Search

The consortium blockchain has been widely applied in various fields such as agricultural product traceability, supply chain management, and logistics transportation. As an indispensable component of a consortium blockchain, the consensus algorithm ensures the consistency and trustworthiness of each node in the network. However, existing consensus algorithms in large-scale consortium blockchain scenarios suffer from low system throughput and high latency due to the complexity of communication processes, rendering them impractical for real-world use. To address these issues, this paper proposes a novel consensus algorithm called credit evaluation-based practical Byzantine fault tolerance (CE-PBFT). This algorithm designs a new node credit evaluation model that considers node completion rate, consensus decay, and node behavior. It effectively measures and reflects the specific reliability status of nodes during system operation, thereby enhancing system reliability and security. Additionally, the paper introduces the innovative use of decision tree algorithms to analyze network node behavior and simplifies the existing consensus protocol. Nodes are categorized as excellent, good, ordinary, or poor based on the classification results, and non-Byzantine nodes are dynamically selected accordingly. This greatly improves the overall efficiency of the system. The performance of CE-PBFT is validated through experiments and compared with PBFT, G-PBFT, RBFT, WBFT and PPoR. Experimental results demonstrate that in large-scale consortium scenarios, CE-PBFT significantly improves system throughput, effectively reduces transaction latency and communication overhead, and outperforms the compared protocols. [ABSTRACT FROM AUTHOR]

The objective of image hiding is to conceal a secret image in a cover image inconspicuously. The challenges for image hiding focus on the embedding capacity, image quality and security. To contend with these challenges, this paper presents a novel image hiding method using Invertible Rescaling Net (IRN) and Similarity of Bits Pairs (SBP). Because of the downscaling ability of IRN, our method is able to hide a secret image into a cover image with the same dimensions. Moreover, the superior rescaling capabilities of IRN enable us to produce a recovered image of high-quality. We improve the SBP embedding technique and combine it with differential coding to boost the quality of the stego image. In the experiments, the quality of the recovered secret image and stego image is assessed using various quality evaluation metrics, and for the security, the anti-steganalysis performance is also evaluated in this paper. Extensive experimental results reveal that the quality of both the recovered secret image and the stego-image in our method outperforms several advanced methods and provides a high degree of security. • We apply invertible rescaling net (IRN) to image hiding task for the first time. • We improve the SBP encoding algorithm to prevent the degradation of the quality of the stego image. • Our method considers the robustness against the classical adversary's steganalysis. [ABSTRACT FROM AUTHOR]

The widespread development of monitoring devices in power system has indeed led to the generation of large amounts of power consumption data. Storing and transmitting this enormous volume of data has become a significant challenge for power system operators and researchers. Although high data rates are available for transmission, data compression is still necessary for power system applications to lessen the load of data transmission and storage. The wavelet transform plays an important role in data compression for power system applications. This paper presents an adaptive data compression algorithm based on the discrete wavelet transform (DWT) for power system applications. In general, some wavelet coefficients are neglected to produce DWT-based data compression by using hard or soft thresholds. But the volume of compressed data differs for various threshold values. In this context, selecting an optimal threshold is a challenging task in power system data compression. This paper proposes a multi-objective particle swarm optimisation (MO-PSO) for optimal threshold selection. The proposed approach is tested using IEEE power quality wave data sets and Dutch Residential Energy Datasets (DRED). The proposed MO-PSO algorithm finds the global optimum threshold, and it outperforms the other existing algorithms. The proposed algorithm efficiently compresses the test dataset with a maximum compression ratio (CR) of 2.07. • The development of an adaptive algorithm for data compression is applied in power system data. • MO-PSO algorithm is proposed to find the optimal threshold in WT based data compression. • Results are compared with recent research works. • The efficiency of data compression algorithm is evaluated by using compression ratio, mean square error and signal-to-noise ratio. [ABSTRACT FROM AUTHOR]

Economic dispatch (ED) has received considerable interest in the field of energy management and optimization. The problem aims to determine the most cost-effective power allocation strategy that satisfies the power demand and all physical constraints of the power system. To solve this problem, we propose an algorithm based on differential evolution and adopt a hybrid mutation strategy, a linear population size reduction mechanism, and an improved single-unit repair mechanism. Experimental results confirmed that these mechanisms are useful for performance improvement. The proposed algorithm (L -HMDE) showed good performance when compared with more than 90 algorithms in solving 22 test cases. It could provide high-quality solutions stably and efficiently. In addition to designing a good algorithm, we present a review of over 100 papers and highlight their algorithm features. We also provide a comprehensive collection of test cases in the literature. Through careful examination and verification, data coefficients of these test cases and solutions to them are included in this paper as a useful reference for researchers who are interested in this problem. • A differential evolution-based algorithm (L-HMDE) is proposed to address the economic dispatch problem. • The L-HMDE integrates a hybrid mutation strategy, a population size reduction mechanism, and an improved repair procedure. • It shows good solution quality and high efficiency when compared with more than 90 existing algorithms on 22 test cases. • A comprehensive collection of test cases and solutions is also provided. [ABSTRACT FROM AUTHOR]

Satellite range scheduling always plays a crucial role in tracking, telemetry, and control of the spacecraft. With the significant increase in the number and type of satellites in orbit, the demands of users for satellite range scheduling are becoming more and more diverse. However, existing studies for the satellite range scheduling problem (SRSP) rarely consider multiple optimization objectives, which is quite significant in practice. Hence, this paper investigates a multi-objective satellite range scheduling problem (MO-SRSP) that optimizes three objectives simultaneously: the overall profits of tasks, load-balance of antennas, and completion timeliness of tasks. To address MO-SRSP, this paper establishes a mathematical model on the basis of analysis of MO-SRSP and proposes a multi-objective evolutionary algorithm, which is called multi-objective differential evolution algorithm based on space division and adaptive selection strategy (MODE-SDAS). The space division strategy will uniformly divide the objective space into a set of subspaces and preserve a set of non-dominated solutions in each subspace during the environmental selection even if some of these solutions are dominated by other solutions in other subspaces, so as to maintain the diversity of the algorithm. The adaptive selection strategy will adaptively allocate computational resources to different subspaces to improve the convergence of the population. Besides, problem-specific designs such as coding and encoding methods, the discrete differential evolution operator, as well as objective-specific individual variation operators are incorporated into the algorithm to enhance the search capability. Finally, extensive experiments based on simulation test cases are carried out to verify the effectiveness and efficiency of MODE-SDAS. The comparison results show that MODE-SDAS significantly outperforms its competitors in terms of three metrics. Meanwhile, knee point analysis, sensitivity analysis, and application insights are presented. • A tri-objective satellite range scheduling problem. • A multi-objective differential evolution algorithm is proposed. • Space division and adaptive selection strategies are combined. • Problem-specific and objective-specific designs are applied. [ABSTRACT FROM AUTHOR]

The flying ad hoc network (FANET) is an emerging network focused on unmanned aerial vehicles (UAVs) that has attracted the attention of researchers around the world. Due to the cooperation between UAVs in this network, data transfer between these UAVs is very essential. Routing protocols must determine how to make routing paths for each UAV with others in a wireless ad hoc network to facilitate the data transmission between UAVs. Nowadays, reinforcement learning (RL), especially Q-learning, is an effective response for solving existing challenges in the routing approaches and adding features such as autonomous, self-adaptive, and self-learning to these approaches. In this paper, Q-learning is used to enhance and increase network performance, and a Q-learning-based routing method using an intelligent filtering algorithm called QRF is presented for FANETs. The main innovation in this paper is that QRF manages the size of the state space using the proposed filtering algorithm. This will increase the convergence rate of the Q-learning-based routing algorithm. On the other hand, QRF regulates the learning parameters related to Q-learning so that this scheme is better adapted to the FANET environment. In the last step, the network simulator version 2 (NS2) is employed to execute the simulation process related to QRF. In this process, five evaluation criteria, namely energy consumption, packet delivery rate, overhead, end-to-end delay, and network longevity are evaluated, and the results obtained from QRF are compared with those of QFAN, QTAR, and QGeo. The simulation results in this paper show that QRF makes a balanced energy distribution between UAVs and thus extends the network longevity. Moreover, the intelligent filtering algorithm designed in QRF has reduced delay in the routing process but is associated with communication overhead. [ABSTRACT FROM AUTHOR]

For decades, vision scientists have contemplated the topic of plant species classification. As plants are of great importance to medicinal research, they are utilized in a wide range of medications. Plants are required in a variety of ways in order to save the species from extinction and provide an abundance of food through agriculture. Therefore,Botanists and computer scientists must conduct extensive plant species research. The plant resources are necessary for the survival of the world's nations The purpose of this paper is to examine the frequently utilized and publicly accessible dataset for plant classification in the past. We explored over 200 research papers for a deep understanding of the area. Briefly described are the procedural advancements and developments in the field of leaf classification. All the major techniques with significant advancements, the new effective approaches, and the novel techniques are discussed in this research. For the benefit of future researchers, the findings, research gap and transition, and coherence of algorithms in terms of several measurements are underlined. The hundreds of publications on a single benchmark dataset illustrate the progression of the recognition process, improvements, and innovations. • The article is about the brief overview of the studies in plant leaf classification. • The research outlines the brief overview of the field in the last two decades. • The insights found from the deep analysis of over 200+ research articles. • The evolution of the feature extraction and classifier designs with time and novel algorithms proposed for the solution. • The anticipated questions and queries about the field and outline of the trends in plant research. [ABSTRACT FROM AUTHOR]

This paper provides a novel approach to stitching surface images of rotationally symmetric parts. It presents a process pipeline that uses a feature-based stitching approach to create a distortion-free and true-to-life image from a video file. The developed process thus enables, for example, condition monitoring without having to view many individual images. For validation purposes, this will be demonstrated in the paper using the concrete example of a worn ball screw drive spindle. The developed algorithm aims at reproducing the functional principle of a line scan camera system, whereby the physical measuring systems are replaced by a feature-based approach. For evaluation of the stitching algorithms, metrics are used, some of which have only been developed in this work or have been supplemented by test procedures already in use. The applicability of the developed algorithm is not only limited to machine tool spindles. Instead, the developed method allows a general approach to the surface inspection of various rotationally symmetric components and can therefore be used in a variety of industrial applications. Deep-learning-based detection Algorithms can easily be implemented to generate a complete pipeline for failure detection and condition monitoring on rotationally symmetric parts. [ABSTRACT FROM AUTHOR]

Co-location patterns in spatial dataset are the interesting collection of dissimilar objects which are located in proximity. We keep similar objects in an entity set and maintain that no two objects in a co-location pattern belong to an entity set. Location proximity is based on Euclidean distance measure. However, algorithms for mining patterns in transactional datasets are not directly applicable to spatial datasets for mining co-location patterns. Conventional methods are not applicable to distributed temporal data and many applications generating spatial dataset are inherently distributive in nature. In this paper, a Map-Reduce based approach is proposed to find all co-location patterns from a spatial dataset distributed over nodes. This approach is modularized one and consists of four algorithms. With the first three algorithms in the first approach and by proposing an algorithm for dynamic datasets, this paper contains another approach for the co-location patterns set, that also updates in an incremental manner (not from scratch) whenever certain changes occur in the dataset. Experimental results on larger datasets are also presented. [ABSTRACT FROM AUTHOR]

Parameters for defining photovoltaic models using measured voltage–current​ characteristics are essential for simulation, control, and evaluation of photovoltaic-based systems. This paper proposes an enhanced chaotic JAYA algorithm to classify the parameters of various photovoltaic models, such as the single-diode and double-diode models, accurately and reliably. The proposed algorithm introduces a self-adaptive weight to regulate the trend to reach the optimal solution and avoid the worst solution in various phases of the search space. The self-adaptive weight capability also allows the proposed technique to reach the best solution at the earliest phase, and later, the local search process starts, which also increase the ability to explore. A three different chaotic process, including sine, logistics and tent map, is proposed to optimize the consistency of each generation's best solution. The proposed algorithm and its variants proposed are used to solve the parameter estimation problem of various PV models. To show the proficiency of the suggested algorithm and its variants, an extensive simulation is carried out using MATLAB/Simulink software. Two statistical tests are conducted and compared with the latest techniques for validating the performance of the suggested algorithm and its variants. Comprehensive analysis and experimental results display that the suggested algorithm can achieve highly competitive efficiency in terms of accuracy and reliability compared to other algorithms in the literature. This research will be backed up with extra online service and guidance for the paper's source code at https://premkumarmanoharan.wixsite.com/mysite. • A new CJAYA algorithm is proposed to estimate the parameters of SDM and DDM models. • Chaotic and self-adaptive weights are combined with JAYA to get the best solution. • The performance of CJAYA and its variants are tested on 23 benchmark functions. • Four PV models are considered to validate the performance of CJAYA and its variants. • Detailed analysis, results, and statistical tests show that the CJAYA is superior. [ABSTRACT FROM AUTHOR]

• Discretionary or ex gratia payouts are widespread in parametric insurance programs. • Payouts attempt to secure social license to operate despite contractual basis risk. • Discretionary payouts obscure and entrench insurers' market power. • Attempts at conciliation often stoke further demands from aggrieved collectivities. • Geospatial monitoring alone cannot resolve questions of post-disaster distribution. The past decade has seen the dramatic proliferation of geospatial tools to remotely monitor, measure, and transfer weather and climate risk, particularly in the Global South. These "parametric" tools are calculative market devices used to commodify risk and facilitate its distantiated exchange via insurance markets. Yet the environmental estimates they generate are frequently wrong, sometimes grossly so. This paper investigates what happens after calculative market devices fail, analyzing so-called ex gratia ("from grace") practices in which insurers make payouts to aggrieved clients even when none are due under contractual terms. Though these payments are commonly deployed to dispel discontent, these "public secrets" of the industry have gone unnoticed in insurance scholarship. This paper documents numerous ex gratia payouts in parametric programs across Africa, disputing the myth of autonomous insurance markets that function according to formal, transparent rules administered by dispassionate calculative devices. Instead, these "discretionary" monetary transfers reintroduce human decision making in informal, black-boxed ways, cloaking the inadequacy of the parametric contracts they shore up. Far from incidental, I argue that these practices have been constitutive of the parametric insurance market's persistence and expansion. Though ex gratia payments sometimes give rise to negotiations over indemnification with aggrieved collectivities, these unfold on insurers' terms, informalizing power and delegitimizing complaint. The growing emphasis on parametric insurance as a tool for climate adaptation makes it all the more important to excavate the mechanics and politics of ex gratia, and to relinquish expectations that geospatial algorithms alone can resolve questions of post-disaster redistribution. [ABSTRACT FROM AUTHOR]

The second-order synchrosqueezing S-transform (SSST2) is an important method for instantaneous frequency (IF) estimation of non-stationary signals. Based on the synchrosqueezing S-transform, the instantaneous frequency calculation method is modified using the second-order partial derivatives of time and frequency to achieve higher frequency resolution. However, weak multi-frequency signals with strong background noise are often drowned out during the transformation process. To achieve enhanced extraction of weak fault characteristic signals due to mechanical faults, this paper proposes an optimally weighted sliding window signal segmentation algorithm based on the SSST2. The results of simulations and experiments show that the time–frequency aggregation of the second-order synchrosqueezing S-transform based on the optimally weighted sliding window (OWSW-SSST2) is not only significantly higher than that of commonly used time–frequency transforms, but it also has better operational efficiency than the second-order synchrosqueezing S-transform. In this paper, the proposed algorithm is used to analyze fault signals from actual high-speed railway wheelset bearings. The results show that the OWSW-SSST2 algorithm greatly improves the spectral aggregation of the signal, and crucially, that high-precision IF estimates for signals can be obtained in low signal-to-noise ratio environments. This research is both of academic interest and significant for practical engineering use to ensure safe high-speed rail operations. It helps enable monitoring the status of wheelset bearings, correctly estimating the locations and causes of failures, and providing up-to-date systematic maintenance and system improvement strategies. • This paper proposes a novel method named OWSW-SSST2. • The proposed method overcomes the drawbacks of SSST. • The signal processing performance of OWSW-SSST2 is analyzed comparatively. • Simulation and application show the validity and superiority of OWSW-SSST2. [ABSTRACT FROM AUTHOR]

Firefly algorithm (FA) is a meta-heuristic optimization algorithm inspired by nature. Due to its superior performance, it has been widely used in real life. However, it also has some shortcomings in some optimization cases, such as low solution accuracy and slow solution speed. Therefore, in this paper, distributed parallel firefly algorithm (DPFA) with four communication strategies is presented to improve these shortcomings. The distributed parallel technique is implanted to divide the initial fireflies into several subgroups, and exchange the information based on communication strategies among subgroups after the fixed iteration. The communication strategies include the maximum of the same group, the average of the same group, the maximum of different groups and the average of different groups. For verifying its performance, this paper compared DPFA with famous optimization algorithms, and experimental results show that DPFA has stronger competitiveness under the test suite of CEC2013. Furthermore, the proposed DPFA is also applied to the PID parameter tuning of variable pitch wind turbine, and conducted experiments show that DPFA outperforms other algorithms. It can smooth the power output and reduce the impact on the power grid when the wind speed fluctuates. • Developed distributed parallel mechanism as a method to balances the exploration and exploitation of algorithms. • A proposed distributed parallel firefly algorithm (DPFA) improves the performance of the original FA. • Compared DPFA with other well-known optimization algorithms under the test suite of CEC2013. • DPFA is applied in the control of variable pitch wind turbine to tune PID parameters. [ABSTRACT FROM AUTHOR]

This paper introduces a cyber-physical system for building automation and control that is developed based on a distributed model predictive control. The implemented distributed method significantly reduces computation overhead with respect to the centralized methods. However, continuous data transfer between subsystems, which are often far from each other, is required when using this method. Information transmission between subsystems is very often subject to the limitations of transmission bandwidth and/or short communication range resulting in significant communication overhead. This causes significant time latency between making measurements and applying control commands, which adversely affects the control performance. Therefore, the distributed method used in this paper implements a two-level communication architecture to reduce the communication overhead. In order to avoid collision in communication inside neighborhood using this method, the TDMA-OFDMA scheme is used for wireless communication between distributed devices. Under these assumptions, the communication overhead is calculated. Then, a novel algorithm for finding the size of neighborhoods resulting in the lowest time latency between making measurements and applying control commands is presented for a typical office building. Finally, the satisfactory performance of the proposed cyber-physical system for the temperature control of a typical office building in the presence of disturbance and model inaccuracy is illustrated using computer simulations. [ABSTRACT FROM AUTHOR]

Particle Swarm Optimization (PSO) provides a metaheuristic optimization technique for real-life functions with complex behavior. Inspired by the metaphor of social behavior as exhibited by swarms operating in natural surroundings, the algorithm captures the Emergent Complexity demonstrated by individual components of large groups which work together using simple rules and create complex, yet efficient, adaptive, and self-organizing systems. The paper seeks to rigorously analyze the hyperparameters of the algorithm to find the relative importance of cognitive(personal) vis-à-vis social (swarm) parameters of the algorithm so as to gain a perfect understanding of the importance of exploitation versus exploration parameters thus enabling us to enhance the application efficiency of the algorithm. The paper further suggests and applies a rolling coefficient updating technique to the algorithm parameters so as to use a formal statistical procedure in the initialization and subsequent iterations for updating coefficients rather than leaving it on trial and error or on a practitioner's knowledge. Results suggest that the technique employed provides an enhancement in the efficiency of the algorithm by creating a dynamic Emergent Complexity environment. [ABSTRACT FROM AUTHOR]

This paper is devoted to the practical application of parallel sorting algorithms and parallel input-output methods for the problem of genome alignment. The paper considers different approaches to the implementation of such algorithms, taking into account the capabilities of high-performance systems. Main purpose of the work is to develop a genome sorting program, the efficiency of which significantly exceeds the efficiency of free software analogues. The genome sorting program is implemented for a supercomputer using the C++ language and the OpenMP and OpenMPI. The developed program demonstrates a significant increase in the speed of operation (up to 10 times) compared to free software analogues due to massive parallel data input and output. Different approaches for data input/output parallelization and data processing considered in the paper can be applied in other subject areas. [ABSTRACT FROM AUTHOR]

Block symmetric cryptographic algorithms are the essential and inalienable element of any information security system. The main component of block symmetric cryptographic algorithms is the S-box, which largely determines the speed and cryptographic quality of the entire cryptographic transformation. The rapid development of cryptanalysis methods, including the development of quantum computers, requires a more careful research of all possible representations of nonlinear elements of block symmetric cryptographic algorithms. In view of the fact that in addition to the mathematical apparatus of Boolean functions used today to estimate the cryptographic quality of S-boxes, a cryptanalyst can apply the mathematical apparatus of functions of many-valued logic, which makes relevant the task of researching and comparing the cryptographic quality of S-boxes of modern cryptographic algorithms, represented by functions of many-valued logic. This paper presents a research and comparative analysis of nonlinear transformations of the cryptographic algorithms AES, Kalyna, BelT, and Kuznechik when represented by functions of many-valued logic. It was found that only the nonlinear transformation of the BelT cryptographic algorithm is characterized by growth when represented by many-valued logic functions, while the Kalyna cryptographic algorithm demonstrates the greatest decrease in nonlinearity when represented by 16-functions among the cryptographic algorithms researched. The results obtained in the paper indicate a significant unused reserve of cryptographic quality, which can be used in the design of new cryptographic algorithms and their structural elements. [ABSTRACT FROM AUTHOR]

The paper focuses on the problem of instance selection. Instance selection is currently crucial to enhance the efficacy and efficiency of machine-learning tools when they are used to solve a data-mining task and when the data are large and they are seen through the prism of the big data phenomenon. Instance selection eliminates redundant instances and thus reduces the size of the training data set. The training data, with redundant cases removed, can be more useful and ensure better performance of the final classification models. The instance selection problem belongs to the NP-hard class, so it can be solved with an approximation tool. In this paper the firefly algorithm is proposed for solving the instance selection problem. This paper is one paper, where the firefly algorithm has been used to solve a discrete optimisation problem, when in more cases previously it has been used for solving continuous optimisation problems. The firefly-based instance selection algorithm is presented and its validation is carried out. The results of the computational experiment show that the algorithm is competitive with others. The results obtained are discussed and conclusions are formulated. [ABSTRACT FROM AUTHOR]

This paper addresses the Multiobjective Travelling Salesman Problem (MoTSP) with the aim to study the effects of including random immigrants in the population of solutions processed by the evolutionary algorithm. Random immigrants are typically used in evolutionary optimization in order to increase the diversity of the population and to allow the algorithm to explore a larger area of the search space. Introducing random immigrants incurs a certain overhead which is especially significant in combinatorial optimization, because local search procedures are usually employed, which, while effective in improving the solutions, are computationally expensive. In this paper several strategies of introducing new specimens are tested with the aim of improving the effectiveness of the optimization process given a limited computation time. In the experiments the proposed approach was tested on kroABnnn instances of the MoTSP. It was found to improve the results of multiobjective optimization in terms of both the hy-pervolume and the IGD indicators. The most effective immigration strategy turned out to be to decrease the number of immigrants with time. [ABSTRACT FROM AUTHOR]

In this paper feasibility-preserving genetic operators for hybrid algorithms using TSP solvers for the Inventory Routing Problem (IRP) are studied. The IRP is a problem of jointly optimizing delivery schedules and routes for vehicles transporting products from a supplier to a number of retailers. This optimization problem is highly constrained, because limits on inventory levels as well as the vehicle capacity have to be taken into account. Moreover, the IRP is a generalization of the TSP and solving the TSP effectively is an important part of obtaining good solutions to the IRP. In this paper evolutionary algorithms are used for solving the IRP, but finding good routes is delegated to a state-of-the-art TSP solver. Therefore, genetic operators used in this paper focus on constructing the delivery schedule and not on optimizing the routes. In the experimental part of the paper an evolutionary algorithm using feasibility-preserving genetic operators is compared to the Infeasibility Driven Evolutionary Algorithm (IDEA) that uses the selective pressure to obtain feasible solutions. Presented results suggest that designing good feasibility-preserving genetic operators is important, because allowing the optimization algorithm to generate infeasible solutions and handling infeasibility in IDEA using the selective pressure leads to inferior results. [ABSTRACT FROM AUTHOR]

The paper considers the disadvantages of existing approaches to testing software and hardware data security tools in order to confirm compliance of the implemented functionality with the declared characteristics. It demonstrates the necessity of ensuring completeness and optimality of testing. The paper describes some testing approaches based on the development of mathematical models using the automata theory and ensuring completeness of testing, but leaving the question of its optimality open. It describes the approach proposed earlier by the authors, which ensures both completeness and optimality of testing using the graph theory. In accordance with this approach, the software and hardware data security tool is represented as a directed graph without loops or multiple edges. The graph vertices correspond to the states of the software or hardware component, and the directed edges correspond to the transitions of the data security tool from one state to another when performing non-target functions or security functions. On the basis of this approach, the authors propose an algorithm for solving the problem of testing software and hardware data security tools using a number of well-known algorithms on graphs. In the paper, it is substantiated that a solution to the problem of ensuring completeness and optimality of testing exists if and only if any vertex of the derived graph obtained by removing all unused vertices and edges either belongs to a directed chain or lies in a strongly connected component. Application of the proposed algorithm for solving the problem of testing one of the software and hardware security tools is considered, and the possibility of its application in practice is confirmed. [ABSTRACT FROM AUTHOR]

The past decade has witnessed an explosion in the generation of Arabic textual data, written in both modern standard Arabic (MSA) and in dialectal formats. Observing existing data reveals that verses from the Holy Quran are often quoted whether someone is giving a speech, conveying condolences, going through a hardship, and when expressing hope or joy among other emotions. Many applications can benefit from the automatic detection of those verses yet detecting Quranic Verses in text is not as easy as it may initially seem. This paper lists the challenges posed by this task, and proceeds to present an intelligent matching algorithm that addresses those. The paper also briefly describes a tool that has implemented the proposed algorithm, and which is currently publicly available as an open-source tool. [ABSTRACT FROM AUTHOR]

Academic document plagiarism is the most common infringement in the copyright protection of digital resources. Plagiarism detection is based on document similarity detection. This paper presents a copyright arbitration algorithm of digital resources. The algorithm combines the digital fingerprint generation algorithm with other factors to extract the key words of documents, such as word relevance, word semantics, TF-IDF features and position factor. These headings are processed with the SHA-1 encoding dimensionality reduction method to form a digital fingerprint based on document content, and then the source of a plagiaristic document is accurately tracked and positioned through a comparison between local digital fingerprints. In this paper, 55 academic documents as samples underwent an experiment. The experiment shows that the digital fingerprints generated by the algorithm presented in this paper are highly robust. [ABSTRACT FROM AUTHOR]

In this study, we aimed to construct a system to perform statistical analyses for educational improvement while preserving privacy. Various probabilistic statistical algorithms have been developed for data agitation. However, one of the major challenges in using these algorithms is determining appropriate parameters. To address this issue, our previous research proposed the "α-criterion" as a criterion that must be satisfied by appropriate parameters. This paper outlines a system that calculates the parameters that satisfy the α-criterion while performing real-time data agitation on the given aggregate data. To verify that our implementation actually works, we show a use case with sample data on kibana-Elastic log analysis provided by Elastic N. V. [ABSTRACT FROM AUTHOR]

Coalition formation with task dependencies has been the focus of few of the literature on multi-agent coalition formation. In contrast, very little attention has been given to the case where each agent has several alternative sets of tasks leading it to its goal satisfaction. The task dependencies impact the feasibility of the coalitions depending on the considered tasks alternative at a given time. Hence, the performance of a single task, whether by coalition formation (group of agents) or by a single performance, could affect the feasibility of other coalitions in the system. However, these task dependencies play a crucial role in many real-world multi-agent applications. Against this background, we consider in this paper multiple self-interested agents each of which has a goal it needs to achieve by performing a set of tasks. Each agent has several alternative sets of tasks leading it to its goal satisfaction. The tasks in an alternative exhibit dependencies and require sequential execution. So, to jointly achieve goals, the agents may form interdependent coalitions. We introduce a new algorithm that we call the Selective Exploration Algorithm (SEA) for coalition formation that accounts for the task dependencies to consider only feasible coalitions and reduce the size of the search space to explore and identify the optimal coalition structure. [ABSTRACT FROM AUTHOR]

The paper presents a description of the research methodology dedicated to a two-step discretisation process applied to the input numeric data, with combining the characteristics of selected supervised and unsupervised algorithms, which leads to extended processing of some attributes in train and test sets. The methodology was illustrated with the investigations carried out in the domain of stylometric analysis of texts, for two datasets prepared for the task of binary authorship attribution. The several variants of transformed input data obtained were subjected to exploration using two selected machine learning methods capable of inducing knowledge from both continuous and categorical forms, namely the PART and J48 classifiers. The results from the experiments indicate that, as can be expected, supervised transformations of data work well enough, however, they do not always return the best outcome. The two-step processing of some attributes shows sufficient promise to warrant a closer study, as opposed to always unconditionally relying only on supervised algorithms as outperforming all other approaches. [ABSTRACT FROM AUTHOR]

Brain tumours and strokes are increasingly common, even from a young age. For this reason preliminary screenings, such as MRI scans, are crucial steps in detecting the abnormalities and finding a treatment. Given the increasing number of people developing different brain problems, there is a need in developing automated segmentation systems. Regardless the various methods presented in the literature, the lack of ground truth images determines the researchers to move towards unsupervised techniques. This paper presents an modified graph-based unsupervised brain segmentation method that uses a minimal spanning tree to segment brain from non-brain tissue. The original method uses human intervention for node selection. The aim is to eliminate human intervention and reduce the computational time required for brain segmentation. The presented method was compared with the original one in two ways: by resizing and scaling the images, and using images without any pre-processing step. Experimental results were obtained on the NFBS dataset and in both experiments the proposed approach delivers better results, both visually and numerically. Performance measures have improved, leading to better overall segmentation. The new method increased the precision and dice coefficient by 20%, resulting in a more accurate segmentation. [ABSTRACT FROM AUTHOR]

The paper presents a computationally efficient method developed to automatically detect obstacles that appear at railroad-road crossings. The proposed algorithm works maintenance-free and automatically detects obstacles that appear and stay or are left at the crossing. These obstacles can pose a threat for the trains causing even a trail derailment. When a detected obstacle is a person it is crucial to generate a warning in order to react and safely remove the person before the train arrives. The proposed algorithm is based on live video stream analysis. The standard image processing methods were used in order to detect obstacles in the acquired images. However, several techniques were proposed to obtain the desired results dealing with image vibrations, heavy rain and snow. Such robustness was obtained by building and maintaining a fuzzy background frame and appropriate filtering. The obstacle detection system was implemented and tested. The results confirmed its correct operation and usefulness in real-world conditions. [ABSTRACT FROM AUTHOR]

In a dynamic world, data streams are continuously generated, which poses immense challenges for machine learning (ML) algorithms to adapt to changing statistical properties that are subject to a non-stationary context. The underlying scenario is defined as concept drift (CD), where changes in the relationship between response and prediction variables (real CD) or a change in input data (virtual CD) are accompanied by a significant degradation in the predictive performance of the models, causing ML models to reach unacceptable levels of system accuracy. In this paper, the state of the art for CD algorithms is analyzed and compared. For this purpose, a systematic literature review was performed. Then, the 10 most popular CD algorithms were extracted from the literature using a newly-developed metric. Subsequently, the algorithms were analyzed and compared with respect to their functionality and limitations. Based on these, the optimization potentials were systematically derived. This work presents a summarized overview of CD algorithms and provides the basis for algorithm optimization in this domain. [ABSTRACT FROM AUTHOR]

In this paper, the problem of imbalanced data stream classification is considered. To eliminate the problem of imbalanced data, over- and under-sampling procedures are implemented within a dedicated framework called Weighted Ensemble with one-class Classification and Over-sampling and Instance selection (WECOI). To increase the quality of synthetic instance generation (carried out under the umbrella of an over-sampling procedure), an agent-based population algorithm is proposed. The problem is defined, and the agent-based algorithm is presented. A discussion of selected computational results is also included. [ABSTRACT FROM AUTHOR]

In a world of connectivity empowered by the advancement of the Internet of Things (IoT), an infinite number of data streams have emerged. Thus, data stream clustering is crucial for extracting hidden knowledge and data mining. Various data stream clustering methods have lately been introduced. Yet, the majority of such algorithms are affected by the curse of high dimensionality. Lately, a fully online buffer-based clustering algorithm for handling evolving data streams (BOCEDS) was developed. Similarly to other existing density-based clustering methods, BOCEDS is not capable of handling high-dimensional data and has high computational power and high memory utilization. This paper introduces an Entropy Window Reduction (EWR) algorithm, which is an improved version of the BOCEDS technique. EWR is a fully online clustering technique for handling high-dimensional data streams using feature ranking and sorting. This process is accomplished by calculating the entropy of specific features with respect to the time window. The findings of the experiments are compared to the outcomes of BOCEDS, CEDAS, and MuDi-Stream algorithms. The outcomes indicate that the EWR algorithm outperformed the baseline clustering algorithms. The results are demonstrated using the KDDCup'99 dataset in terms of quality and complexity evaluation on the average of F-Measures, Jaccard Index, Fowlkes–Mallows index, Purity, and Rand Index as well as the memory usage and computational power with 88%, 66%, 81%, 100%, and 66%, respectively. The results also show low memory usage and computing power in comparison with the baseline algorithms. [ABSTRACT FROM AUTHOR]

This paper studies the online vector bin packing (OVBP) problem and the related problem of online hypergraph coloring (OHC). Firstly, we use a double counting argument to prove an upper bound on the competitive ratio of FirstFit for OVBP. Our proof is conceptually simple, and strengthens the result in [ 1 ] by removing the dependency on the bin size parameter. Secondly, we introduce a notion of an online incidence matrix that is defined for every instance of OHC. Using this notion, we provide a reduction from OHC to OVBP, which allows us to carry known lower bounds on the competitive ratio of algorithms from OHC to OVBP. Our approach significantly simplifies the previous argument from [ 1 ] that relied on using intricate graph structures. In addition, we slightly improve their lower bounds. Lastly, we establish a tight bound on the competitive ratio of algorithms for OHC, where input is restricted to be a hypertree, thus resolving a conjecture in [ 2 ]. The crux of this proof lies in solving a certain combinatorial partition problem about multi-family of subsets, which might be of independent interest. [ABSTRACT FROM AUTHOR]

This research paper proposes a hybrid Whale Optimization Algorithm (WOA) variant based on Equilibrium Optimizer (EO), named Equilibrium Whale Optimization Algorithm (EWOA). The major finding lies in an efficient hybridization of bio-inspired (WOA) and physics-based (EO) metaheuristic algorithms. Upon mathematical modelling, EWOA proposes a main architecture that combines WOA's encircling and net-bubble attacking mechanisms via EO's weight balance strategy. The proposed algorithm was tested on 23 classical, 28 constrained CEC 2017, 30 unconstrained CEC 2017, 10 CEC 2019, and 10 CEC 2020 benchmark problems, in comparison with six recently proposed state-of-the-art algorithms (including WOA and EO). EWOA outperforms other algorithms with the best statistical mean performance on 46 out of 101 functions and the most promising clustering data in the graph, respectively. The fact that EWOA could achieve best statistical SD performance on 2 of the total 5 benchmark sets proves that EWOA is competitively robust. EWOA can converge to the optimum before 50% iterations of most benchmark functions, achieving the fastest convergence rate compared to other algorithms. The major contribution thereby lies in the successful development of this hybrid algorithm, which yields better optimization efficiency than the original and other state-of-the-art algorithms in terms of statistics, convergence and clustering. [ABSTRACT FROM AUTHOR]

This paper proposes an extension of the KLMS algorithm to the Vector-Valued Reproducing Kernel Hilbert Space (VV-RKHS), enabling the use of the operator-valued kernel (OV-kernel) in the online identification of multi-input multi-output (MIMO) nonlinear systems. The yielded multivariate kernel model offers more design flexibility and involves fewer parameters than other vector-valued KLMS algorithms present in the literature. Conditions ensuring the convergence of the proposed OV-KLMS algorithm are given. Experiments on a multivariate chaotic attractor as well as numerical simulations are carried out and show the effectiveness of the proposed algorithm • A Kernel LMS algorithm in Vector Valued Reproducing Kernel Hilbert Space is proposed. • The proposed algorithm makes use of Operator Valued Kernels. • Proofs of the algorithm convergence are given. • The yielded kernel model is more accurate compared to state-of-the-art algorithms. • It is a low time consumption algorithm and is suitable for online identification of nonlinear Multi Input Multi Output systems. [ABSTRACT FROM AUTHOR]

The development of quantum machine learning (QML) has received a lot of interest recently thanks to developments in both quantum computing (QC) and machine learning (ML). One of the ML paradigms that can be utilized to address challenging sequential decision-making issues is reinforcement learning (RL). It has been demonstrated that classical RL can successfully complete many difficult tasks. A leading method of building quantum RL agents relies on the variational quantum circuits (VQC). However, training QRL algorithms with VQCs requires significant amount of computational resources. This issue hurdles the exploration of various QRL applications. In this paper, we approach this challenge through asynchronous training of QRL agents. Specifically, we choose the asynchronous training of advantage actor-critic variational quantum policies. We demonstrate the results via numerical simulations that within the tasks considered, the asynchronous training of QRL agents can reach performance comparable to or superior to classical agents with similar model sizes and architectures. [ABSTRACT FROM AUTHOR]

The Graph Partitioning Problem (GPP) is a classical combinatorial optimization problem that has been extensively researched. In recent years, many methods for solving the GPP have been proposed, which can be divided into direct partitioning approaches and iterative improvement approaches. Direct partitioning approaches directly give a complete partition of the input graph. Iterative improvement approaches require further adjustment of feasible solutions based on the result of direct partitioning approaches in order to obtain a better performance. In this paper, we summarize the recent trends in algorithms and applications for GPP. In addition, we propose a graph partitioning algorithm based on semi-supervised learning in combination with graph filtering methods. [ABSTRACT FROM AUTHOR]

The DBSCAN algorithm is a well-known cluster method that is density-based and has the advantage of finding clusters of different shapes, but it also has certain shortcomings, one of which is that it cannot determine the two important parameters Eps (neighborhood of a point) and Mints (minimum number of points) by itself, and the other is that it takes a long time to traverse all points when dataset is large. In this paper, we propose an improved method which is named as K-DBSCAN to improve the running efficiency based on self-adaptive determination of parameters and this method changes the way of traversing and only deals with core points. Experiments show that it outperforms DBSCAN algorithms in terms of running time efficiency. [ABSTRACT FROM AUTHOR]

In this present work, we study new algorithms to solve the split equality fixed-point problems for total quasi-asymptotically nonexpansive mappings in Hilbert spaces. In addition, we have established the convergence criteria for the proposed algorithms, at the end, we provided numerical results that justified our theoretical results. The results presented in this paper, provided a unified framework for studying this kind of problem involving different classes of mappings. [ABSTRACT FROM AUTHOR]

The number of research works on dynamic constrained optimization problems has been increasing rapidly over the past two decades. In this domain, many real-life decision problems need to be solved repeatedly with changing data and parameters. However, no research on dynamic problems with changes in the coefficients of the constraint functions has been reported. In this paper, to deal with such problems, a new evolutionary framework with multiple novel mechanisms is proposed. The new mechanisms are for (1) dealing with both linear and non-linear components in the constraint functions, (2) identifying the rate of change in the coefficients of the variables and (3) updating the population efficiently after every change occurs in the problem. To evaluate the performance of the proposed algorithm, we designed a new set of 13 dynamic benchmark problems, each of which consists of 20 dynamic changes and 3 different scenarios. The results demonstrate that the proposed algorithm significantly contributes in achieving good quality solutions, high feasibility rates and fast convergence in rapidly changing environments. In addition, the framework shows its capability of using different meta-heuristics to solve dynamic problems. [ABSTRACT FROM AUTHOR]

Penetration path planning for stealth unmanned aerial vehicles (SUAVs) in the integrated air defense system (IADS) has been a hot research topic in recent years. The present study examines penetration path planning in different threat environments. Firstly, for the complex terrain and static radar threats, a modified A-Star algorithm containing the bidirectional sector expansion and variable step search strategy is proposed to elude static threats rapidly. Then, with regard to bandit threats, the minimal radar cross-section (RCS) tactics are presented to achieve path replanning. Furthermore, the combinatorial methodology of the minimum RCS tactics and the modified A-Star algorithm is applied to achieve the dynamic path planning for SUAV. The simulation results indicate that the modified A-Star algorithm and minimal RCS tactics can significantly reduce the probability of radar system, which has better superiority in calculation efficiency, path cost and safety. And the minimal RCS tactics have better real-time performance and are more convenient in dealing with dynamic threats, which enhances the survivability of SUAV and verifies the effectiveness of the proposed methodology. • This paper presents a novel framework to settle dynamic path planning problem for stealth unmanned aerial vehicles. • A modified A-Star algorithm that adopts the bidirectional sector variable step search strategy. • The minimal radar cross-section tactics are convenient to deal with the bandit threats and enhance real-time performance. • The combinatorial methodology has better superiority in calculation efficiency, path cost and safety. [ABSTRACT FROM AUTHOR]

Internet Protocol version 6 (IPv6) is the latest version of IP that goal to host 3.4*1038 unique IP addresses of devices in the network. IPv6 needed a number of protocols such as the Address Auto-configuration scheme and Internet Control Message Protocol (ICMPv6), IPv6 is vulnerable to numerous attacks such as Denial of Service (DoS) and Distributed Denial of Service (DDoS), DDoS is one of the most dangerous attacks carried out through ICMPv6 messages that impose security and pecuniary implications. Therefore, an Intrusion Detection System (IDS) is a monitoring system of the security of a network that detects suspicious activities and deals with a massive amount of data comprised of repetitive and inappropriate features which affect the detection rate. A feature selection technique helps to reduce the computation time and complexity by selecting the optimum subset of features. This paper proposes a method for detecting ICMPv6 DDoS attacks using a modified Flower Pollination Algorithm (MFPA). The main purpose of the proposed method, first MFPA is to select the most relevant features from the ICMPv6 dataset to the detect ICMPv6 DDoS attacks. Second, an enhanced detecting DDoS flooding attacks model based on a multi-objective FPA has proposed. The results show that the first proposed method (MFPA) achieved the best accuracy equal to 97.96% with 10 features and the second proposed method Multi-Objective FPA achieved the best accuracy 97.01% with 5 features. [ABSTRACT FROM AUTHOR]

In recent years, urban population growth and the diversity of vehicles have increased. Location prediction in VANETs is extremely necessary for consumer applications such as routing, network management, knowledge dissemination protocols, and road cognition, among others. This could increase the performance of VANETs. In this paper a Kalman filter is used to predict the vehicle's future location. We conducted experiments exploitation each vehicle quality traces and model-driven traces. We quantitatively compare the prediction performance of a Kalman filter and neural network-based methods. This paper proposes a location prediction algorithm for nonlinear vehicular movement using an Extended Kalman filter (EKF). Evaluation of the ESCL-VNET algorithm with EKF assess the given better results. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid system is proposed for speech emotion recognition (SER). The algorithm in this paper adopts a two-stage design concept. In the first stage, we use the ensemble learning model random forest algorithm to obtain the importance of each feature. We use Emo-DB for experimental comparison and find that the combination of the logistic regression algorithm and the WBCS algorithm achieves best results. Cross-training method is used to ensure the features adapt to various situations. Under 100 training sets, the sentiment classification results are satisfactory. The proposed method is more accurate than state-of-the-art intelligent optimization dimensionality reduction algorithms. [ABSTRACT FROM AUTHOR]

Cyber-physical system (CPS) is the core technology of Industry 4.0. The deterministic behaviors of the CPS require real-time deterministic guarantee. Therefore, this paper improves the ant colony optimization (ACO) into a scheduling algorithm for time-triggered flows in time-sensitive network (TSN), a standard developed by the IEEE 802.1 Working Group that fully satisfies the strict end-to-end delay requirements of industrial applications. Simulation results show that the improved ACO (IACO) can schedule the time-triggered flows in the TSN excellently, and outperform the traditional ACO in convergence speed, optimization ability and the proneness to local optimum trap. To sum up, this paper provides an effective real-time guarantee for the TSNs. [ABSTRACT FROM AUTHOR]

• Roboadvisors discipline investors to become passive financial subjects. • Roboadvisors' opaque algorithms create greater investor uncertainty. • Automated investing may hamper financial literacy and education. • State-led initiatives may encourage further financialization of consumers. The burgeoning financial technology scene in Singapore has seen the emergence of robo-advisors, which aim to disrupt traditional financial advisories by using algorithms to automate client advising and investment recommendations. Using an ecologies concept to explore how lay investors are articulated into global financial networks through robo advisors, this paper contributes to studies on the "financialization of everyday life". It argues that investors are rendered passive by the disciplinary tools of algorithms, contemporary finance theories and elements of robo-advisor platforms that feed into these sociotechnological assemblages. The state's role in embedding citizen investors in these human-machine relationships is considered. The fragmented landscape of free, nonprofessional online financial advice and the opaque qualities of investing algorithms make investor subject formation incomplete and uncertain, especially when markets are highly volatile. This paper explores how both financial inclusion and exclusion operate simultaneously in robo-advisors and argues that robo-advisors may weaken efforts to promote financial literacy and education. [ABSTRACT FROM AUTHOR]

The demand for electricity is growing very fast; as a result, the entire power sector is facing a real problem of meeting the additional demand. Rigorous energy audit suggests the replacement of energy-efficient devices from standard one, operating with poor efficiency and consumes large power. 3-phase induction motor is widely used as driving power in most of the industries and it consumes almost 65% of the total power. The energy-efficient design of such motors saves a considerable amount of energy and reduces the cost of operation. In this paper, an attempt has been made to design energy-efficient induction motor from different perspective of using design and optimization without high-quality material. In this paper, the cost of yearly energy losses is considered as objective function and it is optimized to save energy and money as well. The design problem is a nonlinear constraint optimization problem, which involves many variables and constraints. Water Cycle Algorithm (WCA) is one of the most recently developed metaheuristic algorithm is taken for the optimization for the case study of 5 HP and 10 HP, 3- phase, Squirrel cage induction motor. The objective function is optimized by WCA and Genetic Algorithm and their result is compared for accuracy from cost and performance point of view. WCA found to be the most efficient tool to optimize the problem and helps to design an energy-efficient motor. [ABSTRACT FROM AUTHOR]

Negotiation is a core activity between stakeholders with different goals. This paper offers a solution based on the automated bilateral negotiation model using a recent meta-heuristic algorithm Owl Search Algorithm (OSA), and chaos theory. The proposed algorithm called Chaotic Owl Search Algorithm (COSA). This algorithm is used to adapt negotiation strategies for computing negotiation offers throughout the negotiation process. For this aim, a negotiation grasped between two parties during several negotiation rounds. The results of the proposed algorithm compared with the standard OSA, PSO and the most common negotiation tactics. Different control parameters considered for accurate judgments of the suggested optimization techniques. The comparative study proved that the COSA provides accurate results over compared algorithms in terms of Average buyers' /seller's utility, Average negotiation rounds and Average processing time. This paper is the first of integrating chaos theory with the OSA in optimization problems and especially in the negotiation process. [ABSTRACT FROM AUTHOR]

Aiming at the problems of single optimization strategy and poor comprehensive performance of MOFA, multi-objective firefly algorithm with adaptive region division is proposed in this paper. By leveraging the convergence index, our algorithm intelligently divides the dominant and non-dominant solution groups into three sub-regions, namely balance, exploration, and development areas, each with a distinct learning strategy that complements the strengths of fireflies. Specifically, fireflies in the balance area learn from global optimal particles with diversity to achieve a balanced exploration and development ability. Fireflies in the exploration area jointly learn from globally optimal particles with convergence and diversity, increasing the algorithm's likelihood of discovering Pareto optimal solutions. Lastly, fireflies in the development area rapidly converge under the guidance of the globally optimal particle of convergence, thus improving the algorithm's development ability. To further enhance the comprehensive optimization performance, we introduce a novel fusion index as an external archive update strategy that preserves solutions with superior convergence and diversity. Our experiments on 20 benchmark functions and a multi-objective optimization power flow example demonstrate that our algorithm outperforms other multi-objective optimization algorithms, highlighting its superior optimization performance. • This paper proposes a multi-objective firefly algorithm with adaptive region division. • Based on the idea of adaptive region division, the firefly population was divided into adaptive regions and regions, and multiple learning strategies were integrated. • Our algorithm has higher performance than the classical MOEA on instances of benchmarking functions and multi-objective optimization currents. [ABSTRACT FROM AUTHOR]

Recently, practitioners and researchers have concentrated on the use of meta-heuristics in the design of multi-objective supply chain networks. The number of publications in this field reflects this interest. The purpose of this paper is to propose a novel metaheuristic approach for designing supply chain network problems in the case of multi-objective supply chains. The proposed algorithm hybridizes three meta-heuristic approaches; simulated annealing, tabu search, and variable neighborhood algorithms. The proposed algorithm is also combined with a linear programming approach. The purpose of hybridization is to aggregate the approaches in order to benefit from the advantages of these solution algorithms. The features of these algorithms are investigated in this paper for the first time. The most useful characteristics of each algorithm are then utilized for developing the new algorithm. The performance of the proposed algorithm is compared with an exact algorithm, simulated annealing, and tabu search algorithms. The results indicated that the proposed algorithm is comparable to the exact in the case of small and medium-sized supply chain problems. The findings revealed that the proposed algorithm takes on an average of 6.3 min to solve small and medium problems, while the exact algorithm takes 412 min. Moreover, the proposed algorithm outperforms other algorithms with a mean ideal distance (MID) of 13,606,871, a percent of domination (POD) of 0.84, and a computational time of 15.64 min compared to the tabu search algorithm's MID of 15,574,523, a POD of 0.55, and a computational time of 21.46 min. The simulated annealing algorithm, on the other hand, achieved an average MID of 18,145,931, a POD of 0.40, and a computational time of 30 min. Furthermore, the findings showed that the proposed algorithm is capable of solving complex and large supply chain problems in a reasonable time when exact approaches fail. [Display omitted] • Developing a novel metaheuristic algorithm for solving the MOSC network. • Optimizing the proposed algorithm parameters using regression models. • Comparing the proposed algorithm with other algorithms. • Confirming the performance of the proposed algorithm for solving MOSC problems. [ABSTRACT FROM AUTHOR]

This paper presents a new training algorithm that can update the situation of layers' network, and therefore, connections, neurons, and firing rate of neurons based on FORCE (first-order reduced and controlled error) training algorithm. The Quantized Full FORCE algorithm (QFF) also updates the number of neurons and connections between different layers in the network per iteration in a way that the whole firing rate of each layer is updated via selecting the best neurons and combining strong features. The update method is sequential, so that with each instance passing through the network, the network structure is updated with the Full FORCE algorithm. The algorithm updates the structure of networks with a multiple/single middle layer of the supervised version of feed forward networks such as Multilayer perceptron (MLP), changing them into partially-connected networks. A combination of principal component analysis PCA and Linear Discriminant Analysis (LDA) algorithms has been used to cluster the network input features. The paper focuses on the deep supervised MLP network with backpropagation (BP) and various datasets and its comparison with other MLP based stat of art methods and hybrid evolutionary algorithms. We achieved 98.15 percent accuracy for facial expression 98.6 and 97.7 percent for Wisconsin breast Cancer and Iris Flower in respectively. The training algorithm employed in the study enjoys a lower computational complexity while yielding faster and more accurate convergence, starting with a very low level of errors of 0.009 in comparison with the full connection network and it solves the challenge of getting stuck in local minima and poor convergence of Gradient Decent with BP. • Providing the new training algorithm to update the connections and firing rate of neurons in each iteration. • The proposed training model is based on Quantized Full FORCE (first-order reduced and controlled error) training. • Providing an accurate framework to update the number of neurons, converting the network to a partial connection network. • In the new training model, the best features have the highest number of connections and neurons within the middle layers. • Being the decision speed of the network in the proposed method much faster than a fully connected network. • Cost-effectiveness and much lower resource requirements for implementation of deep networks on hardware such as FPGAs. [ABSTRACT FROM AUTHOR]