Search

Budget allocation across multiple advertising channels involves periodically dividing a fixed total budget among various channels. Yet, the challenge of making sequential decisions to optimize long-term benefits rather than short-term gains is often overlooked. Additionally, more apparent connections must be made between actions taken on one advertising channel and the outcomes on others. Furthermore, budget limitations narrow down the range of potential optimal strategies that can be pursued. In response to these challenges, this study unveils a pioneering multi-channel advertising budget allocation approach that leverages a reinforcement learning (RL) Q-learning framework enriched with an advanced Differential Evolution (DE) algorithm to refine the Q-learning methodology. The RL element makes informed sequential decisions, adeptly adjusting strategies to favor long-term rewards by assimilating environmental feedback. Complementing this, the enhanced DE algorithm introduces an inventive clustering-based mutation technique, exploiting key groupings within the DE population to generate novel and practical solutions. The model is further bolstered by a discretization tactic aimed at simplifying the model by streamlining costs. The proposed methodology is rigorously validated using two extensive datasets: the Chinese Internet Company Advertising Dataset (CICAD) and CRITEO-UPLIFT v2, employing metrics like Area Under the Cost Curve (AUCC) and Expected Outcome Metric (EOM) as measures of performance. The empirical results affirm the superiority of the model, showcasing its exceptional performance with significant scores (AUCC =0.750 and EOM =0.736 for CICAD; AUCC =0.813 and EOM =0.829 for CRITEO-UPLIFT v2), thereby illustrating the model’s proficiency in navigating the multifaceted challenges associated with multi-channel budget allocation and establishing a new benchmark in the field.

This paper examines and compares the performance characteristics of inner and outer rotor surface permanent magnet (SPM) machines. Notably, this research distinguishes itself through a rigorous methodology that carefully selects an optimization dataset rather than relying on arbitrary data. Consequently, this methodology has yielded valuable insights in two significant aspects: 1) The trends of key design parameters for both inner and outer rotor types, such as split ratio, aspect ratio, and magnet-gap ratio, are revealed using the optimization dataset. 2) The torque-to-weight ratio values between the inner and outer rotor types are investigated from various perspectives. Through this analysis, it becomes numerically evident that a significant advantage can be obtained using the outer rotor type compared to the inner rotor type. Overall, this study provides valuable insights for researchers, particularly those involved in the initial design stage of SPM machines for both rotor types.

Fuzzy PID control is a control method with good adaptability and stability in complex environments. It is used to achieve precise regulation and stable control of the system. In this paper, a fish scale evolution GSOM is proposed to improve the control method of fuzzy PID. Firstly, the fish scale regulation system is established and the differential evolution theory is introduced to realize the evolutionary upgrading of the system. Secondly, the GSOM module is introduced. The system is optimized by self-organized mapping neural network to achieve dynamic regulation of polymorphic inputs. Meanwhile, the fuzzy rule base and parameter regulation mechanism in fuzzy PID control are dynamically optimized. Improve the performance of the control system. Finally, the control method of improved fuzzy PID for fish scale evolution GSOM is simulated using MATLAB. The simulation experiments also compare several traditional PID control methods. The comparison indexes include stability, robustness, control accuracy and feedback output effect. The results show that the method in this paper is more stable and has fewer iterations when facing the dynamic input environment. The tracking error and control output of the controller system are significantly improved. It has good feedback output effect, solves the saturation problem and has higher control accuracy.

Offshore oilfield inspections play a crucial role in environmental conservation and resource management. However, these inspections traditionally depend on manual approaches, which are not only inefficient but also incur high costs. In response to this challenge, this study introduces an innovative drone-based approach to optimize offshore oilfield inspections, focusing specifically on minimizing the total flight duration through effective routing optimization. Based on this approach, we develop a novel and mathematical model that accounts for drone power limitations and inspection time windows. To solve this model efficiently, we propose a refined differential evolution algorithm. This algorithm incorporates both a roulette decoding method and a variable neighborhood search strategy, each contributing uniquely to enhance the solution quality. Experimental results demonstrate that our method markedly reduces the total flight duration of drones, substantially outperforming traditional approaches that do not incorporate routing optimization. This reduction in flight duration leads to more efficient and cost-effective drone operations for offshore oilfield inspections.

Performance modelling of a deep learning application is essential to improve and quantify the efficiency of the model framework. However, existing performance models are mostly case-specific, with limited capability for the new deep learning frameworks/applications. In this paper, we propose a generic performance model of an application in a distributed environment with a generic expression of the application execution time that considers the influence of both intrinsic factors/operations (e.g. algorithmic parameters/internal operations) and extrinsic scaling factors (e.g. the number of processors, data chunks and batch size). We formulate it as a global optimisation problem and solve it using regularisation on a cost function and differential evolution algorithm to find the best-fit values of the constants in the generic expression to match the experimentally determined computation time. We have evaluated the proposed model on three deep learning frameworks (i.e., TensorFlow, MXnet, and Pytorch). The experimental results show that the proposed model can provide accurate performance predictions and interpretability. In addition, the proposed work can be applied to any distributed deep neural network without instrumenting the code and provides insight into the factors affecting performance and scalability.

This paper proposes a variable-length Differential Evolution for Association Rule Mining. The proposed algorithm includes a novel representation of individuals, which can encode both numerical and discrete attributes in their original or absolute complement of the original intervals. The fitness function used is comprised of a weighted sum of Support and Confidence Association Rule Mining metrics. The proposed algorithm was tested on fourteen publicly available, and commonly used datasets from the UC Irvine Machine Learning Repository. It is also compared to the nature inspired algorithms taken from the NiaARM framework, providing superior results. The implementation of the proposed algorithm follows the principles of Green Artificial Intelligence, where a smaller computational load is required for obtaining promising results, and thus lowering the carbon footprint.

The increasing dependence on smartphones with advanced sensors has highlighted the imperative of precise transportation mode classification, pivotal for domains like health monitoring and urban planning. This research is motivated by the pressing demand to enhance transportation mode classification, leveraging the potential of smartphone sensors, notably the accelerometer, magnetometer, and gyroscope. In response to this challenge, we present a novel automated classification model rooted in deep reinforcement learning. Our model stands out for its innovative approach of harnessing enhanced features through artificial neural networks (ANNs) and visualizing the classification task as a structured series of decision-making events. Our model adopts an improved differential evolution (DE) algorithm for initializing weights, coupled with a specialized agent-environment relationship. Every correct classification earns the agent a reward, with additional emphasis on the accurate categorization of less frequent modes through a distinct reward strategy. The Upper Confidence Bound (UCB) technique is used for action selection, promoting deep-seated knowledge, and minimizing reliance on chance. A notable innovation in our work is the introduction of a cluster-centric mutation operation within the DE algorithm. This operation strategically identifies optimal clusters in the current DE population and forges potential solutions using a pioneering update mechanism. When assessed on the extensive HTC dataset, which includes 8311 hours of data gathered from 224 participants over two years. Noteworthy results spotlight an accuracy of 0.88±0.03 and an F-measure of 0.87±0.02, underscoring the efficacy of our approach for large-scale transportation mode classification tasks. This work introduces an innovative strategy in the realm of transportation mode classification, emphasizing both precision and reliability, addressing the pressing need for enhanced classification mechanisms in an ever-evolving digital landscape.

While fake news is morally reprehensible, irresponsible parties intentionally use it to achieve their goals by disseminating it to vulnerable and targeted groups. Machine learning techniques have been researched extensively to detect fake news. On the other hand, evolutionary-based algorithms are now gaining popularity in the research community. In this study, a two-stage evolutionary approach is proposed to generate and optimize a mathematical equation for fake news detection. In the first stage, tree-based Genetic Programming (GP) algorithm is used to generate mathematical expressions to detect correlations between the language-independent (Lang-IND) features, extracted from Fake.my-COVID19 dataset, the newly curated fake news dataset in a mixed Malay - English language. The uniqueness of the proposed approach is that the mathematical expressions are formed by basic arithmetic operators or to include complex arithmetic operators such as addition, multiplication, subtraction, division, square, abs, log1p, sign, square root, and exponential together with Lang-IND features as the variables. Prior to second stage of the evolutionary approach, a sensitivity analysis is applied to shorten the best equation while maintaining the F1-score performance. In the second stage, an Adaptive Differential Evolution (ADE), is used to fine-tune the mathematical model. The experimental results conclude that the proposed two-stage evolutionary approach can be applied in fake news detection and the model can learn to predict using the Lang-IND features. Results from the first stage shows that the equation from GP scores F1-score of 83.23% on Fake.my-COVID19 dataset using complex arithmetic operators and at tree depth of 8. After the fine-tuning stage, the model performance increases the F1-score to 84.44%. The performance of the proposed two-stage evolutionary approach outperforms the baseline performance of six commonly-used machine learning algorithms, with Random Forest having the highest F1-score of 84.07%. The mathematical model is also tested separately on two other unseen datasets of different domain topic or language and achieves acceptable F1-scores.

Proportional-Integral-Derivative (PID) is a simple and intuitive feedback-based control mechanism being useful to track set points and to reject disturbances. A key question in gradient-free optimization is to ascertain whether the class of optimization algorithms based on the difference of vectors generalize reasonably well to tackle a large class of PID control problems. For generalization and practical purposes, it would be desirable to render algorithms being able to tune PID controllers over a diverse and large set of control problems/tasks with minimal human intervention (self-adaptation features), and under tight computational budgets. In this paper, aiming to fill the above-mentioned gap, we propose and investigate the effectiveness of a new class of algorithm based on the difference of vectors and self-adaptation mechanisms for PID tuning. As such, we introduce a new class of Differential Evolution with success-based Particle Adaptations (DEPA), which unifies the principles of difference of vectors, particle schemes and trial/parameter adaptation through archive (memory) mechanisms. Our computational simulations using a large/relevant set of 25 control problem instances (tracking of linear, nonlinear, continuous, and discontinuous trajectories in motor position control, motor velocity control, magnetic levitation, inverted pendulum, crane stabilization), and the comparisons with a large set of closely related optimization algorithms, and their extended adaptive variants (23 optimization algorithms in total) has shown the outperforming benefits of the proposed approach in convergence performance under tight function evaluation budgets (1000 function evaluations). Also, the experiments on a real-world inverted pendulum device show the potential for transferability of the learned gains to unseen situations during training. Furthermore, we evaluated the algorithmic extension and the generalization towards diverse fitness landscapes in the CEC 2017 benchmark suite, showing the attractive/outperforming performance overall problem instances. In particular, the proposed framework performed better in 558 control instances when using ISE as a performance metric, and in 358 control instances when using IAE, ITAE and ITSE as performance metrics. Also, the algorithmic extension for general optimization landscapes performed better than the related algorithms in 182, 215 and 235 problem instances of CEC 2017 benchmark suite for 10, 30 and 50 dimensions, respectively. Our obtained results have the potential to further advance towards developing efficient and self-adaptive optimization algorithms based on the difference of vectors, which may find use in a wider set of optimization and control problems.

Software testing (ST) is one of the most important software development life cycle (SDLC) phases and ST effort is often expressed as a percentage of SDLC effort. Unfortunately, in the literature ST effort percentage ranges from 10% to 60%. In the literature most of the machine learning algorithms and metaheuristics for optimizing them have looked at predicting overall SDLC effort without focusing on any specific SDLC phase, including testing. Therefore, this study investigates the application of the Software Testing Effort Prediction (STEP) of Gradient Boosting (GB) machine learning regression algorithm optimized through Differential Evolution (DE). Its prediction accuracy is compared with those obtained when the GB is also optimized through Particle Swarm Optimization (PSO) and Genetic Algorithms (GA). The performance of GB-DE, GB-PSO, and GB-GA was also compared to that of statistical regression (SR). Seven data sets of actual projects were selected from an international public repository for software projects. The results showed that GB-DE was statistically better than SR in all seven data sets at 95% confidence, whereas GB-PSO and GB-GA were better than SR in four and three data sets, respectively. Thus, we can conclude that GB-DE can be used for STEP of either new projects or enhancement projects developed in either the third or fourth programming language generation.

Since the inception in 1995, Differential Evolution (DE) has gained significant attention from researchers worldwide, and many DE variants proposed in the last decades obtained excellent performance in many scientific and engineering applications. However, the vast majority of these well-performed DE variants employ binomial crossover rather than exponential crossover in generating trial vector candidates though both of the two schemes were proposed simultaneously. That may be also the reason why there still doesn’t exist such a thorough analysis of DE with exponential crossover. Different from the majority of DE researchers believing that DE variants with binomial crossover usually exhibit superior performance than the ones employing exponential crossover and DE variants with exponential crossover are good at tackling optimization problems with linkages among neighboring variables, we found that DE variants with exponential crossover can achieve competitive performance with the ones employing binomial crossover regardless of whether there are linkages among the variables or not after discovering the proper crossover rate $CR$ and its corresponding parameter control. In order to enrich research of DE on exponential crossover, this paper presents an thorough experimental analysis of DE algorithm with exponential crossover in numerical optimization, presenting the basic concepts of exponential crossover, giving the mathematical analysis why they can actually achieve similar optimization between exponential crossover and binomial crossover, experimental validation under the 100 benchmark functions from CEC2013, CEC2014, CEC2017, CEC2022 test suites as well as the tension/compression spring design problem, and summarizing and classifying various engineering applications that exponential crossover DEs are used to solve. Furthermore, we also look into the future challenges and potential directions for further development of DE with exponential crossover.

Recently, convolutional neural networks (CNNs) have shown promising achievements in various computer vision tasks. However, designing a CNN model architecture necessitates a high-domain knowledge expert, which can be difficult for new researchers while solving real-world problems like medical image diagnosis. Neural architecture search (NAS) is an approach to reduce human intervention by automatically designing CNN architecture. This study proposes a two-phase evolutionary framework to design a suitable CNN model for medical image classification named TPEvo-CNN. The proposed framework mainly focuses on architectural depth search and hyper-parameter settings of the layered architecture for the CNN model. In the first phase, differential evolution (DE) is applied to determine the optimal number of layers for a CNN architecture, which enhances faster convergence to achieve CNN model architectures. In the second phase, the genetic algorithm (GA) is used to fine-tune the hyper-parameter settings of the generated CNN layer architecture in the first phase. Crossover and mutation operations of GA are devised to explore the hyper-parameter search space. Also, an elitism selection strategy is introduced to select the potential hyper-parameters of the CNN architecture for the next generation. The suggested approach is experimented on six medical image datasets, including pneumonia, skin cancer, and four COVID-19 datasets, which are categorized based on image types and class numbers. The experimental findings demonstrate the superiority of the proposed TPEvo-CNN model compared to existing hand-crafted, pre-trained, and NAS-based CNN models in terms of classification metrics, confusion matrix, radar plots, and statistical analysis.

In conventional optimization problems, it is assumed that all relevant parametric constraints remain stationary. In contrast, optimization problems encountered in practical applications are dynamic and supervened by uncertainties. The research community has evinced a keen interest in multi-population approaches combined with nature-inspired algorithms to manage dynamic optimization problems efficiently. Applying multi-population approaches to solve dynamic optimization problems engenders specific vital issues, such as reproducing sub-populations in new environments influenced by archival information. Moreover, over-partitioning the population may lead to aberrant utilization of computational resources among the sub-populations. These impediments are addressed using the proposed hybrid multi-population reinitialization strategy, which is a combination of distributed differential evolution algorithmic framework and re-initialization strategy. This scheme relies on simple reinitialization to surmount the dynamism. This framework was assessed on different instances in a moving peak benchmark problem, a proven benchmarking function in the domain of dynamic optimization. Furthermore, this study encompasses a comparative and statistical analysis to validate the effectiveness of the proposed approach in comparison to cutting-edge algorithms in solving dynamic optimization problems efficiently. The experimental results consistently show that the hybrid multi-population reinitialization strategy outperforms conventional Differential Evolution algorithms across various parameter configurations. This hybrid multi-population reinitialization strategy showcases its effectiveness in the successful handling of increased shift lengths and number of peaks, which are pivotal parameters in solving moving peak benchmark function.

This study addressed the autonomous planning of three-dimensional (3D) underwater inspection paths for autonomous underwater vehicles (AUVs) in marine ranching by integrating differential evolution and particle swarm optimization (PSO) algorithms. First, a modified PSO algorithm incorporating swap operators, mutation, and crossover strategies was employed to enable autonomous obstacle avoidance during the inspection of offshore net cages in fish farms situated within a 3D marine environment. This approach addresses the problem of planning full-traversal paths for multiple inspection points. Second, the performance of the proposed algorithm was assessed through comparative tests with other algorithms. The proposed algorithm demonstrated significant improvements in convergence speed, accuracy, and stability under complex scenarios involving multiple optima and intense oscillations. To validate the superiority and overall planning proficiency of the modified method, an experimental setup comprising of two distinct 3D marine cage environments with a series of checkpoints was utilized. The experimental results demonstrated the ability of the proposed algorithm to generate an optimal path while traversing all inspection points of fish farm offshore net cages. By ensuring the safety of AUVs and closely adhering to the surfaces of offshore net cages during the inspection process, the algorithm exhibits remarkable adaptability to specific application scenarios, effectively mitigating concerns related to local optima and premature convergence.

Differential evolution (DE) algorithm is one of the most effective and efficient heuristic approaches for solving complex black box problems. But it still easily suffers from premature convergence and stagnation. To alleviate these defects, this paper presents a novel DE variant, named enhanced adaptive differential evolution algorithm with multi-mutation schemes and weighted control parameter setting (MWADE), to further strengthen its search capability. In MWADE, a multi-schemes mutation strategy is first proposed to properly exploit or explore the promising information of each individual. Herein, the whole population is dynamically grouped into three subpopulations according to their fitness values and search performance, and three different mutant operators with various search characteristics are respectively adopted for each subpopulation. Meanwhile, in order to ensure the exploration of algorithm at the later evolutionary stage, a weight-controlled parameter setting is proposed to suitably assign scale factors for different differential vectors. Moreover, a random opposition mechanism with greedy selection is introduced to avoid trapping in local optima or stagnation, and an adaptive population size reduction scheme is devised to further promote the search effectiveness of algorithm. Finally, to illustrate the performance of MWADE, thirteen typical algorithms are adopted and compared with MWADE on 30 functions from IEEE CEC 2017 test suite with different dimensions, and the effectiveness of its proposed components are also investigated. Numerical results indicate that the proposed algorithm has a better search performance.

Differential Evolution(DE) is a widely used technique to tackle complex optimization problems owing to its easy-implementation and excellent performance, nevertheless, the inborn weakness of the crossover operation has not been solved even in the recent state-of-the-art DE algorithms. There are two commonly used crossover schemes in DE, the exponential crossover and binomial crossover. The exponential crossover is actually a combination of 1-point and 2-point crossover schemes originated with Genetic Algorithm (GA), and it has positional bias because of the dependence on parameter separation. The binomial crossover tackles the positional bias by separating each dimension separately and treating them independently, however, bias still exists from a higher dimensional view, we name it selection bias, and that is the reason why the QUATRE algorithm was proposed. The evolution matrix is the primary component of the QUATRE algorithm which solves the selection bias of DE, however, the previous QUATRE variants still suffer the adaptation of the evolution matrix and can not be able to escape some local optima in complex optimization. Therefore, this paper proposes a new QUATRE with better adaptations of evolution matrix and control parameter, moreover, a perturbation mechanism is firstly proposed for the enhancement of population diversity. The main contributions of our algorithm can be summarized as follows. First, a new generation of evolution matrix is proposed, which can obtain better adaptation to the landscape of the objectives and help the algorithm jump out some local optima. Second, novel adaptations of control parameters are also proposed by incorporating historical memory mechanism and population reduction. Third, a new perturbation mechanism is proposed to enhance the population diversity. In order to validate the proposed algorithm, intensive experiments are conducted under 88 benchmark functions from the universal CEC2013, CEC2014, and CEC2017 test suites in comparison with several excellent DE variants and QUATRE variants, and the results support our superiority.

Early detection of Diabetic Retinopathy (DR) is crucial as it may cause blindness. Manual diagnosis of DR severity by ophthalmologists is challenging and time consuming. Therefore, there has been a significant focus on developing an automated system for identifying DR using retinal fundus images. Recent research has revealed that utilizing pre-trained deep learning networks for diverse image classification tasks provides notable benefits in this context. In this paper, a Transfer Learning (TL) approach with optimized feature weights and parameters is proposed for DR detection and grading tasks. To obtain better generalization during training and to optimize classification, features are extracted from the average pooling layers and fed to an Error Correction Output Code (ECOC) ensemble configuration. Two pre-trained networks (ShuffleNet and ResNet-18) are considered as each pre-trained network offers a different “point of view” of the fundus images, thereby providing more opportunities for accurate “grade-wise” discrimination. A simultaneous feature selection and parameter tuning of the ensemble is applied to further enhance the overall DR detection and grading. Adaptive Differential Evolution (ADE) is chosen for this purpose because it automatically configures the parameters, eliminating the need for manual parameter selection. In this paper, we evaluate two public domain datasets: 1) APTOS and 2) combination of EyePac + Messidor-2. Simulation results show that our proposed method performs better that the conventional deep learning models and are on a par with the existing research work. In particular, the optimal configuration for APTOS 5-class DR grading achieves an accuracy rate of 82%, while for APTOS 2-class grading, it achieves a higher accuracy rate of 96%. Finally, the best configuration for EyePac + Messidor-2 3-class grading results in 75% accuracy.

Mutation takes a vital part in assisting differential evolution (DE) to achieve satisfactory performance. The most crucial factor for a good mutation scheme is to mutate individuals dispersedly but with fast convergence to optimal regions. With this purpose, this paper designs a novel mutation approach, termed as “DE/current-to-gselite/1”, by utilizing the Gaussian distribution to sample guiding exemplars around elites in the population to evolve individuals. Accordingly, a Gaussian sampling guided differential evolution (GSGDE) is devised to hopefully tackle optimization problems effectively. With the assistance of the Gaussian distribution, GSGDE mutates distinct individuals with very different guiding exemplars. Hence, high mutation diversity is expectedly maintained, which leads to that individuals could traverse the problem space in diverse directions. Thanks to the narrow sampling range of the Gaussian distribution, the generated guiding exemplars are likely better and thus individuals in the population are anticipated to move towards optimal regions fast. This is of great profit for fast convergence to high-quality solutions. Further, a dynamic parameter adjustment strategy is proposed to dynamically regulate the number of elites. Hereafter, GSGDE gradually shifts from concentrating on exploring problem space to focusing on exploiting found optimal areas. Cooperated with an existing adaptive parameter strategy, GSGDE is anticipated to strike a good balance between exploitation and exploration to traverse the problem space and hence likely obtain satisfactory performance. Experiments have been extensively carried out on the latest CEC2014 and CEC2017 problem suites with three settings of the dimensionality. Experimental results substantiate that GSGDE has a good scalability and attains highly competitive performance with or even significantly superior performance to 11 latest and representative DE methods. Particularly, its superiority becomes more and more significant as the dimensionality increases.

In order to improve the tracking ability of the vehicle mounted photoelectric tracking platform, and make its tracking system has the characteristics of rapid response, small overshoot, high-precision position tracking, strong anti-interference and good robustness. In this paper, a joint active disturbance rejection control (ADRC) and sliding mode control (SMC) method is proposed, which can effectively improve the tracking ability of the equipment. Firstly, the mathematical model of the DC motor is analyzed, and then the sliding mode control based on the linear extended state observer (LESO) and the third-order tracking differentiator is established as the speed loop control of the system. Finally, the parameters of the nonlinear ADRC which built control system’s position loop are optimized by the improved differential evolution (DE) algorithm. The speed loop simulation results show that the proposed algorithm has better control effect than PID control algorithm, Robust control algorithm, and ADRC control algorithm;The simulation of position loop demonstrates that the performance of the controller optimized by DE algorithm is better than the parameter tuning based on experience. The experimental results illustrate that the proposed control algorithm can ensure that the optoelectronic tracking equipment can track the target which 3km away with 0.1 mrad accuracy.

The ankle rehabilitation in certain injuries requires passive movements to aid in the prompt recovery of ankle movement. In the last years, parallel ankle rehabilitation robots with multiple degrees of freedom have been the most studied for providing such movements in a controlled way. Nevertheless, the high cost does not make it viable for home healthcare. Then, this paper presents an optimization approach where a spherical mechanism of one-degree-of-freedom is proposed as a low-cost ankle rehabilitation device to provide the passive rehabilitation exercise for plantar flexion/dorsiflexion and adduction/abduction ankle movements. The approach is formulated as a mono-objective constraint optimization problem where the relative motion angle of the mechanism, the Grashof criterion, the force transmission, and the rehabilitation routine are included. The link lengths of the mechanism parameterized in Cartesian coordinates are found by the two most representative differential evolution variants. The statistical analysis of optimizers indicates that the $DE/rand/1/bin$ finds, on average, more promising solutions through algorithm executions than the $DE/best/1/bin$ . The numerical simulation results and the motion simulation of the CAD model illustrate the obtained ankle rehabilitation mechanism, indicating that the percentage error between the desired rehabilitation path and the curve generated by the coupler point of the mechanism is in the interval $[{0.036,0.437}]\%$ . Manufacturing the ankle rehabilitation mechanism with a 3D printer validates the optimization approach and verifies the resulting mechanism.

Significant opportunity for savings in energy and investment through improved performance of power distribution systems exists in the optimal placement and rating of capacitors, a conventionally cost-effective and popular reactive power compensating technology. A novel optimal capacitor planning (OCP) procedure is proposed for large-scale utility power distribution systems, which is exemplified on an existing utility circuit of approximately 4,000 buses. An initial sensitivity analysis is employed to intelligently reduce OCP computation time and maintain quality of optimal configurations. Three optimization objectives are considered, including the minimization of total system active power losses, standard deviation of node voltages, and investment in total capacitor power rating. Eight multi-objective optimization methods that employ the non-dominated sorting algorithm III (NSGA-III) concept are compared to determine individual merits. Differences between the methods include the incorporation of a penalty constraint for voltage violations and the automatic readjustment of load-tap-changing (LTC) transformer tap settings for proposed capacitor re-configurations concurrently within the optimizer, which ensures peak system performance and fair comparison to the reference case. A multi-step model conversion process was developed with OpenDSS to enable the OCP procedure to be generally applicable to real large-scale utility circuits. OCP is performed for three example sub-circuits served by a substation with a 48MW, 9Mvar peak load, which represents the most extreme case and offers the best opportunity for savings. Example configurations from the resulting Pareto sets through a pseudo-weight vector approach are also analyzed through a systematic procedure of comparison between the most extreme configuration types to inform configuration selection.

This paper presents a visualisation tool (ECvis) that aids the development of population based numerical optimisation algorithms such as genetic algorithms and differential evolution. The tool provides a simple interface with three modes: A Density mode that allows the user to quickly view the distribution and density of the population throughout the fitness and search space for high dimensional problems. This provides the ability to quickly establish where the population is clustering, which can indicate potential local and global minima; A Statistical mode that allows the user to visualise the individuals that have statistical significance in the population and their location in the search space; A Ranges mode that provides the user with a windowed average of the minimum, maximum and median value of each parameter of the population and whether the range of each parameter has changed since the previous window. This allows the user to see whether the population is exhibiting exploration or exploitation properties, as well as convergence properties such as the variance of each parameter. As examples of the usefulness of ECvis, two well known, high dimensional functions are optimised using differential evolution with ECvis being used to provide information on the performance of the optimisation.

A lot of studies for spacecraft design have been carried out in the past to ensure space mission success without compromising the scientific data but electromagnetic issues always puzzle engineers. The mission science objectives rely on the scientific payload high sensitivity to accurately capture the space environment. Electromagnetic cleanliness is a permanent issue in order for the measurements to reflect that and not the spacecraft emissions. The majority of the past and current ESA’s, NASA’s and JAXA’s science missions utilizes more or less the same basic working units, i.e. RF switches, batteries, Command & Data Handling Management units, Power Conditioning and Distribution Units, S-Band Transceivers, etc. These components that can be easily measured and electromagnetically characterized in ground facilities and testing laboratories. This work provides the framework for a complete unit positioning methodology, considering the unit test-level information, in order to predict and properly allocate the spacecraft equipment for simultaneous electric and magnetic cleanliness even in different sensors locations. This methodology can be adapted for a fast pre-compliance testing and possibly early design considerations in every space mission.

SMOTE is a classical oversampling method and aims to improve imbalanced classification by creating synthetic minority class samples. Overgeneralization is a great challenge in SMOTE and its improvements. Multiple variations of SMOTE are proposed against imbalances between classes and overgeneralization. However, they still have the following issues: 1) most methods depend on too many parameters; 2) most methods fail to detect suspicious noise effectively and modify them; 3) interpolation of almost all methods is susceptible to abnormal samples. To overcome the above issues, a new synthetic minority oversampling technique based on adaptive local mean vectors and improved differential evolution (SMOTE-LMVDE) is proposed. First, a new noise detection technique based on the defined adaptive local mean vectors (NDALMV) is proposed to find suspicious noise. Second, an improved differential evolution is proposed to modify and improve detected suspicious noise. Finally, a new interpolation based on the defined adaptive local mean vectors is proposed to create synthetic minority class samples. Experiments prove that the proposed method superior to 7 popular oversampling approaches on extensive data sets in the training nearest neighbor classifier and the decision tree classifier.

Slime Mould Algorithm (SMA) is a new meta-heuristics algorithm that is inspired by the behaviors of slime mould from nature. Due to its effective performance, SMA has shown its competitive performance among other meta-heuristics algorithms and has been used in many mathematical optimization and real-world problems. However, SMA tends to sink into local optimality and lacks the diversity of the population. Therefore, to cope with the drawbacks of the classical SMA, this paper proposes an improved SMA algorithm named CHDESMA. First of all, the chaotic maps methods have the characteristics of ergodicity and randomness, and we used chaotic maps methods to replace the original random initialization to improve the diversity of the algorithm, which is more suitable for exploring the potential areas in the early stage. Then, based on the superior searching ability of the differential evolution algorithm (DE), the crossover and selection operations of DE are applied to CHDESMA, and the position is updated by the combination of the original SMA operator and the mutation strategy of DE, which effectively avoids the algorithm falling into local optimum. CHDESMA was evaluated using CEC2014 and CEC2017 test suits and four real-world engineering problems. CHDESMA was compared with advanced algorithms and DE variants. The experimental results and statistical analysis indicate that CHDESMA has competitive performance compared with the state-of-the-art algorithms.

In this study, an improved African vulture optimization algorithm (IAVOA) that combines the African vulture optimization algorithm (AVOA) with both quasi-oppositional learning and differential evolution is proposed to address specific drawbacks of the AVOA, including low population diversity, bad development capability, and unbalanced exploration and development capabilities. The improved algorithm has three parts. First, quasi-oppositional learning is introduced in the population initialization and exploration stages to improve population diversity. Second, a differential evolution operator is introduced in the local search position update of each population to improve exploration capability. Third, adaptive parameters are introduced to the differential evolution operator, thus balancing the algorithm exploration and development. A numerical simulation experiment based on 36 different types of benchmark functions showed that while the IAVOA can enhance the convergence speed and solution accuracy of the basic AVOA and two variants of AVOA, IAVOA outperforms the other 7 swarm intelligence algorithms in the mean and best values of 33 benchmark functions.

The differential evolution (DE) is a well known population-based evolutionary algorithm that has shown capabilities for solving real-world problems such as resource allocation, multicast routing, and localization of target nodes. However, the accuracy of the DE, like other evolutionary algorithms, depends on the settings of its control parameters. The localization of target nodes is highly nonlinear and multi-modal, which may trap the DE in a local optimum. A local optimum may be avoided by a proper selection of the control parameters. One of the key control parameters is the population size (PS), which affects directly the localization accuracy and computational complexity. Finding an adequate PS throughout the evolution process is a challenging task. Even if an adequate PS is found it may not be the adequate PS anymore when the scenario of a problem changes. Although several approaches have been proposed for adapting the PS, they have not been evaluated when solving the localization problem. In this paper, a comprehensive comparison in terms of accuracy and computational demand is conducted among the state-of-the-art PS adaptation techniques when employed with the DE for solving the localization problem of target nodes in various scenarios. We also propose three new PS adaptation techniques, namely, exponential, parabolic, and logistic reduction. The results from extensive numerical simulations show that, after setting the initial PS properly, there is no technique that outperforms the others in practically all the scenario of the localization problem. Additionally, the DE with the proposed techniques provides competitive localization accuracy with considerably less computational complexity. Specifically, The proposed approaches reduce the computational demand by approximately 50 % over the standard DE in all the scenarios considered here.

In the new era, the Internet of Everything (IoE) provides distributed services like data, processes, people, and things, etc. The services to the connected IoE significantly increase the time of service, workload, energy consumption, and delay. These objectives conflict with each other. To address the issue, a novel multi-objective based evolutionary algorithm is proposed. In the proposed method, a new rapid mutation operator is incorporated with multi-objective differential evolution (MODE) to overcome the stagnation of the local optimum. The proposed method to maintain the diversity and enhance the convergence speed of the existing MODE algorithm is described. The proposed method provides more diversity and convergence speed for choosing better candidate solutions. The addition of the proposed method is evaluated with the application of IoE services. We have designed the two objective and three objective-based IoE services scenarios. Furthermore, the proposed method optimizes services like service cost, service delay, and the lifetime of sensors. It is interesting to observe that the proposed approach better performs the most recent state-of-the-art multiobjective evolutionary algorithms.

In this work, a new constrained numerical optimization approach is proposed for solving offline the Inverse Kinematics Problem (IKP) of articulated robots, which consists on optimizing the joint displacement while the end effector is positioned and oriented in a desired pose. The novelty of this approach is in the formulation of the optimization problem, where the objective function calculates the minimum joint displacement, with the position and orientation errors handled as equality constraints. This formulation may avoid configurations containing singularities. The IKP is solved for a defined trajectory in the dexterous workspace of the robot by using two versions of the Differential Evolution algorithm and considering two stages. First, DE/rand/1/bin is used for positioning and orienting the end effector at the first point of the trajectory regardless of its initial position. The second stage applies DE/best/1/bin in order to emphasize the exploitation process and minimize the computational time to obtain the inverse kinematics due to the closeness that exists between the consecutive points that make up the trajectory. This combination of DE versions is another contribution of the proposed approach that speeds up considerably the search process by first prioritizing the exploration and then the exploitation, and this sequential application can be used to the solution of diverse constrained numerical optimization problems. Finally, the IKP for the IRB-1600 robot was solved as a case study considering two trajectories in its dexterous workspace, circular and Lissajous. The results generated by the proposed approach for the case study were simulated in the RoboDK® industrial robot simulator.

In this paper, efficient optimal design approaches based on mosaic optimization concept are developed for NRD guide devices to realize the high-performance compact millimeter-wave integrated circuit. Binary representation-based genetic algorithm, differential evolution algorithm, harmony search algorithm, firefly algorithm, and particle swarm optimization are developed to efficiently optimize the pixel pattern in the design region of NRD guide devices. To demonstrate the usefulness of these population-based optimizations, a comparative study based on the problem-solving success rate is conducted first. To carry out this study, four NRD circuit components are designed which include low crosstalk waveguide crossing, T-branch power splitter, bending waveguide, and frequency demultiplexer. The proposed optimal devices achieve high transmission efficiencies greater than 99.9%, 49.9%:49.9%, 99.9% at 60 GHz and 96.4%, 98.5% at 59 GHz and 61 GHz. In addition, the same NRD guide components except frequency demultiplexer are also designed at wideband operation and achieve broad bandwidth around 5 GHz, 4 GHz, and 3 GHz. In order to improve the computational efficiency, the originally developed two-dimensional full vectorial finite element method is employed for the numerical simulations. This paper demonstrates the detailed implementation procedure of developed evolutionary approaches for the material distribution in the design region of NRD guide devices, comparative study of developed optimization approaches, and proposed highly attributed NRD circuit components for the realization of NRD based high-performance compact millimeter-wave circuit.

In the face of massive texts, dimensionality reduction algorithm and efficient classification model have become the key steps for sentiment classification of microblogs. X2 statistics and TF-IDF statistics are commonly used dimension reduction methods. When applied to micro-blog sentiment analysis, traditional X2 statistics do not consider the probability of a certain sentiment word in a micro-blog text. TF-IDF weight measure ignores the synonyms in the text of micro-blog. Therefore, this paper proposes a NewChi-TF-IDF feature selection method combining form and semantics. In the classification stage, the generalization performance of single classifier is low. To enhance the generalization performance of Weibo sentiment classification, based on the existing ensemble strategy, differential evolution algorithm is introduced to assign different excitation functions to multiple weak classifiers to train the optimal weight distribution. Thus, the problem that the weight of weak classifier is difficult to determine is solved. Experimental results show that NewChi-TF-IDF feature selection method reduces the dimension, and the generalization ability of the proposed algorithm is enhanced, and the average F-score of the proposed algorithm is improved to a higher degree than that of Ada-All and Vote-All classifiers.

Early fault diagnosis is essential for the proper operation of rotating machines. This article proposes a fitness function in differential evolution (DE) that considers accuracy rate and false negative rate for optimization in brushless DC (BLDC) motor fault diagnosis. Feature selection based on a distance discriminant (FSDD) calculates the feature factors which base on the category separability of features after the Hilbert–Huang transform (HHT) which extracts the features of four different type signals from BLDC motor Hall sensor. The feature rank through DE to optimize before the features into the backpropagation neural network (BPNN) in order. By reducing the feature number of Hall signal and decreasing the complexity of neural network input, the combined method was proposed in this article can significantly reduce the calculation cost. Finally, the identification model obtained an accuracy rate of 98.98% and false negative rate of 13.66% when there were 18 features; besides, receiver operating characteristic (ROC) curve and probability curve have been evidenced the number of false negative is decreased. Moreover, the experiments have verified that the proposed method is effective in UCI data set.

Evolutionary algorithms have shown great successes in various real-world applications ranging in molecule to astronomy. As a mainstream evolutionary algorithm, differential evolution (DE) possesses the characteristics of simple algorithmic structure, easy implement, and efficient search performance. Nevertheless, it still suffers from the issues of local optimal trapping and premature of evolution problems. In this study, we innovatively improve the performance of DE by incorporating a full utilization of information feedback, which includes the population’s holistic information and the direction of differential vectors. The proposed permutation-archive information directed differential evolution (PAIDDE) algorithm is verified on a set of 29 benchmark numerical functions and 22 real-world optimization problems. Extensive experimental and statistical results show that PAIDDE can significantly outperform other 12 state-of-the-art algorithms in terms of solution qualities. Additionally, the computational complexity, solution distribution, convergence speed, search dynamics, and population diversity of PAIDDE are systematically analyzed.

UAV-enabled mobile edge computing (MEC) is an emerging technology to support resource-intensive yet delay-sensitive applications with edge clouds (ECs) deployed in the proximity to mobile users and UAVs served as computing base stations in the air. The formulated optimization problems therein are highly nonconvex and thus difficult to solve. To tackle the nonconvexity, the successive convex approximation (SCA) technique has been widely used to solve for the nonconvex optimization problems by transforming the nonconvex objective functions and constraints into suitable convex surrogates. However, the optimal solutions are based on the approximated optimization problem not the original one and they are highly dependent on the feasible solution initialization. Unlike SCA, Differential Evolution (DE) is a global optimization method that iteratively updates the best candidate solutions with respect to the predefined objective functions. DE works well especially in unconstrained optimization problems since it can freely search very large regions of possible solutions without considering the convexity of the original problem. However, when it comes to the constrained optimization problem, DE becomes inefficient to find the feasible and optimal solutions within given time limits. In view of the shortcomings incurred in both DE and SCA, we propose an innovative algorithm by jointly applying DE and SCA (DE-SCA) to solve for the nonconvex optimization problems. However, directly using full DE solutions to initialize the SCA-based algorithm will result in worse objective function values as the DE solutions are often infeasible. Therefore, we further design to screen the feasible parts from the DE solutions and utilize them to initialize the SCA-based algorithm. In experimental simulations, we consider a system of UAV-enabled MEC where IoT devices, the UAV and ECs interact with each other. The simulation results demonstrate that our proposed Screened DE-SCA algorithm largely outperforms the benchmarks including DE, SCA-based and state-of-the-art algorithms in the UAV-enabled MEC system.

The paper is a continuation of our previous research where a novel concept of multisize island model was proposed. Such multisize approach facilitates the design of island-based algorithms and brings such benefits as: improved fitness dynamics throughout the entire time of operation even without the migration of solutions between the islands. The absence of migration eliminates the need to establish the topology and the policy of migration. It also makes the efficiency of multisize island-based algorithms independent of the particular islands’ size and eliminates the need of tuning the size of islands which is usually done in the case of the canonical island model. All these features indicate the superiority of the multisize island model over the canonical one. In this paper we improved earlier proposed multisize island-based DE algorithm by adding to it the ability to automatically optimize the number of islands in operation. This feature enables the release of most computational units before the algorithm completes its operation in the case of concurrent execution of the algorithm on multiple computational units, or reduction of the algorithm running time in the case of its execution on a single computational unit. The proposed algorithm was tested by solving computationally difficult scheduling problem, which is the discrete-continuous scheduling with continuous resource discretization.

In the decomposition-based multiobjective evolutionary algorithms (MOEA/Ds), a set of subproblems are optimized by using the evolutionary search to exploit the feasible regions. In recent studies of MOEA/Ds, it was found that the design of recombination operators would significantly affect their performances. Therefore, this paper proposes a novel genetically hybrid differential evolution strategy (GHDE) for recombination in MOEA/Ds, which works effectively to strengthen the search capability. Inspired by the existing studies of recombination operators in MOEA/Ds, two composite operator pools are introduced, each of which includes two distinct differential evolution (DE) mutation strategies, one emphasizing convergence and the other focusing on diversity. Regarding each selected operator pool, two DEs are applied on parents' genes to hybridize offspring by adaptive parameters tuning. Moreover, a fitness-rate-rank-based multiarmed bandit (FRRMAB) is embedded into our algorithm to select the best operator pool by collecting their recently achieved fitness improvement rates. After embedding GHDE into an MOEA/D variant with dynamical resource allocation, a variant named MOEA/D-GHDE is presented. Various test multiobjective optimization problems (MOPs), i.e., UF, F test suites, and MOPs with difficult-to-approximate (DtA) PF boundaries, are used to assess performances. Compared to several competitive MOEA/D variants, the comprehensive experiments validate the superiority of our algorithm.

Bitcoin generates a massive amount of data every day due to its innate transparency and capacity of operating completely decentralised. In this paper, we introduce on-chain metrics derived from data on the bitcoin network that enable us to describe the state and usage of the underlying network. Based on their characteristics, we classify them into user, miner, exchange activities and run a correlation analysis with the price to understand the dynamics of bitcoin's price and its underlying mechanics. Using the correlated data, we develop a deep learning model. However, determining the best values of parameters in a deep learning model can be a very challenging and time-consuming task. Hence, we propose a self-adaptive technique using a jSO optimization algorithm to find the best values of these parameters to accurately predict the price of bitcoin. Compared to traditional LSTM model, our approach is highly accurate and optimised with a minimum error rate.

This paper proposes a novel adaptive range composite differential evolution (ARCoDE) algorithm to efficiently and accurately solve optimal reactive power dispatch (ORPD) problem. Because of a novel adaptive range strategy for control parameters, the proposed ARCoDE possesses superior exploration and exploitation capabilities that can efficiently handle the ORPD problem involving complicated constraints and discrete and continuous variables. This has been demonstrated in case studies using the IEEE optimal power flow testbeds considering complex wind and demand scenarios. The superior performance of ARCoDE has been further validated through comparisons with several award-winning algorithms in 2014 IEEE Competition on “Application of Modern Heuristic Optimization Algorithms for Solving Optimal Power Flow Problems”, given limited iterations of in evolutionary optimization process.

Optimization algorithms have proven to be a useful tool in different areas of water resource management including water distribution network (WDN), which may be modelled as a large scale, combinatorial problem subject to constraints with the typical objective of minimizing the cost. In this study, a fuzzy C-means adaptive differential evolution (FCADE) is proposed to solve three well-known WDN problems: the two-loop distribution network problem, the Hanoi distribution network problem, and New York tunnel distribution network problem. FCADE is integrated with a well-known simulation software EPANET to manage the pressure constraints requirement. A comparative analysis of results through various performance metrics indicate the competence of FCADE for solving complex WDN problems.

In this article, the concurrent optimal design of a planar five-bar parallel robot for a high-speed pick and place task is considered. A trade-off between trajectory tracking, energy consumption and deformation of the flexible links is sought. Due to the high-speed operation, the minimization of the vibratory effect is considered since the design stage. Thus, the design is stated as a non-linear multi-objective dynamic optimization problem that is solved through the Differential Evolution (DE) algorithm, as well as, feasibility rules for constraints handling. Mechanical structural variables that modify the inertial parameters of the rigid and flexible links, as well as, control variables related to gains of a PID controller are considered as independent variables. This problem is subject to maximum torque that each motor could provide; inherent constraints for link manufacture; dimensional synthesis; Grashof's criterion and initial and boundary conditions. Results show that it is possible, despite the vibrational phenomenon, to reduce the energy consumption without loss of precision through an appropriate mass balance of the actuated links.

Power flow (PF) analysis of microgrids (MGs) has been gaining a lot of attention due to the evolution of islanded MGs. To calculate islanded MGs’ PF solution, a globally convergent technique is proposed using Differential Evolution (DE)- a popular optimization algorithm for global non-convex optimization. This paper formulates the PF problem as a constrained optimization problem (COP) considering all the operating conditions of the Droop Controlled Islanded MGs (DCIMGs). To solve the proposed COP, $\epsilon $ DE-NGM, (Epsilon based Differential Evolution with Newton-Gauss-based mutation) is proposed. The proposed algorithm, $\epsilon $ DE-NGM, is a novel variant of DE since it comprises a novel mutation operator, Newton-Gauss-based mutation (NGM). NGM includes all the important features of DE’s mutation strategies as well as reduces the constraint violation by utilizing the information of constraint-space. Numerical experiments validate that the global convergence ability of proposed algorithms in solving COPs than existing state-of-the-art algorithms. Furthermore, the proposed algorithm as a PF tool has better robustness than existing tools on ill- and well-conditioned systems with heavy loads, different limit violations, and inappropriate final solutions (far from the flat start). The performed comparative analysis confirms good agreement of accuracy and efficacy with the existing method for islanded MG’s PF.

This article presents an 11-level operation of the WE (Wee)-Type inverter. The topology employs a single DC-source, has a reduced number of components, and exhibits a boosting capability. A voltage balancing algorithm is proposed where the inverter’s redundant states are employed to maintain the auxiliary DC-link voltage. It is shown that with the control algorithm, the link voltage is preserved at half the primary DC-link voltage, and the 11-level operation is possible for any load. The presented 11-level WE-type structure is also compared with recent 11-level structures and has a lowest cost factor. Two modulation strategies verify the 11-level operation of the inverter: first, a modified nearest level control (MNLC) with the usage of both zero states is developed; and, second, selective harmonic elimination (SHE) is employed, where the angles are generated using a differential evolution (DE) technique. The maximum efficiency of the inverter is 97.55 %. The performance of the inverter is validated in MATLAB/Simulink and on the hardware-in-the-loop platform.

During last two decades, Differential Evolution (DE) proved to be one of the most popular and successful evolutionary algorithms for solving global optimization problems over continuous space. Proposing new mutation strategies to improve the optimization performance of (DE) is considered a significant research study. In DE, mutation operation plays a vital role in the performance of the algorithm. Therefore, in this paper, comprehensive analysis of the contributions on basic and novel mutation strategies that were proposed between 1995 and 2020 is presented. A new taxonomy based on the structure of the novel mutations is proposed. Numerical experiments on a set of 30 test problems from the CEC2017 benchmark for 10, 30, 50 and 100 dimensions, including a comparison with classical DE schemes and recent mutations schemes are executed. Furthermore, theoretical, and empirical convergence behavior analysis of all mutations is discussed. The paper also presents many recommendations, guidelines, insights, and suggestions for experienced practitioners and interested researchers in designing and developing effective and efficient DE algorithms to address various optimization problems in different fields.

When disasters happen, victims suffer from lots of miseries. Vehicles are used to carry relief supplies for these victims. However, these vehicles are subject to threats as roads and bridges are often destroyed by these disasters. To dispatch vehicles safely and minimize the misery of victims, a disaster emergency vehicle path planning model is proposed by introducing the deprivation cost function and two constraints. One constraint is the risk of the route, and the other is the angle of the vehicle. A differential evolution algorithm based on the exponential selection is developed to optimize the model. The proposed algorithm uses the exponential ranking method, making individuals have exponential probability as parents enter into the mutation stage. The approach improves the exploitation capacity while maintain the exploration ability of the algorithm. Three disaster scenarios in three-dimension are used to do simulations. The experimental results have verified that our proposed model can deal well with the vehicle path planning problem in disaster emergency management. The proposed algorithm has acquired superior performances compared with differential evolution variant algorithms.

Different from multiobjective differential evolution algorithm (MODE) based on traditional mutation operators and a single population, this paper developed a bagging based MODE with multiple subpopulations (BagMPMODE) by incorporating the idea of bagging into the evolution process of MODE. In this algorithm, multiple subpopulations with different evolution operators are adopted to maintain search diversity, as did by some previous researches on MODE. During evolution, the subpopulations will compete with each other, i.e., the size of each subpopulation will be adjusted based on its contribution to the whole search result. Based on the multiple subpopulation strategy, the idea of bagging ensemble is adopted to generate offspring solutions, which can be viewed as the cooperation of these multiple subpopulations. The proposed BagMPMODE algorithm is evaluated on a set of 22 benchmark problems, and computational experiments illustrate that the BagMPMODE algorithm is competitive or even superior to several state-of-the-art MODEs and some other multiobjective evolutionary algorithms in the literature for most problems.

This article studies the data collection task planning for a fixed-wing unmanned aerial vehicle (UAV) in forest fire monitoring. Multiple wireless-based detection nodes (DNs) are distributed in high-risk areas of the forest to monitor the surrounding environment. The task of UAV is to circularly fly to them and collect the environmental data. Because of the kinematic constraints of UAV and the effective communication range between UAV and DN, this problem can be generally regarded as a Dubins traveling salesman problem with neighborhood (DTSPN). A bi-level hybridization-based metaheuristic algorithm (BLHMA) is proposed for solving this problem. At the first level, differential evolution (DE) optimizes the continuous-valued communication positions and UAV headings by the population-based search. For the asymmetric traveling salesman problem (ATSP) corresponding to the combination of the positions and headings generated by DE, a constructive heuristic based on self-organized multi-agent competition (SOMAC) is proposed to determine the discrete collection sequence. By competitive iterations in such a cooperative way in DE, a high-quality data collection tour can be generated. At the second level, a local search based on multistage approximate gradient is proposed to further refine the positions and headings, which accelerates the convergence of the BLHMA. Referring to a real-world scene of forest fire monitoring, the simulation experiments are designed, and comparative results show that BLHMA can find significantly shorter data collection tours in most cases over three state-of-the-art algorithms. The proposed UAV data collection planning algorithm is conducive to the efficient execution of the forest fire monitoring data collection mission and the energy saving of UAV.

The recent years has witnessed a rapid development of Deep Learning (DL) based Automation Modulation Classification (AMC) methods, which has proved to outperform traditional classification approaches. In order to disturb the deep neural networks for AMC, in this paper, we propose an adversarial attack method to generate fake signals for fooling DL-based classifiers. Firstly, some constraints on visual difference and recoverability of fake signals are defined. Next, a Few Data Point Attacker (FDPA) is proposed to generate fake signals with few perturbed data points via differential evolution algorithm. Some experiments are taken on a public dataset, RML 2016.10a, and the results show that fake signals generated by the FDPA can remarkably reduce the accuracies of three types of DL-based AMC classifiers, a Convolutional Neural Network (CNN) based classifier, a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) based classifier, and a classifier combined with CNN and LSTM-RNN. The code will be available.

Prediction of incidences of thunderstorms using different techniques is quite well established. To add to this knowledge, in this paper, a heuristic equation is proposed which relates the correlation coefficient of atmospheric parameters with the number of hourly incidences of thunderstorms. There are four ways to compute the indices values from the proposed heuristic equation. These indices values are used in the classification of the hourly incidences of thunderstorms. The proposed equation and indices work well, as tested on pre-monsoon hourly atmospheric data from 2018 and validated with hourly data from April 2019 and 2020. From the four indices, the first index value is computed with normalized average values of parameters of only hourly incidence of thunderstorms data of 2016-2017 in the month-wise method. The other three indices use optimization techniques namely, the Teaching Learning Based Optimization (TLBO) technique, Differential Evaluation (DE), and Simulated Annealing (SA). TLBO shows better classification of hourly incidences of thunderstorms for 2018 atmospheric data. TLBO is also precisely validating the hourly incidences of thunderstorms for April 2019 and April 2020 hourly atmospheric data. It performed better with 2020 data by 88%. The variations of atmospheric parameters before, after or, during the incidences of thunderstorms are also depicted.

Chaotic maps used to shuffle and manipulate the image pixels are important for image encryption (IE). In this study, a novel 2D optimized chaotic map (OPMAP) using a triple-objective differential evolution (TODE) algorithm is presented for IE. A model for OPMAP with eight decision variables is empirically designed, and then its variables are determined utilizing TODE through minimizing a triple-objective function that involving Lyapunov exponent (LE), entropy and 0–1 test. OPMAP is assessed with respect to credible measurements like bifurcation, 3D phase space, LE, 0–1 test, permutation entropy (PE) and sample entropy (SE). The capability of OPMAP is then verified through an IE scheme including permutation and diffusion through various cryptanalyses: key space 2298, mean entropy 7.9995, mean correlation 13.61E-5, number of pixels changing rate (NPCR) 99.6093, unified average changing intensity (UACI) 33.4630 and encryption processing time (EPT) 0.2919 (s). A detailed review of IE schemes reported elsewhere is presented and IE performance of OPMAP is also validated by comparison with those IE schemes with and without optimization used. The 2D-OPMAP-based IE is faster and has low computational complexity. Moreover, the proposed it shows better cryptanalysis results for the most of the comparisons.

Electricity theft has emerged as one of the major reasons of Non-Technical Losses (NTLs) in the power distribution systems and has become a global issue. Therefore, power utilities are concerned about resolving the issue of electricity theft. In this regard, the data collected by Advanced Metering Infrastructure (AMI) can be used to devise data-driven machine learning-based Electricity Theft Detection (ETD) methods. In this paper, a novel data-driven ETD method is proposed that firstly labels the electricity consumers as fair or malicious based on three analyses: intra-consumer, inter-consumer, and temperature-electricity consumption relation. After assigning labels to the data, significant features are extraction from data by introducing a new feature extractor that is based on Reconstruction Independent Component Analysis (RICA) and sparse auto-encoder. Finally, classification is performed using two newly proposed enhanced classifiers, named as Differential Evolution (DE) Random Undersampling Boosting (DE-RUSBoost) and Jaya-RUSBoost. The performance of RUSBoost is enhanced using two nature-inspired swarm intelligence-based optimization algorithms, namely DE and Jaya optimization. The performance evaluation of the proposed classifiers is performed by conducting comprehensive simulations on real-world data taken from the UMass* smart homes electricity consumption dataset and the State Grid Corporation of China (SGCC) electricity theft dataset. DE-RUSBoost achieves an Area Under the Curve (AUC) of 0.89 and Jaya-RUSBoost achieves AUC of 0.95. The proposed classifiers have superior performance compared to two state-of-the-art benchmarks, i.e., Wide And Deep Convolution Neural Network (WADCNN) and grid search-based RUSBoost.