphasized that this algorithm for DTW calculation is an accurate one, which is one of the main contributions of this paper. The mathematical proof is also given to prove the accuracy of this algorithm. Several examples with different practical prospects are given to show the effectiveness of the proposed accurate and fast DTW calculation algorithm.

With the advancements of Information and Communication Technologies (ICT), large scale distributed computing and massive data center infrastructures are becoming more common these days. Such trends have drastically put a lot of load on the volumes of data transferred over networks, thus necessitating close to capacity link utilizations flexible forwarding decision-making. Software-defined networking (SDN), with its inherent segregation of control and data planes, provides flexible decision making that can leverage the global network information available to the SDN controller for dynamic and accurate solutions. However, contemporary researchers have focused on the flexibility and security aspects of SDN, widely ignoring energy consumption strategies in next-generation IP networks, which otherwise is a crucial driver in any research field. The scanty existing energy minimization strategies are mostly based on aggregate traffic, which leads to imbalanced utilization of links and affects the quality of service (QoS) adversely. In this paper, we leverage SDN’s key benefits for reducing energy network consumption while realizing dynamic load balance with a few QoS constraints. To this end, a multiobjective optimization problem (MOOP) is formulated that attempts to minimize power consumption and link utilization. With different capacities of switches and links, finding optimal configurations and deciding best paths, even for relatively small networks, become computationally challenging and is, in fact, an NP-hard problem. In this paper, we propose to employ the Clonal Selection Algorithm (CSA), a discrete, metaheuristic solution to find out optimal solutions for this MOOP, namely a Clonal Selection based Energy Minimization (CSEM). Simulations have been carried out for testing the efficacy of the proposed CSEM using real-life network topologies and link-traffic data. The results obtained by the proposed CSEM prove to be efficacious, and the same have also been validated with three different benchmark functions to test the suitability of SDN for CSA.

COVID-19 infection was reported in December 2019 at Wuhan, China. This virus critically affects several countries such as the USA, Brazil, India and Italy. Numerous research units are working at their higher level of effort to develop novel methods to prevent and control this pandemic scenario. The main objective of this paper is to propose a medical decision support system using the implementation of a convolutional neural network (CNN). This CNN has been developed using EfficientNet architecture. To the best of the authors’ knowledge, there is no similar study that proposes an automated method for COVID-19 diagnosis using EfficientNet. Therefore, the main contribution is to present the results of a CNN developed using EfficientNet and 10-fold stratified cross-validation. This paper presents two main experiments. First, the binary classification results using images from COVID-19 patients and normal patients are shown. Second, the multi-class results using images from COVID-19, pneumonia and normal patients are discussed. The results show average accuracy values for binary and multi-class of 99.62% and 96.70%, respectively. On the one hand, the proposed CNN model using EfficientNet presents an average recall value of 99.63% and 96.69% concerning binary and multi-class, respectively. On the other hand, 99.64% is the average precision value reported by binary classification, and 97.54% is presented in multi-class. Finally, the average F1-score for multi-class is 97.11%, and 99.62% is presented for binary classification. In conclusion, the proposed architecture can provide an automated medical diagnostics system to support healthcare specialists for enhanced decision making during this pandemic scenario., Highlights • An automated system to support the diagnosis of COVID-19 patients using EfficientNet. • The proposed method has been validated using 10-fold cross-validation. • An external dataset also has been used for validation. • An accuracy of 99.62% and 96.70% is reported for binary and multi-class classification.

This study presents a novel probabilistic algorithm for the optimal placement of underground power cables to maximize lifetime and ampacity and minimize total cost of the cable system at the same time. In this paper, the Imperialist Competition Algorithm (ICA) and Monte Carlo (MC) simulation are used to solve probabilistic optimization problem. In our previous study, we have just considered probabilistic parameters that are effective on ampacity. However, In fact, we need to consider all the other parameters such as cable’s lifetime and harmonic of demand side for co-optimizing the ampacity and lifetime to obtain the best arrangement of cable system. The cost function of optimization has been improved relative to the last one. Cable lifetime and harmonic of power system, as two important design factors, have been added to cost function in this paper. The novelty of this paper is consisted of economic co-optimization of ampacity and lifetime simultaneously. Furthermore, all statistical variations of cable system parameters, ambient temperature, dimensions of native/backfill soil and uncertainty in demand side such as load current fluctuation and harmonic are considered as design parameters at the same time. Since, all design parameters are stochastic; the change of seasons and climate can modify these parameters along the cable system. Hence, this paper indicates the necessity of consideration of uncertainty parameters at the design phase by taking into account cable lifetime based on a probabilistic approach and avoid using deterministic value. For a better explanation of this method, a numerical example is reported by using corrugated aluminum sheath cable model.

This paper attends to solve the multi-linear equations with special structure, e.g., the multi-linear M -tensor equation, which frequently appears in engineering applications such as deep learning and hypergraph. For its critical and promising role, there are numbers of resolving schemes devoting to obtain a high-performing solution of the multi-linear M -tensor equation. However, few investigations are discovered with noise-suppression ability till now. To be proper with digital devices and further improve the solving effectiveness, it is desirable to design a discrete-time computational algorithm with noise-suppression ability and high-performing property. Inspired by the aforementioned requirements, this paper proposes a modified Newton integration (MNI) neural algorithm for solving the multi-linear M -tensor equation with noise-suppression ability. Additionally, the corresponding robustness analyses on the proposed MNI neural algorithm are provided. Simultaneously, computer simulative experiments are generated to explain the capabilities and availabilities of the MNI neural algorithm in noise suppression. As a result, in terms of noise suppression, the proposed MNI neural algorithm is superior to other related algorithms, such as Newton–Raphson iterative (NRI) algorithm (Ding and Wei, 2016), discrete time neural network (DTNN) algorithm (Wang et al., 2019), and sufficient descent nonlinear conjugate gradient (SDNCG) algorithm (Liu et al., 2020).

Automatically designing new dispatching rules (DRs) by genetic programming has become an increasingly researched topic. Such an approach enables that DRs can be designed efficiently for various scheduling problems. Furthermore, most automatically designed DRs outperform existing manually designed DRs. Most research focused solely on designing priority functions that were used to determine the order in which jobs should be scheduled. However, in some scheduling environments, besides only determining the order of the jobs, one has to additionally determine the allocation of jobs to machines. For that purpose, a schedule generation scheme (SGS), which constructs the schedule, has to be applied. Until now the influence of different choices in the design of the SGS has not been extensively researched, which could lead to the application of an SGS that would obtain inferior results. The main goal of this paper is to perform an analysis of different SGS variants. For that purpose, three SGS variants are tested, two of which are proposed in this paper. They are tested in several variations which differ in details like whether they insert idle times in the schedule, or if they select the job with the highest or lowest priority values. The obtained results demonstrate that the automatically designed DRs with the tested SGS variants perform better than manually designed DRs, but also that there is a significant difference in the performance between the different SGS types and variants. The best DRs are analysed and show that the main reason why they performed well was due to the more sophisticated decisions they made when selecting the appropriate machine for a job. The results suggest that it is best to apply SGS variants which use the evolved priority functions to choose both the next job and the appropriate machine for that job.

The paper relates to decisions made by traders on the Forex market. Existing trading systems based on technical analysis use crisp relations–binary activation functions to generate BUY or SELL signals for the trader. A large number of signals generated independently by different indicators and relatively low accuracy of the signals is observed, so that they cannot be effectively used in decision-making processes. A new fuzzy multicriteria approach is proposed in this paper. It includes the application of the theory of fuzzy systems and multicriteria analysis. The crisp relations are replaced by fuzzy ones. The signals generated by different indicators at the same time are analyzed in a multicriteria space. Each criterion relates to different indicator with the value defined by a respective membership function. A multicriteria optimization problem is formulated in which the currency pairs — variants in the analysis, having maximum values of all criteria are looked for. An original dominance-based algorithm is presented. It calculates a selected set of non-dominated variants that can be presented to the trader. A computer-based system is constructed on the basis of the proposed approach and including the proposed algorithm. The system having data from the market derives selected variants for further analysis and also check their prediction accuracy. Numerical experiments on real data from the Forex market show advantages of the proposed approach in comparison to the existing traditional crisp systems.

Feature selection plays a crucial role in classification problems, which tries to remove redundant or irrelevant features by mapping high-dimensional data to low-dimensional ones. Thus, this approach can improve the classification accuracy and reduce the computational cost to train the classification model. In this paper, we suggest an improved multi-objective immune algorithm (MOIA) for feature selection in intrusion detection. Specifically, the feature subsets for intrusion detection are treated as the individuals for immune optimization, which will select suitable feature subsets in order to reduce the dimensions of the dataset. After that, a neural network is used to train the classification model using the selected suitable feature subsets, and the output of the classification model is regarded as the target fitness value for each individual. As multiple attack types are considered in this paper, a traditional MOIA is modified by using an elite selection strategy based on the reference vectors, which can maintain the individuals with more promising performance when distinguishing more than five attack types in intrusion detection. By this way, the proposed algorithm can accelerate the convergence speed of classification, which also improves the classification accuracy. Experimental results on the NSL-KDD and UNSW-NB15 datasets validate the higher classification accuracy of the proposed algorithm.

In China, online banking and third-party online payment systems have a special relationship in which cooperation and competition co-exist. Quantifying the degree of competition and collaboration between them and predicting their future development trends will help to achieve a win-win situation. This paper uses the Lotka–Volterra model to quantitatively analyse and predict the impact of commercial banks’ online payment systems on the development of third-party online payment systems. The predator is an online bank, and the prey is a third online payment system. In the modelling process, the continuous model is discretized by using the grey theory. To improve modelling accuracy, a background coefficient is introduced. The parameters of the model are estimated by the least-squares method, and the Grey–Lotka–Volterra model for fitting the relationship between third-party payment and bank competition and cooperation is obtained. This paper empirically analyses quarterly transaction volume data for online banking and third payment. The results show that before 2011, the relationship between the two is more inhibition than cooperation, and the inhibition of online banking on third-party payment transactions is more significant than the third payment reaction. Only by strengthening cooperation can they win-win; the growth rate of third-party online payment transactions is more durable than that of online banking, but the market share is lower than that of banks; after 2011, the inhibition of third-party payment by banks is more significant than that of online banking. Compared with the period before 2011, this use decreased from inhibition to cooperation, and the growth of the overall turnover of the two plays a role in improving their development.

Clustering is a common data mining technique whose main principle states that the samples within a cluster are similar to one another and dissimilar to those in other clusters. This means that samples in the same cluster possess high homogeneity, while different clusters possess high heterogeneity. However, a user may require a result of diversified clustering. Compared to traditional clustering methods, the aim of diversified clustering is to make samples of the same cluster possess high heterogeneity, and different clusters possess high homogeneity. Diversified clustering can be practically applied to aspects of our daily lives such as normal class grouping, student grouping in learning, cluster sampling, balanced diets and assignment of jobs. Nevertheless, our survey of related papers in the research field of data mining found that there has been no proposed research for diversified clustering. In this paper, we formal define the problem of diversified clustering and propose a new method to solve this problem. Experimental results showed that our method can generate good diversified clustering. However, our method is currently only appropriate for small data sets since the execution time of our method increases quickly as the number of diversified clusters increases. We also hope this paper will garner interest in more research on effective methods to generate diversified clusters for use in data mining.

Due to the frequent and violent fluctuation of energy futures prices, the investment risk of energy investors is increased. Forecasting energy futures prices has progressively become the focus of research. However, traditional prediction model only conducts forecasting based on historical data without considering the behavior of the market, resulting in poor accuracy. In this paper, the random time effective function that considers the timeliness of historical data and the random change of market environment is applied to the long short term memory model to establish a novel prediction model, which is denoted by long short term memory with random time effective function model (LSTMRT). LSTM model has the characteristics of selective memory and the internal influence of time series, which is very suitable for the prediction of price time series. Random time effective function can give different weights to historical data. Furthermore, using multiscale cross-sample entropy (MCSE) as an innovative method to reveal the performance of prediction. Finally, comparing with other models selected in this paper, error evaluations and statistical comparisons are utilized to demonstrate the advantages and superiority of the proposed model. LSTMRT model has the effect of random movement and keeps the trend fluctuation of the original nonlinear data, which makes the prediction more accurate and more credible.

Because of the lag in sinter composition detection, fluctuations in production conditions are not conducive to making timely adjustments to sintering. In this paper, the characteristics of sintering production data are studied, and three core conclusions are drawn. We find that these data have (1) noise, (2) high dimensionality, and (3) time correlation. Based on these findings, an integrated model based on a deep neural network (DNN) and a long short-term memory (LSTM) network is proposed; using a DNN and an LSTM network solves the problem of developing a system model according to the given input and output data to predict the chemical composition of sinter. Specifically, first, we use a box plot and an isolated forest (iForest) algorithm to detect and filter noise in the data preparation stage and then propose using key feature selection and the Pearson correlation coefficient to reduce the high dimensionality of the data. Then, both an online component monitoring model based on a DNN and an advance component prediction model based on an LSTM are proposed to help the field operators to control the change of the sinter composition in real time. The results of many experiments show that the proposed method performs better than the current methods: the goodness of fit (R2) score of the better model is above 0.92, and both the mean square error (MSE) and mean absolute error (MAE) are approximately zero. The deep neural network-based method proposed in this paper is more suitable for the online monitoring and advance prediction of sinter components.

Based on the analysis of multi-objective flexible job-shop scheduling problem (FJSP), a multi-objective low-carbon job-shop scheduling problem(MLFJSP) with variable processing speed constraint is proposed in this paper. The optimization objectives of MLFJSP include minimizing the makespan, total carbon emission and machine loading. Meanwhile, an improved artificial bee colony algorithm (IABC) is designed to solve the MLFJSP. The improvement of algorithm mainly includes: (1) an effective three-dimensions encoding/decoding mechanism and a mixed initialization strategy are designed to generate a better initial population; (2) special crossover operators and mutation operators were designed to increase the diversity of the population in the employed bee phase; (3)an efficient dynamic neighbor search (DNS) is applied to enhance local search capabilities in the onlooker bee phase; (4) the new food sources generation strategy was proposed to reduce the blindness in the scout bee phase. Finally, this paper carried out a series of comparative experimental studies, including the comparison before and after algorithm improvement, and the comparison between the improved algorithm with MOPSO, MODE and NSGA-II. The results demonstrate that the IABC can achieve a better performance for solving the MLFJSP.

Graphical abstractDisplay Omitted In this paper we present a new traffic sign detection and recognition (TSDR) method, which is achieved in three main steps. The first step segments the image based on thresholding of HSI color space components. The second step detects traffic signs by processing the blobs extracted by the first step. The last one performs the recognition of the detected traffic signs. The main contributions of the paper are as follows. First, we propose, in the second step, to use invariant geometric moments to classify shapes instead of machine learning algorithms. Second, inspired by the existing features, new ones have been proposed for the recognition. The histogram of oriented gradients (HOG) features has been extended to the HSI color space and combined with the local self-similarity (LSS) features to get the descriptor we use in our algorithm. As a classifier, random forest and support vector machine (SVM) classifiers have been tested together with the new descriptor. The proposed method has been tested on both the German Traffic Sign Detection and Recognition Benchmark and the Swedish Traffic Signs Data sets. The results obtained are satisfactory when compared to the state-of-the-art methods.

Graphical abstractDisplay Omitted HighlightsThis paper presents an automatic system based on biomarker for assessing water quality.The proposed system utilized case-based reasoning for indicating the degree of water quality.Water quality is classified based on the histopathological changes in fish gills and liver.Performance evaluation metrics are retrieval accuracy, receiver operating receiver (ROC) curves, F-measure, and G-mean.That proposed CBR based system has obtained water quality classification accuracy of 97.9%. Water pollution by organic materials or metals is one of the problems that threaten humanity, both nowadays and over the next decades. Morphological changes in Nile Tilapia "Oreochromis niloticus" fish liver and gills can also represent the adaptation strategies to maintain some physiological functions or to assess acute and chronic exposure to chemicals found in water and sediments. This paper presents an automatic system for assessing water quality, in Sharkia Governorate - Egypt, based on microscopic images of fish gills and liver. The proposed system used fish gills and liver as hybrid-biomarker in order to detect water pollution. It utilized case-based reasoning (CBR) for indicating the degree of water quality based on the different histopathological changes in fish gills and liver microscopic images. Various performance evaluation metrics namely, retrieval accuracy, receiver operating characteristic (ROC) curves, F-measure, and G-mean have been used in order to objectively indicate the true performance of the system considering the unbalanced data. Experimental results showed that the proposed hybrid-biomarker CBR based system achieved water quality prediction accuracy of 97.9% using cosine distance similarity measure. Also, it outperformed both SVMs and LDA classifiers for the tested microscopic images dataset.

Graphical abstractDisplay Omitted This paper presents a novel approach for multiclass classification by fusion of KAZE and Scale Invariant Feature Transform (SIFT) features followed by Minimal Complexity Machine (MCM) as the classifier. Unlike the existing features, the paper proposes a new feature SIKA to represent characteristics of an object, as opposed to just forming a compendium of interest points in an image to represent the object characteristics. Further we append a strong and lightweight classifier, MCM to the technique. The resulting classifier easily outperforms existing techniques based on handcrafted features. Two new scores Keypoint Overlap Score (KOS) and Mean Keypoint Overlap Score (MKOS) have also been proposed as part of this work which are useful in establishing the strength of features for object representation.

Display Omitted A review of VIKOR and its fuzzy extensions on applications is presented.The systematic classification covers 13 different application areas.It provides an insight for researchers and practitioners on VIKOR applications. Multi criteria decision making (MCDM) is one of the research areas of operations research and management science which has widely studied by researchers and practitioners. It finds a compromise solution for evaluating and ranking alternatives from the best to the worst under conflicting criteria with respect to decision maker(s) preferences. In a compromise approach, the VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR; that means multi-criteria optimization and compromise solution) continues to be applied satisfactorily across different application areas. This paper conducts a state-of-the-art literature review to categorize, analyze and interpret the current research on VIKOR applications. It also discusses the extensions of VIKOR applied in fuzzy environments. A total of 343 papers are classified into 13 different application areas and a number of sub-application areas. Furthermore, all papers are also categorized with respect to publication year, published journal, country of origin, application type (real case study vs empirical study), and version of fuzzy sets used. This comprehensive literature review provides an insight for researchers and practitioners on VIKOR applications in terms of showing current state and potential areas for future attempts to be focused in the future.

Graphical abstractDisplay Omitted The multi-level thresholding is a popular method for image segmentation. However, the method is computationally expensive and suffers from premature convergence when level increases. To solve the two problems, this paper presents an advanced version of gravitational search algorithm (GSA), namely hybrid algorithm of GSA with genetic algorithm (GA) (GSA-GA) for multi-level thresholding. In GSA-GA, when premature convergence occurred, the roulette selection and discrete mutation operators of GA are introduced to diversify the population and escape from premature convergence. The introduction of these operators therefore promotes GSA-GA to perform faster and more accurate multi-level image thresholding. In this paper, two common criteria (1) entropy and (2) between-class variance were utilized as fitness functions. Experiments have been performed on six test images using various numbers of thresholds. The experimental results were compared with standard GSA and three state-of-art GSA variants. Comparison results showed that the GSA-GA produced superior or comparative segmentation accuracy in both entropy and between-class variance criteria. Moreover, the statistical significance test demonstrated that GSA-GA significantly reduce the computational complexity for all of the tested images.

Display Omitted In this paper a novel bipolar framework is proposed for improving efficiency in Cloud's resource provisioning.The proposed bipolar framework enables the cloud provider to provide resources for clients' requests proactively based on demands rather than conventional workload based predictive resource allocation.Artificial neural networks are employed to provide anticipation for demand. Cloud's profitability is mainly driven by the business, and on the other hand, a successful business is hardly geared with clients' satisfaction. Therefore, there is high competition between cloud providers for satisfying clients and attracting more of them. In this way, long term business success factors should also be considered in addition to short term profit factors regarded in conventional resource provisioning procedures. Conventional resource management approaches to achieve short term profit inevitably lead to job rejection and violation from response time based SLAs while short response time and low job rejection are of those important factors to clients' satisfaction. Therefore, this paper proposes a novel bipolar resource management framework which results in preventing from job rejection and having considerably reduced violations from response time based SLAs as well as providing short term profits. The proposed framework uses a neural network based predictor and genetic algorithm for optimal resource management through live migration. It also employs a prediction based temporal infinite pool, called the temporal cloud, which regards job rejection prevention. The evaluation of the proposed framework demonstrates that it can provide short term profits, beside it prevents from job rejection and reduces response time violations considerably.

Graphical abstractThe effects of origin bias on the Teaching-Learning-Based-Optimization algorithm. Display Omitted HighlightsA geometric interpretation is applied to explain population convergence.A property of TLBO introduces an origin bias in the Teacher Phase.A converged population will continue searching in the direction of the origin for better solutions.The origin bias is directly tied to convergence.A faster rate of convergence yields a higher success rate for problematic functions. Teaching-Learning-Based-Optimization (TLBO) is a population-based Evolutionary Algorithm which uses an analogy of the influence of a teacher on the output of learners in a class. TLBO has been reported to obtain very good results for many constrained and unconstrained benchmark functions and engineering problems. The choice for TLBO by many researchers is partially based on the study of TLBO's performance on standard benchmark functions. In this paper, we explore the performance on several of these benchmark functions, which reveals an inherent origin bias within the Teacher Phase of TLBO. This previously unexplored origin bias allows the TLBO algorithm to more easily solve benchmark functions with higher success rates when the objective function has its optimal solution as the origin. The performance on such problems must be studied to understand the performance effects of the origin bias. A geometric interpretation is applied to the Teaching and Learning Phases of TLBO. From this interpretation, the spatial convergence of the population is described, where it is shown that the origin bias is directly tied to spatial convergence of the population. The origin bias is then explored by examining the performance effect due to: the origin location within the objective function, and the rate of convergence. It is concluded that, although the algorithm is successful in many engineering problems, TLBO does indeed have an origin bias affecting the population convergence and success rates of objective functions with origin solutions. This paper aims to inform researchers using TLBO of the performance effects of the origin bias and the importance of discussing its effects when evaluating TLBO.

Membrane algorithmDisplay Omitted This paper proposes a new membrane algorithm based on rules of PSO defined within the framework of cell-like P-systems to solve Sudoku.A novel way is introduced to define the search space for solving the problem of Sudoku.Using the proposed algorithm the success rate for Sudoku puzzles of order 3 of "easy", "medium" and "hard" level is 100%.For "Evil" puzzles the success rate is however only 93% but it is the best ever recorded by any algorithm using PSO rules, as per the knowledge of the authors.Also, Sudoku of higher order is solved for which the success rate is about 87%. Sudoku, of order n, is a combinatorial puzzle having partially filled n2?n2 grid consisting of sub-grids of n?n dimension. In this paper, a new membrane algorithm, namely MA_PSO_M, is presented. It uses the modified rules of Particle Swarm Optimization coupled with a carefully designed mutation operator within the framework of cell-like P-systems. Another significant contribution of this paper is the novel way in which the search space for solving the Sudoku problem is defined. Initially, the proposed algorithm is used to solve Sudoku puzzles of order 3 available in literature. On the basis of experiments performed on sample Sudoku puzzles of 'easy' and 'medium' difficulty levels it is concluded that the proposed membrane algorithm, MA_PSO_M, is very efficient and reliable. For the 'hard' and 'evil' difficultly levels, too the algorithm performs very well after incorporating an additional deterministic phase. The performance of the algorithm is further enhanced with an increased population size in a very small computational time. To further demonstrate efficiency of algorithm it is applied to Sudoku puzzles of order 4. The obtained results prove that the proposed membrane algorithm clearly dominates any of the PSO based membrane algorithm existing in the literature.

Display Omitted Multicriteria decision analysis based on interval-valued intuitionistic fuzzy sets.Development of a projection-based compromising method.Establishment of projection-based compromising indices and comprehensive indices.Determination of the ranking order and the approval status of alternatives.Comparative analyses with other relevant compromising decision-making methods. The purpose of this paper is to develop a projection-based compromising method for addressing multiple criteria decision-making problems based on interval-valued intuitionistic fuzzy sets. The concept of projections considers not only the distance but also the included angle between evaluative ratings of alternative actions with respect to a criterion. In the interval-valued intuitionistic fuzzy context, this paper determines the respective projections of the evaluative ratings of each alternative on the positive-ideal and negative-ideal solutions and explores several essential properties. Next, this paper introduces the concepts of projection-based compromising indices and comprehensive compromising indices and further investigates relevant theorems for supporting the usefulness of these indices. Additionally, this paper proposes the projection-based comparative index and the comprehensive comparative index to serve as benchmark values for the comparison purpose. The improvement percentage of the comprehensive compromising value is acquired to determine the priority order of the alternatives, including the complete ranking order and the approval status for each alternative. The feasibility and the applicability of the proposed method are validated with an application problem of watershed site selection. Finally, several comparative analyses are conducted to verify the effectiveness and advantages of the proposed method over other relevant compromising decision-making methods.

Display Omitted A review regarding application of MCDM techniques in E-learning is conducted.Five major databases have been considered for this review.ScienceDirect, Emerald, Taylor and Francis, IEEE, and Springer have been selected.A systematic and meta analysis methodology called "PRISMA" has been proposed.Papers between 2001 and 2015 have been considered for this review. Academic research on E-learning has increased extensively over the past few years. Although, many multi-criteria decision making methods have been proposed to evaluate and examine the effectiveness of E-learning, there is a lack of study concerning systematic literature review and classification of research in this area. Regarding this, five major databases including ScienceDirect, Emerald, Taylor and Francis, IEEE, and Springer have been selected and a systematic methodology proposed. Consequently, a review of 42 published papers appearing in 33 academic journals and international conferences between 2001 and 2015 have been obtained to achieve a comprehensive review of MCDM application in E-learning. Accordingly, the selected papers have been classified by the year of publication, MCDM techniques, and journals and conferences in which they appeared. In addition, the significant criteria in evaluating E-learning were found. This study supports researchers and practitioners in effectively adopting MCDM techniques regarding E-learning evaluation and provides an insight into its state-of-the-art.

Display Omitted Novel cluster-space controller for non-holonomic systems based Behavioral Adaptive Fuzzy tuning algorithm (BAFC).Controller is easy to implement and performs tasks based on their importance.Fuzzy tuned controller uses position error and its rate of change as inputs.Implementation using SIMULINK on Lego EV3 WMRs wheeled robot is presented.Wi-Fi link establishes communication between agents and controller. Cooperation between autonomous robot vehicles holds several promising advantages like robustness, adaptability, configurability, and scalability. Coordination between the different robots and the individual relative motion represent both the main challenges especially when dealing with formation control and maintenance. Cluster space control provides a simple concept for controlling multi-agent formation. In the classical approach, formation control is the unique task for the multi-agent system. In this paper, the development and application of a novel Behavioral Adaptive Fuzzy-based Cluster Space Control (BAFC) to non-holonomic robots is presented. By applying a fuzzy priority control approach, BAFC deals with two conflicting tasks: formation maintenance and target following. Using priority rules, the fuzzy approach is used to adapt the controller and therefore the behavior of the system, taking into accounts the errors in the formation states and the target following states. The control approach is easy to implement and has been implemented in this paper using SIMULINK real-time platform. The communication between the different agents and the controller is established through Wi-Fi link. Both simulation and experimental results demonstrate the behavioral response where the robot performs the higher priority tasks first. This new approach shows a great performance with a lower control signal when benchmarked with previously known results in the literature.

Display Omitted This paper studies the order acceptance and scheduling problem with class setups in a single machine environment.An enhanced artificial bee colony algorithm is proposed for solving this problem.Experimental results reveal that the proposed algorithm is both computationally efficient and effective. This paper considers the order acceptance and scheduling problem in a single machine environment where each customer order is characterized by a known processing time, due date, revenue, and class setup time. The objective is to maximize the total revenue. Since the problem is computationally intractable, we first conduct a preliminary study of applying the basic artificial bee colony algorithm to address the problem under study. Specifically, we design appropriate neighborhood operators with respect to the problem. Based on the results of the preliminary study and the problem characteristics, an enhanced artificial bee colony algorithm is developed with a series of modifications. The extensive experimental results indicate that the enhanced artificial bee colony algorithm is both computationally efficient and effective for large sized problem instances.

Display Omitted This paper presents an approach for breast cancer diagnosis in digital mammograms using shearlet transform.A new approach is represented for feature extraction using shearlet transform, t-test statistic and dynamic thresholding.The system uses two datasets (ROIs) obtained from two different database; MIAS and DDSM database.The datasets include all abnormalites for breast cancer.The classification section was performed to distinguish the ROIs as normal-abnormal and benign-malignant. In this paper, I introduce a new method for feature extraction to classify digital mammograms using fast finite shearlet transform. Initially, fast finite shearlet transform was performed over mammogram images, and feature vectors were built using coefficients of the transform. In subsequent calculations, features were ranked according to t-test statistics, and capabilities were distinguished between different classes. To maximize differences between class representatives, a thresholding process was implemented as a final stage of feature extraction, and classifications were calculated over the optimal feature set using 5-fold cross validation and a support vector machine (SVM) classifier. The present results show that the proposed method provides satisfactory classification accuracy.

Load dispatch is developed by thermal and wind units with its uncertainties.Consider many objective functions into a new multi objective method.Propose a new decision making method to select best Pareto front.Propose some new operators for local and global searches.Propose a new online training mechanism for self adaptive goals. This paper addresses the effect of the wind power units into the classical Environment/Economic Dispatch (EED) model which called hereafter as Wind/Environment/Economic Dispatch (WEED) problem. The optimal dispatch between thermal and wind units so that minimized the total generating costs are considered as multi objective model. Normally, the nature of the wind energy as a renewable energy sources has uncertainty in generation. Therefore, in this paper, use a practical model known as 2m-point to estimate the uncertainty of wind power. To solve the WEED problem, this paper proposed a new meta-heuristic optimization algorithm that uses online learning mechanism. Honey Bee Mating Optimization (HBMO), a moderately new population-based intelligence algorithm, shows fine performance on optimization problems. Unfortunately, it is usually convergence to local optima. Therefore, in the proposed Online Learning HBMO (OLHBMO), two neural networks are trained when reached to the predefined threshold by current and previous position of solutions and their fitness values. Moreover, Chaotic Local Search (CLS) operator is use to develop the local search ability and a new data sharing model determine the set of non-dominated optimal solutions and the set of non-dominated solutions to kept in the external memory. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) as a decision-making technique is employed to find the best solution from the set of Pareto solutions. The proposed model has been individually examined and applied on the IEEE 30-bus 6-unit, the IEEE 118-bus 14-unit, and 40-unit with valve point effect test systems. The robustness and effectiveness of this algorithm is shows by these test systems compared to other available algorithms.

Graphical abstractDisplay Omitted This paper presents a maiden application of EMA to solve power system ORPD problems.Steps of implementation of EMA to solve ORPD are elaborately discussed.The performance of EMA is tested on standard IEEE test systems.The selection of control parameters of EMA is done through exhaustive parametric study. In this paper, an exchange market algorithm (EMA) approach is applied to solve highly non-linear power system optimal reactive power dispatch (ORPD) problems. ORPD is most vital optimization problems in power system study and are usually devised as optimal power flow (OPF) problem. The problem is formulated as nonlinear, non-convex constrained optimization problem with the presence of both continuous and discrete control variables. The EMA searches for optimal solution via two main phases; namely, balanced market and oscillation market. Each of the phases comprises of both exploration and exploitation, which makes the algorithm unique. This uniqueness of EMA is exploited in this paper to solve various vital objectives associated with ORPD problems. Programs are developed in MATLAB and tested on standard IEEE 30 and IEEE 118 bus systems. The results obtained using EMA are compared with other contemporary methods in the literature. Simulation results demonstrate the superiority of EMA in terms of its computational efficiency and robustness. Consumed function evaluation for each case study is mentioned in the convergence plot itself for better clarity. Parametric study is also performed on different case studies to obtain the suitable values of tuneable parameters.

This paper presents an approach for breast cancer diagnosis in digital mammograms using wave atom transform.I examine the wave atom transform to determine which couple (scale, ratio of biggest coefficients) will give the highest classification rate.The system uses two sets of feature matrixes obtained from two different database; MIAS and DDSM database.These are tested with classifiers in changing ratios (10% and 90% of coefficients) for each scale.The classification is performed using two different classifiers; Support Vector Machine and k-Nearest Neighbors. This paper presents an approach for breast cancer diagnosis in digital mammograms using wave atom transform. Wave atom is a recent member of the multi-resolution representation methods. Primarily, the mammogram images are decomposed on the basis of wave atoms, and then a special set of the biggest coefficients from wave atom transform is used as a feature vector. Two different classifiers, support vector machine and k-nearest neighbors, are employed to classify mammograms. The method is tested using two different sets of images provided by MIAS and DDSM database.

This paper introduces weight uncertainty into ELM-AE and presents WuELM-AE.WuELM-AE extracts useful features that constitute higher level representation.ML-WuELM stacks WuELM-AE to create a multi layer network.Proposed ML-ELM-RBF achieves satisfactory results on multi-label data sets. Many neural network methods such as ML-RBF and BP-MLL have been used for multi-label classification. Recently, extreme learning machine (ELM) is used as the basic elements to handle multi-label classification problem because of its fast training time. Extreme learning machine based auto encoder (ELM-AE) is a novel method of neural network which can reproduce the input signal as well as auto encoder, but it can not solve the over-fitting problem in neural networks elegantly. Introducing weight uncertainty into ELM-AE, we can treat the input weights as random variables following Gaussian distribution and propose weight uncertainty ELM-AE (WuELM-AE). In this paper, a neural network named multi layer ELM-RBF for multi-label learning (ML-ELM-RBF) is proposed. It is derived from radial basis function for multi-label learning (ML-RBF) and WuELM-AE. ML-ELM-RBF firstly stacks WuELM-AE to create a deep network, and then it conducts clustering analysis on samples features of each possible class to compose the last hidden layer. ML-ELM-RBF has achieved satisfactory results on single-label and multi-label data sets. Experimental results show that WuELM-AE and ML-ELM-RBF are effective learning algorithms.

The paper presents techniques for autonomous path tracking of heavy vehicles at high speeds.Vehicle state estimation is based on fuzzy logic, and a Takagi-Sugeno type controller is used for vehicle lateral control.The paper describes the real implementation and testing of the controllers in a real truck.The implementation of high speed robot controllers for heavy vehicles is more difficult in practice than for small mobile robots.The paper also describes experiments with the soft controller at high speeds, up to 100km/h. This paper presents techniques for GPS based autonomous navigation of heavy vehicles at high speed. The control system has two main functions: vehicle position estimation and generation of the steering commands for the vehicle to follow a given path autonomously. Position estimation is based on fusion of measurements from a carrier-phase differential GPS system and odometric sensors using fuzzy logic. A Takagi-Sugeno fuzzy controller is used for steering commands generation, to cope with different road geometry and vehicle velocity. The presented system has been implemented in a 13tons truck, and fully tested in very demanding conditions, i.e. high velocity and large curvature variations in paved and unpaved roads.

This paper proposes a two-level self-adaptive variable neighborhood search (TLSAVNS) algorithm for the prize-collecting vehicle routing problem (PCVRP) based on the fact there are two levels of decisions in the PCVRP, namely the selection of customers to visit and the vehicle scheduling of selected customers. Computational results illustrates the efficiency of the proposed algorithm. A two-level self-adaptive variable neighborhood search algorithm is developed based on the two levels of decisions in the PCVRP, namely the selection of customers and the vehicle scheduling of selected customers.The neighborhood sequence can be self-adaptively changed based on the analysis of the search history.A graph extension method is adopted to obtain the lower bound for PCVRP by transforming the proposed mixed integer programming model of PCVRP into an equivalent traveling salesman problem model. This paper investigates the prize-collecting vehicle routing problem (PCVRP), which has a strong background in practical industries. In the PCVRP, the capacities of all available vehicles are not sufficient to satisfy the demands of all customers. Consequently it is not a compulsory requirement that all customers should be visited. However, a prize can be collected once a customer is visited. In addition, it is required that the total demands of visited customers should reach a pre-specified value at least. The objective is to establish a schedule of vehicle routes so as to minimize the total transportation cost and at the same time maximize the prize collected by all vehicles. The total transportation cost consists of the total distance of vehicle routes and the sum of vehicles used in the schedule. To solve the PCVRP, a two-level self-adaptive variable neighborhood search (TLSAVNS) algorithm is developed according to the two levels of decisions in the PCVRP, namely the selection of customers to visit and the visiting sequence of selected customers in each vehicle route. The proposed TLSAVNS algorithm is self-adaptive because the neighborhoods and their search sequence are determined automatically by the algorithm itself based on the analysis of its search history. In addition, a graph extension method is adopted to obtain the lower bound for PCVRP by transforming the proposed mixed integer programming model of PCVRP into an equivalent traveling salesman problem (TSP) model, and the obtained lower bound is used to evaluate the proposed TLSAVNS algorithm. Computational results on benchmark problems show that the proposed TLSAVNS algorithm is efficient for PCVRP.

We propose a new subband implementation of the Forward BSS algorithm.We proposed a new two-channel variable step-size techniques adapted to the proposed FBSS algorithm.The new FBSS algorithm is used to separate speech form noise and therefore enhance the speech signal intelligibility.The new algorithm improves the steady state values of the cross adaptive filters which are used by the FBSS algorithm. This paper addresses the problem of speech enhancement and acoustic noise reduction by adaptive filtering algorithms. Recently, we have proposed a new Forward blind source separation algorithm that enhances very noisy speech signals with a subband approach. In this paper, we propose a new variable subband step-sizes algorithm that allows improving the previous algorithm behaviour when the number of subband is selected high. This new proposed algorithm is based on recursive formulas to compute the new variable step-sizes of the cross-coupling filters by using the decorrelation criterion between the estimated sub-signals at each subband output. This new algorithm has shown an important improvement in the steady state and the mean square error values. Along this paper, we present the obtained simulation results by the proposed algorithm that confirm its superiority in comparison with its original version that employs fixed step-sizes of the cross-coupling adaptive filters and with another fullband algorithm.

Graphical abstractDisplay Omitted HighlightsThe paper presents an improvement of control performance of sliding mode control.The proposed method reduces duration of the undesirable approaching phase.The control parameters are tuned by fuzzy logic rules.The performance improvement was confirmed by simulation study. A continuous sliding mode control with moving sliding surface for nonlinear systems of arbitrary order is presented in this paper. The sliding surface is moved repetitively toward the target sliding surface in order to ensure that the system trajectory is close to the actual surface during the whole control process. The parameters of sliding mode control are tuned by a fuzzy logic. The proposed procedure reduces the time when the system operates in the approaching phase during which the control performance is deteriorated since the system is more susceptible to external disturbances and model uncertainties. The effectiveness of the presented approach is demonstrated on a control of a flexible robot manipulator arm.

Developing an IVIF permutation method with likelihood-based preference functions.Using a hybrid approach of the likelihood calculation method and PROMETHEE.Establishing new measurements of concordance/discordance to evaluate permutations.Presenting two algorithms for IVIF importance weights and incomplete information.Verifying the effectiveness using comparative analyses and applications to NPD. This paper presents an interval-valued intuitionistic fuzzy permutation method with likelihood-based preference functions for managing multiple criteria decision analysis based on interval-valued intuitionistic fuzzy sets. First, certain likelihood-based preference functions are proposed using the likelihoods of interval-valued intuitionistic fuzzy preference relationships. Next, selected practical indices of concordance/discordance are established to evaluate all possible permutations of the alternatives. The optimal priority order of the alternatives is determined by comparing all comprehensive concordance/discordance values based on score functions. Furthermore, this paper considers various preference types and develops another interval-valued intuitionistic fuzzy permutation method using programming models to address multiple criteria decision-making problems with incomplete preference information. The feasibility and applicability of the proposed methods are illustrated in the problem of selecting a suitable bridge construction method. Moreover, certain comparative analyses are conducted to verify the advantages of the proposed methods compared with those of other decision-making methods. Finally, the practical effectiveness of the proposed methods is validated with a risk assessment problem in new product development.

This paper proposes a hybrid time-series ANFIS model based on EMD to forecast stock price.In order to evaluate the forecasting performances, the proposed model is compared with other models.The experimental results show that proposed model is superior to the listing models. Time series forecasting is an important and widely popular topic in the research of system modeling, and stock index forecasting is an important issue in time series forecasting. Accurate stock price forecasting is a challenging task in predicting financial time series. Time series methods have been applied successfully to forecasting models in many domains, including the stock market. Unfortunately, there are 3 major drawbacks of using time series methods for the stock market: (1) some models can not be applied to datasets that do not follow statistical assumptions; (2) most time series models that use stock data with a significant amount of noise involutedly (caused by changes in market conditions and environments) have worse forecasting performance; and (3) the rules that are mined from artificial neural networks (ANNs) are not easily understandable.To address these problems and improve the forecasting performance of time series models, this paper proposes a hybrid time series adaptive network-based fuzzy inference system (ANFIS) model that is centered around empirical mode decomposition (EMD) to forecast stock prices in the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and Hang Seng Stock Index (HSI). To measure its forecasting performance, the proposed model is compared with Chen's model, Yu's model, the autoregressive (AR) model, the ANFIS model, and the support vector regression (SVR) model. The results show that our model is superior to the other models, based on root mean squared error (RMSE) values.

Define a ratio-based similarity index for a pair of interval-valued cross ratios.Develop new similarity measures for interval reciprocal preference relations (IRPRs).Devise an induced interval-valued cross ratio ordered weighted geometric operator.Develop a consensus model to solve group decision making problems with IRPRs. Similarity analysis and preference information aggregation are two important issues for consensus building in group decision making with preference relations. Pairwise ratings in an interval reciprocal preference relation (IRPR) are usually regarded as interval-valued And-like representable cross ratios (i.e., interval-valued cross ratios for short) from the multiplicative perspective. In this paper, a ratio-based formula is introduced to measure similarity between a pair of interval-valued cross ratios, and its desirable properties are provided. We put forward ratio-based similarity measurements for IRPRs. An induced interval-valued cross ratio ordered weighted geometric (IIVCROWG) operator with interval additive reciprocity is developed to aggregate interval-valued cross ratio information, and some properties of the IIVCROWG operator are presented. The paper devises an importance degree induced IRPR ordered weighted geometric operator to fuse individual IRPRs into a group IRPR, and discusses the derivation of its associated weights. By employing ratio-based similarity measurements and IIVCROWG-based aggregation operators, a soft consensus model including a generation mechanism of feedback recommendation rules is further proposed to solve group decision making problems with IRPRs. Three numerical examples are examined to illustrate the applicability and effectiveness of the developed models.

This paper first analyzes the size of the interval priority weight.Two models are built to derive the interval priority weight of each object.Then, two models are built to cope with the inconsistency for each object.Furthermore, two models are constructed to derive the missing values.Numerical examples and comparison analysis are made. Interval fuzzy preference relations that can well cope with the vagueness and uncertainty are commonly used by the decision maker. The most crucial issue is how to derive the interval priority vector from an interval fuzzy preference relation. This paper first analyzes the size of the interval priority weights. Then, two linear programming models are built, by which the interval priority weights are obtained, respectively. Considering the inconsistent case, two consistency-based linear programming models are built to derive the additive consistent fuzzy preference relations. Different to the current methods, new models consider the consistency and the interval priority weight simultaneously. In some situations, the decision maker may only offer an incomplete interval fuzzy preference relation, namely, some judgments are missing. To cope with this situation, we first classify the missing intervals into three categories and then apply the associated linear equations to denote the missing values. After that, we construct two consistency-based linear programming models to determine the missing values to cope with the consistent and inconsistent cases. It is worth noting that the built models can cope with the situation where ignorance objects exist. Meanwhile, the associated numerical examples are offered, and the analysis comparison is made.