Search

In real life, some complex problems are multi-objective optimization problems. Most of the existing studies have focused on how to obtain the optimal solutions distributed on the whole Pareto-optimal frontier. However, in some fields such as industrial production, the decision-makers of enterprises usually care about what specific measures can maximize the comprehensive benefits of enterprises. Due to this kind of realistic demands, we prefer to find a small part of the optimal solutions according to the preference information suggested by the decision-makers rather than obtain all of the Pareto-optimal solutions. However, almost all of the existing methods only repeat calculation when they meet the scenario where the user-preferences change over time. To address the multi-objective optimization problem under the scenario with dynamic user-preferences information, we propose a MOEA/D-DPRE (multi-objective optimization algorithm based on dynamic preference information) algorithm in this paper, and its framework is inspired by the MOEA/D-PRE (decomposition user-preference multi-objective evolutionary) algorithm. We analyze the four position relations between the distribution region of the old preference weight vectors (old preference region), and we also present the distribution region of the new preference weight vectors (new preference region) and propose the different strategy to the different case respectively. When the preference information changes, the MOEA/D-DPRE can converge to the region of new interest by responding to the change of preference and the historical information. Experimental results show that the proposed method is better than the compared method in convergence speed and distribution under the scenario with dynamic user-preferences information.

Concrete columns are the most important load-bearing components in civil structures. The potential damage in reinforced concrete (RC) columns could be categorized into three different failure modes: flexural shear (FS) failure, flexural-failure (FF), and shear failure (SF). The corresponding hysteresis loops for each mode differ significantly. Therefore, a multi-parameter hysteretic restoring force model is needed to describe the hysteretic energy dissipation phenomenon and behavior. Identification of the optimal parameter values of a multi-parameter hysteresis model of RC columns under different failure modes is essential in the evaluation of structural inelastic seismic performance. In this paper, a multi-objective optimization algorithm called NSGA-II is employed to identify the parameters of Bouc–Wen–Baber–Noori model (BWBN) hysteresis model, this model has been used for describing the response and modelling restoring force behavior in several structural and mechanical engineering systems, that can fully describe the hysteretic restoring force characteristics of RC columns. An objective function for the restoring force is proposed to identify the parameters of BWBN model. In order to ensure the accuracy of identification, based on the sensitivity analysis, the parameters distribution law of RC columns in different failure modes is obtained. Furthermore, the reference values under different failure modes are proposed. The results presented in this paper will significantly reduce the calculation of subsequent identification. Twelve groups of experimental data are randomly selected to verify the feasibility of the above algorithm. It is demonstrated that using the multi-objective optimization algorithm leads to better identification accuracy with minimum prior experience. Performance of the algorithm is verified using simulated and experimental data. The experimental data of the RC columns were collected from the database of the Pacific Earthquake Engineering Research Center.

This paper presents a new and efficient hybrid multi-objective optimization algorithm based on marine predators algorithm (MPA) and differential evolution (DE) for solving the economic emission dispatch (EED) problem considering wind power uncertainty. In this algorithm: (1) the MPA is improved properly and extended to the multi-objective domain; (2) the improved MPA and the DE algorithm are combined to enhance the optimization performance of the proposed algorithm by taking advantage of their individual advantages. (3) an external archive based on a new dynamic crowding distance is used to obtain a uniformly distributed Pareto optimal front. In addition, to obtain feasible solutions, a constraint handling method in which feasible solutions dominate is embedded in the proposed algorithm to deal with the various constraints of the problem. Simulation experiments are carried out on the IEEE 30-bus 6-generator test system injecting the wind power and 10-generator test system considering the wind power and valve-point effect. Results show that the proposed algorithm is effective and superior to other algorithms.

Engine hood is one of the important parts of the vehicles, which has influences on the lightweight, structural safety, pedestrian protection, and aesthetics. The optimization design of engine hood is a high-dimensional, multi-objective, and mixed-variable optimization problem. In order to reduce the physical test investment in the development and improve the efficiency of optimization, this article proposes a data-driven method for optimal hood design. A newly proposed single-objective optimization algorithm is improved by several strategies for multi-objective constrained problem with mixed variables. Then the hood is optimized through the specially designed machine learning model. Finally, both the hood's weight and pedestrian injury are reduced while maintaining structural stiffness and frequency in the desired range. The comparative study and final hood optimization results prove the effectiveness of the proposed method.

The difficulty of obtaining the characteristics of the corpus database of neural machine translation is a factor hindering its development. In order to improve the effect of English intelligent translation, based on the machine learning algorithm, this paper improves the multi-objective optimization algorithm to construct a model based on the English intelligent translation system. Moreover, this paper uses parallel corpus and monolingual corpus for model training and uses semi-supervised neural machine translation method to analyze the data processing path in detail and focuses on the analysis of node distribution and data processing flow. In addition, this paper introduces data-related regularization items through the probabilistic nature of the neural machine translation model and applies it to the monolingual corpus to help the training of the neural machine translation model. Finally, this paper designs experiments to verify the performance of this model. The research results show that the translation model constructed in this paper is highly intelligent and can meet actual translation needs.

Feature selection (FS) is a critical step in data mining, and machine learning algorithms play a crucial role in algorithms performance. It reduces the processing time and accuracy of the categories. In this paper, three different solutions are proposed to FS. In the first solution, the Harris Hawks Optimization (HHO) algorithm has been multiplied, and in the second solution, the Fruitfly Optimization Algorithm (FOA) has been multiplied, and in the third solution, these two solutions are hydride and are named MOHHOFOA. The results were tested with MOPSO, NSGA-II, BGWOPSOFS and B-MOABC algorithms for FS on 15 standard data sets with mean, best, worst, standard deviation (STD) criteria. The Wilcoxon statistical test was also used with a significance level of 5% and the Bonferroni–Holm method to control the family-wise error rate. The results are shown in the Pareto front charts, indicating that the proposed solutions' performance on the data set is promising.

Obtaining a specific region from the efficient front for multi-objective and practical optimization problems helps decision-makers. Reference point approaches are suggested to reach the region of i...

5G network plays a vital role in each field. Recently, the number of 5G users are increasing due to their vast merits. But, these users require various resources to operate effectively. Recently, t...

In the past few decades, evolutionary multi-objective optimization has become a research hotspot in the field of evolutionary computing, and a large number of multi-objective evolutionary algorithms (MOEAs) have been proposed. However, MOEA is still faced with the problem that the diversity and convergence of non-dominated solutions are difficult to balance. To address these problems, an efficient multi-objective optimization algorithm based on level swarm optimizer (EMOSO) is proposed in this paper. In EMOSO, a sorting method is introduced to balance the diversity and convergence of non-dominated solutions in the whole population, which is based on non-dominated relationship and density estimation. Meanwhile, a level-based learning strategy is introduced to maintain the search for non-dominated solutions. Finally, DTLZ, ZDT and WFG series problems are utilized to verify the performance of the proposed EMOSO. Experimental results and statistical analysis indicate that EMOSO has competitive performance compared with 6 popular MOEAs. The source code of EMOSO is provided at: https://github.com/xuweizhang163/EMOSO .

Stirling engines operate in a variety of temperatures and the electric power production via dish Stirling systems could be considered as an appropriate alternative for high-temperature solar concen...

Most production scheduling problems, including standard flexible job shop scheduling problems, assume that machines are continuously available. However, in most cases, due to preventive maintenance activities, machines may not be available for a certain time. Meanwhile, in the entire workshop production process, the transportation process of workpieces cannot be ignored. Therefore, the impact of transportation on the production planning should be considered in the scheduling process. To consider both preventive maintenance and transportation processes in the flexible job shop scheduling problem, this paper proposes a flexible job shop scheduling problem considering preventive maintenance activities and transportation processes and establishes a multi-objective flexible job shop scheduling model optimizing the total energy consumption and total makespan. Furthermore, a multi-region division sampling strategy-based multi-objective optimization algorithm integrated with a genetic algorithm and a differential evolution algorithm (MDSS-MOGA-DE) is proposed to solve the model. In the proposed algorithm, a multi-region division sampling strategy and two evaluation functions are utilized to improve the diversity of solutions. In addition, this paper combines a genetic operation and a differential operation to further enhance the search ability of the algorithm. The validity of the algorithm is verified by a real case. The computational results reveal that the proposed model and algorithm obtain appropriate results and have the potential to be applied to other similar problems.

The 2MW wind turbine tower is considered as the baseline configuration for structural optimization. The design variables consist of the thickness and height located at the top tower junction. The relationships between the design variables and the optimization objectives (mass, equivalent stress, top displacement and fatigue life) are mapped on the basis of uniform design and regression analysis. Subsequently, five solutions are developed by an algorithm, NSGA-III. According to their efficiency and applicability, the most suitable solution is found. This approach yields a decrease of 0.48% in the mass, a decrease of 54.48% in the equivalent stress and an increase of 8.14% in fatigue life, as compared with existing tower designs. An improved wind turbine tower is obtained for this practice.

The application of multiple UAVs in complicated tasks has been widely explored in recent years. Due to the advantages of flexibility, cheapness and consistence, the performance of heterogeneous multi-UAVs with proper cooperative task allocation is superior to over the single UAV. Accordingly, several constraints should be satisfied to realize the efficient cooperation, such as special time-window, variant equipment, specified execution sequence. Hence, a proper task allocation in UAVs is the crucial point for the final success. The task allocation problem of the heterogeneous UAVs can be formulated as a multi-objective optimization problem coupled with the UAV dynamics. To this end, a multi-layer encoding strategy and a constraint scheduling method are designed to handle the critical logical and physical constraints. In addition, four optimization objectives: completion time, target reward, UAV damage, and total range, are introduced to evaluate various allocation plans. Subsequently, to efficiently solve the multi-objective optimization problem, an improved multi-objective quantum-behaved particle swarm optimization (IMOQPSO) algorithm is proposed. During this algorithm, a modified solution evaluation method is designed to guide algorithmic evolution; both the convergence and distribution of particles are considered comprehensively; and boundary solutions which may produce some special allocation plans are preserved. Moreover, adaptive parameter control and mixed update mechanism are also introduced in this algorithm. Finally, both the proposed model and algorithm are verified by simulation experiments.

The cognitive radio networks is an adaptive and intelligent radio network that is capable of automatically identifying the available channels in the spectrum that is wireless. Cognitive radios modify the parameters supporting the conveyance according to the needs of communication to enhance the operating radio behavior and avail a concurrent communication within the allotted spectrum band at one location. To improvise the parameter configuration the intelligent optimization techniques are been followed nowadays. The paper puts forth a multi-objective optimization algorithm (MO-OPA) for the power management in the cognitive radio networks. The proposed method utilizes the hybridized evolutionary algorithm to reduce the power consumption by minimizing the delay in the communication, intervention and the error rate of the packets. The validation of the proposed method is done to using the network simulator-2 to evince the capabilities of the proposed MO-OPA.

Improving the control performance of active vibration isolation systems is crucial to provide an ultra-quiet environment for precision instruments. This paper presents a new fractional-order robust model reference adaptive controller for the piezo-actuated active vibration isolation systems with a relative-degree-one model. One advantage of the proposed controller lies in that its controller parameters are adjusted online by fractional proportional–integral-type adaptive laws, which not only speeds up the convergence of the closed-loop system, but also improves the control energy efficiency. Moreover, the proposed controller only uses the measurable input and output of the plant as feedback signals, which is convenient for controller implementation. The stability of the closed-loop system is proved based on the Lyapunov theory in detail. The optimal values of the fractional order and adaptive gains for adaptive laws are determined using the multi-objective genetic algorithm through off-line simulation. Comparative experiments on the piezo-actuated active vibration isolation systems are conducted to verify the effectiveness of the proposed controller. Results show that the proposed controller achieves satisfactory isolation performance in a wider frequency band of 20–500 Hz, and simultaneously reduces the control effort compared with the traditional MRAC methods.

Artificial bee colony algorithm as a recent meta-heuristic algorithm, inspired from the foraging behavior of honey bees, can be considered as a proper technique to handle optimization probl...

When the photovoltaic (PV) and solar thermal energy (STE) systems, which share the rooftop area, are installed in the same building, a trade-off problem occurs in terms of the energy, economic, and environmental aspects, and thus, steps need to solve this problem. Therefore, this study aimed to develop a multi-criteria decision support system of the PV and STE systems using the multi-objective optimization algorithm. This system was developed in the following six steps: (i) database establishment; (ii) designing the variables of the PV and STE systems; (iii) development of the analysis engine of the PV and STE systems; (iv) environmental and economic assessment from the life cycle perspective; (v) integrated multi-objective optimization (iMOO) with a genetic algorithm; and (vi) establishment of a multi-criteria decision support system. To verify the robustness and reliability of the developed model, an analysis of “D” City Hall and “I” Airport as target facilities was performed. The optimal PV and STE systems that consider the energy, economic, and environmental aspects at the same time were determined with respect to the 1.23 × 1015 and 1.05 × 1016 installation scenarios, respectively, in terms of effectiveness. The iMOO scores of the existing PV and STE systems installed in “D” City Hall and “I” Airport were 0.358 and 0.346, respectively, whereas those of the optimal solutions were 0.249 and 0.280, showing score improvements. In terms of efficiency, the times required for determining the optimal solutions were 20 and 30 min, respectively. The developed model makes the final decision-maker to find the optimal solution in introducing the PV and STE systems in the early design phase at the same time.

Ecological and economics issues are caused to give careful consideration to electric vehicles (EV) and sustainable power source assets. One of the proposed answers for increment the impact of these assets, is to utilize the electric vehicles potential. The capability of electric vehicles require planning for Smart Distribution Systems (SDS). Request reaction programs, as a suitable device to utilize endorsers’ potential in ideal administration of the system, gives dynamic nearness of supporters in control framework execution change and these projects, in basic conditions, can give the request prerequisites diminishment, in a brief timeframe. In this work, attempts to presents a multi-objective scheduling of EV based on the sustainable assets in smart grid, cover uncertainty caused by inexhaustible assets and EVs, by considering of the request reaction projects and EV battery stockpiling framework, limit the working expenses and the measure of intensity framework contamination, with enhancing procedures. Improved optimization algorithm is utilized for taking care of the advancing issue. Operating costs dropped much further utilizing monetary model of the demand response and vehicle charge/discharge and smart program in the hours when the load is lower. Effectiveness of proposed method is applied on 33 bus standard power system.

In this paper, a novel multi-objective optimization method based on a recently introduced algorithm known as Lightning Attachment Procedure Optimization (LAPO) is presented. The proposed algorithm is based on non-dominated sorting approach where the best solutions chosen from the Pareto Optimal Front (POF), based on crowding distance, are stored in a repository matrix called an Archive matrix. The procedure is performed such that the final best solutions are distributed evenly along the optimal PF. Then, the proposed algorithm is tested by some multi-objective optimization functions and some classical engineering problems also. The results are compared to those of four well-known methods and then discussed. The results are compared using 4 criteria which show how to select a POF close to the true POF, how the results are distributed, and how close the final results approximate all the possible outcomes of true POF. It is shown that the proposed method outperforms the other methods with regards to 3 criteria and yields comparable results regarding the last criteria. Superiority of the proposed method in finding the true POF while covering a wide range of possible optimal results is discussed in the results section. Therefore, it is concluded that the proposed method does an excellent job at solving a wide range of multi-objective optimization problems.

In cloud computing environment, in order to optimize the deployment scheduling of resources, it is necessary to improve the accuracy of the optimal solution, guarantee the convergence ability of the algorithm, and improve the performance of cloud computing. In this paper, a multi-objective optimization algorithm based on improved particle swarm is proposed. A multi-objective optimization model is built. Improved multi-scale particle swarm is used to optimize the built multi-objective model. The combination of the global search capability and the local search capability of the algorithm is realized by using Gaussian variation operator with varied scales. The large scale Gaussian variation operator with concussion characteristics can complete fast global search for decision space, so that particles can quickly locate the surrounding area of the optimal solution, which enhances the ability to escape the local optimal solution of the algorithm and avoids the occurrence of precocious convergence. The small scale variation operator gradually reduces the area near the optimal solution. Experimental results show that the improved particle swarm optimization algorithm can effectively improve the precision of the optimal solution and ensure the convergence of the algorithm.

The data transmission system in the optical WDM network increases the speed of packet transmission by the wavelength of light beams . The Selection of the wavelength and the shortest path to transmit the packets form source to destination is a challenge in a large network architecture. To solve these two problems, the optimization model must handle both the objectives. In this paper we are proposing a novel multi-objective optimization algorithm to solve both the problem of wavelength allocation and shortest path identification in a WDM network. This can be achieved by the enhanced model of Multi-Objective Hunger Locust Optimization algorithm (MO-HLO). In this, it analyse traffic level in a network path and the availability of wavelength present at each time instant. The proposed system retrieves the parameters of network architecture and with the weight value of dynamic traffic occur in the routing path. Among these data, the optimization selects the best among overall feature set of the WDM arrangement. The MO-HLO algorithm extracts the combination of each attribute to form the cluster that segregates the routing path along with the traffic range. From the fitness of the objective function of MO-HLO, the best routing path and the availability of wavelength for a node can be analysed at each time instant. Index Terms: Wavelength Division Multiplexing (WDM), Optimal routing system, Multi-Objective Hunger Locust Optimization algorithm (MO-HLO).

The growing requirement for real-time Internet of Things (IoT) applications has ended with Quality of Service (QoS) communication protocols. where heterogeneous IoT data collection and communication processing contains specific requirements in terms of energy, reliability, latency, and priority. Due to energy constraints, a proper estimation model for monitoring and control is accomplished by the objective of sensing and end-to-end communication respectively. moreover, the connectivity requires a QoS routing protocol to finding the route selection for sensor networks. Hence, data routing and prioritization and Satisfying the QoS requirements are the significant challenges in such networks. So for the Multi-objective Optimization for QoS Routing method is used for differentiating the traffics while data communication and gives the requirements to be caring about the network resource. In this paper, the Energy-Efficient Priority-based Multi-Objective QoS routing (PMQoSR) mechanism ensures the energy and Qos in IoT networks. the proposed system regulates the routing performance based on the QoS parameters, using optimization technique for three hybrid algorithms, named as WLFA- Whale Lion Fireworks optimization algorithm with Fitness Function Routing(FFR) mechanisms .the WLFA to prevent congestion and minimizes the localization error using and select the shortest routing path through the network period uses Priority label and time delay patterns when sending data to the destination. We evaluate its performance and existing competing schemes in terms of Energy-Efficient. The results demonstrate that PMQoSR holds out considering network traffic, packets forwarding, error rate, energy, and distance between the nodes and also considers priority-aware routing to improve the traffic load, throughput, end-to-end delay, and packet delivery ratio when compared with the existing systems.

Research on the integration of renewable distributed generators (RDGs) in radial distribution systems (RDS) is increased to satisfy the growing load demand, reducing power losses, enhancing voltage profile, and voltage stability index (VSI) of distribution network. This paper presents the application of a new algorithm called ‘coyote optimization algorithm (COA)’ to obtain the optimal location and size of RDGs in RDS at different power factors. The objectives are minimization of power losses, enhancement of voltage stability index, and reduction total operation cost. A detailed performance analysis is implemented on IEEE 33 bus and IEEE 69 bus to demonstrate the effectiveness of the proposed algorithm. The results are found to be in a very good agreement.

Electronic spam is a big problem for huge international corporations like AOL, Google, Yahoo and Microsoft. Spam creates many issues and may cause economic damage. Spam causes many problems. Spam creates issues in traffic and bottlenecks, reducing memory, processing capacity and distance. We can describe classification output optimization in computer vision as a multi-objective optimization problem. This paper presents an evolutionary multi-objective optimization algorithm (E-MOA) of the anti-spam filtering issue that discusses both e-mail classification requirements (FP and FN error rates) and e-mail classification times (minimisation). Test findings using a freely accessible model corpus have enabled us to draw significant aspects concerning both the effectiveness of rule-based classification filtering and the appropriateness of a spam filtering two-way classification system. This dataset also uses the DNN classification method, and this classification involves cross-validation. Finally, the e-mail spam classifier is defined based on error rate, accuracy and recall.

The efficient design of battery thermal management systems (BTMSs) plays an important role in enhancing the performance, life, and safety of electric vehicles (EVs). This paper aims at designing and optimizing cold plate-based liquid cooling BTMS. Pitch sizes of channels, inlet velocity, and inlet temperature of the outermost channel are considered as design parameters. Evaluating the influence and optimization of design parameters by repeated computational fluid dynamics calculations is time consuming. To tackle this, the effect of design parameters is studied by using surrogate modeling. Optimized design variables should ensure a perfect balance between certain conflicting goals, namely, cooling efficiency, BTMS power consumption (parasitic power), and size of the battery. Therefore, the optimization problem is decoupled into hydrodynamic performance, thermodynamic performance, and mechanical structure performance. The optimal design involving multiple conflicting objectives in BTMS is solved by adopting the Thompson sampling efficient multi-objective optimization algorithm. The results obtained are as follows. The optimized average battery temperature after optimization decreased from 319.86 K to 319.2759 K by 0.18%. The standard deviation of battery temperature decreased from 5.3347 K to 5.2618 K by 1.37%. The system pressure drop decreased from 7.3211 Pa to 3.3838 Pa by 53.78%. The performance of the optimized battery cooling system has been significantly improved.

The research is aimed at coping with the inherent computational intensity of Bayesian multi-objective optimization algorithms. We propose the implementation which is based on the rectangular partition of the feasible region and circumvents much of computational burden typical for the traditional implementations of Bayesian algorithms. The included results of the solution of testing and practical problems illustrate the performance of the proposed algorithm.

Electricity load prediction is of great significance to the development of the power market and stable operation of power systems. In recent years, scholars in this field have only considered point forecasting, which ignores the inevitable prediction bias and uncertain information. To fill this gap, this study proposes an interval prediction system consisting of an advanced data reconstruction strategy, a multi-objective optimization algorithm based on the theory of non-negative constraints, and an outstanding interval forecasting model fitted by the predicted fluctuation characteristics. Moreover, this study theoretically proves that the weight assigned by the optimization algorithm is the Pareto optimal solution. Empirical data with 30 min intervals from Queensland, Australia are selected as samples for research. The results not only demonstrate the superiority of the proposed model but also provide effective technical support for power grid operation and dispatch by quantifying changes in the prediction results caused by uncertainties.

In mathematics, it’s very easy to find the maximum point or minimum point of a function or a set of functions, but it’s difficult to find a set of function simultaneously in the real world due to the different kinds of mathematical relationships between objective functions. So the multi objective optimization algorithm has the ability to deal with a many objectives instead of one objective, because of the difficulties in the classical methods of multi objectives optimization, the evolutionary algorithm (EA) is effective to eliminate these difficulties, in order to apply the evolutionary algorithms to improve the multi-objective optimization algorithm, the multi - objective evolutionary algorithm based on decomposition is one of the algorithms that solve multi objective optimization problems. This paper aims to enhance the e-mail spam filtering by using multi - objective evolutionary algorithm for classifying the e-mail messages to spam or non-spam in high accuracy. The first step in the proposal is applying normalization. The second step is applying feature selection which is implemented to choose the best features. Finally, implement multi - objective evolutionary algorithm based on decomposition. The evaluation of the performance of model by using testing databases from the spam database. The model depended accuracy as a criterion to evaluate model performance. The experimental results showed that the proposed system provides good accuracy in the experiment 1 (91%), very good accuracy in the experiment 2 (92%) and excellent accuracy in the experience 3 (98%).

A successful mechanical property data-driven prediction model is the core of the optimal design of hot rolling process for hot-rolled strips. However, the original industrial data, usually unbalanced, are inevitably mixed with fluctuant and abnormal values. Models established on the basis of the data without data processing can cause misleading results, which cannot be used for the optimal design of hot rolling process. Thus, a method of industrial data processing of C-Mn steel was proposed based on the data analysis. The Bayesian neural network was employed to establish the reliable mechanical property prediction models for the optimal design of hot rolling process. By using the multi-objective optimization algorithm and considering the individual requirements of costumers and the constraints of the equipment, the optimal design of hot rolling process was successfully applied to the rolling process design for Q345B steel with 0.017% Nb and 0.046% Ti content removed. The optimal process design results were in good agreement with the industrial trials results, which verify the effectiveness of the optimal design of hot rolling process.

This paper proposes a multi-objective version of recently developed Spotted Hyena Optimizer (SHO) called Multi-objective Spotted Hyena Optimizer (MOSHO). It is used to optimize the multiple objectives problems. In the proposed algorithm, a fixed-sized archive is employed for storing the non-dominated Pareto optimal solutions. The roulette wheel mechanism is used to select the effective solutions from archive to simulate the social and hunting behaviors of spotted hyenas. The proposed algorithm is tested on 24 benchmark test functions and compared with six recently developed metaheuristic algorithms. The proposed algorithm is then applied on six constrained engineering design problems to demonstrate its applicability on real-life problems. The experimental results reveal that the proposed algorithm performs better than the others and produces the Pareto optimal solutions with high convergence.

Multi-objective optimization problems can be divided into continuous multi-objective optimization problems and discrete multi-objective optimization problems, and discrete multi-objective optimization is not universal. In practical applications, there are many discrete multi-objective optimization problems. The solution of different problems needs to design different evolutionary multi-objective algorithms according to their specific conditions. The threshold in the traditional multi-objective optimization of wireless network is a preset constant. It has relatively poor performance in the synthesis of images with different noise levels. An adaptive wireless network multi-objective optimization algorithm based on image synthesis is proposed. Based on the maximum inter class variance and maximum peak signal to noise ratio (SNR), an adaptive wireless network multi-objective optimization algorithm is established. The accuracy and noise immunity of image synthesis are also considered. In order to avoid the effect of threshold increase on algorithm efficiency, multi-objective optimization algorithm is introduced into the algorithm. Experiments show that the method proposed in this paper is accurate and robust and has good universality for the synthesis of different noise images.

There are many diverse fields and applications such as data mining, engineering, operations research, economics, and science can be formulated as multi-objective optimization problems. In this paper, we describe and propose a novel and a useful multi-objective artificial algae algorithm (MO-AAA) to solve multi-objective engineering design problems. Our proposed algorithm, (MO-AAA), is based on the search technique of artificial algae algorithm(AAA) algorithm. MO-ADA applies the elitist non-dominated sorting and crowding distance approach to preserve the diversity among the optimal set of solutions and obtains various non-domination levels, respectively. Also, we evaluate the effectiveness of the proposed algorithm by applying it on different multi-objective benchmark problems (20 challenging benchmark problems from CEC 2009 for unconstrained and constrained multi-objective optimization problems) and engineering design benchmark problems with distinctive features. Finally, our results show that MO-AAA efficiently generates the Pareto front and is easy to implement, promising and competitive compared to other state-of-the-art algorithms considered in this work.

In order to effectively solve the dynamic multi-objective optimization problem, a new dynamic multi-objective optimization algorithm based on prediction strategy is provided in this paper. The algorithm detects changes in the environment by recalculating individuals. At the same time, the prediction model is established based on individuals of the first two generations, which is used to generate the new individual. In order to improve the diversity, Cauchy Mutation is used in the algorithm. Then, there are the non-dominated sort and tournament selection to deal the individual. The proposed algorithm is validated on several typical test functions. Meanwhile, the algorithm is compared to DNSGA-A. The experimental results show that the rate of convergence gets improved and the population solution is closer to the real solution. The algorithm do well in resolving the basic dynamic multi-objective function.

With the continuous consumption of commodities, the number of waste products is also increasing, and its impact on the environment and resources has also attracted great attention. Therefore, the reuse of waste products is one of the ways to solve the problem of increasing waste products at present. In this work, the cycle time constraint of disassembly components is considered in a multi-product partial U-shaped disassembly-line-balancing problem. Moreover, the maximum profit and the minimum idle time are taken as the optimization objectives, and a mathematical model of multi-objective optimization under the cycle time constraints is established. To optimize this problem, an S-metric selection evolutionary multi-objective optimization algorithm (SMS-EMOA) is proposed. The SMS-EMOA is compared with the multi-objective evolutionary algorithm based on decomposition and the indicator-based evolutionary algorithm. The experimental results show the practicability and feasibility of the SMS-EMOA algorithm.

Convolutional neural networks (CNNs) have been used to solve many problems in computer science with a high level of success, and have been applied in many fields in recent years. However, most of the designs of these models are still tuned manually; obtaining the highest performing CNN model is therefore very time-consuming, and is sometimes not achievable. Recently, researchers have started using optimization algorithms for the automatic adjustment of the hyper-parameters of CNNs. In particular, single-objective optimization algorithms have been used to achieve the highest network accuracy for the design of a CNN. When these studies are examined, it can be seen that the most significant problem in the optimization of the parameters of a CNN is that a great deal of time is required for tuning. Hence, optimization algorithms with high convergence rates are needed for the parameter optimization of deep networks. In this study, we first develop an algorithm called MODE-CNN, based on the multi-objective differential evolution (MODE) algorithm for parameter optimization of CNN or CNN-based methods. MODE-CNN is then compared with four different multi-objective optimization algorithms. This comparison is carried out using 16 benchmark functions and four different metrics, with 100 independent runs. It is observed that the algorithm is robust and competitive compared to alternative approaches, in terms of its accuracy and convergence. Secondly, the MODE-CNN algorithm is used in the parameter optimization of a CNN-based method, developed previously by the authors, for the segmentation and classification of medical images. In this method, there are three parameters that influence the test time and accuracy: the general stride (GS), neighbour distance (ND), and patch accuracy (PA). These parameters need to be optimized to give the highest possible accuracy and lowest possible test time. With the MODE-CNN algorithm, the most appropriate GS, ND, and PA values are obtained for the test time and accuracy. As a result, it is observed that the MODE-CNN algorithm is successful, both in comparison with multi-objective algorithms and in the parameter optimization of a CNN-based method.

Numerous surrogate-assisted expensive multi-objective optimization algorithms were proposed to deal with expensive multi-objective optimization problems in the past few years. The accuracy of the surrogate models degrades as the number of decision variables increases. In this paper, we propose a surrogate-assisted expensive multi-objective optimization algorithm based on decision space compression. Several surrogate models are built in the lower dimensional compressed space. The promising points are generated and selected in the lower compressed decision space and decoded to the original decision space for evaluation. Experimental studies show that the proposed algorithm achieves a good performance in handling expensive multi-objective optimization problems with high-dimensional decision space.

A key challenge to software product line engineering is to explore a huge space of various products and to find optimal or near-optimal solutions that satisfy all predefined constraints and balance multiple often competing objectives. To address this challenge, we propose a hybrid multi-objective optimization algorithm called SMTIBEA that combines the indicator-based evolutionary algorithm (IBEA) with the satisfiability modulo theories (SMT) solving. We evaluated the proposed algorithm on five large, constrained, real-world SPLs. Compared to the state-of-the-art, our approach significantly extends the expressiveness of constraints and simultaneously achieves a comparable performance. Furthermore, we investigate the performance influence of the SMT solving on two evolutionary operators of the IBEA.

In order to raise the quality of higher order mutation testing, in this paper, we propose an approach for effect improving of multi-objective optimization algorithms which can be used in the field of higher order mutation testing in order to reduce the number of generated mutant, generate the hard-to-kill mutant and construct the quality higher order mutants. We have performed an empirical evaluation with 20 real-word, open-source projects and 10 multi-objective optimization algorithms (including 5 original algorithms and 5 corresponding modification algorithms) to evaluate experimental results as well as bring out some opinions to effectiveness apply multi-objective optimization algorithms into higher order mutation testing. The study results indicate that our approach is an effectiveness one to get better the quality of higher order mutation testing.

Swarm intelligence optimization algorithm is an important technology that solves the complex optimization problem by simulating the behavior of biological groups in nature. Monarch butterfly optimization (MBO) algorithm is such a swarm intelligence algorithm that simulates the migration behavior of the monarch butterflies in nature. It has received great success on solving single-objective optimization problems, but few contributions on multi-objective problems. In this paper, we modify MBO to solve multi-objective problems, and then propose a new multi-objective optimization algorithm based by combining effective strategies from other swarm-based algorithms. A series of benchmark functions are employed to evaluate the performance of this algorithm. We compare the experimental results with three basic algorithms and state-of-the-art algorithms. It is shown that the proposed algorithm performs better than the compared algorithms on most of the benchmark functions.