Search

Summary: Multi‐user multiple‐input multiple‐output (MU‐MIMO) system has the capability of delivering optimal system capacity that provides the simultaneous service to a large number of users using dirty paper coding (DPC) scheme. However, the DPC scheme is quite difficult to be implemented in the real‐time scenario as the computational complexity is very high and the process cannot be accomplished within the duration of few coherence periods. In this paper, we have adopted a newly developed binary spider monkey optimization (binary SMO) algorithm for the joint user and antenna scheduling (JUAS) problem to maximize the achievable system sum‐rate performance. It has been shown that JUAS with binary SMO achieves nearly 99% of system throughput achieved by the extensive search algorithm (ESA) using DPC. Also it is compared with binary flower pollination algorithm (binary FPA) to check which of the two gives better result. It is observed that the binary SMO in JUAS achieves a globally optimal solution quite rapidly, to remain well within the modern‐day packet data communication interval. The proposed binary SMO shows low computational complexity and computation time as compared to ESA (i.e., DPC). Also when it is compared with binary FPA, it shows quite a significant improvement in system throughput. Moreover, the effectiveness of binary SMO in the MU‐MIMO broadcasting scenario is verified through extensive simulation results. [ABSTRACT FROM AUTHOR]

One of the useful knowledge representation tools, which can describe the joint probability distribution between some random variables with a graphical model and can be trained by a dataset, is the Bayesian network (BN). A BN is composed of a network structure and a conditional probability distribution table for each node. Discovering an optimal BN structure is an NP‐hard optimization problem that various meta‐heuristic algorithms are applied to solve this problem by researchers. The genetic algorithms, ant colony optimization, evolutionary programming, artificial bee colony, and bacterial foraging optimization are some of the meta‐heuristic methods to solve this problem using a dataset. Most of these methods are applying a scoring metric to generate the best network structure from a set of candidates. A Fixed Structure Learning Automata‐Based (FSLA‐B) algorithm is presented in this paper to solve the structure learning problem of BNs. There is a fixed structure learning automaton for each pair of vertices in the BN's graph structure in the proposed algorithm. The action of this automaton determines the presence and direction of an edge between the vertices. The proposed algorithm performs a guided search procedure using the FSLA and escapes from local optimums. Several datasets are utilised in this paper to evaluate the performance of the proposed algorithm. By performing various experiments, multiple meta‐heuristic algorithms are compared with the introduced new one. The obtained results represented that the proposed algorithm could produce competitive results and find the near‐optimal solution for the BN structure learning problem. [ABSTRACT FROM AUTHOR]

This paper fuses ideas from reinforcement learning (RL), Learning from Demonstration (LfD), and Ensemble Learning into a single paradigm. Knowledge from a mixture of control algorithms (experts) are used to constrain the action space of the agent, enabling faster RL refining of a control policy, by avoiding unnecessary explorative actions. Domain‐specific knowledge of each expert is exploited. However, the resulting policy is robust against errors of individual experts, since it is refined by a RL reward function without copying any particular demonstration. Our method has the potential to supplement existing RLfD methods when multiple algorithmic approaches are available to function as experts, specifically in tasks involving continuous action spaces. We illustrate our method in the context of a visual servoing (VS) task, in which a 7‐DoF robot arm is controlled to maintain a desired pose relative to a target object. We explore four methods for bounding the actions of the RL agent during training. These methods include using a hypercube and convex hull with modified loss functions, ignoring actions outside the convex hull, and projecting actions onto the convex hull. We compare the training progress of each method using expert demonstrators, employing one expert demonstrator with the DAgger algorithm, and without using any demonstrators. Our experiments show that using the convex hull with a modified loss function not only accelerates learning but also provides the most optimal solution compared with other approaches. Furthermore, we demonstrate faster VS error convergence while maintaining higher manipulability of the arm, compared with classical image‐based VS, position‐based VS, and hybrid‐decoupled VS. [ABSTRACT FROM AUTHOR]

Summary: Distributed optimization algorithms have various advantages and wide applications, while the distributed nature also makes them flimsy in the face of external attacks. In this paper two Byzantine attack models are designed, in which the edge attack model is seldom considered before. A resilient distributed consensus algorithm based on the trusted nodes and edges is proposed to defend against the two attack models. The agreement and optimality of the proposed consensus algorithm are guaranteed with theoretical analysis. The simulation results and comparison experiments verify the proposed algorithm to be more effective than the compared one. In the perspective of attackers, which attack model is more recommended is also analysed based on the experiments. [ABSTRACT FROM AUTHOR]

To improve the state‐of‐the‐art works in breast cancer diagnosis, this paper proposes ensemble‐based deep‐transfer learning with classifiers namely optimizable K‐nearest neighbors, optimizable naïve Bayes, optimizable ensemble, and optimizable support vector machine algorithms for the auto‐feature extraction, detection, and severity classification of input mammograms. The hyperparameters of these classification algorithms are optimized by using the Bayesian optimization technique. The extracted robust features are normalized and then classified using the Bayesian optimized classifiers. Thus, the work throws a light of research on detecting whether the input mammogram is normal or abnormal. Afterward, it further focuses on the severity classification of abnormalities that is, benign or malignant. The aforesaid algorithms are trained and tested for the three‐class classification problem, thus achieving a maximum performance using the Bayesian optimized SVM algorithm applied with ResNet18 deep features providing classification accuracy of 99.689% for MIAS and 98.883% for INbreast dataset. [ABSTRACT FROM AUTHOR]

In this paper, an optimal collision‐free trajectory is developed based on the hybrid optimization algorithms for industrial robotic manipulators (IRMs). Three IRMs such as PUMA 560 (six degrees of freedom—6DOF), KUKA LBR iiwa 14 R820 (7DOF), and ABB IRB 140 (6DOF) are considered. The key objective is to enhance the smoothness and efficiency of manufacturing robots by optimum joint trajectory design using the seventh‐order polynomial function. The proposed approach is to solve both kinematics and trajectory planning problems by using the different combinations of the hybrid meta‐heuristic algorithms. The kinematic parameters including jerk, acceleration, and velocity mostly impact the travel smoothness of the robot end‐effector on the trajectory path. Therefore, these parameters are to be constrained for generating the collision‐free path. The endurance of velocity and acceleration can be obtained by reducing the jerk which leads to smooth robotic motion. The proposed work is executed using a robotic toolbox in MATLAB with a graphical user interface. The values of acceleration, velocity, and jerk are computed for the robot joints. Each robot obtained the minimum traveling time for without and with an obstacle which is 0.0118 and 0.0313 s for PUMA and 0.0117 and 0.0310 s for KUKA, and 0.0114 and 0.0120 s for ABB IRB 140 robot. From the experimental outcomes, the proposed scheme of the hybrid optimization algorithms is more effective for the trajectory planning of IRMs than that of other works. [ABSTRACT FROM AUTHOR]

Variational quantum algorithms (VQAs) have been successfully applied to quantum approximate optimization algorithms, variational quantum compiling and quantum machine learning models. The performances of VQAs largely depend on the architecture of parameterized quantum circuits (PQCs). Quantum architecture search (QAS) aims to automate the design of PQCs in different VQAs with classical optimization algorithms. However, current QAS algorithms do not use prior experiences and search the quantum architecture from scratch for each new task, which is inefficient and time consuming. In this paper, a meta quantum architecture search (MetaQAS) algorithm is proposed, which learns good initialization heuristics of the architecture (i.e., meta‐architecture), along with the meta‐parameters of quantum gates from a number of training tasks such that they can adapt to new tasks with fewer gradient updates, which leads to fast learning on new tasks. The proposed MetaQAS can be used with arbitrary gradient‐based QAS algorithms. Simulation results on variational quantum compiling (VQC) and quantum approximate optimization algorithm (QAOA) show that the architectures optimized by MetaQAS converge faster than a state‐of‐the‐art gradient‐based QAS algorithm, namely DQAS. MetaQAS also achieves a better solution than DQAS after fine‐tuning of gate parameters. [ABSTRACT FROM AUTHOR]

Parameter extraction of photovoltaic (PV) models based on measured current–voltage data plays an important role in the control, simulation, and optimization of PV systems. Despite the fact that various parameter extraction strategies have been dedicated to solving this problem, they may have certain drawbacks. In this paper, an effective hybrid optimization method based on adaptive rat swarm optimization (ARSO) and pattern search (PS) is presented for effectively and consistently extracting PV parameters. The proposed method employs the global search ability of ARSO and the local search ability of PS. The performance of the new algorithm is investigated using a set of benchmark test functions, and the results are compared with those of the standard RSO and some other methods from the literature. The extraction of parameters from several PV models, such as single‐diode, double‐diode, and PV modules, confirms the performance of the suggested method. Simulation results show that the proposed method surpasses other state‐of‐the‐art procedures in terms of accuracy, reliability, and convergence speed. [ABSTRACT FROM AUTHOR]

High penetration of Renewable Energy Sources into unbalanced distribution systems faces many challenges due to the uncertainty nature of both Renewable Energy Sources and loads as well as the unbalance degree of the distribution systems. This paper proposes the planning of Renewable Energy Sources in unbalanced distribution systems. Different types of Renewable Energy Sources, photo‐voltaic and Wind are considered. A multi‐objective optimisation problem is formulated using non‐dominated sort and crowing distance for multi objective hybrid algorithm that combines the merits of Particle Swarm Optimisation and Sine Cosine Optimisation algorithms. Three objectives, improving voltage profile, power losses minimisation, and minimisation of voltage unbalance, are considered. The proposed method determines the optimal Renewable Energy Sources' specifications such as site/size/type of distributed generators, number of photo‐voltaic modules or wind turbines in each distributed generator and their power factor and connection phases. Also, it determines the optimal setting of substation tap changer and system voltage regulators. Moreover, both Renewable Energy Sources and loads uncertainty are considered and modelled using Monte Carlo simulations. An improved matrix‐based backward–forward load flow method is developed by using coefficient matrices. The proposed procedure is conducted on IEEE 13‐node, 37‐node, and 123‐node unbalanced distribution systems. The proposed algorithm results compared with individual optimisers show significant performance improvements. The optimal plans resulted by using the proposed hybrid algorithm achieve a reduction in power losses that reached 89% in some cases. Also, the system unbalance index is reduced with a ratio reached 34%. Large improvement in the system voltages profile all over the year is achieved as the system voltage profile index is reduced by a ratio reached 70%. [ABSTRACT FROM AUTHOR]

Salp swarm algorithm (SSA) is one of the efficient recent meta‐heuristic optimization algorithms, where it has been successfully utilized in a wide range of optimization problems in different fields. In the research process, it is found that it is very difficult to maintain the balance between the exploration and exploitation capabilities of a certain algorithm. Therefore, one of the main purposes of this article is to provide an algorithm that can intelligently balance between exploration and exploitation, so that it can balance exploration and exploitation capabilities. Later, in the research process, it was found that the sine and cosine function and the salp foraging trajectory have a high mathematical similarity, which greatly improves the optimization ability of the algorithm. In addition, the variable neighbourhood strategy can appropriately expand the optimization range of the algorithm. So in this paper, a novel golden sine cosine salp swarm algorithm with variable neighbourhood search scheme (GSCSSA‐VNS) is proposed, the another objective of proposing this algorithm is as a new optimization method for shape matching. As a relatively new branch, atomic potential matching (APM) model is inspired by potential field attractions. Compared to the conventional edge potential function (EPF) model, APM has been verified to be less sensitive to intricate backgrounds in the test image and far more cost effective in the computation process. Experimental results of four realistic examples show that GSCSSA‐VNS is able to provide very competitive results and outperforms the other algorithms. [ABSTRACT FROM AUTHOR]

Rationale: Ion mobility spectrometry (IMS) is a powerful analytical tool extensively applied in numerous domains. However, there still exists the phenomenon of peaks overlapping in the analysis of isomers with similar structures due to the limited resolution of IMS. In this paper, a dynamic inertia weight particle swarm optimization (DIWPSO) algorithm combined with second-order differentiation is proposed to separate the IMS overlapping peaks efficiently and precisely. Methods: It can identify the component number of overlapping peaks and limit those parameters (ion mobility, intensity, and full-width at half maximum of each single peak) of the peak model in a small range using second-order differentiation. Based on this, DIWPSO that has been set the best operating parameters is capable of accurately separating IMS overlapping peaks to identify the compound within a short time. Results: A comparison between the performance of DIWPSO and the improved particle swarm optimization (IPSO) found that DIWPSO with separation errors less than 2.34% overall outperforms IPSO whose maximum error is up to 5.58%. Moreover, the running time of DIWPSO is 30-80 times less than that of IPSO, and DIWPSO exhibits stronger robustness. Conclusions: This method can automatically identify the component number of IMS overlapping peaks and resolve them with muticomponents and different overlapped degrees rapidly and accurately, which further improves the structural resolution of IMS. [ABSTRACT FROM AUTHOR]

Summary: The increased usage of Internet of Things (IoT) applications in several areas, like healthcare, agriculture, and business, has aggravated mobile traffic issues to a large extent. The deployment of 5G technology has resulted in increased traffic globally. These coherent devices, on the other hand, use the internet to fine‐tune the quality of service in order to provide scalability, anonymity, and accessibility. Despite its numerous virtues, it is bound to encounter issues with interference management, fairness, throughput, and computational complexities. In this paper, a novel Multi‐Objective Gradient‐based African Buffalo Optimization (MOGABO) algorithm is developed to handle proportional fairness scheduling, improve interference management, increase throughput, and reduce computational complexities in cellular communication systems, particularly device‐to‐device (D2D) communication. The simulation analysis is done against other approaches such as the Hungarian technique, DDDPG technique, heuristic technique, and SC‐FDMA technique demonstrates that this method has improved system fairness over the existing approaches. Our method maximizes throughput, and for 500 UE, the throughput is 10.4 Mbps, with an average queuing delay of 24 ms. As a result, when compared to the existing method, MOGABO method offers a 1.2% increase in throughput. Thus, our method offers better coverage and throughput for D2D cellular communication with the reduction of computational complexities. [ABSTRACT FROM AUTHOR]

Summary: Crowdsourcing is now one of the most important and transformative paradigms, with great success in a variety of application tasks. Crowdsourcing obtains knowledge and information to solve cognitive or intelligence‐intensive tasks from an evolving group of participants via the Internet. Unfortunately, providing a hard privacy guarantee and query optimization is incompatible when a higher task acceptance rate needs to be accomplished and this case is common in most existing crowdsourcing solutions. The state of art systems suffered from different complexities such as lack of crowdsourcing optimization techniques, increased cost, latency, security, and scalability issues. In this paper, we have proposed a crowdsourcing model to optimize the cost and latency, issues that occur while query optimization using the Moth Flame and Tunicate Swarm Algorithm (MF‐TSA). The TSA algorithm is added to the MF algorithm to enhance its exploitation capability and yield fast convergence. The data privacy concerns of the worker and the requestor are addressed using homomorphic encryption that simultaneously enhances the efficiency of the crowdsourcing framework. The main aim of this work is to optimize the cost and latency for query plan selection along with security. Initially, the homomorphic encryption model is used to encrypt the data. In query design, two kinds of crowd‐controlled administrators, that is, Crowd Powered Selection (CSelect) and Crowd Powered Join (CJoin) are connected for assessing query. The proposed framework utilizes MF‐TSA to optimize the selection and join queries with low cost and latency. Finally, the experimental results demonstrate better query optimization performance than other existing algorithms such as sequential, parallel, and CrowdOp. [ABSTRACT FROM AUTHOR]

Fourier ptychography is a new type of computational imaging technology, which uses a stack of low‐resolution images obtained from overlapped apertures (or equivalent) to reconstruct super‐resolved image. However, the accuracy of the aperture position will directly affect the quality and resolution of the reconstructed image. This paper proposes a new perspective for FP positional deviations correction using the neural network. We construct a trainable neural network to perform positional deviations correction along with object reconstruction. The real part and imaginary part of the object as well as the different and irregular positional deviations of each aperture are set as the weights of convolutional layer. The gradients over these weights are computed automatically, and gradient‐based optimization algorithm is employed to recover the object and find the correct aperture position. Simulation and experiment are performed to verify our algorithm. The results show that the proposed algorithm can accurately find the aperture position and improve the reconstruction quality. [ABSTRACT FROM AUTHOR]

Different nature‐inspired meta‐heuristic algorithms have been proposed to solve optimization problems. One of these algorithms is called social spider optimization (SSO) algorithm. Spiders' natural behaviors have inspired them to find the bait position by detecting vibrations in their web. Although the SSO algorithm has good accuracy in achieving optimal solutions, it suffers from a low convergence rate. In this paper, we attempted to improve SSO by changing its motion and mating parameters. To provide a practical example of using the new proposed algorithm, we based it on multi‐objective opposition‐based SSO, named MOPSSO. We used this algorithm in a feature selection process for analyzing text psychology, which is a multi‐objective problem. Textual psychology analysis is used in various fields, including collecting and analyzing people's views on various products, topics, social and political events. After selecting features, in order to classify the text, we used a new hybrid method that hybrids fuzzy C‐MEANS data clustering technique, a decision tree (DT), and Naïve Bayes (NB). Experimental results show that the improved SSO algorithm performs better than SSO, social spider algorithm, and CMA‐ES algorithms. Additionally, the performance of the proposed hybrid classification method is better than those of NB and DT. [ABSTRACT FROM AUTHOR]

Summary: Cloud computing is the current computing standard, which provides information technology (IT) services over the Internet on demand. In the cloud environment, a task is mapped with an available resource to attain a good result. Task scheduling is the technique that is used to allocate tasks on virtual machines (VMs) of a server based on its capacity of workload. Tasks are scheduled to the server in such a way to minimize traffic and time delay. Particle swarm optimization (PSO) is the best existing algorithm used to schedule a task to an existing resource on the environment of the cloud. By PSO, the task is scheduled for an existing resource to reduce computational cost. In this paper, a hybrid swarm optimization (HSO) algorithm, which is the combination of PSO and salp swarm optimization (SSO), is proposed to resolve task scheduling issues in the cloud environment. The main goal of HSO is to schedule the task to the available resource in such a way to reduce the execution time and computation cost. Multilayer logistic regression (MLR) is an approach used to detect the overloaded VMs, so that a task can be scheduled to a VM according to its capacity of workload. The proposed HSO algorithm with MLR is simulated on the cloudsim toolkit, and the results reveal the efficiency of the proposed algorithm in terms of cost, execution time, and makespan. Compared to the existing algorithms such as the genetic algorithms (GAs), the improved efficiency evolution (IDEA), and the PSO, the proposed algorithm reveals superiority in terms of efficiency, resource utilization, and speed. [ABSTRACT FROM AUTHOR]

In the existing mobile edge computing (MEC) environment, edge servers have limited computing power and cannot process data in real time. To solve this problem, this paper proposes a task segmentation and computing offloading algorithm for mobile edge computing (MEC). Firstly, the computing tasks of mobile terminals are segmented under the network framework of cloud‐side‐device collaboration, and a task offloading optimization model is designed to minimize the total delay of mobile devices. Secondly, the computing resource allocation parameters and action space parameters are discretized, and a computing offloading algorithm based on Deep Q Network (DQN) is proposed. The algorithm extracts feature from high‐dimensional data and uses deep neural network to estimate Q‐value of actions to maximize the summation of system delays. Finally, simulation experiments show that when the cloud computing capacity is 7 × 1011 central processing unit (CPU) cycle/s, the total delay of proposed algorithm is only 1.116 s, while the total delays of comparison algorithms are 1.251 s and 1.193 s, respectively. Therefore, compared with the comparison algorithm, the proposed algorithm can better reduce the total system delay. [ABSTRACT FROM AUTHOR]

To reduce the short‐term load forecasting (STLF) error of off‐line forecasting model, a VMD‐IWOA‐LSTM (VIL) method for STLF is proposed. Firstly, variational mode decomposition (VMD) is used to decompose the historical power load signals. Then, the decomposed signals are reconstructed according to the similarity of Pearson correlation coefficient (PCC), and meteorological data are chosen for each reconstructed component based on the set PCC threshold. The long short‐term memory (LSTM) models are used to predict the corresponding components, and improved whale optimization algorithm (IWOA) is used to optimize the parameters in LSTM. Finally, the forecast results of each component are added together to get the final forecast result. The experimental results of power load data in a certain area show that the proposed method has the advantages of strong anti‐interference performance and high prediction accuracy compared with other methods, and has strong practicability. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Stochastic gradient descent algorithm is a classical and useful method for stochastic optimisation. While stochastic gradient descent has been theoretically investigated for decades and successfully applied in machine learning such as training of deep neural networks, it essentially relies on obtaining the unbiased estimates of gradients/subgradients of the objective functions. In this paper, by constructing the randomised differences of the objective function, a gradient‐free algorithm, named the stochastic randomised‐difference descent algorithm, is proposed for stochastic convex optimisation. Under the strongly convex assumption of the objective function, it is proved that the estimates generated from stochastic randomised‐difference descent converge to the optimal value with probability one, and the convergence rates of both the mean square error of estimates and the regret functions are established. Finally, some numerical examples are prsented. [ABSTRACT FROM AUTHOR]

Recent trend indicates that the assessment of low complexity is crucial for an effectual design of digital filter. Earlier the existing algorithms solely focused on reducing the pass band ripples and the stop band ripples in spite of the requirement of low implementation complexity in finite impulse response (FIR) filter design. In this regard, the optimization‐based FIR filter using multiobjective improved Salp swarm optimization algorithm have been designed. The proposed method not only minimizes the ripples of pass band and stop band but also minimizes the transition band, number of sparsity, which is used to implement a FIR filter that abides the specified frequency. The nondominated solution of filter design has a set of an optimum solution as pareto front that maintains the trade‐off between the various specifications. The designed FIR filter has been compared with other reported method to validate the applicability of the proposed method. The evaluation and analysis have been performed regrading minimum pass band ripples, minimum stop band ripple, minimum transition band, and implementation complexity. To prove the practical applicability of the proposed method, the designed FIR filters have been implemented in Xilinx ISE14.7 (Virtex‐VII) environment. The comparison result shows that the proposed method performs better than all other reported method in achieving minimum ripples and implementation complexity. [ABSTRACT FROM AUTHOR]

Cloud computing is a rapidly evolving computational technology. It is a distributed computational system that offers dynamically scaled computational resources, such as processing power, storage, and applications, delivered as a service through the Internet. Virtual machines (VMs) allocation is known as one of the most significant problems in cloud computing. It aims to find a suitable location for VMs on physical machines (PMs) to attain predefined aims. So, the main purpose is to reduce energy consumption and improve resource utilization. Because the VM allocation issue is NP‐hard, meta‐heuristic and heuristic methods are frequently utilized to address it. This paper presents an energy‐aware VM allocation method using the improved grey wolf optimization (IGWO) algorithm. Our key goals are to decrease both energy consumption and allocation time. The simulation outcomes from the MATLAB simulator approve the excellence of the algorithm compared to previous works. [ABSTRACT FROM AUTHOR]

Nature‐inspired optimization algorithms especially those based on the hunting behaviors of the creatures assume that the hunting operations are performed in a safe environment. However, generally, there are threats in real‐life for the hunter‐animals. This paper focuses on these threat factors and proposes that they can be used to improve the searching abilities of the algorithms. Gray wolf optimization (GWO) algorithm was selected to present the proposed approach and it was assumed that there was a mountain lion as the threat factor living in the same habitat with the wolf pack. The relations between the two predators were modeled and used to improve the performance of the algorithm. Five experiments were conducted to test the performance of the proposed method and the results were compared with the GWO and four optimization algorithms from the literature. It is shown that the proposed algorithm obtained best results for 21 of the 50 benchmark functions, while its closest competitor achieved the best results for 16 functions. Besides, the results of the Wilcoxon signed‐rank test indicated that the proposed method is superior to all other methods. In addition, it was shown that the threat factor approach does not cause a significant increase in the processing time. [ABSTRACT FROM AUTHOR]

Plant leaves play an important role in the diagnosis of plant diseases. Losses from such diseases can have a significant economic as well as environmental impact. Thus, examination of leaves into a healthy or infected carries substantial importance. An improved artificial plant optimization (IAPO) algorithm using machine learning has been introduced that identifies the plant diseases and categorize the leaves into healthy and infected on a private dataset of 236 images. Features are extracted from the images using histogram of oriented gradients (descriptor). The concepts of artificial plant optimization are then applied to study the features of healthy leaves using IAPO. A machine learning algorithm has been created to make the model adaptive with varied datasets. The degree of infection is eventually computed, and the leaves with infection greater than a certain calculated threshold are classified as infected leaves. The results show that IAPO can be used for classification of infected and healthy leaves and this algorithm can be generalized to solve problems in other domains as well. The proposed IAPO is also compared with other classification algorithms including k‐nearest neighbours, support vector machine, random forest and convolution neural network that show accuracies of 78.24%, 83.48%, 87.83%, and 91.26%, respectively, whereas IAPO shows quite accurate results in classification of leaves with an accuracy of 97.45% on training set and 95.0% accuracy on test set. [ABSTRACT FROM AUTHOR]

Summary: In the fields of wireless communication and data processing, there are varieties of mathematical optimization problems, especially nonconvex and nonsmooth problems. For these problems, one of the biggest difficulties is how to improve the speed of solution. To this end, here we mainly focused on a minimization optimization model that is nonconvex and nonsmooth. Firstly, an inertial Douglas–Rachford splitting (IDRS) algorithm was established, which incorporate the inertial technology into the framework of the Douglas–Rachford splitting algorithm. Then, we illustrated the iteration sequence generated by the proposed IDRS algorithm converges to a stationary point of the nonconvex nonsmooth optimization problem with the aid of the Kurdyka–Łojasiewicz property. Finally, a series of numerical experiments were carried out to prove the effectiveness of our proposed algorithm from the perspective of signal recovery. The results are implicit that the proposed IDRS algorithm outperforms another algorithm. [ABSTRACT FROM AUTHOR]

In the application of moving horizon estimation (MHE) algorithm, the window length will affect the estimation accuracy and the computing efficiency. For this kind of problem, a method of parameter optimization is proposed to obtain suitable window length. Firstly, in order to facilitate online solution, the optimization problem involved in the algorithm is transformed into a quadratic programming (QP) problem in matrix form. Secondly, for the time index and the estimated residual index that measure different properties, the normalization idea is adopted to incorporate them into the same dimension to design the fitness function, and a genetic optimization algorithm based on simulated annealing mechanism is given to search for the optimal window length. Finally, the proposed parameter optimization method is verified by two cases. The results show that the parameter optimization method has the advantages of excellent local search ability and sufficient convergence, and the window length obtained by this method can better take into account the two performance indexes of the MHE algorithm and improve the estimation performance. [ABSTRACT FROM AUTHOR]

There has been a growing interest in the cooperative communication of power line and wireless dual‐medium, due to the promising transmission quality and immense flexibility of the network. However, under the condition of hybrid fading and impulsive noise, the theoretical analysis of two‐way relaying communication with power line and wireless is difficult because of the lack of closed analytical expressions. In this study, the authors propose a relaying signal processing method based on Log Likelihood Ratio information estimation for two‐way relaying systems; and a power allocation optimisation algorithm based on Q‐learning, which can adaptively select the appropriate transmission power to maximise the mutual information. More precisely, the ϵ ${\epsilon}$‐greedy strategy is adopted for the estimated forwarding protocol and the transmission power of each node is adjusted to determine the optimal power allocation factor. The performances such as mutual information and outage probability are analysed and compared and the simulation shows that the algorithm is reliable and effective. [ABSTRACT FROM AUTHOR]

Considering that the evolution operators of common optimization algorithms such as genetic algorithm has a poor convergence speed and solution accuracy in the interior ballistic performance optimization of artillery, an improved firefly algorithm is selected for the interior ballistic performance optimization of cased telescoped ammunition (CTA). It is applied to the interior ballistic mathematical model of CTA to carry out single‐objective optimization and multi‐objective optimization respectively. The results show that in the single‐objective optimization, the muzzle velocity obtained by using the improved firefly algorithm is larger than other commonly used optimization algorithms. Under the constraints of maximum chamber pressure and relative burnout point, the muzzle velocity can be increased by about 30 m/s. In the multi‐objective optimization, three sub‐objectives of muzzle velocity, ballistic efficiency and muzzle pressure are considered respectively, and the multi‐objective firefly algorithm is applied to comprehensively optimize the interior ballistic performance of CTA. Then, the results are compared with the commonly used multi‐objective optimization algorithms, such as non‐dominated sorting genetic algorithm version II (NSGA‐II) and non‐dominated sorting genetic algorithm version III (NSGA‐III), the solution results are a series of Pareto optimal solutions. The obtained optimization results improved the interior ballistic performance and launch safety, providing reference for the reasonable matching of charge structure parameters and the selection of optimization algorithm upon the interior ballistic performance optimization of CTA to some extent. [ABSTRACT FROM AUTHOR]

Summary: Massive multiple input multiple output (M‐MIMO) methods make reference to a useful method for using multipath propagation to communicate and receive multiple data signals at once over a single radio channel. To simultaneously transfer numerous data streams, it makes use of various antennas. The quantity of power used grows as the quantity of antennas rises. As a result, choosing the best transmit antennas, which is a major difficulty in M‐MIMO systems, becomes important. In this research, "Hybrid Sea Lion‐Whale Algorithm (HS‐WA)" is introduced by choosing a best transmit antenna while taking into account several objectives. This method optimizes overall capacity and efficiency. The chosen method combines the "Whale Optimization Algorithm (WOA) and Sea Lion Optimization Algorithm (SLnO)" that determines which antenna should be chosen while also optimizing the antenna quantity. Finally, energy efficiency (EE) and capacity analysis results demonstrate that the provided approach is superior to all other models. [ABSTRACT FROM AUTHOR]

Summary: Scientific and technological advancements lead to the continuous generation of a large amount of data. These datasets are analyzed computationally to reveal patterns and trends. While the presence of noisy and irrelevant features or attributes in these datasets is unavoidable, they negatively impact the performance of classification techniques. Feature selection is a method to pre‐process these datasets by selecting the most informative features while concurrently improving the classification accuracy. Recently, several metaheuristic algorithms were employed in this feature selection process, including particle swarm optimization (PSO). PSO is prominent in the field of feature selection due to its simplicity and global search abilities. However, it may get stuck in local optima. To solve this problem, a new update mechanism in PSO is proposed and the PSO is hybridized with a local search method. To evaluate the performance of the proposed algorithm, benchmark datasets from the University of California in Irvine (UCI) repository were utilized, the k‐nearest neighbor as the classifier. Results show that the proposed feature selection technique outperforms other optimization algorithms on these feature selection problems. [ABSTRACT FROM AUTHOR]

The routing process in WSN needs to be more secure and safe, thus a secure routing process is carried out in this research, where the source node transmits packet simultaneously to destination. WSN nodes are simulated initially, and then the optimal cluster head (CH) from the entire nodes are selected. Here, CH selection is done with the developed Fractional Artificial Lion algorithm (FAL) method. The proposed FAL approach is introduced by combining fractional Calculus, Lion Optimization Algorithm (LOA), and the Artificial Bee Colony (ABC). Moreover, the fitness parameters, like delay, energy, distance, and link lifetime (LLT) where the minimal distance is chosen as the best path. Consequently, route maintenance is done after the secure routing. Moreover, the performance of devised FAL is compared with various performance metrics, like several alive nodes, energy, distance, and throughput. The developed FAL approach obtains a maximal alive node of 45, a minimal distance of 9.29 m, maximal energy of 0.14 J, and maximal throughput of 92.25%. [ABSTRACT FROM AUTHOR]

In this study, the joint design of discrete phase transmit sequences and receive filters with the low peak sidelobe level and integrated sidelobe level in radar systems is considered. The problem is formulated as a minimisation of the peak (integrated) sidelobe level, forcing a unimodular discrete phase constraint at the design stage. To deal with the resulting non‐convex and in general the NP‐hard optimisation problem, an iterative method based on the alternate optimisation approach is proposed. Each iteration of the proposed method involves a non‐convex min–max problem to be solved. In addition, a sequential rank‐one constraint relaxation framework is proposed to initialise the procedure, each iteration of which requires the solution of a convex problem. Simulation results show that using the proposed framework for jointly finding transmit sequences and receive filters leads to a better peak sidelobe ratio and integrated sidelobe ratio for discrete phase sequences than the optimal mismatched filters design approach. [ABSTRACT FROM AUTHOR]

Detection and accurate position estimation have become an essential task for any static underwater acoustic sensor networks. Many localization schemes have been introduced in the field of terrestrial WSN over the last few decades. These schemes are still not perfectly realizable in a harsh underwater environment due to their erroneous communication channel and infrastructure‐less environment. Limited localization coverage, propagation error, and accuracy are the major drawbacks in acoustic communication. This article proposed an adaptive virtual anchor node based on the improved shortest path algorithm with PSO technique. The main advantages of this proposed scheme are divided into two parts. First, introducing an enhanced shortest path algorithm can reduce the propagation error generated through multi‐hop zigzag movement and improve the coverage. Second, the particle swarm optimization algorithm with virtual anchor nodes can significantly enhance the accuracy by reducing the errors to localize the unknown nodes. Investigational results manifest that the proposed methodology performed better than the Improved DV‐Hop +PSO, IRL‐WOA, and basic DV‐Hop methods as far as their restriction. The proposed method improved 23%, 30%, and 35% better localization error, 10%, 15%, and 22% better relative localization error, and 10%, 18%, and 25% better accuracy respectively. [ABSTRACT FROM AUTHOR]

Retrieving the relevant information from the high‐dimensional dataset enhances the classification accuracy of a predictive model. This research critique has devised an improved marine predator algorithm based on opposition learning for stable feature selection to overcome the problem of high‐dimensionality. Marine predator algorithm is a population‐based meta‐heuristics optimization algorithm that works on the 'survival‐of‐the‐fittest' theory. Classical marine predator algorithm explores the search space merely in one direction, affecting its converging capacity while being responsible for stagnation at local minima. The proposed opposition‐based learning nuances enhance the exploration capacity of marine predator algorithm and productively converges the model to global optima. The proposed OBL‐based marine predator algorithm selects stable, substantial elements from six different high‐dimensional microarray datasets. The performance of the proposed method is investigated using five predominantly used classifiers. From the result, it is understood that the proposed approach outperforms other conventional feature selection techniques in terms of converging capability, classification accuracy, and stable feature selection. [ABSTRACT FROM AUTHOR]

We propose optimisation based algorithm using wavelet decomposition for segmentation of echocardiography images. The objective of the proposed method is to find an optimal threshold value for segmentation. This threshold value is used for separating the left ventricle by segmenting wavelet decomposed coefficients. The proposed method evaluates the optimal value of threshold using a nonlinear derivative free optimising algorithm. Its objective function is the contrast property of GLCM. The contrast would be highest at the correct position of the boundary between image regions. Accordingly, optimization task is formulated as a maximization problem. The proposed method is an iterative process for finding optimum threshold. Segmentation is carried out using this optimised threshold value. Further, the exact left ventricle contour is extracted using morphological operations and user provided location input. The proposed method is observed to be performing better and found to have 94% accuracy compared to ground truth labels. [ABSTRACT FROM AUTHOR]

Summary: In the Internet of Things (IoT) scenario, the integration with cloud‐based solutions is of the utmost importance to address the shortcomings resulting from resource‐constrained things that may fall short in terms of processing, storing, and networking capabilities. Fog computing represents a more recent paradigm that leverages the wide‐spread geographical distribution of the computing resources and extends the cloud computing paradigm to the edge of the network, thus mitigating the issues affecting latency‐sensitive applications and enabling a new breed of applications and services. In this context, efficient and effective resource management is critical, also considering the resource limitations of local fog nodes with respect to centralized clouds. In this article, we present FPFTS, fog task scheduler that takes advantage of particle swarm optimization and fuzzy theory, which leverages observations related to application loop delay and network utilization. We evaluate FPFTS using an IoT‐based scenario simulated within iFogSim, by varying number of moving users, fog‐device link bandwidth, and latency. Experimental results report that FPFTS compared with first‐come first‐served (respectively, delay‐priority) allows to decrease delay‐tolerant application loop delay by 85.79% (respectively, 86.36%), delay sensitive application loop delay by 87.11% (respectively, 86.61%), and network utilization by 80.37% (respectively, 82.09%), on average. [ABSTRACT FROM AUTHOR]

The particle swarm optimization (PSO) and the whale optimization algorithm (WOA) are two admired optimization methods that have drawn various researchers' attention. The PSO implements some particles' intelligent movements in a search space, and the WOA is originated based on the hunting mechanism of humpback whales. The PSO and WOA have different strategies for moving towards the optimum solution. Nevertheless, both algorithms' performances encounter several problems, such as premature convergence and falling in local optimums. Several approaches have been proposed to enhance meta‐heuristic algorithms' performance, such as applying the chaotic maps, adding mathematical or stochastic operators or local searches, and hybridizing the algorithms. In this article, a new hybrid algorithm denoted as chaotic‐based hybrid whale and PSO has been presented by improving the WOA, combining it with PSO, and using the chaotic maps. The hybrid algorithm has significantly more diverse movements than both of the mentioned algorithms. Therefore, it explores different regions of a problem's search space more precisely and avoids local optima. The roulette wheel selection operator has also been applied based on their fitness value to select the proposed algorithm's search agents and exploit promising regions of the search space. In the hybrid algorithm, the chaotic maps have been applied to initialize the whales' population, particles of the particle swarm, and adjust motion parameters to increase population diversity. The multi‐swarm version of the proposed algorithm with higher performance than the single‐swarm version and other methods has been introduced in this article too. The proposed algorithms have been evaluated using 23 mathematical benchmark functions, including unimodal, multimodal, and composite functions and four engineering optimization problems. The obtained results and statistical tests prove that the proposed algorithms provide competitive solutions for most of the experiments, compared to the state‐of‐the‐art and well‐known optimization meta‐heuristic methods in terms of convergence towards the global optimum, local optima avoidance, exploration, and exploitation. [ABSTRACT FROM AUTHOR]

Considering structural strength and castability in topology optimization is very attractive from the perspective of theory and application. This article introduces stress considerations into casting‐oriented topology optimization to explore structural optimization methods that simultaneously consider the above two vital design indicators. Two stress‐related topology optimization formulations for castable design are proposed and assessed systematically, namely, a compliance minimization with stress and casting constraints and a stress minimization with casting constraint. An effective optimization algorithm is developed to overcome various numerical difficulties caused by stress and castability issues in the solution. Particularly, a nonuniform threshold scheme along with the corresponding implementation algorithm is proposed to improve the casting constraint on irregular structures without appreciably increased computational effort. Benchmark examples are presented to discuss the numerical characteristics of the achieved designs and demonstrate the effectiveness of the introduced algorithms. This research illustrates the necessity and feasibility of stress considerations in casting‐oriented topology optimization. The results show that it is more appropriate to treat stress as a constraint rather than an optimization objective in the casting‐constrained topology optimization. The proposed formulations and algorithms allow designers to effectively achieve high‐performance castable designs with required structural strength requirements. [ABSTRACT FROM AUTHOR]

Summary: VANET routing is a serious concern due to some of the limitations in terms of routing costs. More research has already worked on VANET routing strategies for enhancing the performance of the network. However, optimal route selection is a tedious or complex issue in this scenario. To cope with this issue, this research work attempts to introduce a new VANET routing model that considers certain network quality measures such as congestion, travel, collision, and QoS awareness cost. A new cost model is designed based on the given constraints. Along with this, the fuzzification of the QoS factor is considered along with the total routing cost. This work determines the optimal route selection with minimized routing cost by employing a novel optimization algorithm called Rider Integrated Cuckoo Search (RI‐CS) that hybridizes the concept of Rider Optimization Algorithm (ROA) and Cuckoo Search (CS). Finally, the performance of the proposed RI‐CS is analyzed against the conventional models like Particle Swarm Optimization (PSO), Firefly algorithm (FA), Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WAO), ROA, CS, Mean Computing Jaya Algorithm (MC‐JA), and Grey Updated Butterfly Operator (GU‐BO) in terms of certain cost analysis. [ABSTRACT FROM AUTHOR]

It is common in algorithm courses to assess the correctness of algorithms via testing as well as conducting experiments to measure their run‐time performance. However, two severe problems must be addressed: both activities are conducted using different procedures and tools, and algorithm assessment systems do not support well optimization problems due to their unique characteristics. Given the relevant role of optimization algorithms in computing, we present a unified framework to support experimentation with both criteria, that is, optimality and efficiency. The contributions of the article are twofold. First, we present a unified framework to experiment with both criteria, by using explicit principles and by presenting its instantiation in the AlgorEx system. The homogeneous treatment of optimality and time efficiency contributes to smoother integration of experimentation into a course syllabus and to easier adoption of the system. Second, we present our experience in several academic years in an algorithm course. Initially, it was noticed that students had severe difficulties dealing with experimentation, but their academic performance sharply increased by fully integrating experimentation along the complete course. The article also identifies some opportunities for extension in AlgorEx. [ABSTRACT FROM AUTHOR]

Long-term monitoring of fetal heart is vital for early clinical diagnosis and timely treatment of fetus. However, the collected signals from the abdomen of the pregnant woman are always corrupted by many interfering sources, most significantly affected by the maternal electrocardiograph (ECG). Similar with blind source separation (BSS), fetal ECG extraction can be considered as the separation of fetal ECG from the recordings. This letter proposes a novel multi-layer polynomial network to extract the fetal ECG waveform, where the non-linear mixing process is approximated with multiple polynomials. The network starts with the first-order polynomial layer, and further requirements to decrease the error between the output and target signal is achieved by increasing the number of layers. The proposed approach turns the inverse transformation of traditional BSS into a model learning problem, which is then solved by a simple convex optimization algorithm. Compared with the state-of-the-art BSS methods, experimental results show that the proposed method has better performance. [ABSTRACT FROM AUTHOR]

For the scenario where the overall layout is known and the obstacle distribution information is unknown, a dynamic path planning algorithm combining the A* algorithm and the proximal policy optimization (PPO) algorithm is proposed. Simulation experiments show that in all six test environments, the proposed algorithm finds paths that are on average about 2.04% to 5.86% shorter compared to the state‐of‐the‐art algorithms in the literature, and reduces the number of training epochs before stabilization from tens of thousands to about 4000. [ABSTRACT FROM AUTHOR]