Because of the complexity of data sets from the real world, it is difficult to classify the data sets clearly and effectively, thus we prefer to adopt fuzzy clustering approaches to analyze the data sets. However, due...
详细信息
Because of the complexity of data sets from the real world, it is difficult to classify the data sets clearly and effectively, thus we prefer to adopt fuzzy clustering approaches to analyze the data sets. However, due to the variety of fuzzy clustering algorithms, the different number of clusters will lead to different clustering results. The number of clusters is closely related to the clustering division, so how to determine the number of fuzzy clustering (k ) has become a problem. Until now, many researchers have proposed utilizing fuzzy clustering validity indexes to deal with this kind of problem. However, the effectiveness index of fuzzy clustering can only be evaluated on the basis of the fuzzy clustering algorithm FCM to divide the clusters. When the range of k value is too large, FCM's clustering for different k values is quite time-consuming. From this perspective, this paper proposes a fuzzy clustering optimal k selection method based on multi-objectiveoptimization (FMOEA-K). Different from the traditional methods, this method combines the fuzzy clustering effectiveness index with multi-objective optimization algorithm (MOEA), and uses multi-objective optimization algorithm to search the appropriate cluster center concurrently. Because of the concurrency of the multi-objective optimization algorithm, the calculation time is shortened. The experimental results show that compared with the traditional method, the FMOEA-K can shorten the calculation time and improve the accuracy of calculating the optimal k value.
The urban land-use allocation problem is a spatial optimization problem that allocates optimum land-uses to specific land units in urban *** problem is an NP(nondeterministic polynomial time)-hard problem because of i...
详细信息
The urban land-use allocation problem is a spatial optimization problem that allocates optimum land-uses to specific land units in urban *** problem is an NP(nondeterministic polynomial time)-hard problem because of involving many objective functions,many constraints,and complex search ***,this subject is an important issue in smart cities and newly developed areas of cities to achieve a sustainable arrangement of *** types ofmulti-objective optimization algorithms(MOOAs)based on Artificial Intelligence(AI)have been frequently employed,but their ability and performance have not been evaluated and compared *** paper aims to employ and compare three commonly used MOOAs ***-Ⅱ,MOPSO,and MOEA/D in urban land-use allocation *** algorithms belong to different categories of MOOAs family to investigate their advantage and *** objective functions of this study are compatibility,dependency,suitability,and compactness of land-uses and the constraint is compensating of Per-Capita demand in the urban *** of results is based on the dispersion of the solutions,diversity of the solutions'space,and comparing the number of dominant solutions in *** results showed that all three algorithms improved the objective functions related to the current arrangement of the ***,the run time of NSGA-Ⅱ is the worst,related to the Diversity Metric(DM)which represents the regularity of the distance between solutions at the highest ***,MOPSO provides the best Scattering Diversity Metric(SDM)which shows the diversity of solutions in the solution ***,In terms of algorithm execution time,MOEA/D performed better than the other ***,Decision-makers should consider different aspects in choosing the appropriate MOOA for land-use manage-ment problems.
Air pollution nowadays has seriously hindered the sustainable development. PM2.5 greatly affects air quality and human health, even facilitates virus transmission, making its concentration prediction is crucial. Howev...
详细信息
Air pollution nowadays has seriously hindered the sustainable development. PM2.5 greatly affects air quality and human health, even facilitates virus transmission, making its concentration prediction is crucial. However, previous studies are limited to single PM2.5 concentration series, neglecting optimization of prediction stability, and lacking uncertainty analysis. To address these issues, this research proposed a combined PM2.5 prediction system (CPPs) based on modular concept. Firstly, the temporal and spatial correlations of PM2.5 were fully extracted by data pretreatment and feature selection modules. Subsequently, the results of single submodel prediction module were integrated by multi-objective slime mould algorithm in combination weighted module, achieving Pareto optimality theoretically. Eventually, interval forecasting module analyzed the predictive uncertainty. Notably, a truly accurate metric for predictive directional accuracy was proposed for the first time. Validating CPPs using PM2.5 data from Shanghai during COVID-19 epidemic showed superior performance in point and interval forecasts. This research achieves optimization of prediction accuracy and stability as well as uncertainty analysis based on multiple data sources, contributes to improved air quality and public health protection.
The aerodynamic braking has become an attractive option with the continuous improvement of train *** study aims to obtain the optimal opening angles of multiple sets of braking plates for the maglev ***,a multi-object...
详细信息
The aerodynamic braking has become an attractive option with the continuous improvement of train *** study aims to obtain the optimal opening angles of multiple sets of braking plates for the maglev ***,a multi-objectiveoptimization method is adopted to decrease the series interference effect between multiple sets of *** the computational fluid dynamics method,based on the 3-D,RANS method and SST k-ωturbulence model,is employed to get the initial and iterative ***,the aerodynamic drag and lift are analysed,as well as the pressure and velocity distribution of the flow field with the braking plates open at 75°.Then,the aerodynamic forces of each braking plate pre and post optimization are ***,the correlation between each set of braking plates and the optimized objective is *** is found from the results that the aerodynamic drag and lift of the train have significant differences with or without multiple sets of braking ***,the design variable corresponding to the number of iterations of 89 is taken as the rela-tive optimal solution,and its opening angles of braking plates(B2-B5)are 87.41°,87.85°,87.41°,and 89.88°,*** results are expected to provide a reference for the opening angles design scheme for the future engineering application of high-speed maglev train braking technology.
Metamaterial (MM) is very promising in engineering application since it exhibits extraordinary physical properties that do not exist in nature. Nevertheless, the development of a MM still faces bottleneck problems suc...
详细信息
ISBN:
(纸本)9798350348958;9798350348965
Metamaterial (MM) is very promising in engineering application since it exhibits extraordinary physical properties that do not exist in nature. Nevertheless, the development of a MM still faces bottleneck problems such as to maximize negative permeability and ensure the robustness of the high permeability at the working frequency in engineering applications. To address the inefficiencies of existing multi-objective robust optimization methodologies in applications to MM designs, an improved multi-objective genetic algorithm and an adaptive response surface model are proposed. The numerical optimization results of a prototype MM unit have demonstrated the feasibility and merits of the proposed methodology.
Water-cooled components of air compressor provide a feasible way to improve the performance of automotive fuel cells. Due to the large heat generation during air compression, the efficiency of air compressor is normal...
详细信息
Water-cooled components of air compressor provide a feasible way to improve the performance of automotive fuel cells. Due to the large heat generation during air compression, the efficiency of air compressor is normally not easily enhanced. To recover power and prevent excessive gas temperature, this paper has proposed an optimized water-cooled volute for the turbine-based air compressor used for automotive fuel cells. Firstly, a three-dimensional numerical model of the volute integrated with impeller has been developed, upon comparison with the measured isentropic efficiency and pressure ratio, the mean absolute errors were found to be 0.0669 and 0.0117, respectively. Then, a closed flow passage on the volute outer wall is constructed to form an initial watercooled volute structure. Numerical simulation analysis is then conducted on the initial water-cooled volute under different cooling water inlet conditions. The Box-Behnken method is used to generate the design space for the water-cooled volute structure, and a response surface model is fitted using a second-order function. The response surface model is then used as the objective function of multi-objective genetic algorithm to perform global optimization and generate the Pareto front. The combinations of parameters for the water-cooled volute structures are determined from the optimal solution set. The results showed that the isentropic efficiency of the optimized water-cooled volute was improved by 12.43 % compared to the original volute, and the outlet gas temperature was reduced by 1.29 % compared to the initial water-cooled volute. The proposed water-cooled volute and its design method can enhance the overall performance of the air compressor for automotive fuel cells.
In the context of Mobile Edge Computing (MEC) for the Internet of Vehicles (IoV), vehicles can establish communication connections with other entities to access relevant IoV services. However, current research on offl...
详细信息
In the context of Mobile Edge Computing (MEC) for the Internet of Vehicles (IoV), vehicles can establish communication connections with other entities to access relevant IoV services. However, current research on offloading schemes rarely considers the utilization of idle computing resources available on the road. To address this issue and provide a more efficient offloading scheme that makes more efficient use of computing resources, we propose a vehicle-edge-cloud collaborative offloading scheme incorporating Vehicle-to-Vehicle (V2V) communication. Our scheme effectively utilizes the computing resources of Task-Requesting Vehicles (TRVs), Idle Computing Resource Vehicles (ICRVs), edge devices, and the cloud. First, a vehicle position determination mechanism is designed to ensure the stability of the task offloading process. Second, latency models, energy consumption models, task completion quality models, and multi-objectiveoptimization models are constructed. In addition, an improved NSGA-II algorithm is proposed for task offloading decisions. Finally, the feasibility and stability of the proposed scheme are validated through simulation experiments. The results show that, compared with other schemes, the proposed scheme significantly improves system latency, energy consumption, and service quality.
A high-performance bidirectional-output wavelength-switchable narrow-linewidth thulium-doped fiber laser (TDFL) is proposed and has been demonstrated. Based on the uniform fiber Bragg grating for wavelength selection,...
详细信息
A high-performance bidirectional-output wavelength-switchable narrow-linewidth thulium-doped fiber laser (TDFL) is proposed and has been demonstrated. Based on the uniform fiber Bragg grating for wavelength selection, combined with compound ring cavity (CRC) structure for longitudinal mode selection, single longitudinal mode (SLM) laser operation at wavelengths of similar to 2048.502 and similar to 1942.080 nm are achieved in clockwise (CW) and counterclockwise (CCW) directions, respectively. The multi-objective optimization algorithms, including multi-objective particle swarm optimization (MOPSO) and non-dominated sorting genetic algorithm II (NSGA-II), are introduced to achieve a trade-off between suppression ratio (SR) and transmittance while determining multiple CRC parameters. Switching among the three states - CW SLM output, CCW SLM output, and simultaneous bidirectional SLM output in both CW and CCW directions - is achieved based on the optical path transmission characteristics of the circulators and the intracavity loss adjustment mechanism. Spectrum stability, optical signal-to-noise ratio (OSNR), linewidth, relative intensity noise (RIN), and relaxation oscillation peak are all investigated for the three states. The CW and CCW SLM output can generate stable laser output with an OSNR larger than 74.11 dB. The fluctuations of the center wavelength and the peak power are less than 0.01 nm and 1.037 dB, respectively, over 60 min. Linewidth does not exceed 1.93 kHz and the RIN is less than -125.03 dB/Hz at frequencies greater than 2 MHz. The proposed TDFL is expected to be integrated with wavelength-division multiplexing and free-space optical communication systems in the future.
Provincial inherent heterogeneity in resource endowment, steel demand, and managerial guidance poses not only challenges but also chances to the decarbonization of China's iron and steel industry (ISI). Previous s...
详细信息
Provincial inherent heterogeneity in resource endowment, steel demand, and managerial guidance poses not only challenges but also chances to the decarbonization of China's iron and steel industry (ISI). Previous studies have primarily concentrated on the technological dimension at the national level or plant level but have neglected potential regional synergies. This study proposed a framework encompassing macroeconomic models and multi-objectivealgorithms to optimize interprovincial allocation of scrap resources for coordinating the steelmaking process transition, aiming to minimize total carbon emissions from ISI. Results indicate that optimizing scrap allocation can reduce carbon emissions by 173.97-215.66 million tons, achieving a 99% reduction by 2060 compared to 2020 levels. Under the coordination strategy, 19 out of 28 provinces can achieve carbon neutrality and realize more than 90% pollutant reduction in the ISI. Notably, provinces such as Hebei, Inner Mongolia, Shanxi, Heilongjiang, and Liaoning still need to import more scrap resources and implement innovative low-carbon technologies. Finally, we propose interprovincial coordinated transition strategies, including regional integration management, national data platform, and preferential economic instrument. This work guides national and provincial administrations to formulate differentiated low-carbon transition targets and collaborative actions in ISI, which can be also applied to other substantially heterogeneous industries to achieve carbon neutrality.
Convolutional neural networks (CNNs) have achieved great success in the fields of radiology and pathology. The automatic recognition of vestibular schwannoma (VS) based on magnetic resonance imaging (MRI) can signific...
详细信息
Convolutional neural networks (CNNs) have achieved great success in the fields of radiology and pathology. The automatic recognition of vestibular schwannoma (VS) based on magnetic resonance imaging (MRI) can significantly enhance the speed and accuracy of disease diagnosis, and reduce the threat of the disease to patients' lives. At present, patients are diagnosed using contrast enhanced T1-weighted mode images from MRI but there is growing interest in high resolution T2-weighted mode images. However, due to the complex relationship between these two modes, applying a CNN using a simple multi-mode fusion strategy makes it difficult to learn complex information between the modes, and the feature information cannot be well matched and fused. In addition, most CNN hyper-parameters require fine tuning by experts in numerous "trial and error" experiments to achieve better results, and it is difficult to balance multiple objectives such as the model accuracy and training time. The cost of optimization is very expensive. Therefore, we propose a high-performance "non-deep" VS recognition model with dual-mode multi-channel feature perception coupled with a surrogate-assisted multiobjective particle swarm optimizationalgorithm based on a Kullback-Leibler (KL)-Dropout network to balance multiple objectives while reducing model optimization costs and human influence. Our experimental results showed that the proposed algorithm reached the optimal level in the benchmark test problem. By combining the proposed algorithm with the proposed model, the accuracy was better in the comparison and the amount calculated by the model was controllable, which verified the effectiveness and generalizability of the proposed method.
暂无评论