检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Weizhen He, Jianping Duan, Xiaoming Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

Policy gradient methods are one of the most successful methods for solving challenging reinforcement learning problems. However, despite their empirical successes, many SOTA policy gradient algorithms for discounted problems deviate from the theoretical policy gradient theorem due to the existence of a distribution mismatch. In this work, we analyze the impact of this mismatch on the policy gradient methods. Specifically, we first show that in the case of tabular parameterizations, the methods under the mismatch remain globally optimal. Then, we extend this analysis to more general parameterizations by leveraging the theory of biased stochastic gradient descent. Our findings offer new insights into the robustness of policy gradient methods as well as the gap between theoretical foundations and practical implementations. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global Convergence Guarantees of (A)GIST for a Family of Nonconvex Sparse Learning Problems

引用

IEEE Transactions on Cybernetics 2022年第5期52卷 3276-3288页

作者： Zhang, Hengmin Qian, Feng Shang, Fanhua Du, Wenli Qian, Jianjun Yang, Jian East China University of Science and Technology Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education School of Information Science and Engineering Shanghai200237 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xi'an710071 China Peng Cheng Laboratory Shenzhen518066 China Nanjing University of Science and Technology Pca Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

In recent years, most of the studies have shown that the generalized iterated shrinkage thresholdings (GISTs) have become the commonly used first-order optimization algorithms in sparse learning problems. The nonconvex relaxations of the \ell _{0} -norm usually achieve better performance than the convex case (e.g., \ell _{1} -norm) since the former can achieve a nearly unbiased solver. To increase the calculation efficiency, this work further provides an accelerated GIST version, that is, AGIST, through the extrapolation-based acceleration technique, which can contribute to reduce the number of iterations when solving a family of nonconvex sparse learning problems. Besides, we present the algorithmic analysis, including both local and global convergence guarantees, as well as other intermediate results for the GIST and AGIST, denoted as (A)GIST, by virtue of the Kurdyka-Lojasiewica (KL) property and some milder assumptions. Numerical experiments on both synthetic data and real-world databases can demonstrate that the convergence results of objective function accord to the theoretical properties and nonconvex sparse learning methods can achieve superior performance over some convex ones. © 2013 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Du, Zhenbang An, Jiayu Tu, Yunlu Hong, Jiahao Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Open Set Domain Adaptation (OSDA) copes with the distribution and label shifts between the source and target domains simultaneously, performing accurate classification for known classes while identifying unknown class samples in the target domain. Most existing OSDA approaches, depending on the final image feature space of deep models, require manually-tuned thresholds, and may easily misclassify unknown samples as known classes. Mixture-of-Experts (MoE) could be a remedy. Within an MoE, different experts handle distinct input features, producing unique expert routing patterns for various classes in a routing feature space. As a result, unknown class samples may display different expert routing patterns to known classes. This paper proposes Dual-Space Detection, which exploits the inconsistencies between the image feature space and the routing feature space to detect unknown class samples without any threshold. A Graph Router is further introduced to better make use of the spatial information among the image patches. Experiments on three datasets validated the effectiveness and superiority of our approach. © 2020 IEEE.

关键词： Mixture-of-Experts Open Set Domain Adaptation Routing Feature

来源：评论

学校读者我要写书评

暂无评论

Data-driven Fault Diagnosis Method Based on Fusion of Multi-direction and Multi-source Signals 5

Data-driven Fault Diagnosis Method Based on Fusion of Multi-...

引用

5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

作者： Yang, Yang Wang, Junda Li, Ning Shanghai Jiaotong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

As a pivotal mechanical component of turbine drive-chain, gearbox suffers from various accidents and fault diagnosis could remarkably enhance its reliability and maintain running safety and lifetime. Vibration-based analysis on single-channel is mainly adopted in previous diagnostic, which cannot catch full vibration inner information in gearbox sensors and bring model performance down. In this paper, a novel method based on the fusion of multi-direction and multi-source signals and the convolutional neural network (MDMS-CNN) is presented. This method can obtain multi-dimensional feature maps from MDMS and preserve the time correlation among different signal sequences. First, features from MDMS are extracted via a corrosion conversion method that converts signals into two-dimensional (2-D) gray images. Then, homologous images are spliced into same channels, while heterogeneous images are superimposed to different channels. Finally, fusion features are input into CNN for fault classification. In experiments, the method is validated on a gearbox diagnosis case. Results have shown that the proposed method achieves 99.86% recognition accuracy and faster convergence speed compared to others. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

The ameliorative effects of ginger against heat-induced oxidative stress and mitochondrial dysfunction in Caenorhabditis elegans

引用

Food Science and Human Wellness 2025年

作者： Tingting Xu Mingfang Tao Rong Li Shuxin Tang Yuting Huang Ting Wu Senem Kamiloglu Siyi Pan Xiaoyun Xu Key Laboratory of Environment Correlative Dietology (Ministry of Education)， Huazhong Agricultural University Hubei Key Laboratory of Fruit & Vegetable Processing & Quality Control， Huazhong Agricultural University College of Food Science and Technology， Huazhong Agricultural University Department of Food Engineering， Faculty of Agriculture， Bursa Uludag University Science and Technology Application and Research Center (BITUAM)， Bursa Uludag University

Ginger， rich in gingerols and shogaols， exhibits multiple biological properties. However， the mechanisms underlying its thermotolerance remain unclear. The study employed network pharmacology and experimental validation in Caenorhabditis elegans to investigate how gingerol-related compounds within ginger extract (GE) mitigated damage caused by heat stress (HS). A total of 18 types of gingerol analogues were identified in GE， among which 6-， 8-， and 10-gingerol， as well as 6-， 8-， and 10-shogaol were quantified. Collectively， these six compounds accounted for 54.4% of the total composition. Supplementation with 15 μg/mL GE significantly extended heat-stress lifespan by 20.30%， while the combination of the six major gingerols and shogaols at the same concentration prolonged lifespan by 18.93%. Additionally， pretreatment with GE and the combination alleviated HS-induced oxidative damage by eliminating reactive oxygen species (ROS) and upregulating antioxidant enzymes. Network pharmacology analysis suggested that the MAPK pathway may play a crucial role in thermotolerance. Experimental findings confirmed that ginger attenuated oxidative damage through the activation of SKN-1/Nrf2 and DAF-16/FOXO via the MAPK pathway. Moreover， GE stabilized mitochondrial membrane potential and restored ATP levels， thus preserving mitochondrial function during heat exposure. Further investigations using molecular docking and molecular dynamics simulations revealed that shogaols， with more stable binding affinities for KEAP1 protein， exhibited more potent effects than gingerols in prolonging lifespan and reducing ROS levels under HS conditions. In short， gingerol analogues from ginger conferred thermal resistance to nematodes by mitigating oxidative damage and mitochondrial dysfunction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Based Scene Text Recognition for Industrial Applications

Knowledge-Based Scene Text Recognition for Industrial Applic...

引用

2022 IEEE International Conference on Industrial Technology, ICIT 2022

作者： Deng, Guowei Tu, Jingzheng Chen, Cailian He, Jianping Le, Xinyi Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China 200240 Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai China 200240

ISBN: (纸本)9781728119489

Scene text recognition (STR) methods combined with semantic information have made great progress to recognize texts in natural scenes, most of which are daily words. However, research on mining semantic information in industrial texts attracts less attention. Since industrial texts follow a different semantic pattern defined by industry standards, it challenges many existing methods to conduct accurate semantic reasoning. In this paper, we abstract the industry standards into two aspects of prior knowledge: the grouping property and the prior lexicon. Correspondingly, a knowledge-based language model is proposed with several group-wise correlation modules and a lexicon-based reasoning module to learn semantic rules from both data and the prior knowledge. Besides, we transfer the prior knowledge into data by generating synthetic pure text datasets according to the industry standards' rules, which introduces more prior knowledge to the language model. Furthermore, a novel STR framework is presented by combining the knowledge-based language model and an attention-based vision model. For evaluation, two industrial text datasets called CIN and SB are collected from real-world industrial field surveillance. Experiments indicate that our method's word-level accuracy outperforms state-of-the-art methods with 15% and 10.61% on CIN and SB datasets respectively. © 2022 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

引用

17th Chinese Intelligent Systems Conference, CISC 2021

作者： Liu, Binye Wang, Jinlong Wu, Kaitian Xu, Zhezhuang College of Electrical Engineering and Automation Fuzhou University Fuzhou350000 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China

ISBN: (纸本)9789811663192

The robots have been used in the inspection of industrial wireless sensor networks (IWSNs), that includes data collection and wireless charging. The sensor nodes are always densely deployed and their appearances are similar, thus it is a non-trivial challenge to identify a specific node by the machine vision. To solve this problem, we propose to use the proximity estimation algorithm, which uses wireless signals to estimate neighbor nodes, to help the robot to identify a specific node in the network. The algorithm is deployed a patrol inspection testbed with a mobile robot and multiple sensor nodes, and the experiments are executed to verify its performance. The experimental results show that the proximity estimation algorithm is a reasonable solution to identify similar nodes in the inspection of the IWSN. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

PORTABLE ELECTROCHEMICAL SENSOR BASED ON MOLECULARLY IMPRINTED POLYMER FOR OXYTETRACYCLINE DETECTION 10

PORTABLE ELECTROCHEMICAL SENSOR BASED ON MOLECULARLY IMPRINT...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Tang, Yuxin Hu, Jingfang Wang, Linzhe Wei, Wensong Song, Yu Li, Yansheng Gao, Guowei Beijing key Laboratory of sensor Beijing Information Science & Technology University Beijing100101 China Key Laboratory of Agricultural Product Processing Ministry of Agriculture Institute of Food Science and Technology Chinese Academy of Agricultural Sciences Beijing100193 China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science & Technology Unive rsity Beijing100192 China Zibo Institute for Digital Agriculture and Rural Research Zibo255051 China

ISBN: (纸本)9781837242672

Reduced graphene oxide (rGO) plays a critical role in enhancing the performance of electrochemical sensors through its excellent electrical conductivity, large surface area, ease of functionalization, chemical stability, and synergy with other nanomaterials. In this paper, A novel electrochemical sensor was developed based on rGO and molecularly imprinted polymer (MIP) for detection of trace oxytetracycline (OTC) in water. The MIP/rGO composites are synthesized by in-situ electrochemical modification on a disposable screen-printed electrode (SPE). Due to the large surface area and good electron transport rate of rGO, as well as the specific recognition for TC of MIP, the sensitive determination of trace TC at MIP/rGO/SPE was realized. Linear sweep voltammetry (LSV) was performed on the sensor for the electrochemical analysis of OTC. Under optimized conditions, the peak current of MIP/rGO/SPE exhibited a good linear correlation with OTC concentration in a wide linear range (1-25 (j,mol/L), possessed a detection limit of 0.34 (j,mol/L. Spiked detection of OTC was applied for the sensor in actual water samples, with relative standard deviations (RSDs) of 93.2%-108.7%. These results indicate that the proposed MIP/rGO/SPE sensor has the ability to accurately, rapidly and selectively detect OTC in water samples. © The Institution of Engineering & Technology 2024.

关键词： Reduced Graphene Oxide

来源：评论

学校读者我要写书评

暂无评论

PI2-CMA Based Trajectory Planning Method for the Tractor-Trailer Vehicle 6

PI2-CMA Based Trajectory Planning Method for the Tractor-Tra...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Wang, You Wang, Zehao Wang, Jingchuan Guo, Rui Xiao, Peng Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Institute of Medical Robotics and Department of Automation Shanghai200240 China State Grid Intelligence Technology CO. LTD China

ISBN: (纸本)9798350325485

The motion primitive-based state lattice trajectory planning method has been widely used in the field of trajectory planning. However, due to the limitations of the search space and resolution of motion primitives, and the lack of consideration of scenario information during offline generation of motion primitives, the tractor-Trailer vehicles can easily fall into "jackknife phenomenon"when making large pose adjustments in narrow scenarios, which brings dilemma for trajectory planning. In this paper, a trajectory planning algorithm is proposed based on a general model of tractor-Trailer vehicle, which combines global planning and local optimization. The method first generates a series of motion primitives, including forward and backward driving conditions, and then an A based global state lattice planner is used to obtain a planning result, which is imported as the initial solution into the local trajectory optimizer based on PI2-CMA (Path Integral Policy Improvement with Covariance Matrix Adaptation) algorithm and dynamic potential method. Experiments show that this method significantly improves the performance in the obstacle avoidance, "jackknife phenomenon"avoidance and curvature compared to traditional motion primitive-based state lattice planning methods. © 2023 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Comprehensive Feature Aggregation Network for Road Scene Segmentation 8

Cross-Modality Comprehensive Feature Aggregation Network for...

引用

8th International Symposium on Computer Science and Intelligent control, ISCSIC 2024

作者： Yang, Yale Zhang, Zihao Hou, Huifang Zhang, Wenwen Zhuang, Chunsheng Henan University of Technology College of Information Science and Engineering Zhengzhou China Henan University of Technology Key Laboratory of Grain Information Processing and Control Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control School of Artificial Intelligence and Big Data Zhengzhou China Data Henan University of Technology School of Artificial Intelligence and Big Zhengzhou China Henan Academy of Sciences Zhengzhou China

ISBN: (纸本)9798350380286

RGB-thermal semantic segmentation is a potential solution for reliable semantic scene understanding under adverse weather and complex lighting conditions. However, past studies have primarily focused on the design of fusion paradigms. Unfortunately, these methods have not fully considered the modality differences caused by different imaging mechanisms, thereby reducing the performance of pixel-level semantic analysis. In response to this issue, this paper proposes an innovative Cross-Modality Comprehensive Feature Aggregation Network (CFANet). This method first designs a Cross-Modality Feature Rectification Module (CFRM) to align modality differences;then, it constructs a Global-Local Fusion Module (GLF) to sharpen object edges and refine the segmentation map. Results on two urban scene understanding datasets demonstrate that CFANet can effectively aggregate multi-layer deep features and outperform existing advanced deep learning methods in scene understanding performance. © 2024 IEEE.

关键词： Semantic Segmentation

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：