Earticle

The importance of eco-friendly architectural design has become an essential design element along with the global climate crisis. Nevertheless, eco-friendly considerations are generally made in the mid to late stages of the architectural design process, and in particular, there is a high tendency to focus on consideration of architectural facilities or facade design rather than determining the overall shape, such as the layout, height, or orientation of the building. However, as mentioned above, the decisions made in the early design process often determine the actual performance of the building, so more advanced research is needed on ways to increase the energy performance of buildings in the early design stage. An algorithm was designed so that the eco-friendly design techniques derived through this study can be universally applied not only to specific sites but also to unspecified sites. Through the two proposed stages - placement, height and orientation - it was possible to derive an optimized building shape in the early design stage, and thus it can be said to be a technique that enables a high level of energy savings throughout the entire life cycle of the building.

본 연구의 목적은 학교주변지역에서 진화 알고리즘을 적용한 방범카메라의 설치계획기법을 제시함에 있다. 이를 위해 교통안전, 범죄이론, 3차원 방범카메라 기술 및 진화연산이론을 포함한 일련의 이론적 고찰이 진행되었다. 개발된 기법은 지형, 건물 및 가로구성의 3차원 조건과 관련하여 학교주변지역의 물리적 조건과 방범카메라의 기계적 특성을 활용하였다. 본 연구는 옥외공간에서의 관측성능에 영향을 미치는 조건들과 요소들을 정량화하였다. 특히 전주의 중간부분은 방범카메라를 위한 설치위치로 설정되었다. 방범카메라의 관측위치, 수평회전각, 수직경사각 및 화각은 설정된 초기 연산조건에서 설치조합 탐색과정을 가능하게 하는 입력변수로 활용되었다. 비관측편중율, 음영지역, 노출영역 및 초점거리는 적용된 진화 알고리즘을 수행하기 위한 적합도의 지속적인 평가를 지원하였다. 결과적으로 방범카메라의 설치조합을 위한 생성기법은 학교주변지역의 DEM에 적용되어 계획 적용성을 보였다.

The purpose of this study was to suggest a surveillance camera installation planning method in school zone with using evolutionary algorithm. A series of theoretical searches including traffic safety issues, crime theories, surveillance camera technologies on three-dimensional physical settings and evolutionary computation theories were conducted. The developed method also accommodated physical settings of school zones and mechanical properties of surveillance cameras in conjunction with three-dimensional conditions of topographies, buildings and pathway configurations. This study quantified the conditions and components affecting surveillance performance at outdoor spaces. Especially, middle parts of electric poles were set to the installation positions for surveillance cameras. Surveillance positions, panning angles, tilting angles and FOVs(Fields of View) were utilized as input variables which enabled the surveillance camera layout search process under the assigned initial computing conditions. Non- surveillance load rate deviations, shadow area rates, surveilled areas and focal lengths supported evaluating sequentially calculated fitness factors for processing the adopted evolutionary algorithm. Finally, the generation method for surveillance camera layout showed the planning applicability with simulating a school zone DEM(Digital Elevation Model)　case.

According to Genetic algorithms principle, the new hybrid evolutionary algorithm (HEA) is proposed in this paper by combining the Immune algorithm, Genetic algorithm and Pareto optimal solutions. The HEA has high convergence precision and improved the diversity of population. Multiple near optimization paths can be developed by the algorithm with multi‐objective restriction, and satisfy to minimize the routing of transportation and the numbers of the vehicles. The HEA has been used to solve the vehicle routing problem, the results of simulation experiment show that the HEA can gain higher global convergence rate and higher speed.

This study was aimed to develop a planning method of CCTV cameras surveilling juvenile victimization to school crimes. With spatial settings of school common spaces, evolutionary algorithm was applied to implement the planning method for accommodating numerous variable compositions. The required variables, their initial conditions and boundary conditions were derived from the theoretical exploration on precedent research works. The applied evolutionary algorithm used a search method with tracking fitness factor. The fitness factor of the implemented algorithm was calculated from standard deviation of distributed non-surveillance ratio and shadow area ratio. The overall algorithm utilized, as computational parameters, the camera layout information including each camera’s position, panning angle and tilting angle under the initial and boundary conditions. Finally, the developed method enabled CCTV camera layout schemes, surveillance areas and the quantitative results to be generated by the heuristic search process. This study also showed method applicability to school settings especially focusing on indoor common spaces.

With the fast development of data analysis and computer science technology, the design and implementation of image retrieval system has been a hot topic. The prior research focus more on image-size based approaches which are not intelligent or convenient. In this paper, we present a novel modified evolutionary algorithm based image retrieval framework theoretically with applications. To achieve more accuracy in less number of iteration, this paper, proposed a new approach to enhance the performance of content guided retrieval methodology by improving the performance of RF through Particle Swarm Optimization, Genetic Algorithm and Support Vector Machine. The objective of using Genetic Algorithm and Particle Swarm Optimization is to increase the number of images in relevant set where SVM is used to classify the relevant and irrelevant images. The experimental and numerical simulation indicate the efficiency of our method which means the presented technique is helpful in the fields where high accuracy rate of image retrieval is required. Further work of interest is also discussed in the final section.

The paper represents an evolutionary algorithm (EA) solution to the unit commitment problem for Virtual Power Plants. EAs are general optimization techniques based on principles inspired from the biological evolution, using metaphors of mechanism such as natural selection, genetic recombination and survival of the fittest. One of EA implementation using the standard crossover and mutation operators could locate near optimal solution. Theoretical results and expectations are proved through simulations of a realistic scenario.

An optimal Fractional Order PIλDμ (FOPID) controller is designed for a full vehicle nonlinear active suspension system. The optimal values of FOPID controller parameters for minimizing the cost function are tuned using an Evolutionary Algorithm (EA), which offers an optimal solution to a multidimensional rough objective function. The fitness parameters of FOPID controller (proportional constant P, integral constant I, derivative constant D, integral order λ and derivative order μ) are selected from ranges of reliable values, depending on survival-to-the-fitness principle used in the biology science. A full vehicle nonlinear active suspension model including hydraulic actuators, nonlinear dampers and nonlinear springs has been proposed with structural and analytical details. The nonlinear frictional forces due to rubbing of piston seals with the cylinders wall inside the actuators are taken into account to find the real supply forces generated by the hydraulic actuator. The results of the full vehicle nonlinear suspension system using the FOPID controller are compared with the corresponding passive suspension system (system without controller). The controlled suspension system has been investigated under typical vehicle maneuvers: cruising on rough road surface, sharp braking and cornering. The results have clearly shown the effectiveness and robustness of the proposed controller.

Under mild conditions, it can be induced from the Karush–Kuhn–Tucker condition that the Pareto set, in the decision space, of a continuous Multiobjective Optimization Problems(MOPs) is a piecewise continuous (m 1)  D manifold(where m is the number of objectives). One hand, the traditional Multiobjective Optimization Algorithms(EMOAs) cannot utilize this regularity property; on the other hand, the Regular Model-Based Multiobjective Estimation of Distribution Algorithm(RM-MEDA) only able to build the linear model of decision space using linear modelling algorithm, such as: the local principal component analysis algorithm(Local PCA).Aim at the shortcomings of EMOAs and RM-MEDA, the Manifold-Learning-Based Multiobjective Evolutionary Algorithm Via Self-Organizing Maps(ML-MOEA/SOM) is proposed for continuous multiobjective optimization problems. At each generation, first, via Self-Organizing Maps, the proposed algorithm learns such a nonlinear manifold in the decision space; then, new trial solutions is built through expanding the neurons of SOM with random noise; at the end, a nondominated sorting-based selection is used for choosing solutions for the next generation. Systematic experiments have shown that, overall, ML-MOEA/SOM outperforms NSGA-II, and is competitive with RM-MEDA in terms of convergence and diversity, on a set of test instances with variable linkages. We have demonstrated that, compared with NSGA-II and RM-MEDA, via self-Organizing maps, ML-MOEA/SOM can dig nonlinear manifold hidden in the decision space of multiobjective optimization problems.

The real challenge in pattern recognition tasks and machine learning processes is to train a discriminator using labeled data and use it to distinguish between future data points as accurate as possible. However, most of the problems in the real world have numerous data. Therefore assigning labels to every data points in these problems are a cumbersome or even impossible matter. Semi-supervised learning is one approach to overcome these types of problems. It uses only a small set of labeled with the company of huge remain and unlabeled data to train the discriminator. In semi-supervised learning, it is very essential that which data is labeled and depend on position of data it effectiveness changes. In this paper, we proposed an evolutionary approach called Artificial Immune System (AIS) to determine which data is better to be labeled to get the high quality data. The experimental results represent the effectiveness of this algorithm in finding these data points.

이 논문은 진화생성 개념을 이용하여 자동적으로 추상적인 이미지를 생성하는 자동생성 진화컬 러필드에 대한 작업 연구이다. 자동생성 진화컬러필드(Self-Generated Evolving Color-Field (SGECF)) 는 유전자 알고 리즘(Genetic Algorithm), 재귀 프로그래밍(Recursive Programming), 세포기계(Cellular Automata)를 이용, 예측 불가능한 이미지를 자동 생성하여 언제나 단 하나뿐인 새로운 이미지를 감상할 수 있게 한다. 이 실험은 추상 이미지와 컬러의 시각화를 연구했던 추상표현주의(Abstract Expressionism)의 컬러필드 페인팅 (Color-Field Painting)에서 영감을 얻어 작업했으며, 이 개념을 통해 진화생성예술의 창조적 잠 재력을 찾으 려 한다. 이는 디지털 컬러 필드에 감성적인 이미지를 생성하는 새로운 형식의 컬러 구성과 구도 로 묘사 되어 디지털 추상이미지 생성에 또 다른 방법을 제시한다.

This paper describes a work of Evolutionary Generative Art called SGECF(Self-Generated Evolving Color-Field which automatically generates random abstract images by variation, selection, mutation etc. to be used the concept of evolution. The artist gets the motivation from the origin of evolutionary generative art’s field. Aesthetics matter in this work, the evolutionary visualization is created emotional moods by selfdeveloped, assembled, designed, generated inspired by Color Filed Painting. According to the abstract expressionism that Color Filed Painting involved in, the self- generated images transfer the emotional message to the significant of space.

This paper discusses the use of new graph structural genetic programming for automatic programming, which creates finite state machines (FSM) by evolution. Generally, FSM must define their transition rules for all combinations of states and possible inputs, thus the FSM program will become large and complex when the number of states and inputs is large. In our work, the nodes are connected by trajectory information sets, so it is possible that only the essential problem’s behavior obtained in the current situation are used in the network flow, and it can determine an action by not only the current, but also the past information. In addition, the proposed algorithm enhances evolutionary process by using fitness inheritance technique. Constraining the depth of genetic programming tree is one of the ways to overcome its bloat problem. Finally, fitness inherent is used when fitness evaluation is computationally expensive. Fitness inherent is based on averaging; therefore it reflects some assumptions of smoothness in the search space

This paper introduces a novel intelligent computation adopted from a natural phenomenon entitled Thunderstorm Algorithm (TA) which is applied to optimize an economic dispatch under various technical constraints and environmental requirements. These studies used an IEEE-62 bus system as the sample model for demonstrating ability of TA while searching the optimal solution. Obtained results show that TA gives good performances for determining the optimal solution. This demonstration also describes that the optimal solution is searched in faster convergence and shorter time. This computation also performs its characteristic in smooth and stable processes for completing all steps. In detail, the optimal solution is obatined in 22 steps for 15,586 $/h after pointing at 28,858 $/h at the first streaming. Based on executions, the computation needed 2.5 s for the streaming and it also needed 0.09 for covering the dead tracks included 0.5 s for the replacement.

In this paper, chaos theory and the traditional multi-objective optimization evolutionary algorithm is put forward, "Chaos-based multi-objective evolutionary algorithm", combines a variety of optimization strategies. The traditional multi-objective evolutionary algorithm for repeating individual causes of variation is based on chaotic analysis of multi-objective evolutionary algorithm and demonstration. According to the characteristics of chaotic map tent, NSGA-II algorithm in this paper on the basis of chaotic map was proposed based on chaotic tent initialization and chaotic mutation multi-objective evolutionary algorithm. The original NSGA-II algorithm is improved, and the introduction of adaptive mutation operator and a new crowding distance is calculated and applied to the design of the algorithm. Analysis and experimental results show that these methods can better improve the distribution of population performance.

Co-evolutionary mechanism is now used into evolutionary algorithms and provides these algorithms the power to promote the convergence. In order to promote the performance of the traditional quantum-inspired evolutionary algorithm (QEA), we proposed a novel quantum-inspired co-evolutionary algorithm (NQCEA), in this paper. The quantum state population is firstly divided into multiple sub-populations, which complete the evolution processes independently. In each evolution cycle, every sub-population will produce an elitist individual, which is then selected to construct an elite library. Subsequently, these individuals in this elite library can help the poor sub-population to find the global optimal solution or near-optimal solution. In addition, a diversity indicator is defined for every sub-population and is used to measure the diversity of the corresponding sub-population. As for the sub-population with poor diversity, the mutation strategies are implemented in order to expand its diversity and improve its global search ability. Finally, the NQCEA is compared with the traditional QEA to test their performance. Experiments are performed on the global numerical optimization functions and the simulation results indicate that this new algorithm has the characteristics of good global search capability and more stable performance than the traditional QEA.

To further enhance the distribution uniformity and extensiveness of the solution sets and to ensure effective convergence of the solution sets to the Pareto front, we proposed a MOEA approach based on a clustering mechanism. We named this approach improved multi-objective evolutionary algorithm (LMOEA). This algorithm uses a clustering technology to compute and maintain the distribution and diversity of the solution sets. A fuzzy C-means clustering algorithm is used for clustering individuals. Finally, the LMOEA is applied to solve the classical multi-objective knapsack problems. The algorithm performance was evaluated using convergence and diversity indicators. The proposed algorithm achieved significant improvements in terms of algorithm convergence and population diversity compared with the classical NSGA-II and the MOEA/D.

This paper proposes the application method of an Adaptive Quantum-Inspired Evolutionary Algorithm (AQEA) to Vehicular Ad Hoc Networks (VANETs) for enhancing clustering and routing performance. AQEA integrates quantum-inspired principles, including quantum bits, quantum superposition, and adaptive quantum rotation gates, to effectively navigate the highly dynamic and complex environments characteristic of VANETs. By dynamically balancing exploration and exploitation, AQEA encodes cluster configurations as quantum states and adjusts them using a fitness-driven rotation operator. Comparative simulations reveal that AQEA consistently produces larger, more stable clusters and reduces both reconfiguration overhead and routing costs compared to conventional algorithms such as the Grasshopper Optimization Algorithm (GOA) and Whale Optimization Algorithm (WOA). AQEA consistently achieves larger and more stable clusters, significantly reduces cluster reconfiguration overhead, and minimizes routing costs. Statistically significant improvements were observed: a 59.5% increase in cluster size and a 29.10% reduction in stability penalty relative to WOA, and a 32.99% reduction in routing cost compared to GOA. These results confirm AQEA’s superior adaptability and robustness, positioning it as an effective solution for managing clustering and routing in dynamic VANET environments. These results validate the practical relevance and algorithmic superiority of AQEA, positioning it as a robust and adaptive solution for managing clustering and routing in dynamic VANET scenarios. Also, these results highlight AQEA’s robustness and adaptability, positioning it as an effective solution for managing clustering and routing in dynamic VANET scenarios. Future research directions include real-world validations, expanded performance evaluations, and further refinement of the algorithm's adaptive mechanisms.

Active disturbance rejection control (ADRC) is a unique control strategy that combines the effectiveness of error driven PID controller, usefulness of state observer and strength of nonlinear feedback. This control algorithm, not only actively (online) estimates but also compensates the effects of unknown internal and external disturbances, present inherently in the plant with the help of a well-tuned extended state observer (ESO). Although, the classical solution to the parameter tuning performed by using parameterization technique provides good solution, it is not optimal for having desired performance specifications. Consequently, it became imperative to have intelligent tuning technique to achieve optimized solution to parameter tuning problem. In this regards, the Evolutionary Algorithms (EA), inspired by natural system and based on swarm intelligence, are proven to be the best tool to find the optimized solution of multi-dimensional problems. This paper presents an application of an EA optimized ADRC controller on an uncertain 2-DoF revolute-prismatic (RP) robotic manipulator for efficient trajectory tracking and parametric robustness. Eventually, the conventional ADRC design problem is converted into a special optimization problem for finding the optimal controller tuning parameters. To accomplish this task, two well-known EA’s viz. Particle Swarm Optimization (PSO) and Bacteria Foraging Optimization (BFO) are implemented and performance of EA based controller-plant configuration is individually analyzed for each algorithm. The results of this note illustrate the benefits and weakness of the EA for implementing ADRC on MIMO systems. The performance of both the optimization techniques is compared in terms of computational time and convergence efficiency. Further, the optimized controllers are tested for the robustness in presence of disturbance and sensor noise to imitate real engineering. MATLAB based simulation results are presented and compared to demonstrate the effectiveness of both the EA's in designing an ADRC controller for improving manipulator tracking ability.

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields, however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an Adaptive Tracking Control of Nonlinear System the radial basis function network that is a kind of neural networks. The learning method involves structural adaptation and parameter adaptation. No prior knowledge of the plant is assumed, and the controller has to begin with exploration of the state space. The exploration versus exploitation dilemma of reinforcement learning is solved through smooth transitions between the two modes. The controller is capable of asymptotically approaching the desired reference trajectory, which is showed in simulation result.

Due to the normal forecasting methods for subgrade settlement using observation data have different applicabilities, and the predicting results has bigger volatility and lower accuracy. In view of the above problems, a method based on least square support vector regression (LSTSVR) and real-coded quantum evolutionary algorithm (RQEA) is proposed. Firstly, the LSTSVR parameter is chosen as a combinatorial optimization problem, and determining the objective function of the combinatorial optimization problem, then, using RQEA to solve the combinatorial optimization problem and optimize the LSTSVR parameters, Finaly, LSTSVR-RQEA is used to sovle the prediction of subgrade settlement. The simulation results show that RQEA is an effective method to select LSTSVR parameters, and has excellent performance when applied to the prediction of subgrade settlement.