检索结果-内蒙古大学图书馆

A New Adaptive Prediction a*algorithm for Judicial Sentencing with Empirical Studies

Journal of Systems Science & Complexity 2025年第1期38卷 3-20页

作者： DAI Ruifen WANG Fang GUO Lei ata Science Institute Shandong UniversityJinan250100China Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing100190China

With the development and applications of the Smart Court System(SCS)in China,the reliability and accuracy of legal artificial intelligence have become focal points in recent ***,criminal sentencing prediction,a significant component of the SCS,has also garnered widespread *** to the Chinese criminal law,actual sentencing data exhibits a saturated property due to statutory penalty ranges,but this mechanism has been ignored by most existing *** this,the authors propose a sentencing prediction model that combines judicial sentencing mechanisms including saturated outputs and floating boundaries with neural *** on the saturated structure of our model,a more effective adaptive prediction a*algorithm will be constructed based on the fusion of several key ideas and techniques that include the utilization of the L1 loss together with the corresponding gradient update strategy,a data pre-processing method based on large language model to extract semantically complex sentencing elements using prior legal knowledge,the choice of appropriate initial conditions for the learning a*algorithm and the construction of a double-hidden-layer network *** empirical study on the crime of disguising or concealing proceeds of crime demonstrates that our method can achieve superior sentencing prediction accuracy and significantly outperform common baseline methods.

关键词： Adaptive prediction a*algorithm judicial mechanism neural networks sentencing prediction

来源：评论

学校读者我要写书评

暂无评论

An Asynchronous Genetic a*algorithm for Multi-agent Path Planning Inspired by Biomimicry

引用

Journal of Bionic Engineering 2025年第2期22卷 851-865页

作者： Bin Liu Shikai Jin Yuzhu Li Zhuo Wang Donglai Zhao Wenjie Ge School of Mechanical Engineering Northwestern Polytechnical UniversityXi’an710072China

To address the shortcomings of traditional Genetic a*algorithm (GA) in multi-agent path planning, such as prolonged planning time, slow convergence, and solution instability, this paper proposes an Asynchronous Genetic a*algorithm (AGA) to solve multi-agent path planning problems effectively. To enhance the real-time performance and computational efficiency of Multi-Agent Systems (MAS) in path planning, the AGA incorporates an Equal-Size Clustering a*algorithm (ESCA) based on the K-means clustering method. The ESCA divides the primary task evenly into a series of subtasks, thereby reducing the gene length in the subsequent GA process. The a*algorithm then employs GA to solve each subtask sequentially. To evaluate the effectiveness of the proposed method, a simulation program was designed to perform path planning for 100 trajectories, and the results were compared with those of State-Of-The-Art (SOTA) methods. The simulation results demonstrate that, although the solutions provided by AGA are suboptimal, it exhibits significant advantages in terms of execution speed and solution stability compared to other a*algorithms.

关键词： Multi-agent path planning Asynchronous genetic a*algorithm Equal-size clustering Genetic a*algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive graph neural network protection a*algorithm based on differential privacy

引用

JOURNAL OF SYSTEMS AND SOFTWARE 2025年 225卷

作者： Yu, Junjie Li, Yong Liu, Zhandong Yang, Qianren Xinjiang Normal Univ Coll Comp Sci & Technol Urumqi 830054 Xinjiang Peoples R China

Graph Neural Networks (GNNs) have gained widespread adoption across various fields due to their superior capability in processing graph-structured data. Nevertheless, these models are susceptible to unintentionally disclosing sensitive user information. Current differential privacy a*algorithms for graph neural networks exhibit constrained adaptability and prolonged runtimes. To address these issues, this paper introduces an adaptive GNN protection a*algorithm grounded in differential privacy. The a*algorithm offers robust privacy safeguards at both node and edge levels, employing a bespoke normalization approach based on mean and variance to effectively manage data non-uniformity and outliers, thereby enhancing the model's adaptability to diverse data distributions. Furthermore, the implementation of an early stopping strategy markedly decreases runtime while exerting negligible influence on accuracy, thus enhancing computational efficiency. Experimental results indicate that this approach not only improves the model's predictive accuracy but also significantly reduces its computational time.

关键词： Graph neural networks Differential privacy Adaptive a*algorithm Privacy protection

来源：评论

学校读者我要写书评

暂无评论

Arithmetic optimization a*algorithm with cosine composite chaotic mapping in polar coordinate system for economic load dispatching problems in power systems

引用

APPLIED SOFT COMPUTING 2025年 175卷

作者： Li, Yi-Xuan Wang, Jie-Sheng Zhang, Si-Wen Zhang, Shi-Hui Guan, Xin-Yi Ma, Xin-Ru Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan Liaoning Peoples R China

Economic load dispatch (ELD) aims to minimize the total cost of generating electricity while satisfying load demand and different operational constraints. The Arithmetic Optimization a*algorithm (AOA) with cosine composite chaotic mapping in polar coordinate system is put forward to solve the ELD problems in the power system with the valve point effect, prohibited operation area, transmission loss and other factors. Firstly, seven polar coordinate system chaotic mappings are proposed to be embedded into the MOP and MOA parameters in the AOA. Secondly, a chaotic system based on the cosine transform is put forward. Then, the proposed cosine transform based chaotic system is combined with polar coordinate system chaotic mapping to form polar coordinate system cosine transform composite chaotic mapping. Eventually, these six polar coordinate system cosine transform composite chaotic mapping is then embedded into the MOA and MOP of the AOA to balance the a*algorithm's global and local search capabilities, improve the performance of the a*algorithm and avoid falling into the local optima. The superiority of the improved a*algorithm is verified by employing 12 benchmark test functions in CEC2022. Then, it is compared with the Coati Optimization a*algorithm (COA), Prairie Dog Optimization (PDO), Butterfly Optimization a*algorithm (BOA), Reptile Search a*algorithm (RSA), Bat a*algorithm (BAT) and Osprey Optimization a*algorithm (OOA) to verify its convergence. The ELD problem for a total demand of 2500 MW is solved by using the AOA with cosine composite chaotic mapping in polar coordinate system. The experimental results show that the improved AOA outperforms other optimization a*algorithms on the 12 benchmark functions in CEC2022 and the ELD problems.

关键词： Economic load dispatching Arithmetic optimization a*algorithm Two-dimensional Chaotic mapping Cosine composite chaotic system Valve point effect

来源：评论

学校读者我要写书评

暂无评论

Bias-Compensated PNLMS a*algorithm With Multi-Segment Function for Noisy Input

引用

IEEE ACCESS 2025年 13卷 43741-43748页

作者： Jin, Zhan Yang, Zhonghao Li, Qianjin Ma, Linfeng Qiqihar Univ Coll Commun & Elect Engn Qiqihar 161006 Peoples R China

To address the estimation bias caused by ignoring input noise in existing adaptive filtering a*algorithms, a new proportionate-type a*algorithm is proposed in this paper. First, a bias-compensation term is derived based on an unbiased criterion when constructing the cost function of the a*algorithm to achieve unbiased estimation. Next, this bias-compensation term is integrated into the mu-law PNLMS (MPNLMS) a*algorithm to design the bias-compensated PNLMS combined with the multi-segment function (BC-MS-PNLMS) a*algorithm. Simulation results for echo paths and underwater channels demonstrate that the BC-MS-PNLMS a*algorithm outperforms other sparse-type a*algorithms in sparse experimental environments.

关键词： Adaptive filtering a*algorithm proportional NLMS a*algorithm MPNLMS a*algorithm unbiased estimation multi-segment function Adaptive filtering a*algorithm proportional NLMS a*algorithm MPNLMS a*algorithm unbiased estimation multi-segment function

来源：评论

学校读者我要写书评

暂无评论

Sustainable forestry logistics: Using modified A-star a*algorithm for efficient timber transportation route optimization

引用

FOREST POLICY AND ECONOMICS 2025年 173卷

作者： Veisi, Omid Moradi, Mohammad Amin Gharaei, Beheshteh Maleki, Farid Jabbari Rahbar, Morteza Univ Siegen Business Informat & New Media Siegen Germany Univ Toronto Sch Informat Toronto ON Canada Univ Coll Rouzbahan Sch Architecture & Engn Mazandaran Iran Islamic Azad Univ Dept Architecture Damavand Branch Damavand Iran MUT Univ Tehran Telecommun Engn Tehran Iran Iran Univ Sci & Technol Sch Architecture & Environm Design Tehran Iran

The use of brown, recyclable wood resources has significant importance in a country like Canada, given their abundant availability. Nevertheless, the conveyance of these timber resources to wood recycling facilities offers many economic and environmental benefits to pertinent entities. One potential drawback is that the forest ecosystem could endure substantial harm and ultimately disappear if every road were utilized as access points for timber-transporting vehicles. The main aim of this project is to collect the maximum amount of recycled wood using a minimum forest road network to achieve smart logistics systems. An additional objective of this research is to ascertain the optimal search radius and blocks of area for conducting woodland searches at each station, taking into consideration the quantity of collected wood. The methodology employed in this study involves the application of geometric networking integration techniques in Geographic Information Systems to generate integrated maps using the forest route data, and a modified A-Star a*algorithm is utilized to efficiently determine the optimal wood recycling forest road. The study's results suggest that using the Modified A-Star a*algorithm enables a recycling rate between 50 % and 70 % for the collection of all wood items while utilizing just 10 % of the road network. This approach and technique might be used in future research conducted in countries with similar forest coverage levels.

关键词： Sustainable transportation A-star a*algorithm Forest road network Forestry logistics Route optimization

来源：评论

学校读者我要写书评

暂无评论

Parameter identification of photovoltaic cells/modules by using an improved artificial ecosystem optimization a*algorithm and Newton-Raphson method

引用

ALEXANDRIA ENGINEERING JOURNAL 2025年 123卷 559-591页

作者： Wang, Li Yuan, Qing Zhao, Bin Zhu, Biao Zeng, Xiangjun Changsha Univ Sci & Technol Sch Elect & Informat Engn Changsha 410114 Hunan Peoples R China Changsha Univ Sci & Technol State Key Lab Disaster Prevent & Reduct Power Grid Changsha 410114 Hunan Peoples R China Changsha Univ Sci & Technol Coll Energy & Power Engn Changsha 410114 Hunan Peoples R China

Precise models of photovoltaic (PV) modules are crucial for simulating PV system characteristics. To address the challenges of accurately and promptly acquiring parameters from measured current-voltage (I-V) data of PV modules, an improved artificial ecosystem optimization (IAEO) a*algorithm was proposed. The IAEO a*algorithm enhanced the producer diversity within the production operator by introducing a probabilistic selection mechanism and an evolution mechanism. Moreover, a mutation operation based on historical values was introduced into the consumption operator to enhance the search ability. A comparative analysis was conducted among IAEO and the other six a*algorithms for parameter extraction of PV cells/modules using publicly available datasets. The IAEO a*algorithm demonstrated high identification accuracy and speed. The identification accuracy was improved by constructing a two-layer optimization structure with Newton-Raphson method and using the double-diode model. The Newton-Raphson method integrated IAEO a*algorithm achieved root mean squared error (RMSE) values of 7.32392x10-4, 1.67191x10-3, 9.89002x10-3, and 1.48362x10-3 for France cell, STM6-40, STP6-120, and PWP 201, respectively. An I-V tester was designed to measure the I-V data of different PV modules on the experimental platform. Results showed that the IAEO a*algorithm exhibited superior performance in extracting four specific PV modules, and the relative error of power is below 2.5%.

关键词： Artificial ecosystem optimization a*algorithm Newton-Raphson method Photovoltaic power generation Parameter extraction Current-voltage curve

来源：评论

学校读者我要写书评

暂无评论

Effect of Tooth Geometry on Multi-cycle Meshing Temperature of POM Worm Gears: Parametric Study via an Adaptive Iteration a*algorithm

引用

CHINESE JOURNAL OF MECHANICAL ENGINEERING 2025年第1期38卷 1-13页

作者： Li, Kaixing Xu, Wujiao Liu, Yonggang Qin, Datong Chongqing Univ Coll Mat Sci & Engn Chongqing Key Lab Adv Mold Intelligent Mfg Chongqing 400044 Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China

Meshing temperature analyses of polymer gears reported in the literature mainly concern the effects of various material combinations and loading conditions, as their impacts could be seen in the first few meshing cycles. However, the effects of tooth geometry parameters could manifest as the meshing cycles increase. This study investigated the effects of tooth geometry parameters on the multi-cycle meshing temperature of polyoxymethylene (POM) worm gears, aiming to control the meshing temperature elevation by tuning the tooth geometry. Firstly, a finite element (FE) model capable of separately calculating the heat generation and simulating the heat propagation was established. Moreover, an adaptive iteration a*algorithm was proposed within the FE framework to capture the influence of the heat generation variation from cycle to cycle. This a*algorithm proved to be feasible and highly efficient compared with experimental results from the literature and simulated results via the full-iteration a*algorithm. Multi-cycle meshing temperature analyses were conducted on a series of POM worm gears with different tooth geometry parameters. The results reveal that, within the range of 14.5 degrees to 25 degrees, a pressure angle of 25 degrees is favorable for reducing the peak surface temperature and overall body temperature of POM worm gears, which influence flank wear and load-carrying capability, respectively. However, addendum modification should be weighed because it helps with load bearing but increases the risk of severe flank wear. This paper proposes an efficient iteration a*algorithm for multi-cycle meshing temperature analysis of polymer gears and proves the feasibility of controlling the meshing temperature elevation during multiple cycles by tuning tooth geometry.

关键词： POM worm gears Multi-cycle meshing temperature Adaptive iteration a*algorithm Tooth geometry parameters Parametric study

来源：评论

学校读者我要写书评

暂无评论

Improvement for an optimization a*algorithm and its application in structural model updating

引用

JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING 2025年 1-11页

作者： An, Yonghui Zhong, Yue Yang, Jia-Hua Duan, Yuanfeng Ou, Jinping Dalian Univ Technol Dept Civil Engn State Key Lab Coastal & Offshore Engn Dalian 116023 Peoples R China Guangxi Univ State Key Lab Featured Met Mat & Life cycle Safety Provincially & Ministerially Co Constructed Nanning 530004 Peoples R China Curtin Univ Ctr Infrastructural Monitoring & Protect Sch Civil & Mech Engn Bentley WA 6102 Australia Zhejiang Univ Dept Civil Engn Hangzhou 310058 Peoples R China

Model updating is one of the important components of structural health monitoring. Artificial fish swarm a*algorithm (AFSA) is an effective optimization a*algorithm and can be used in model updating and many research fields. However, its efficiency still requires improvement. A series of improvements for the AFSA is proposed, i.e., accelerating the preying behavior, and setting swimming direction in the previous iteration as the prior direction in the next iteration. After an iteration, the direction of the maximum concentration point within visual distance is selected to swim towards and this direction information is saved;in the preying behavior of the next iteration, the saved direction is considered as the prior direction to prey;if the food concentration in the saved direction is higher than current position, the fish will swim a step in this direction;otherwise, it will prey randomly again. The De Jong Function is used to validate the proposed method and results show that the improvement enhances convergence performance and higher efficiency. Moreover, its application in the finite element model updating of a long-span prestressed concrete continuous rigid frame bridge is investigated;seventeen parameters of the bridge are selected to update its numerical model, and results show that the proposed improvement is successfully applied to model updating. Compared with the AFSA without the proposed improvement, it is more efficient and it saves 25.314% and 32.742% in computational time for the present two examples, respectively. The proposed improvement can be used in various optimization problems of different fields.

关键词： Artificial fish swarm a*algorithm Model updating Rigid frame bridge Structural health monitoring Optimization

来源：评论

学校读者我要写书评

暂无评论

Priority-Based Multi-Objective Routing in Underwater Sensor Networks Using Adaptive Honey Badger a*algorithm

引用

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 2025年第4期34卷

作者： Rex, A. Arul Rose, R. Jemila St Xaviers Catholic Coll Engn Dept Informat Technol Nagercoil Tamil Nadu India ST Xaviers Catholic Coll Engn Dept Artificial Intelligence & Data Sci Nagercoil Tamil Nadu India

Due to the increasing number of applications for various purposes, including commercial, scientific, environmental, and military ones, Underwater Wireless Sensor Networks (UWSNs) have recently attracted substantial attention from academia and enterprises in research and development. Monitoring pollutants, tactical surveillance, tsunami alerts, and offshore drilling are some important applications. Due to acoustic transmission disruptions brought on by extreme noise, extraordinarily lengthy propagation delays, a high bit error rate, a constrained bandwidth, and interference, efficient sensor communication in UWSNs is a difficult challenge. Therefore, designing efficient communication among sensors and sinks is one of the fundamental research themes in UWSNs. This paper proposes an energy-efficient optimal cluster head (CH)-based routing in UWSNs. The proposed methodology consists of three stages namely, cluster formation, CH selection, and priority-based routing. In this study, initially, the clusters are formed using a k-means clustering a*algorithm. Then, the CHs are selected using the Adaptive Honey Badger optimization (AHBO) a*algorithm, which is used to reduce energy consumption and delay. AHBO is a combination of a honey badger, Levy flight, and genetic a*algorithm operators. After the CH selection process, data packets are transferred toward the base station through autonomous underwater vehicles (AUVs). The efficiency of the proposed approach is analyzed based on different metrics and performance compared with the different methods.

关键词： Adaptive honey badger a*algorithm Levy flight genetic a*algorithm autonomous underwater vehicles underwater wireless sensor networks cluster heads

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：