检索结果-内蒙古大学图书馆

4th IEEE International conference on Data Science and Computer Application, ICDSCA 2024

作者： Ma, Jun Sun, Qian Chengdu Neusoft University Sichuan Chengdu611844 China PowerChina Sichuan Electric Power Engineering Co. Ltd. Sichuan Chengdu610041 China

ISBN: (纸本)9798350368239

this paper achieves the dynamic optimization of system performance through the application of Q-learning and deep reinforcement learning (DQN). In traditional systems, decision-making mechanisms often lack self-adjusting capabilities for various requirements. By using adaptive optimization techniques, the system can make real-time adjustments according to the feedback from the operating environment, thus optimizing the decision-making process. the system is mainly composed of two parts: algorithm design and model simulation. Simulation results indicate that in multiple test scenarios, this system significantly enhances the operational efficiency and performance. Data analysis reveals that compared with traditional static mechanisms, the system's task completion rate has increased by 15% and the operation time has been reduced by 12%. Moreover, the universality of the adaptive optimization mechanism in different operating scenarios has been verified through precise analysis of simulation data. In conclusion, this study demonstrates that the adaptive system optimization based on reinforcement learning can not only remarkably improve the performance of individualized decision-making, but also provide effective theoretical support and technical reference for the design of future intelligent systems. ©2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on key technologies of multi-agent game decision distributed learning system for agent equipment decision parameter optimization 4

Research on key technologies of multi-agent game decision di...

引用

4th International Signal Processing, Communications and Engineering Management conference, ISPCEM 2024

作者： Yu, Xie Yu, Changzhou Liu, Siyuan Yang, Guang Xu, Haoran An, Bo Jiangsu WebAce Intelligent Industry Innovation Center CO. LTD. Nanjing211135 China

ISBN: (纸本)9798331528676

the optimization of decision parameters for equipment in the intelligent agent domain is becoming increasingly paramount, driven by advancements in modern technology and the intricacies of battlefield environments. Multi-agent game theory, by simulating the interactions and confrontations of various agents under diverse scenarios, can authentically replicate the complex dynamic relationships inherent in the battlefield. Meanwhile, distributed learning systems demonstrate unique advantages in managing vast data sets and intricate computations. the synergy of these two approaches not only enhances the accuracy and timeliness of decision-making but also propels the innovation and advancement of intelligent agent technology. the transition from theory to practical application encompasses numerous critical technologies, including the construction of multi-agent game models, algorithm design, and the establishment of distributed architectures, all aimed at achieving efficient and precise optimization of intelligent agent equipment decision parameters. ©2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Anomaly Detection in CAN Bus Based on Ensemble learning 4

Network Traffic Anomaly Detection in CAN Bus Based on Ensemb...

引用

4th International conference on Machine learning and intelligent Systems Engineering (MLISE)

作者： Wu, Yuxi Tao, Xiaodong Henan Univ Sch Comp & Informat Engn Kaifeng Peoples R China

ISBN: (纸本)9798350375084;9798350375077

As the transportation and information industries continue to advance, the increasing variety of application scenarios, devices with computing capabilities, and a growing number of open ports have heightened security risks for vehicle networks. To improve the accuracy of detecting abnormal traffic in vehicle networks, we propose a model based on ensemble learning with a Stacking model integration approach. this method includes a meta-classifier composed of decision trees, extremely randomized trees, and extreme gradient boosting. the final classification prediction results are obtained by linearly stacking input features and weights into a SoftMax meta-learner. Additionally, the research enhances the classification accuracy of network flow data through parameter optimization. Testing results on the real automotive hacker attack dataset, Car-Hacking, show that this method achieves an accuracy rate of up to 99.2% in detecting denial of service, gear spoofing, and RPM spoofing attack types, and up to 97.5% accuracy in Fuzzy attack types. the study indicates that this model has a low false positive rate, high detection accuracy, and high detection rate, significantly outperforming traditional detection methods based on other machine learning technologies.

关键词： in-vehicle network controller area network anomaly detection ensemble learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Dimension Reduction for Medical Big Data Using optimization Algorithms 4

A Comprehensive Survey on Dimension Reduction for Medical Bi...

引用

4th International Mobile, intelligent, and Ubiquitous Computing conference

作者： Abdelminaam, Diaa Salama Abu Alheijat, Ahmed Taha, Mohamed Benha Univ Fac Comp & Artificial Intelligence Banha Egypt Misr Int Univ Fac Comp Sci Cairo Egypt Obour High Inst Informat Dept Comp Sci Cairo Egypt

ISBN: (纸本)9798350367782;9798350367775

this paper surveys dimension reduction techniques in medical big data using optimization algorithms to address challenges like computational inefficiency, overfitting, and interpretability in high-dimensional datasets. As medical data from sources like electronic health records, genomics, and imaging grow, efficient processing is essential for personalized healthcare. the paper explores feature extraction (PCA, LDA) and feature selection methods, emphasizing metaheuristic algorithms like Genetic Algorithms (GA), Particle Swarm optimization (PSO), and Ant Colony optimization (ACO). these algorithms enhance machine learning model accuracy by selecting relevant features, reducing computational costs, and handling nonlinear relationships in medical data. Applications in diagnosis, treatment prediction, and disease classification are discussed. Future research aims to integrate various optimization strategies and deep learning for more effective dimensionality reduction in healthcare.

关键词： Dimension Reduction Medical Big Data feature selection optimization Algorithms machine learning Meta-heuristics

来源：评论

学校读者我要写书评

暂无评论

the Application and Challenges of Artificial Intelligence in Supporting Educational Innovation 4

The Application and Challenges of Artificial Intelligence in...

引用

4th International conference on Big Data Engineering and Education, BDEE 2024

作者： Cui, Rongyu Xie, Xin Fan, Long Yang, Xiaoli Higher Vocational College Chengdu Neusoft University Chengdu China

ISBN: (纸本)9798350388268

Amid the rapid development of information technology, artificial intelligence (AI) has brought profound changes to the field of education. By analyzing AI applications in China's educational innovation, this paper explores the potential and challenges of AI in educational reform and proposes strategies to promote the scientific, intelligent, and personalized development of the education system. Specific applications demonstrate AI's practical effects in enhancing teaching efficiency, enriching learning experiences, and improving intelligent education management. this study provides theoretical support and practical guidance for the comprehensive upgrading and optimization of the education system, summarizes the challenges of AI education technology and looks forward to the future development trend. © 2024 IEEE.

关键词： Artificial Intelligence Educational Innovation Educational System optimization intelligent Management Personalized learning

来源：评论

学校读者我要写书评

暂无评论

Research on fault identification method of ru-ral distribution network for optimal control 4

Research on fault identification method of ru-ral distributi...

引用

4th International conference on intelligent Power and Systems, ICIPS 2024

作者： Ye, Jianfeng Gong, Yanling Zhang, Yanpeng Su, Gaoyang Chen, Junxue Li, Yang Gong, Ting Yicheng City Power Supply Company State Grid Hubei Electric Power Co. Ltd Hubei Xiangyang China

ISBN: (纸本)9798331532765

With the rapid economic development in rural areas of our country, the scale of the rural distribution network is ex-panding constantly. However, the existing rural distribution network still has problems, such as unreasonable network structure, weak reliability, and aging equipment. therefore, a fault identification method for rural distribution networks oriented to optimal control is proposed to improve the relia-bility of rural distribution networks. However, due to the limitation of the traditional neural network itself, it can not identify the fault samples well. therefore, an intelligent fault identification model of a rural distribution network based on deep learning is proposed. First, determine the neural network architecture;then the model is trained with the corresponding parameter optimization algorithm. Finally, the deep learning model for fault identification of rural dis-tribution networks can be obtained. the simulation results show that the method is effective. © 2024 IEEE.

关键词： deep learning model neural network parameter optimization algorithm rural distribution network

来源：评论

学校读者我要写书评

暂无评论

Cooperative UAV Maneuver Decision-Making Based on Multi-Agent Reinforcement learning 4

Cooperative UAV Maneuver Decision-Making Based on Multi-Agen...

引用

4th International conference on Computer Science, Electronic Information Engineering and intelligent Control Technology, CEI 2024

作者： Huo, Weiyan Li, Jianxun School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350378542

In this paper, we design a cooperative UAV maneuver decision-making task and use multi-agent reinforcement learning to solve it. In this task, two UAVs must learn cooperating with each other to defeat a stronger enemy. Due to sparse reward signal and insufficient exploration, the agents will learn a suboptimal policy. To mitigate this effect, the weighted entropy of reward is maximized to encouraged agent to explore while the expected cumulative reward is maximized. the weighted entropy of reward as an additional objective can be also optimized with reinforcement learning where the additional reward function is negatively correlated with the frequency of the reward obtained by agent. the test results show that compared with Multi-Agent Proximal Policy optimization (MAPPO), MAPPO with maximizing the weighted reward entropy has better performance. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Sensor Errors Using Neural Networks Optimized by WOA 4

Predicting Sensor Errors Using Neural Networks Optimized by ...

引用

4th International conference on Machine learning and intelligent Systems Engineering (MLISE)

作者： Yu, Yuechi Zhou, Xufeng Lu, Junhui Yi, Zhenghang Jianghan Univ Coll Intelligent Mfg Wuhan Hubei Peoples R China

ISBN: (纸本)9798350375084;9798350375077

When sensors perform measurements, certain errors can occur. In the process of oil pipe welding, inaccurate temperature measurements can severely affect the quality of the welded pipes and may even lead to the scrapping of raw materials. To eliminate the impact of reference end temperature on the input-output characteristics of the sensor, we can apply the Whale optimization Algorithm (WOA) to improve the connection weights and thresholds of the BP neural network, thereby developing a WOA-BP neural network model. By using data such as the distance between the sensor and the measured object, and the sensor measurement values as inputs to the WOA-BP neural network prediction model, and comparing the prediction results with those of the traditional BP neural network, the results indicate that, compared to the traditional BP neural network model, the BP neural network model optimized by the WOA algorithm shows significant improvements. the Mean Absolute Error (MAE) decreased from 0.7521 to 0.255, the Mean Absolute Percentage Error (MAPE) decreased from 0.8642 to 0.194, and the correlation coefficient increased from 0.9471 to 0.9825. there for this improvement can effectively enhance the prediction accuracy of the temperature sensor.

关键词： WOA-Optimized BP Neural Network Temperature Prediction of Temperature Sensors

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning in wind energy - a review

引用

INTERNATIONAL JOURNAL OF GREEN ENERGY 2024年第9期21卷 1945-1968页

作者： Narayanan, Valayapathy Lakshmi Indian Inst Technol Guwahati Ctr Intelligent Cyber Phys Syst Res Bldg 4th floor Gauhati 781039 Assam India

Today's environmental concerns, particularly those related to global warming, have sparked a drive for the usage of renewable energy sources. One of the most significant sources of renewable energy is wind energy and wind energy conversion system are preferred to harvest wind energy. Due to the growing sophistication of wind energy conversion systems, new strategies based on advanced analytics are needed. In this study, reinforcement learning implemented in wind energy has been reviewed, the most popular approaches for various applications are identified, and it has been shown that reinforcement learning may be utilized in place of traditional approaches. According to the application, the techniques are examined and divided into four groups: optimal control, prediction and forecasting, optimization, and other techniques. Consequently, many literature has reported that, on an average, reinforcement learning has improved performance by 5% to 20% than existing methods. Moreover, around 85% of the 153 references included in this article were published after 2018. the purpose of the work is to provide a basis for future research on reinforcement learning applied in wind energy that may be crucial to energy sustainability. the report also addresses the discussion on the reinforcement learning current state, limitations, and future scope.

关键词： Reinforcement learning wind energy conversion system wind turbine optimization control strategies

来源：评论

学校读者我要写书评

暂无评论

Novel Abnormal Data Mining and Detection Algorithm for intelligent Systems 4

Novel Abnormal Data Mining and Detection Algorithm for Intel...

引用

4th International conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Xu, Shaomei Fan, Yanling Lin, Bing Continuing Education Service Center Shandong Institute of Commerce and Technology Shandong Jinan250103 China

ISBN: (纸本)9798331523923

In intelligent systems, as the amount of data increases, how to analyse data and extract abnormal information is an important task. Based on this, in order to improve the detection efficiency and accuracy of abnormal data in intelligent systems, this study proposes a new and efficient abnormal data mining and detection algorithm. In the initial modelling process, this study introduced the minimum modification cost principle based on cross entropy for modelling. this algorithm optimizes the time series data cleaning process, thereby removing noise data while maintaining the integrity of the data sequence. then, the extreme gradient boosting algorithm is combined with the Gaussian kernel function to achieve data dimension reduction. this operation can reduce data dimensions and feature redundancy. Finally, the overall anomaly detection operation by integrating the improved Ada boost algorithm with the sampling balance technology can improve the accuracy of the classifier while solving the problem of unbalanced data. the experimental results show that the proposed method is superior to the traditional algorithms in comprehensive indicators. © 2025 IEEE.

关键词： Abnormal Data Detection Data Mining Algorithms Efficiency optimization intelligent Systems

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：