Search

Cardiovascular diseases (CVD) are a leading cause of mortality globally, necessitating the development of efficient diagnostic tools. Machine learning (ML) and metaheuristic algorithms have become prevalent in addressing these challenges, providing promising solutions in medical diagnostics. However, traditional ML approaches often need to be improved in feature selection and optimization, leading to suboptimal performance in complex diagnostic tasks. To overcome these limitations, this study introduces a new hybrid method called CSA-DE-LR, which combines the clonal selection algorithm (CSA) and differential evolution (DE) with logistic regression. This integration is designed to optimize logistic regression weights efficiently for the accurate classification of CVD. The methodology employs three optimization strategies based on the F1 score, the Matthews correlation coefficient (MCC), and the mean absolute error (MAE). Extensive evaluations on benchmark datasets, namely Cleveland and Statlog, reveal that CSA-DE-LR outperforms state-of-the-art ML methods. In addition, generalization is evaluated using the Breast Cancer Wisconsin Original (WBCO) and Breast Cancer Wisconsin Diagnostic (WBCD) datasets. Significantly, the proposed model demonstrates superior efficacy compared to previous research studies in this domain. This study's findings highlight the potential of hybrid machine learning approaches for improving diagnostic accuracy, offering a significant advancement in the fields of medical data analysis and CVD diagnosis. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVD) are a leading cause of mortality globally, necessitating the development of efficient diagnostic tools. Machine learning (ML) and metaheuristic algorithms have become prevalent in addressing these challenges, providing promising solutions in medical diagnostics. However, traditional ML approaches often need to be improved in feature selection and optimization, leading to suboptimal performance in complex diagnostic tasks. To overcome these limitations, this study introduces a new hybrid method called CSA-DE-LR, which combines the clonal selection algorithm (CSA) and differential evolution (DE) with logistic regression. This integration is designed to optimize logistic regression weights efficiently for the accurate classification of CVD. The methodology employs three optimization strategies based on the F1 score, the Matthews correlation coefficient (MCC), and the mean absolute error (MAE). Extensive evaluations on benchmark datasets, namely Cleveland and Statlog, reveal that CSA-DE-LR outperforms state-of-the-art ML methods. In addition, generalization is evaluated using the Breast Cancer Wisconsin Original (WBCO) and Breast Cancer Wisconsin Diagnostic (WBCD) datasets. Significantly, the proposed model demonstrates superior efficacy compared to previous research studies in this domain. This study’s findings highlight the potential of hybrid machine learning approaches for improving diagnostic accuracy, offering a significant advancement in the fields of medical data analysis and CVD diagnosis.

Converting solar energy to electricity efficiently requires an accurate model with well-estimated parameters in a photovoltaic (PV) system. However, identifying parameters for the PV model remains challenging attributed to the nonlinearity and multimodality inherent in diode circuit models. In this paper, we propose a dual-feedback adaptive clone selection algorithm with a golden sine search. The clonal selection algorithm (CSA), known for its inherent diversity maintenance ability, offers an advantage in handling multimodal optimization problems. The critical factor is the cloning operator, particularly the determination of clone size, crucial for balancing exploration and exploitation. To address the conflict between clone size and convergence speed, we introduce a dual feedback adaptive cloning strategy. This strategy considers both the fitness difference between the hypermutated population and the original population and the harmonic mean distance of the population. Additionally, to improve accuracy, we introduce an elite learning strategy based on the golden sine mechanism. The proposed algorithm’s effectiveness is assessed through comprehensive experiments on PV cells and three PV modules, considering both single diode and double diode models, respectively. The experimental results demonstrate that the accuracy of parameter identification achieved by the proposed algorithm exceeds 99.9% for all three types of PV modules. Moreover, we validate the algorithm’s performance using manufacturer’s datasheets with varying irradiations and temperatures. All experiments consistently indicate the stability and effectiveness of the proposed method in accurately identifying the parameters of PV models.

Aiming at the simultaneous scheduling problem of scheduling jobs and automated guide vehicles (AGVs) in the flexible workshop system, consider building the objective function to minimize maximum processing machine duration, single AGV handling time, and total AGV handling time in the case of a finite number of AGVs and processing machines. Design an improved algorithm that combines NSGA-II (non-dominated sorting genetic algorithms) and clonal selection algorithm (CSA) to solve such problems. Firstly, the workpiece, the processing machine and the AGV are used for three-part coding. Secondly, the total score of non-dominated ranking and objective function value size sorting is introduced to stratify the population, so as to effectively retain excellent individuals. Thirdly, for the cloned population, different probabilities of variation are adopted for different levels of populations, and the genetic recombination of internal exchange and uniform cross-mixing exchange of chromosomes is carried out to effectively improve the diversity of the population and prevent it from falling into local optimum. Finally, three sets of comparative experiments verify that the algorithm has the advantages of short running time, high stability and good convergence when exploring the optimal solution. [ABSTRACT FROM AUTHOR]

Anomaly in geoacoustic emission is an important earthquake precursor. Current geoacoustic anomaly detection methods are limited by their low signal-to-noise ratio, low intensity, sample imbalance, and low accuracy. Therefore, this paper proposes a clone selection algorithm optimized one-class support vector machine method (CSA-OCSVM) for geoacoustic anomaly detection. First, the interquartile range (IQR), cubic spline interpolation, and time window are designed to amplify the geoacoustic signal intensity and energy change rules to reduce the interference of geoacoustic signal noise and intensity. Secondly, to address the imbalance of positive and negative samples in geoacoustic anomaly detection, a one-class support vector machine is introduced for anomaly detection. Meanwhile, in view of the optimization capabilities of the clone selection algorithm, it is adopted to optimize the hyperparameters of OCSVM to improve its detection accuracy. Finally, the proposed model is applied to geoacoustic data anomaly detection in nine different datasets, which are derived from our self-developed acoustic electromagnetic to AI (AETA) system, to verify its effectiveness. By designing comparative experiments with IQR, genetic algorithm OCSVM (GA-OCSVM), particle swarm optimization OCSVM (PSO-OCSVM), and evaluating the performance of the true positive rate (TPR) and false positive rate (FPR), the experimental results depict that the proposed model is superior to the existing state-of-the-art geoacoustic anomaly detection approaches. [ABSTRACT FROM AUTHOR]

At present, many cloning selection algorithms have been studied, and improvements have been made to the cloning, mutation and selection steps. However, there is a lack of research on the optimization of the updating operation steps. The clonal selection algorithm is traditionally updated through a random complement of antibodies, which is a blind and uncertain process. The added antibodies may gather near a local optimal solution, resulting in the need for more iterations to obtain the global optimal solution. To solve this problem, our improved algorithm introduces a crowding degree factor in the antibody updating stage to determine whether there is crowding between antibodies. By eliminating antibodies with high crowding potential and poor affinity, the improved algorithm guides the antibodies to update in the direction of the global optimal solution and ensures stable convergence with fewer iterations. Experimental results show that the overall performance of the improved algorithm is 1% higher than that of the clonal selection algorithm and 2.2% higher than that of the genetic algorithm, indicating that the improved algorithm is effective. The improved algorithm is also transplanted to other improved clonal selection algorithms, and the overall performance is improved by 0.97%, indicating that the improved algorithm can be a beneficial supplement to other improved clonal selection algorithms. [ABSTRACT FROM AUTHOR]

This paper discusses a hybrid grey wolf optimizer utilizing a clone selection algorithm (pGWO-CSA) to overcome the disadvantages of a standard grey wolf optimizer (GWO), such as slow convergence speed, low accuracy in the single-peak function, and easily falling into local optimum in the multi-peak function and complex problems. The modifications of the proposed pGWO-CSA could be classified into the following three aspects. Firstly, a nonlinear function is used instead of a linear function for adjusting the iterative attenuation of the convergence factor to balance exploitation and exploration automatically. Then, an optimal α wolf is designed which will not be affected by the wolves β and δ with poor fitness in the position updating strategy; the second-best β wolf is designed, which will be affected by the low fitness value of the δ wolf. Finally, the cloning and super-mutation of the clonal selection algorithm (CSA) are introduced into GWO to enhance the ability to jump out of the local optimum. In the experimental part, 15 benchmark functions are selected to perform the function optimization tasks to reveal the performance of pGWO-CSA further. Due to the statistical analysis of the obtained experimental data, the pGWO-CSA is superior to these classical swarm intelligence algorithms, GWO, and related variants. Furthermore, in order to verify the applicability of the algorithm, it was applied to the robot path-planning problem and obtained excellent results. [ABSTRACT FROM AUTHOR]

Although the multi-layer perceptron (MLP) neural networks provide a lot of flexibility and have proven useful and reliable in a wide range of classification and regression problems, they still have limitations. One of the most common is associated with the optimization algorithm used to train them. The most commonly used training method is stochastic gradient descent with backpropagation (or backpropagation for short) because it is mathematically tractable (given that the activation functions are differentiable). However, backpropagation is not guaranteed to find the globally optimal set of weights and biases. As a result, the MLP is often incapable of obtaining a desirable solution to the problem. Clonal selection algorithms (CSA) are optimization procedures that effectively explore a complex and large space to find values near the global optimum. Consequently, CSA can be used to solve the problem of training MLP networks. This paper presents a novel implementation of CSA for training MLP architectures to solve real-world problems such as breast cancer diagnosis, active sonar target classification, wheat classification, and flower classification. The CSA is used to find the optimal weights and biases that will significantly increase the classification accuracy of the MLP. The performance of our proposed approach is compared with other popular training methods: genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), Harris hawks optimization (HHO), moth-flame optimization (MFO), flower pollination algorithm (FPA), and backpropagation (BP). The comparison is benchmarked using five classification datasets: Iris Flower, Sonar, Wheat Seeds, Breast Cancer Wisconsin, and Haberman’s Survival. Comparative study results illustrate the improvements in MLP performance gained by using CSA over other training methods, and hence it can be considered a competitive approach to training MLP networks when solving real-world applications in various disciplines.

Son yıllarda oldukça popüler bir alan olan yapay zekânın alt yöntemlerinden Yapay Bağışıklık Sistemi (YBS) ile Klonal Seçim Algoritması (KSA) üzerine bir çok çalışma yapılmaktadır. Bu çalışmada, endüstride geniş bir kullanım alanına sahip kaynak makinası elektrotlarının en uygun değerlerinin bulunabilmesi için Yapay Bağışıklık Sistemi (YBS) algoritması ile, Bulanık Mantık yönteminin bir arada kullanıldığı hibrit bir model önerilmektedir. Gerçekleştirilen çalışmada kaynak sarf malzemesinin daha kaliteli bir ürün olması için gerçekleştirilen Ar-Ge faaliyetlerini hızlandırmak ve maliyetlerini düşürmek amacıyla kaynak parametrelerini optimize ederek kombinasyonlarını veren bir yazılım geliştirilmiştir. Visual Studio ortamında gerçekleştirilen bu çalışma ile farklı kaynak girdi parametreleri kullanılarak kaynak sarf malzemelerinin akma mukavemeti (N/mm²) optimize edilmiştir. Bu çalışmada kaynak üretim Ar-Ge faaliyetlerini hızlandırmak ve maliyetlerini düşürmek amacıyla YBS Klonal Seçim Algoritması (KSA) ile Bulanık Mantık hibrit algoritma yöntemi ele alınmıştır.

The rate of technical innovation, system interconnection, and advanced communications undoubtedly boost distributed energy networks' efficiency. However, when an additional attack surface is made available, the possibility of an increase in attacks is an unavoidable result. The energy ecosystem's significant variety draws attackers with various goals, making any critical infrastructure a threat, regardless of scale. Outdated technology and other antiquated countermeasures that worked years ago cannot address the complexity of current threats. As a result, robust artificial intelligence cyber-defense solutions are more important than ever. Based on the above challenge, this paper proposes an ensemble transfer learning spiking immune system for adaptive smart grid protection. It is an innovative Artificial Immune System (AIS) that uses a swarm of Evolving Izhikevich Neural Networks (EINN) in an Ensemble architecture, which optimally integrates Transfer Learning methodologies. The effectiveness of the proposed innovative system is demonstrated experimentally in multiple complex scenarios that optimally simulate the modern energy environment. The most significant findings of this work are that the transfer learning architecture's shared learning rate significantly adds to the speed of generalization and convergence approach. In addition, the ensemble combination improves the accuracy of the model because the overall behavior of the numerous models is less noisy than a comparable individual single model. Finally, the Izhikevich Spiking Neural Network used here, due to its dynamic configuration, can reproduce different spikes and triggering behaviors of neurons, which models precisely the problem of digital security of energy infrastructures, as proved experimentally. [ABSTRACT FROM AUTHOR]

Companies are trying several ways to offer competitive and highly differentiated products. The goal for the product platform is to share elements for common functions and to differentiate each product in the family by satisfying different requirements as much as possible. This study focuses on the product variety and short product life cycles that result from the increase and diversification in consumer needs and expectations. Proposed methodology aims to maximise the use of common product modules by considering platform-based derivative products and modular product design approaches to minimise the planning complexity in supply chain, manufacturing and service for derivative products. Functional and technical features of the products are determined in the first step. Then, design structure matrix is formed. After defining product components, similarity matrix for derivative products is formed. A clustering algorithm based on Clonal Selection is used to generate critical product modules. Data from a home appliance manufacturer are used to assess three versions of a product by also considering the production process. The grouping enabled to shorten the release time of a new derivative product to the market. [ABSTRACT FROM AUTHOR]

This paper aims to automatically design optimal LSTM topologies using the clonal selection algorithm (CSA) to solve text classification tasks such as sentiment analysis and SMS spam classification. Designing optimal topologies involves determining the best configuration of hyperparameters that will give the best performance. The current state-of-the-art LSTM topologies are often designed using trial and error approaches which are incredibly time-consuming and require domain experts. Our proposed method, referred to as CSA-LSTM, is evaluated using the Large Movie Review Dataset (IMDB). Furthermore, to verify the robustness of the hyperparameters discovered by CSA for the IMDB dataset, we have used them for the other datasets, viz. the Twitter US Airline Sentiment and the SMS Spam Collection. Additionally, the discovered hyperparameters for the LSTM are combined with pre-determined convolutional neural network (CNN) layers to achieve the same or better results to fast the training time and fewer trainable parameters. For further verification and evaluation of the generalization ability and effectiveness of the proposed approach, it is compared with four machine learning algorithms widely used for text classification tasks: (1) random forest (RF), (2) logistic regression (LR), (3) support vector machine (SVM), and (4) multinomial naive Bayes (NB). The results of our experiments show that the LSTM topologies automatically designed by our CSA method are less expensive, reusable and outperform the machine learning algorithms and other models in the literature evaluated on the same three datasets. Through our proposed method, LSTM’s best topology can be self-determined without any human intervention, making CSA-based algorithms a promising approach to automatically design optimal LSTM topologies that provide the best performance for a given task.

This paper discusses a hybrid grey wolf optimizer utilizing a clone selection algorithm (pGWO-CSA) to overcome the disadvantages of a standard grey wolf optimizer (GWO), such as slow convergence speed, low accuracy in the single-peak function, and easily falling into local optimum in the multi-peak function and complex problems. The modifications of the proposed pGWO-CSA could be classified into the following three aspects. Firstly, a nonlinear function is used instead of a linear function for adjusting the iterative attenuation of the convergence factor to balance exploitation and exploration automatically. Then, an optimal α wolf is designed which will not be affected by the wolves β and δ with poor fitness in the position updating strategy; the second-best β wolf is designed, which will be affected by the low fitness value of the δ wolf. Finally, the cloning and super-mutation of the clonal selection algorithm (CSA) are introduced into GWO to enhance the ability to jump out of the local optimum. In the experimental part, 15 benchmark functions are selected to perform the function optimization tasks to reveal the performance of pGWO-CSA further. Due to the statistical analysis of the obtained experimental data, the pGWO-CSA is superior to these classical swarm intelligence algorithms, GWO, and related variants. Furthermore, in order to verify the applicability of the algorithm, it was applied to the robot path-planning problem and obtained excellent results.

The aircraft arrival sequencing problem is to make sequencing with the required safe separations for a given set of aircraft with estimated operation times under certain constraints. In this study, the problem of sequencing aircrafts planning to land on a single runway is discussed. Aircraft are allowed to perform pre-defined number of constrained position shifting (CPS) in their landing sequence determined by first come first served (FCFS) principle. The objective function is to minimize the completion time of operations (makespan). The Clonal Selection Algorithm (KSA), one of the Artificial Immune System (AIS) algorithms, was used to solve the problem. Artificial immune system is a technique used in many areas such as anomaly detection, computer and network security, scheduling, optimization, classification, data mining and is inspired by natural immune system. The algorithm has been tested for scenarios with different numbers and categories of aircraft. The solutions obtained with the algorithm and obtained with a mathematical model solver (GAMS/CPLEX) are compared and solution times are shared.

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the thorough application and development of Intelligent Logistics System, the Path Planning Problem, which is one of the key problems of logistics scheduling, is accelerating to the direction of dynamics, diversification and complexity. In order to better adapt to the new changes, this paper proposes a path planning method based on improved SP-MCTS (Single-Player Monte Carlo Tree Search) algorithm. Unlike the previous heuristic algorithms, SP-MCTS does not completely depend on parameters, and can more effectively solve variable combinatorial optimization problems. Aiming at the problem of path planning, this paper enhances the simulation process of SP-MCTS by clonal selection algorithm, in order to improve the algorithm's accuracy of locating high-potential branches, and further improve the accuracy of the decisions made by SP-MCTS. Experiments show that the method proposed in this paper is less affected by the parameters and can better solve the changing path planning problem. Compared with the existing path planning methods and original SP-MCTS algorithm, it can solve the changeable path planning problem more stably, faster and more accurately.

This article develops a probabilistic approach for assessing transport network vulnerability. A novel performance measure is proposed to evaluate the expected impact when multiple transport network components fail simultaneously at various degrees. The proposed measure captures both the likelihood and consequence of a combination of transport network component failures. The most critical combination of transport network component failures is obtained by solving a bi-level optimization problem. The upper-level problem is to solve for the combination of transport network components together with their corresponding disruption levels, which induces the maximum reduction in the performance measure. The lower-level problem is to capture the response of travelers to network changes due to network component failures and is formulated as a traffic assignment problem. The clonal selection algorithm (CSA), a biologically inspired approach, is adopted to tackle the proposed bi-level optimization problem. Numerical results indicate that neglecting partial capacity degradation and its probability of occurrence could misestimate the worst scenario, and different vulnerability assessment approaches could identify similar critical components but our approach can discover some components that are not found by other existing approaches. Moreover, it is shown that the CSA outperforms the well-known genetic algorithm in terms of solution quality in a large network. [ABSTRACT FROM AUTHOR]

The present paper deals with a variant of hub location problems (HLP): the uncapacitated single allocation p-Hub median problem (USApHMP). This problem consists to jointly locate hub facilities and to allocate demand nodes to these selected facilities. The objective function is to minimize the routing of demands between any origin and destination pair of nodes. This problem is known to be NP-hard. Based on the artificial immune systems (AIS) framework, this paper develops a new approach to efficiently solve the USApHMP. The proposed approach is in the form of a clonal selection algorithm (CSA) that uses appropriate encoding schemes of solutions and maintains their feasibility. Comprehensive experiments and comparison of the proposed approach with other existing heuristics are conducted on benchmark from civil aeronautics board, Australian post, PlanetLab and Urand data sets. The results obtained allow to demonstrate the validity and the effectiveness of our approach. In terms of solution quality, the results obtained outperform the best-known solutions in the literature. [ABSTRACT FROM AUTHOR]

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The collision-free path planning is crucial for an autonomous vehicle. It saves life and helps to complete the task in time. The computational intelligence mimics human intelligence and solves these types of problems in which conventional techniques fail to provide optimal solutions. In literature, computational intelligence techniques except evolutionary techniques have not been utilized for land vehicles. In this regard, we employ clonal selection algorithms for collision avoidance in an autonomous vehicle. To check the effectiveness of our proposed scheme, we compare the performance of the clonal selection algorithm with the genetic algorithm. The results show that the clonal selection algorithm performs better than the genetic algorithm in terms of computation time and also avoids accident within the required time to avoidance.

The rate of technical innovation, system interconnection, and advanced communications undoubtedly boost distributed energy networks’ efficiency. However, when an additional attack surface is made available, the possibility of an increase in attacks is an unavoidable result. The energy ecosystem’s significant variety draws attackers with various goals, making any critical infrastructure a threat, regardless of scale. Outdated technology and other antiquated countermeasures that worked years ago cannot address the complexity of current threats. As a result, robust artificial intelligence cyber-defense solutions are more important than ever. Based on the above challenge, this paper proposes an ensemble transfer learning spiking immune system for adaptive smart grid protection. It is an innovative Artificial Immune System (AIS) that uses a swarm of Evolving Izhikevich Neural Networks (EINN) in an Ensemble architecture, which optimally integrates Transfer Learning methodologies. The effectiveness of the proposed innovative system is demonstrated experimentally in multiple complex scenarios that optimally simulate the modern energy environment. The most significant findings of this work are that the transfer learning architecture’s shared learning rate significantly adds to the speed of generalization and convergence approach. In addition, the ensemble combination improves the accuracy of the model because the overall behavior of the numerous models is less noisy than a comparable individual single model. Finally, the Izhikevich Spiking Neural Network used here, due to its dynamic configuration, can reproduce different spikes and triggering behaviors of neurons, which models precisely the problem of digital security of energy infrastructures, as proved experimentally.

Security vulnerabilities in web traffic can directly lead to data leak. Preventing these data leaks to a large extent has become an important problem to solve. Besides, the accurate detection and prevention of abnormal changes in web traffic is of great importance. In this study, a hybrid approach, called C‐NSA, based on the negative selection algorithm (NSA) and clonal selection algorithm (CSA) of artificial immune systems for the detection of abnormal web traffic on the network is proposed and a user‐friendly application software is developed. The real and synthetic data in the Yahoo Webscope S5 dataset are used for web traffic and the data are split into windows using the window sliding. In the experimental studies, the abnormal web traffic data is detected by monitoring the changes in the number of activated detectors in the C‐NSA. It is observed that the average accuracy performance of finding anomalies in real web traffic data is 94.30% and the overall classification accuracy is 98.22% based on proposed approach. In addition, false positive rate of the proposed approach using C‐NSA is obtained as 0.029. In addition, the results in synthetic web traffic data using C‐NSA are achieved as average 98.57% classification accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Engineering & Architectural Faculty of Eskisehir Osmangazi University / Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi is the property of Eskisehir Osmangazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The recent studies indicate that the protein secondary structure provides very important advantages in determining the function of a protein, treating numerous diseases and drug design. Determining the secondary structure in the laboratory environment is both costly and challenging. Therefore, the prediction of protein secondary structure has been an important study field of bioinformatics and computational biology for many years. The aim of this paper was to provide a contribution to the prediction of protein secondary structure using the nature-inspired methods. The data in the first phase were trained with clonal selection algorithm (CSA) which was modeled by being inspired by the live immune system. The classification was then performed with multilayer perceptron which is one of the deep learning methods modeled by being inspired by the biological nervous system. The results obtained indicated that training of the data with CSA prior to classification contributed positively to classification success.

Predicting the delay in servicing incoming ships to ports is crucial for maritime transportation. In this study, we use support vector regression (SVR) in order to accurately predict this delay for ships arriving to the terminal No. 1 of Shahid Rajaee's port in Bandar Abbas. To achieve this goal, a combination of Clonal Selection and Grey Wolf Optimization algorithms (named as CLOGWO) is used for two purposes: (i) selecting the most important features among the features that affect prediction of this delay and (ii) optimizing SVR parameters for a more accurate prediction. Performance of the proposed method was compared with Genetic Algorithm (GA), Clonal Selection (CS), Grey Wolf Optimization (GWO), and Particle Swarm Optimization (PSO) algorithms on the following metrics: correlation, rate of feature reduction, root mean square error (RMSE), and normalized RMSE (NRMSE). Evaluations on Shahid Rajaee dataset showed that the mean value of these metrics in 10 independent runs of the proposed method were 0.867, 74.45%, 0.080, and 9.02, respectively. These results and evaluations on standard datasets indicate that the proposed method provides competitive results with other evolutionary algorithms. [ABSTRACT FROM AUTHOR]

The clonal selection algorithm(CSA) is a core method in artificial immune system, which is famous for its intelligent evolution in artificial intelligence application. However, There are some shortcomings in the algorithm, such as local optima and low convergence speed, which make its practical effects not ideal. Culture algorithm(CA) is driven by knowledge, which can significantly improve the evolutionary efficiency. Chaos mechanism can make the algorithm have better problem space coverage ability. Therefore, a culture&chaos-inspired CSA(CC-CSA) is proposed in this paper to deal with the problems mentioned before. CC-CSA adopts the double-layer evolutionary framework of CA to extract knowledge and guide the crossover and chaotic mutation operation to complete the evolution process. The implicit knowledge is used to adaptively control the chaotic mutation scale, guide the individuals to jump out of the local optima, and realize the accurate search in the latter evolution cycle to gradually approach the optimal solution. It can be seen from the mathematical model analysis that CC-CSA can converge to the global optimal solution. Compared with the experimental results of the original CSA and its representative, up-to-date improved methods, CC-CSA has the fastest convergence speed and the best detection performances. It is also proved that CC-CSA can solve the problems of local optima and slow convergence speed by using the knowledge guidance of CA's double-layer framework and good coverage ability of chaos mechanism to the problem space. [ABSTRACT FROM AUTHOR]

Clonal selection algorithm and discrete Hopfield neural network are extensively employed for solving higher-order optimization problems ranging from the constraint satisfaction problem to complex pattern recognition. The modified clonal selection algorithm is a comprehensive and less iterative immune-inspired searching algorithm, utilized to search for the correct combination of instances for Very large-scale integrated (VLSI) circuit structure. In this research, the VLSI circuit framework consists of Boolean 3-Satisfiability instances with the different complexities and number of transistors are considered. Hence, a hybrid modified clonal selection algorithm with discrete Hopfield neural network is well developed to optimize the configuration of VLSI circuits with different number of electronic components such as transistors as the instances. Therefore, the performance of the developed hybrid model was assessed experimentally with the standard models, HNNVLSI-3SATES and HNNVLSI-3SATGA in term of circuit accuracy, sensitivity, robustness and runtime to complete the verification process. The results have demonstrated the developed model, HNNVLSI-3SATCSA produced a minimum error (consistently approaching 0), better accuracy (more than 80%) and faster computational time (less than 125 seconds) against changes in the complexity in term of the number of transistors. Furthermore, the developed hybrid model is able to minimize the computational burden and configurational noises for the variant of VLSI circuits. [ABSTRACT FROM AUTHOR]

Technological developments enable the design and manufacturing of products tailored to individual consumers. Cellular Manufacturing Systems (CMS) can be considered as to ease flexibility, to reduce setup time, throughput time, work-in-process inventories, and material handling costs. Cell formation problem (CFP) that is one of the critical CMS design problems is the assignment of parts and machines to specific cells based on their similarity. This study introduces a Clonal Selection Algorithm (CSA) with a novel encoding structure that is efficient to solve real-sized problems. Unlike the methods in literature that define the number of cells as a constant number, this algorithm is significant because it can obtain the optimum number of cell to generate best efficacy value. Proposed CSA is tested by using 67 (35 well-known and 32 less-known) test problems. CSA obtains the same 63 best-known optimal solutions, provides solutions for the 3 of the well-known test problem and a new solution for the largest test problem (50 machine 150 part) that was not possible to be solved by the mixed integer linear programming model due to the high computational complexity. Final CSA grouping results are illustrated with figures to attract attention to the singleton and residual cells. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The cellular manufacturing technology, an application of group technology in manufacturing, has been a widely studied combinatorial optimization problem where the entire production system is divided into many cells and part families. In this paper, a novel clonal selection algorithm (CSA) that uses a new affinity function and part assignment heuristic for solving a multi-objective cell formation problem is studied. The proposed CSA has been hybridized with genetic algorithm for generating feasible cell sequences that fulfill both mutual exhaustivity and exclusion properties of machine cells prior to the initial population generation. Additionally, a new part assignment heuristic function that maps parts to machine cells and a novel basic affinity function have been built into the proposed CSA so that it can act as the utility function to solve the multi-objective cell formation problem. This hybrid CSA (HCSA) has been presented and computational results have been obtained for the proposed scheme with a set of 52 benchmark instances collected from literature. The results presented herein demonstrate that overall proposed HCSA is much more promising in comparison with existing approaches available in recent literatures. Extensive statistical and convergence tests have been carried out to ratify the superiority of the proposed HCSA. The improvements can be attributed to the collaborative interactions in the CSA mechanism, the proposed hybridization for initial population generation and so forth. [ABSTRACT FROM AUTHOR]