Enhancing Evolutionary Algorithms With Pattern Mining for Sparse Large-Scale Multi-Objective Optimization Problems

Sparse large-scale multi-objective optimization problems(SLMOPs)are common in science and engineering.However,the large-scale problem represents the high dimensionality of the decision space,requiring algorithms to traverse vast expanse with limited computational resources.Furthermore,in the context of sparse,most variables in Pareto optimal solutions are zero,making it difficult for algorithms to identify non-zero variables efficiently.This paper is dedicated to addressing the challenges posed by SLMOPs.To start,we introduce innovative objective functions customized to mine maximum and minimum candidate sets.This substantial enhancement dramatically improves the efficacy of frequent pattern mining.In this way,selecting candidate sets is no longer based on the quantity of nonzero variables they contain but on a higher proportion of nonzero variables within specific dimensions.Additionally,we unveil a novel approach to association rule mining,which delves into the intricate relationships between non-zero variables.This novel methodology aids in identifying sparse distributions that can potentially expedite reductions in the objective function value.We extensively tested our algorithm across eight benchmark problems and four real-world SLMOPs.The results demonstrate that our approach achieves competitive solutions across various challenges.

Optimization of water-urban-agricultural-ecological land use pattern:A case study of Guanzhong Basin in the southern Loess Plateau of Shaanxi Province,China

Extensive land use will cause many environmental problems.It is an urgent task to improve land use efficiency and optimize land use patterns.In recent years,due to the flow decrease,the Guanzhong Basin in Shaanxi Province is confronted with the problem of insufficient water resources reserve.Based on the Coupled Ground-Water and Surface-Water Flow Model(GSFLOW),this paper evaluates the response of water resources in the basin to changes in land use patterns,optimizes the land use pattern,improves the ecological and economic benefits,and the efficiency of various spatial development,providing a reference for ecological protection and high-quality development of the Yellow River Basin.The research shows that the land use pattern in the Guanzhong Basin should be further optimized.Under the condition of considering ecological and economic development,the percentage change of the optimum area of farmland,forest,grassland,water area,and urban area compared with the current land use area ratio is+2.3,+2.4,-6.1,+0.2,and+1.6,respectively.The economic and ecological value of land increases by14.1%and 3.1%,respectively,and the number of water resources can increase by 2.5%.

Establishment and Application of Agricultural Landscape Pattern Spatial Optimization Model Based on GIS-MATLAB-CA

Reasonable degree of the landscape pattern spatial distribution directly influences the sustainable use of regional land resources. Aiming at the unreasonable distribution of agricultural ecological landscape pattern, the deterioration of ecological environment, the Cellular Automaton (CA) principles were used to establish the optimized rules, such as landscape suitability rules, landscape prior rules and restraint conditions; and the standardization of the spatial data was realized by the competence of GIS spatial data handling and data spatial analysis, and finally, landscape pattern spatial optimization model was established with the support of MATLAB platform, i.e. LPSO Model. The spatial pattern optimization of agricultural landscape in west Jilin Province has been realized, which also laid a theoretical foundation for the proper spatial distribution of landscape pattern in west Jilin Province and realizing the sustainable agricultural development.

Anti-interference beam pattern design based on second-order cone programming optimization

When signal-to-interference ratio is low, the energy of strong interference leaked from the side lobe of beam pattern will infect the detection of weak target. Therefore, the beam pattern needs to be optimized. The existing Dolph-Chebyshev weighting method can get the lowest side lobe level under given main lobe width, but for the other non-uniform circular array and nonlinear array, the low side lobe pattern needs to be designed specially. The second order cone programming optimization （SOCP） algorithm proposed in the paper transforms the optimization of the beam pattern into a standard convex optimization problem. Thus there is a paradigm to follow for any array formation, which not only achieves the purpose of Dolph-Chebyshev weighting, but also solves the problem of the increased side lobe when the signal is at end fire direction The simulation proves that the SOCP algorithm can detect the weak target better than the conventional beam forming.

Group Decision Making Based Fuzzy Pattern Recognition Model for Lectotype Optimization of Offshore Platforms 1

This paper develops a fuzzy pattern recognition model for group decision making to solve the problem of lectotype optimization of offshore platforms. The lack of data and the inexact or incomplete information for criteria are the main cause of uncertainty in the evaluation process, therefore it is necessary to integrate the judgments from different decision makers with different experience, knowledge and preference. This paper first uses a complementary principle based pairwise comparison method to obtain the subjective weight of the criteria from each decision maker. A fuzzy pattern recognition model is then developed to integrate the judgments from all the decision makers and the information from the criteria, under the supervision of the subjective weights. Finally a case study is given to show the efficiency and robustness of the proposed model.

Ecologically based landscape pattern optimization in northwest of Beijing

Supported by the technologies of remote sensing(RS) and geographical informa-tion system(GIS),we chose northwest of Beijing as a study area and gave priority to under-standing of the spatial-temporal characteristics of landscape pattern change through visually interpreted Landsat TM images of 1989,1996 and 2005.It is believed that there were a series of landscape ecological problems caused by city expansion:landscape ecological connec-tivity was low;landscape structure was simplified;the fragmentation of green land patch was more obvious on the plain areas,moreover,spatial distribution of green land was unbalanced.For this reason,this study adopted accumulative cost distance model,combined with eco-system services and spatial interactions of landscape types,analyzed the spatial difference of the ecological function and the compactness of landscape structure in the study area,and further discussed the landscape pattern optimization proposal.We find that it is essential to protect and establish ecological sources,to establish urban ecological corridors,and to es-tablish ecological nodes at the landscape ecological strategic positions so as to intensify spatial relationships among landscape elements and maintain continuity of landscape eco-logical process and pattern in the course of city expansion.The methods and final results from this study are expected to be useful for landscape ecological planning in Beijing region.

Adaptive backtracking search optimization algorithm with pattern search for numerical optimization

The backtracking search optimization algorithm（BSA） is one of the most recently proposed population-based evolutionary algorithms for global optimization. Due to its memory ability and simple structure, BSA has powerful capability to find global optimal solutions. However, the algorithm is still insufficient in balancing the exploration and the exploitation. Therefore, an improved adaptive backtracking search optimization algorithm combined with modified Hooke-Jeeves pattern search is proposed for numerical global optimization. It has two main parts： the BSA is used for the exploration phase and the modified pattern search method completes the exploitation phase. In particular, a simple but effective strategy of adapting one of BSA＇s important control parameters is introduced. The proposed algorithm is compared with standard BSA, three state-of-the-art evolutionary algorithms and three superior algorithms in IEEE Congress on Evolutionary Computation 2014（IEEE CEC2014） over six widely-used benchmarks and 22 real-parameter single objective numerical optimization benchmarks in IEEE CEC2014. The results of experiment and statistical analysis demonstrate the effectiveness and efficiency of the proposed algorithm.

Landscape Pattern Optimization of Chengdu Based on Modern Garden City

TOptimization of regional landscape pattern is significant for improving function and value of ecosystem,and restraining the expansion of urban layout.Taking Chengdu City for example,this paper applied RS and GIS techniques,landscape indexes and ecological service function evaluation to further analyze the temporal and spatial characteristics of landscape pattern and spatial differences of regional ecological functions,and on this basis,identified the spatial distribution of ecological source lands.Based on the long-term objective of building Chengdu into a modem garden city,this paper applied the accumulative cost distance model and introduced garden city theory to construct regional ecological corridors and ecological nodes,and explored the approaches of optimizing landscape pattern of modem garden city.The results showed that a great deal of arable land has been transferred to construction land in the urbanization;intensity of regional ecological functions showed obvious spatial differences;ecological source lands were mainly distributed in the Longmen Mountain,the Qionglai Mountain,the Changqiu Mountain and the Longquan Mountain;according to actual conditions of the study area,the road ecological corridors,river corridors and agricultural corridors in the layout of "four rings and six radial corridors" were constructed;ecological nodes dominated by intersection,wetland and forest park were formed.This research method and results are significant references for building Chengdu into a modem garden

A Filter-Based Pattern Search Method for Unconstrained Optimization

We discuss a filter-based pattern search method for unconstrained optimization in this paper. For the purpose to broaden the search range we use both filter technique and frames, which are fragments of grids, to provide a new criterion of iterate acceptance. The convergence can be ensured under some conditions. The numerical result shows that this method is practical and efficient.

Fuel loading pattern optimization of a pressurized water reactor by varying internal weights-based particle swarm optimization

Fuel reload pattern optimization is essential for attaining maximum fuel burnup for minimization of generation cost while minimizing power peaking factor(PPF).The aim of this work is to carry out detailed assessment of particle swarm optimization(PSO) in the context of fuel reload pattern search. With astronomically large number of possible loading patterns, the main constraints are limiting local power peaking factor, fixed number of assemblies,fixed fuel enrichment, and burnable poison rods. In this work, initial loading pattern of fixed batches of fuel assemblies is optimized by using particle swarm optimization technique employing novel feature of varying inertial weights with the objective function to obtain both flat power profile and cycle k_(eff)>1. For neutronics calculation, PSU-LEOPARD-generated assembly depletiondependent group-constant-based ADD files are used. The assembly data description file generated by PSU-LEOPARD is used as input cross-section library to MCRAC code, which computes normalized power profile of all fuel assemblies of PWR nuclear reactor core. The standard PSO with varying inertial weights is then employed to avoid trapping in local minima. A series of experiments havebeen conducted to obtain near-optimal converged fuelloading pattern of 300 MWe PWR Chashma reactor. The optimized loading pattern is found in good agreement with results found in literature. Hybrid scheme of PSO with simulated annealing has also been implemented and resulted in faster convergence.

Optimization of horizontal well staggered patterns

Staggered line-drive patterns are widely used in oilfields. In this paper, to optimize a staggered pattern of horizontal wells, a 3D problem was divided into two 2D （x-y plane andy-z plane） problems with the pseudo-3D method, conformal transformation and superposition principle. A productivity equation for a horizontal well was deduced, which can be used to optimize the well pattern. A relationship between the length of horizontal wells and the shape factor of well patterns was established. The result shows that optimized well patterns can improve oil production from horizontal wells. This provides a theoretical basis for horizontal well applications to the development of oilfields, especially for overall development of oilfields by horizontal wells.

Beam Pattern Synthesis Based on Hybrid Optimization Algorithm

As conventional methods for beam pattern synthesis can not always obtain the desired optimum pattern for the arbitrary underwater acoustic sensor arrays,a hybrid numerical synthesis method based on adaptive principle and genetic algorithm was presented in this paper.First,based on the adaptive theory,a given array was supposed as an adaptive array and its sidelobes were reduced by assigning a number of interference signals in the sidelobe region.An initial beam pattern was obtained after several iterations and adjustments of the interference intensity,and based on its parameters,a desired pattern was created.Then,an objective function based on the difference between the designed and desired patterns can be constructed.The pattern can be optimized by using the genetic algorithm to minimize the objective function.A design example for a double-circular array demonstrates the effectiveness of this method.Compared with the approaches existing before,the proposed method can reduce the sidelobe effectively and achieve less synthesis magnitude error in the mainlobe.The method can search for optimum attainable pattern for the specific elements if the desired pattern can not be found.

Economic Load Dispatch with Daily Load Patterns Using Particle Swarm Optimization

ELD （economic load dispatch） problem is one of the essential issues in power system operation. The objective of solving ELD problem is to allocate the generation output of the committed generating units. The main contribution of this work is to solve the ELD problem concerned with daily load pattern. The proposed solution technique, developed based PSO （particle swarm optimization） algorithm, is applied to search for the optimal schedule of all generations units that can supply the required load demand at minimum fuel cost while satisfying all unit and system operational constraints. The performance of the developed methodology is demonstrated by case studies in test system of six-generation units. The results obtained from the PSO are compared to those achieved from other approaches, such as QP （quadratic programming）, and GA （genetic algorithm）.

Distributed versus Lumped Optimization of Cropping Pattern and Water Resources Utilization

Several whole-farm agro-economic optimization models have been developed to deal with lumped planning issues in the agriculture sector. However, these models cannot be used to devise appropriate management strategies at land parcel level, because of the differences between farm characteristics, and the increased complexity of the hydrological processes. Based on Spatial Farm Database (SFD) which is consisted of a number of farm-level spatial data, including location, paddock properties, owner specifications and budgets, it is possible to provide the farm manager with some suggestions regarding the optimal choice of crops and the area to be allocated for each one. To this end, genetic algorithm is used in order to cope with model nonlinearity and a large number of decision variables. In order to test the proposed model, the Mobarakabad district is modeled with 126 agriculture fields, and the optimization model is run for this area. Results showed that the optimization procedure can find more realistic farm-level optimal solutions due to its advantage in adequate modeling of field characteristics, common groundwater resources, and the associated constraints. The results of lumped optimizations could also be used as benchmarks for the purposes of comparison and interpretation.

A Time Pattern-Based Intelligent Cache Optimization Policy on Korea Advanced Research Network

Data is growing quickly due to a significant increase in social media applications.Today,billions of people use an enormous amount of data to access the Internet.The backbone network experiences a substantial load as a result of an increase in users.Users in the same region or company frequently ask for similar material,especially on social media platforms.The subsequent request for the same content can be satisfied from the edge if stored in proximity to the user.Applications that require relatively low latency can use Content Delivery Network(CDN)technology to meet their requirements.An edge and the data center con-stitute the CDN architecture.To fulfill requests from the edge and minimize the impact on the network,the requested content can be buffered closer to the user device.Which content should be kept on the edge is the primary concern.The cache policy has been optimized using various conventional and unconventional methods,but they have yet to include the timestamp beside a video request.The 24-h content request pattern was obtained from publicly available datasets.The popularity of a video is influenced by the time of day,as shown by a time-based video profile.We present a cache optimization method based on a time-based pat-tern of requests.The problem is described as a cache hit ratio maximization pro-blem emphasizing a relevance score and machine learning model accuracy.A model predicts the video to be cached in the next time stamp,and the relevance score identifies the video to be removed from the cache.Afterwards,we gather the logs and generate the content requests using an extracted video request pattern.These logs are pre-processed to create a dataset divided into three-time slots per day.A Long short-term memory(LSTM)model is trained on this dataset to forecast the video at the next time interval.The proposed optimized caching policy is evaluated on our CDN architecture deployed on the Korean Advanced Research Network(KOREN)infrastructure.Our findings demonstrate how add-ing time-based request patterns impacts the system by increasing the cache hit rate.To show the effectiveness of the proposed model,we compare the results with state-of-the-art techniques.

Optimization and Process Design Tools for Estimation of Weekly Exposure to Air Pollution Integrating Travel Patterns during Pregnancy

A growing number of international studies have highlighted that ambient air pollution exposures are related to different health outcomes. To do so, researchers need to estimate exposure levels to air pollution throughout everyday life. In the literature, the most commonly used estimate is based on home address only or taking into account, in addition, the work address. However, several studies have shown the importance of daily mobility in the estimate of exposure to air pollutants. In this context, we developed an R procedure that estimates individual exposures combining home addresses, several important places, and itineraries of the principal mobility during a week. It supplies researchers a useful tool to calculate individual daily exposition to air pollutants weighting by the time spent at each of the most frequented locations (work, shopping, residential address, etc.) and while commuting. This task requires the efficient calculation of travel time matrices or the examination of multimodal transport routes. This procedure is freely available from the Equit’Area project website: (https://www.equitarea.org). This procedure is structured in three parts: the first part is to create a network, the second allows to estimate main itineraries of the daily mobility and the last one tries to reconstitute the level of air pollution exposure. One main advantage of the tool is that the procedure can be used with different spatial scales and for any air pollutant.

The Evolution of Landscape Patterns of and Optimization Measures for Urban Core Areas Against the Background of Urbanization: A Case Study of Yangling Demonstration Zone

Studying tiie urban landscape pattern plays a crucial role in scientific land use and management and in improving the urban ecological environment In this paper, AutoCAD, ArcGIS, Fragstats, and other software were used to analyse the data of the fourth phase of land use in the core atea of Yangling Demonstration Zone. The results showed that： ① in the core area, the percentage of construction land incteased from 18.22% to 61.72%, and the percentage of agricultufal land decreased from 58.36% to 11.14%. And the fafm land was fragmented, and traffic connectivily was strengthened. The afea of garden land was reduced from 251.89 hm2 to 50.38 hm^2, and the landscape metric of forest land showed an inverted V-shaped curve. ②The year 2009 in four phases witnessed the greatest landscape fragmentation, both Edge Density （ED） and Ingest Patch Index （LPI） increased, and human interference enhanced the overall landscape complexity. Measures were fotmulated in terms of deaf development goals, optimized allocation of land resoutces, effective protection of ecological ted lines, and definite ecological responsibility, so as to optimize the urban landscape pattern.

Model of Computer Network Topology Optimization Based on Pattern Recognition Technology

The topological structure of the computer network has an important influence on the efficiency of the whole network system,the exertion of the technical performance, the reliability and the cost. The concept of computer network topology classification, introduces thecharacteristics, based on the analysis of the complex network structure, explore the effective construction of computer network topology model,for its practical application in the design of redundancy is studied, to improve the network system reliability and system safety design，

Structural patterns of land types and optimal allocation of land use in Qinling Mountains

The case study based on Qinling Mountains in Shaanxi Province of China, in virtue of the information from TM image, classifies the land types and analyzes their spatial and temporal differential law, and puts forward three structural patterns of land types in mountainous areas, namely, spatial, quantitative and qualitative structures of mountainous land types. Furthermore, it has been noticed that the analysis of structural patterns can disclose the heterogeneity and orderliness of combination of land types, which can lay the theoretic foundation for comprehensively recognizing ecological characteristics and succession law of structure and function of land types. After the all-around comparative analysis, an optimal allocation of land use in Qinling Mountains has been put forward according to the principle of sustainable development and landscape ecology, which can lay the scientific foundation in practice for the structural adjustment and distribution optimization from the macro level to micro level.

Process Optimization for AZ91 Mg-alloy Low-pressure EPC Process

The influence of a key process variable on the mold filling characteristics of AZ91 Mg-alloy was studied in the low pressure EPC process.The applied flow quantity of insert gas from 1 to 5 m~3/h associated with the pressurizing rate in the low pressure EPC casting process was considered for rectangle and L-shape plate casting. The experimental results show that there is an optimal flow quantity of insert gas for good mold filling characteristics in AZ91 Mg-alloy low-pressure EPC process. The optimal flow quantity of insert gas for the specimens is 3 to 4 m~3/h. Either less or higher than the optimal flow quantity of insert gas would lead to misrun defects or folds, blisters and porosity defects. The practice of hub casting confirmed that the low-pressure EPC process with an optimal processing variable exemplified as 4 m~3/h gas flow quantity was capable of producing complicated magnesium castings without misrun defects.