Multi-objective Search Research Articles

Optimization and decision making of guide vane closing law for pumped storage hydropower system to improve adaptability under complex conditions

The pumped storage hydropower system (PSHS) is considered a high-quality peaking and frequency regulation energy source due to its operational flexibility and fast response. However, its frequent regulation leads to complex operating conditions with potential harm to the stability of the system. This paper focuses on analyzing and improving the adaptability of guide vane closing law under complex conditions. This is obtained by proposing a refined numerical model of PSHS considering non-linear factors and analyzing the effects of the guide vane closing law and initial operating conditions on the load rejection. The results revealed that a suitable two-stage guide vane closing law effectively reduces the risk of load rejection. In addition, when the initial load of two units is different, it is beneficial to improve the load rejection characteristics when the unit with the smaller load rejects the load first. Finally, three groups of parameters for the optimal guide vane closing law (the Pareto solution sets) are obtained by multi-objective sparrow search algorithm (MOSSA) under the rated, maximum water head, and maximum rotational speed conditions. The obtained Pareto solution and the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) are used for scoring the solutions and obtain an optimal suitable for complex operating conditions. The water head and rotational speed are reduced by an average of 7.76 % and 3.74 % for the different operating conditions compared to the model validation results, respectively. These results provide a theoretical basis for the selection of the optimal guide vane closing laws and improve the safety during load rejection under complex practical operating conditions.

Image-based Skin Disease Detection and Classification through Bioinspired Machine Learning Approaches

A self-learning disease detection model will be useful for identifying skin infections in suspected individuals using skin images of infected patients. To detect skin diseases, some AI-based bioinspired models employ skin images. Skin infection is a common problem that is currently faced due to various reasons, such as food, water, environmental factors, and many others. Skin infections such as psoriasis, skin cancer, monkeypox, and tomato flu, among others, have a lower death rate but a significant impact on quality of life. Neural Networks (NNs) and Swarm intelligence (SI) based approaches are employed for skin disease diagnosis and classification through image processing. In this paper, the convolutional neural networks-based Cuckoo search algorithm (CNN-CS) is trained using the well-known multi-objective optimization technique cuckoo search. The performance of the suggested CNN-CS model is evaluated by comparing it with three commonly used metaheuristic-based classifiers: CNN-GA, CNN-BAT, and CNN-PSO. This comparison was based on various measures, including accuracy, precision, recall, and F1-score. These measures are calculated using the confusion matrices from the testing phase. The results of the experiments revealed that the proposed model has outperformed the others, achieving an accuracy of 97.72%.

Multi-objective discrete harmony search algorithm for privacy preservation in cloud data centers

Multi-objective discrete harmony search algorithm for privacy preservation in cloud data centers

Multi-objective squirrel search algorithm for EEG feature selection

Feature selection plays a critical role in the application of Brain Computer Interface (BCI) systems. Many methods have been used to solve the feature selection problem, but they model it as a single-objective problem, considering only classification accuracy or number of features. To close this critical gap, we improve the squirrel search algorithm by combining it with the grid method, and propose a Multi-Objective Squirrel Search Algorithm (MOSSA) to solve the feature selection problem in BCI. We conduct experiments on three publicly available motion imagery datasets, and the experimental results reveal the best classification results of the method on dataset 1. The average classification accuracy of dataset 2 is 96.71%, with the number of selected features reduced to 18 on average. The highest classification accuracy of dataset 3 is 83.57% on the training set and 82.86% on the test set. In addition, we compare MOSSA with other algorithms and the results show the superiority of our proposed method in solving the feature selection problem. Finally, we combine MOSSA with an online application of BCI, where subjects visualize controlling the robot to perform the corresponding actions by the left and right hand movements. The average recognition rate of the three subjects is approximately 70%. In summary, the MOSSA is an effective method for solving the feature selection problem and is useful for the development of online applications of BCI.

Surrogate-assisted operator-repeated evolutionary algorithm for computationally expensive multi-objective problems

Surrogate-assisted strategies work differently in surrogate-assisted multi-objective evolutionary algorithms. How to select suitable surrogate-assisted strategies to balance global and local search and diversity of Pareto optimal solutions is usually difficult for efficient optimization of computationally expensive multi-objective problems, which only allow limited time costs in the optimization process. Therefore, to further improve the optimization efficiency for expensive multi-objective problems, a surrogate-assisted operator-repeated multi-objective evolutionary algorithm is proposed by reasonably integrating several surrogate-assisted strategies in this study. Specifically, the proposed algorithm is based on a operator-repeated offspring creation strategy, which can produce many diverse candidate offspring individuals and thus make the proposed algorithm search globally and efficiently. In addition, a novel infill criterion termed as reference-vector-guided surrogate-assisted penalty-based boundary intersection is proposed and combined with a common Kriging-based expected improvement matrix infill criterion for complementary prescreening over the candidate offspring individuals. These two infill criteria can make a good balance between global search and diversity of Pareto optimal solutions. In addition, to fasten convergence speed, an improved surrogate-based multi-objective local search method with minimum distance-angle sampling is also proposed and embedded in the proposed algorithm. Several benchmark problems with dimensions varying from 8 to 50 and a practical two-objective airfoil design optimization problem with 14 design variables are tested to validate efficiency of the proposed algorithm. The experimental results demonstrate that the proposed algorithm significantly outperforms some state-of-the-art surrogate-assisted multi-objective optimization algorithms on most of problems.

Multiobjective sparrow search feature selection with sparrow ranking and preference information and its applications for high-dimensional data

To reduce the dimensionality of high-dimensional data and enhance its classification accuracy, feature selection can be regarded as a multiobjective optimization problem that can be addressed by evolutionary computation algorithms with promising results. However, balancing the convergence and diversity of nondominated solutions remains challenging. To address these issues, this paper proposes a multiobjective sparrow search feature selection approach with sparrow ranking and preference information and its applications for high-dimensional data. First, during the population updating process, the updating formula of observers is combined with the mutualism phase of the symbiotic organisms search algorithm to design a location updating formula of observers in the sparrow search algorithm, balancing the local development ability and global search ability of sparrow search algorithm and increasing the possibility of moving closer to the optimal solution. Second, based on the dominant and nondominated sparrow individuals of each sparrow, the dominant and nondominated distances are defined, and the sparrow ranking is proposed. The feature ranking is then designed by using the definition of sparrow ranking. Following the definition of sparrow ranking and feature ranking, the selection strategy and location updating formula of the producers in the sparrow search algorithm are proposed. Finally, a preference information-based mutation algorithm is designed to augment the diversity of the nondominated solutions and more effectively guide the whole sparrow population to a better solution. The experimental results on 14 high-dimensional datasets show that the proposed algorithm outperforms different single-objective and multiobjective optimization feature selection algorithms in terms of classification efficiency and diversity of solutions.

Continuous Cartesian Genetic Programming based representation for multi-objective neural architecture search

We propose a novel neural architecture search (NAS) approach for the challenge of designing convolutional neural networks (CNNs) that achieve a good tradeoff between complexity and accuracy. We rely on Cartesian genetic programming (CGP) and integrated real-based and block-chained CNN representation, for optimization using multi-objective evolutionary algorithms (MOEAs) in the continuous domain. We introduce two variants, CGP-NASV1 and CGP-NASV2, which differ in the granularity of their respective search spaces. To evaluate the proposed algorithms, we utilized the non-dominated sorting genetic algorithm II (NSGA-II) on the CIFAR-10, CIFAR-100,and SVHN datasets. Additionally, we extended the empirical analysis while maintaining the same solution representation to assess other searching techniques such as differential evolution (DE), the multi-objective evolutionary algorithm based on decomposition (MOEA/D), and the S metric selection evolutionary multi-objective algorithm (SMS-EMOA). The experimental results demonstrate that our approach exhibits competitive classification performance and model complexity compared to state-of-the-art methods.

Parametrizing analog multi-compartment neurons with genetic algorithms

Background: Finding appropriate model parameters for multi-compartmental neuron models can be challenging. Parameters such as the leak and axial conductance are not always directly derivable from neuron observations but are crucial for replicating desired observations. The objective of this study is to replicate the attenuation behavior of an excitatory postsynaptic potential (EPSP) traveling along a linear chain of compartments on the analog BrainScaleS-2 neuromorphic hardware platform. Methods: In the present publication we use genetic algorithms to find suitable model parameters. They promise parameterization without domain knowledge of the neuromorphic substrate or underlying neuron model. To validate the results of the genetic algorithms, a comprehensive grid search was conducted. Trial-to-trial variations in the analog system are counteracted utilizing spike-triggered averaging. Results and conclusions: The algorithm successfully replicated the desired EPSP attenuation behavior in both single and multi-objective searches illustrating the applicability of genetic algorithms to parameterize analog neuromorphic hardware.

Identifying robust adaptive irrigation operating policies to balance deeply uncertain economic food production and groundwater sustainability trade-offs

Increasing irrigation demand has heavily relied on groundwater use, especially in places with highly variable water supplies that are vulnerable to drought. Groundwater management in agriculture is becoming increasingly challenging given the growing effects from overdraft and groundwater depletion worldwide. However, multiple challenges emerge when seeking to develop sustainable groundwater management in irrigated systems, such as trade-offs between the economic revenues from food production and groundwater resources, as well as the broad array of uncertainties in food–water systems. In this study we explore the applicability of Evolutionary Multi-Objective Direct Policy Search (EMODPS) to identify adaptive irrigation policies that water agencies and farmers can implement including operational decisions related to land use and groundwater use controls as well as groundwater pumping fees. The EMODPS framework yields state-aware, adaptive policies that respond dynamically as system state conditions change, for example with variable surface water (e.g., shifting management strategies across wet versus dry years). For this study, we focus on the Semitropic Water Storage district located in the San Joaquin Valley, California to provide broader insights relevant to ongoing efforts to improve groundwater sustainability in the state. Our findings demonstrate that adaptive irrigation policies can achieve sufficiently flexible groundwater management to acceptably balance revenue and sustainability goals across a wide range of uncertain future scenarios. Among the evaluated policy decisions, pumping restrictions and reductions in inflexible irrigation demands from tree crops are actions that can support dry-year pumping while maximizing groundwater storage recovery during wet years. Policies suggest that an adaptive pumping fee is the most flexible decision to control groundwater pumping and land use.

An Efficient Hybrid Multi-Objective Optimization Method Coupling Global Evolutionary and Local Gradient Searches for Solving Aerodynamic Optimization Problems

Aerodynamic shape optimization is frequently complicated and challenging due to the involvement of multiple objectives, large-scale decision variables, and expensive cost function evaluation. This paper presents a bilayer parallel hybrid algorithm framework coupling multi-objective local search and global evolution mechanism to improve the optimization efficiency and convergence accuracy in high-dimensional design space. Specifically, an efficient multi-objective hybrid algorithm (MOHA) and a gradient-based surrogate-assisted multi-objective hybrid algorithm (GS-MOHA) are developed under this framework. In MOHA, a novel multi-objective gradient operator is proposed to accelerate the exploration of the Pareto front, and it introduces new individuals to enhance the diversity of the population. Afterward, MOHA achieves a trade-off between exploitation and exploration by selecting elite individuals in the local search space during the evolutionary process. Furthermore, a surrogate-assisted hybrid algorithm based on the gradient-enhanced Kriging with the partial least squares(GEKPLS) approach is established to improve the engineering applicability of MOHA. The optimization results of benchmark functions demonstrate that MOHA is less constrained by dimensionality and can solve multi-objective optimization problems (MOPs) with up to 1000 decision variables. Compared to existing MOEAs, MOHA demonstrates notable enhancements in optimization efficiency and convergence accuracy, specifically achieving a remarkable 5–10 times increase in efficiency. In addition, the optimization efficiency of GS-MOHA is approximately five times that of MOEA/D-EGO and twice that of K-RVEA in the 30-dimensional test functions. Finally, the multi-objective optimization results of the airfoil shape design validate the effectiveness of the proposed algorithms and their potential for engineering applications.

Sustainable group tourist trip planning: An adaptive large neighborhood search algorithm

The tourism industry is a key driver of economic growth and contributes to the achievement of sustainability goals. This paper presents a multi-objective group tourist planning problem that considers economic, environmental, and social dimensions simultaneously. The proposed model minimizes total cost and environmental impacts while maximizing the total collected prizes from tourists' interests. We introduce the lost profit opportunity for the cost of tours from an economic perspective for the first time. From an environmental perspective, the model minimizes both carbon emissions for transportation and the waste produced by tourists. Social satisfaction is addressed by considering tourists' preferences for visiting tourist sites and their interests in participating in group tours, maximizing total collected prizes. Uncertainties in travel time and prize values are addressed by using a fuzzy programming approach. A multi-objective adaptive large neighborhood search (ALNS) algorithm is developed to solve the proposed multi-objective group tourist planning problem, offering various removal, insertion, and local search heuristic procedures. Extensive analyses and computations are conducted to demonstrate the performance of the proposed multi-objective optimization model and the ALNS metaheuristic algorithm in solving large-scale instances. The results demonstrate the effectiveness of our approach in aiding tourism managers to make informed decisions that balance economic, environmental, and social objectives.

Bi-level programming and multi-objective optimization for the distribution of resources in hierarchical organizations

The decision regarding the hierarchical distribution of resources is crucial for many organizations that want to allocate such resources efficiently. At the upper level of the hierarchy, a decision-maker may have an objective and a set of feasible solutions partially determined by the lower level. Nevertheless, the upper level can influence but not control the decision-maker at the lower level. Moreover, the objectives of the upper and lower levels are conflicting. Hence, the hierarchical distribution of resources can be formulated as a bi-level programming model. This paper reformulates the hierarchical allocation of resources. The Hooke-Jeeves (HJ) algorithm and the hybrid scatter search–Nelder-Mead (SSNM) method are proposed to solve the newly formulated problem. The problem is also analyzed from a multi-objective perspective to equally prioritize the upper and lower levels while subjecting each to an interdependent set of constraints; a multi-objective scatter search algorithm (MSSA) was developed for that purpose. Tailor-made instances were also designed for the implementation of the developed algorithms. The findings demonstrated that the HJ algorithm provides the best solution according to the upper-level objective function. However, it does not guarantee the best result for the lower level. In comparison, MSSA has a set of best possible solutions for both objectives. The hybrid SSNM method could not match the results provided by the former methods.

Surgical cases assignment problem using a multi-objective squirrel search algorithm

Surgical cases assignment problem (SCAP) is among the most investigated interests in operating room planning. The studies related to the SCAP are mainly focused on the single objective optimization. To concern multiple criteria in the management, this paper reformulates a multi-objective SCAP with minimizing total operating cost and maximizing scheduled surgeries number, simultaneously. Although dozens of multi-objective methods have been introduced in recent years, these cannot be applied into the multi-objective SCAP directly considering the characteristics of the problem. To tackle the multi-objective SCAP, a problem-specified multi-objective squirrel search algorithm (MOSSA) is presented. First, a targeted single-list scheme is devised to encode individuals and an efficient decoding scheme integrating a repair strategy is proposed to construct feasible scheduling plan. Second, two simple heuristics are incorporated into the algorithm to imitate the behaviors of squirrels and improve the search ability. Third, an addition archive is employed to store the non-dominated solutions. Moreover, a DOE method is performed to investigate the influence of parameter settings. The performance of the MOSSA is assessed by a representative benchmark dataset with three different evaluating indicators. Extensive experiments and analysis results demonstrate the effectiveness of the proposed algorithm and the superiority over compared approaches in addressing the multi-objective SCAP.

A Novel Blockchain Framework for Digital Forensics in Cloud Environment Using Multi-objective Krill Herd Cuckoo Search Optimization Algorithm

A Novel Blockchain Framework for Digital Forensics in Cloud Environment Using Multi-objective Krill Herd Cuckoo Search Optimization Algorithm

Key product review extraction based on the RLRSA-CL algorithm

Online product reviews on e-commerce platforms help consumers evaluate and select products. However, the large number of accumulated product reviews leads to information overload and redundancy. It is difficult for consumers to quickly obtain needed information. Therefore, this study proposes a new model for extracting key reviews from the perspectives of supporting consumer purchase decisions and reducing review information overload. First, patterns of contextual information surrounding product attributes are extracted to model the product features, questions, and reviews in the same semantic space. Second, the new key review extraction problem is defined as a multi-objective optimization model. Five objective functions in terms of supporting consumer purchase decisions and reducing review information overload are defined in the model. Product attribute weights and product question weights are designed to construct the objective functions. Third, a binary multi-objective reptile search algorithm RLRSA-CL integrating reinforcement learning and cross-learning strategies is innovatively constructed to solve the optimization model and obtain key reviews. Finally, experiments on a real dataset from Jingdong Mall are performed. The results show that the proposed RLRSA-CL algorithm is valid and superior to other algorithms in key review extraction.

Roboat III: An autonomous surface vessel for urban transportation

AbstractIn this paper, we present our novel autonomous surface vessel platform, a full‐scale Roboat for urban transportation. This 4‐m‐long Roboat is designed with six seats and can carry a payload of up to 1000 kg. Roboat has two main thrusters for cruising and two tunnel thrusters to accommodate docking and interconnectivity between Roboats. We build an adaptive nonlinear model predictive controller for trajectory tracking to account for payload changes while transporting passengers. We use a sparse directed graph to represent the canal topological map and then find the most time‐efficient global path in a city‐scale environment using the algorithm. We then employ a multiobjective algorithm's lexicographic search to generate an obstacle‐free path using a point‐cloud projected two‐dimensional occupancy grid map. We also develop a docking mechanism to allow Roboat to “grasp” the docking station. Extensive experiments in Amsterdam waterways demonstrate that Roboat can (1) successfully track the optimal trajectories generated by the planner with varying numbers of passengers on board; (2) autonomously dock to the station without human intervention; (3) execute an autonomous water taxi task where it docks to pick up passengers, drive passengers to the destination while planning its path to avoid obstacles, and finally dock to drop off passengers.

Probabilistic Semantic Data Association for Collaborative Human-Robot Sensing

Humans cannot always be treated as oracles for collaborative sensing. Robots thus need to maintain beliefs over unknown world states when receiving semantic data from humans, as well as account for possible discrepancies between human-provided data and these beliefs. To this end, this paper introduces the problem of semantic data association (SDA) in relation to conventional data association problems for sensor fusion. It then develops a novel probabilistic semantic data association (PSDA) algorithm to rigorously address SDA in general settings, unlike previous work on semantic data fusion which developed heuristic techniques for specific settings. PSDA is further incorporated into a recursive hybrid Bayesian data fusion scheme which uses Gaussian mixture priors for object states and softmax functions for semantic human sensor data likelihoods. Simulations of a multi-object search task show that PSDA enables robust collaborative state estimation under a wide range of conditions where semantic human sensor data can be erroneous or contain significant reference ambiguities.

Mission and Reliability Driven Fleet-Level Selective Maintenance Planning and Scheduling Two-Stage Method

This paper studies the problem of planning and scheduling in selective maintenance tasks of mission requirements and the health condition of the fleet. In order to deal with the problems of high maintenance cost and long time consumption in maintenance systems, a two-stage fleet maintenance optimization method is proposed. Firstly, a selective maintenance model of fleets based on age reduction is established to maximize the probability of completing the next mission and minimize the maintenance cost. Secondly, a multiobjective sparrow search algorithm is designed to solve the maintenance planning problem in the first stage, and a nondominated solution set of maintenance strategies satisfying the mission constraint is obtained. In the second stage, the simulated annealing algorithm is used to schedule the maintenance task and obtain the minimum maintenance hours required by the maintenance strategy. An example analysis of a vehicle fleet is launched to prove the effectiveness of this method. In a word, this method not only meets the mission requirements but also achieves the purpose of reducing maintenance cost and maintenance hours, which can provide reference for other types of equipment maintenance.

An improved estimation of distribution algorithm for rescue task emergency scheduling considering stochastic deterioration of the injured

Efficient allocating and scheduling emergency rescue tasks are a primary issue for emergency management. This paper considers emergency scheduling of rescue tasks under stochastic deterioration of the injured. First, a mathematical model is established to minimize the average mathematical expectation of all tasks’ completion time and casualty loss. Second, an improved multi-objective estimation of distribution algorithm (IMEDA) is proposed to solve this problem. In the IMDEA, an effective initialization strategy is designed for obtaining a superior population. Then, three statistical models are constructed, which include two tasks existing in the same rescue team, the probability of first task being processed by a rescue team, and the adjacency between two tasks. Afterward, an improved sampling method based on referenced sequence is employed to efficiently generate offspring population. Three multi-objective local search methods are presented to improve the exploitation in promising areas around elite individuals. Furthermore, the parameter calibration and effectiveness of components of IMEDA are tested through experiments. Finally, the comprehensive comparison with state-of-the-art multi-objective algorithms demonstrates that IMEDA is a high-performing approach for the considered problem.

ASMEvoNAS: Adaptive segmented multi-objective evolutionary network architecture search

Network architecture search (NAS) has attracted much attention as an automatic design technique of network architecture. In particular, multi-objective evolutionary algorithms (MOEAs) have been a popular kind of optimizer in NAS due to their global optimization capability. However, as a population-based iterative search method, MOEAs are subject to the unbearable computational cost of individual evaluation on multiple objectives at each generation, which affects their generalization ability and transferability of MOEA-based NAS. Therefore, an adaptive segmented multi-objective evolutionary network architecture search (ASMEvoNAS) method is proposed in this paper. Firstly, an adaptive segmented evaluation strategy is designed to adaptively select different but more suitable objectives to efficiently assess the candidate architectures at different evolutionary stages, instead of evaluating them by all the considered objectives simultaneously. Thus, the computational cost and complexity of the search process can be controlled and reduced to some extent. Secondly, a preference-based pre-selection strategy is designed to filter out the initialized architectures with high parameter quantities to reduce the total parameter scale of the whole population and memory consumption. Last, a novel desirable gene reservation-based crossover and a directed connection-based mutation are proposed to produce offspring. Experimental results show that ASMEvoNAS shows promising performance on CIFAR-10, CIFAR-100, and ImageNet with error rates of 2.21%, 15.57%, and 24.43% top-1, respectively. The proposed method reduces the search cost to 0.36 GPU-Days on CIFAR-10 while maintaining competitive classification performance compared to state-of-the-art networks. In addition, ASMEvoNAS presents superior performance when dealing with the considered transfer tasks, as well as the benchmark dataset of NAS.