检索结果-内蒙古大学图书馆

AKGNN: When Adaptive Graph Neural Network Meets Kolmogorov-Arnold Network for Industrial Soft Sensors

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Yang, Zeyu Mao, Longying Ye, Lingjian Ma, Yiran Song, Zhihuan Chen, Zhichao Huzhou Univ Sch Engn Zhejiang Key Lab Ind Solid Waste Thermal Hydrolysi Huzhou Key Lab Intelligent Sensing & Optimal Contr Huzhou 313000 Peoples R China Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China Guangdong Univ Petrochem Technol Guangdong Prov Key Lab Petrochem Equipment Fault D Maoming 525000 Peoples R China

data-driven soft sensors, which estimate quality variables from process variables, are very important to industrial processes. However, there remains significant room for enhancement in terms of accuracy in the deep learning (DL) era, and one of the promising solutions is embedding graph structure to delineate process variable relationships for feature extraction part and modify network architecture for label inference to make it as close to those industrial (semi-)empirical equations as possible. However, the ground-truth: 1) graph structure and 2) (semi-)empirical equations are unavailable in industrial practice. To alleviate these challenges, this article introduces a novel DL-based soft sensor model termed adaptive Kolmogorov-Arnold-based graph neural network (AKGNN). Specifically, for issue 1), the AKGNN first formulates the graph structure construction as a constrained optimization problem, reformulates the metric space with the help of the entropy function, and derives a novel DL-backend compatible graph construction strategy. Consequently, for issue 2), the Kolmogorov-Arnold network (KAN) is then designed to enable the label inference to be consistent with the (semi-)empirical equations. Finally, the detailed algorithm for AKGNN is summarized and various experiments are conducted to demonstrate the effectiveness of the proposed AKGNN.

关键词： Mathematical models Soft sensors Adaptation models Hidden Markov models Feature extraction data models Training Network architecture Adaptive systems Accuracy Deep learning (DL) graph neural network (GNN) Kolmogorov-Arnold representation theorem soft sensor

来源：评论

学校读者我要写书评

暂无评论

Graph Multi-Resolution Transformer for Road Traffic Anomaly Detection

引用

ieee ACCESS 2025年 13卷 27428-27437页

作者： Park, Donghyun Choi, Sung-Soo Lim, Donghyun Kang, Yong-Shin Adv Inst Convergence Technol Suwon 16229 South Korea

Traffic anomaly detection has become increasingly vital for ensuring the safety, efficiency, and resilience of urban transportation systems. The emergence of megacities and the integration of autonomous vehicles (AVs) introduce new challenges for anomaly detection in mixed-traffic environments. AVs exhibit distinct driving behaviors compared to human drivers, resulting in more complex traffic scenarios that necessitate advanced detection methods. This paper presents a novel Graph Multi-Resolution Transformer (GMRT) model designed for traffic anomaly detection in environments where autonomous and human-driven vehicles coexist. Utilizing simulation data from the autonomous driving demonstration zone in South Korea, the GMRT effectively captures temporal patterns at multiple resolutions and leverages graph-based spatial relationships to enhance anomaly detection performance. Unlike traditional models that focus on macro-level traffic flow, our approach operates at a micro-level (lane-based), enabling precise identification of anomalies on a per-lane basis. Comparative experiments against established time-series models demonstrate the superior accuracy and robustness of GMRT, particularly in early anomaly detection across varied temporal horizons. The results underscore the model's potential as a robust solution for contemporary and future urban traffic management challenges, especially in scenarios involving the increasing penetration of AVs.

关键词： Anomaly detection Roads Transformers data models Road traffic Feature extraction Analytical models Autonomous vehicles Accuracy Time series analysis Deep learning intelligent transportation monitoring road traffic anomaly detection multi-resolution learning time-series analysis

来源：评论

学校读者我要写书评

暂无评论

Smart Grid Management with AI driven Analytics in Solar Energy 2

Smart Grid Management with AI Driven Analytics in Solar Ener...

引用

2nd International conference on Machine learning and Autonomous systems, ICMLAS 2025

作者： Timande, Devanshi Agade, Nishant Gudadhe, Amit Faculty of Engineering & Technology Department of Artificial Intelligence and Data Science Wardha India Faculty of Engineering & Technology Wardha India

ISBN: (纸本)9798331505745

This paper presents an AI-driven framework for real-time smart grid optimization tailored specifically for solar energy integration. The proposed system features a multi-layered architecture that integrates data acquisition from solar irradiance sensors, smart meters, and meteorological sources with advanced pre-processing techniques to ensure data quality and fusion. Using advanced deep learning architectures, such as Long Short-Term Memory networks for forecasting solar irradiance and regression methodologies for predicting load, our proposed framework dynamically adjusts energy dispatch and demand response measures to address the inherent variability associated with solar power. Additionally, a combined strategy that incorporates reinforcement learning is implemented to improve real-time grid stability and operational efficiency, and explainable artificial intelligence methods are used to provide clarity in decision-making processes. Simulation studies conducted on an enhanced ieee 24-bus test system have shown to reduce forecast error by up to 30% and prevent the occurrence of grid instability events by about 40% in contrast with traditional methods. These results are promising for AI-based analytics since it promises to enhance smart grid functionality and enable more sustainable use of renewable resources. Further research will develop this model with additional renewable energy sources and increase cybersecurity. © 2025 ieee.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Managing data Heterogeneity for Ontology-driven Models: Application to Gamified E-learning Contexts 17

Managing Data Heterogeneity for Ontology-Driven Models: Appl...

引用

17th International conference on Computer Supported Education, CSEDU 2025

作者： Gomaa, Yara Lahoud, Christine Abel, Marie-Hélène Moussa, Sherin Laboratoire HEUDIASYC Université de Technologie de Compiègne Sorbonne Universités 57 Avenue Landshut Compiègne60200 France Université Française d’Egypte 21 Ismailia Desert Road Shorouk City Cairo11837 Egypt CIAD UR 7533 Univ. BourgogneFranche-Comté UTBM BelfortF-90010 France Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

ISBN: (纸本)9789897587467

data heterogeneity within gamified e-learning systems exposes a challenge for ontology-driven models, specifically ontology-based recommender systems. These systems can help teachers who are unfamiliar with gamification by offering personalized recommendations to gamify their pedagogical resources. Yet, developing such systems requires collecting and integrating diverse data about users, resources, and game elements, originating from multiple sources, like learning management systems and educational repositories, each with varying formats and inconsistent semantics. This paper proposes an approach to manage the complexities of collecting and preparing heterogeneous data for an ontology-driven model within gamified e-learning contexts. A full overview is provided on the data workflow, which consists of two main phases: (1) data collection, which combines automated techniques through APIs and web scraping, and (2) data Integration by means of mapping the collected data into our Teacher in Gamified e-learning Context (TGC) ontology to produce coherent and semantically enriched structure. The resulting data repository facilitates semantic queries, inference, and knowledge enrichment, overcoming challenges like cold-start scenarios and supporting the dynamic generation of personalized recommendations. This proposed approach aims to establish a robust approach that addresses the challenges of data heterogeneity, ensuring consistent and meaningful integration for ontology-based recommender systems in gamified e-learning contexts. Copyright © 2025 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Knowledge Graph-driven Two-Dimensional Convolutional Embedding Methods in Recommender systems 1

Research on the Application of Knowledge Graph-Driven Two-Di...

引用

1st International conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Dong, Peng School of Business Stevens Institute of Technology HobokenNJ United States

ISBN: (纸本)9798331529246

This article proposes a knowledge graph-driven recommendation method that integrates user preferences and contrastive learning to enhance the performance of the recommendation system. The study introduces knowledge-aware aggregation technology to extract user features from the user-project interaction graph, capturing preference characteristics using user-target factors. Additionally, a two-dimensional convolution method, incorporating both spatial and channel attention mechanisms, is employed to extract project features from the knowledge graph, with recommendation prediction achieved through the inner product. To address challenges posed by noisy knowledge graph data and the reliance on high-quality data, the paper introduces a model combining relationship learning with contrastive learning. This model leverages data augmentation techniques to generate subgraphs, enhancing the knowledge graph's content. By comparing the subgraphs to the original graph, hierarchical features are learned to improve both the accuracy and robustness of the recommendations. The results show that the KG-UIR and KGCRL models significantly enhance recommendation performance and system robustness. They also help mitigate issues related to data sparsity and cold-start problems to some extent. © 2025 ieee.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning-Based Speed Predictor for Distributionally Robust Eco-Driving

引用

ieee ACCESS 2025年 13卷 13904-13918页

作者： Chaudhary, Rajan Sharma, Nalin Kumar Kala, Rahul Singh, Sri Niwas ABV Indian Inst Informat Technol & Management Dept Elect & Elect Engn Gwalior 474015 India Indian Inst Technol Jammu Dept Elect Engn Jammu 180019 India ABV Indian Inst Informat Technol & Management Ctr Autonomous Syst Gwalior 474015 India

This paper proposes an eco-driving technique for an ego vehicle operating behind a non-communicating leading Heavy-Duty Vehicle (HDV), aimed at minimizing energy consumption while ensuring inter-vehicle distance. A novel data-driven approach based on Deep Reinforcement learning (DRL) is developed to predict the future speed trajectory of the leading HDV using simulated speed profiles and road slope information. The DQN-based speed predictor achieves a prediction accuracy of 95.4% and 93.2% in Driving Cycles 1 and 2, respectively. This predicted speed is then used to optimize the ego vehicle's speed plan through a distributionally robust Model Predictive controller (MPC), which accounts for uncertainties in the prediction, ensuring operational safety. The proposed method demonstrates energy savings of 12.5% in Driving Cycle 1 and 8.6% in Driving Cycle 2, compared to traditional leading vehicle speed prediction methods. Validated through case studies across simulated and real-world driving cycles, the solution is scalable, computationally efficient, and suitable for real-time applications in Intelligent Transportation systems (ITS), making it a viable approach for enhancing sustainability in non-communicating vehicle environments.

关键词： Drag Safety Predictive models Lead Trajectory Fuels Force Aerodynamics Vectors Uncertainty Deep reinforcement learning distributionally robust eco-driving heavy-duty vehicles leading vehicle observer model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Noise-Resilient Fault Diagnosis Method Based on Optimized Residual Networks

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Chen, Zhiwen Liu, Jiakun Du, Zhile Fan, Xinyu Luo, Hao Cent South Univ Sch Automat Changsha 410083 Peoples R China Harbin Inst Technol Dept Control & Simulat Ctr Harbin 150001 Peoples R China

In industrial applications, the complexity of systems and the dynamic nature of operating environments often result in raw data being heavily contaminated by noise. This presents significant challenges for traditional deep-learning-based fault diagnosis methods, which may struggle to handle such noisy data effectively. To address these challenges, this article proposes a noise-resilient optimized residual network. The proposed network comprises three main modules: the inverted residual block (IRB), the efficient channel attention (ECA) mechanism, and a soft-thresholding function (ST-func). The IRB enhances the model's ability to capture signal correlations, improve inductive bias, and extract richer local features by varying the input channel dimensions. The ECA mechanism, designed as auxiliary paths for the residual blocks, improves the model's ability to perceive relationships between different channels in the input features, thus focusing more on critical channels and boosting overall performance. Finally, the features extracted through global average pooling (GAP) and ECA are passed through the ST-func to remove irrelevant information and further refine the feature set. Experimental results demonstrate that in comparison to existing mainstream deep learning fault diagnosis methods, the proposed approach offers significant advantages, including a lightweight design and superior robustness in handling noisy fault diagnosis tasks, making it highly suitable for practical industrial applications.

关键词： Noise Fault diagnosis Noise reduction Feature extraction Deep learning Training Convolution Robustness data mining Convolutional neural networks Efficient channel attention (ECA) industrial systems noise-resilient soft threshold

来源：评论

学校读者我要写书评

暂无评论

data-driven Feedforward control for Suppressing Coupled Vibrations in Positioning systems

Data-Driven Feedforward Control for Suppressing Coupled Vibr...

引用

2025 ieee International conference on Mechatronics, ICM 2025

作者： Teramoto, Shota Yamaguchi, Daigo Sato, Shimpei Maeda, Yoshihiro Nagoya Institute of Technology Nagoya Japan

ISBN: (纸本)9798331533892

In the fast and precise control of positioning mechanisms, coupled vibrations often arise owing to the interaction of multiple structural components within industrial machines, leading to deteriorated positioning accuracy and increased complexity in controller design. This paper presents data-driven vibration suppression control (DD-VSC), a feedforward (FF) control method specifically tailored to suppress these coupled vibrations. Theoretically, DD-VSC suppresses coupled vibrations, and by introducing an additional degree-of-freedom in the FF controller structure, it mitigates discontinuities in FF controller outputs during fast and precise positioning. Its effectiveness was validated through experimental comparisons with the estimated response iterative tuning method using a laboratory-positioning device. © 2025 ieee.

关键词： Feedforward control

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Generalized Adaptive Weighted Recursive Least Squares Dictionary learning 6

Semi-Supervised Generalized Adaptive Weighted Recursive Leas...

引用

6th ieee International conference on Image Processing, Applications and systems, IPAS 2025

作者： Yousefi, Mohadeseh Naderahmadian, Yashar Beheshti, Soosan University of Guilan Department of Electrical and Computer Engineering Rasht Iran Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering Toronto Canada

ISBN: (纸本)9798331506520

This work presents a novel semi-supervised dictionary learning framework that updates the dictionary by online learning and is efficient in utilizing the training data. The method employs a two-stage process to train the dictionary: initial training with limited labeled data, followed by online refinement using abundant unlabeled data. We introduce an adaptive correction weight to control the influence of new unlabeled data on the dictionary update based on its consistency with the current model estimate. This approach enables efficient use of the training data set. Moreover, results in faster dictionary convergence and improves data representation accuracy, especially in scenarios with limited training data. Experimental results demonstrate significant enhancement in the classification accuracy of the proposed method compared to the state-of-the-art semi-supervised dictionary learning methods, particularly when dealing with a limited number of training samples. © 2025 ieee.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Model-driven Bayesian Reinforcement learning for IRS-Assisted Massive MIMO-OFDM Channel Feedback, Beamforming, and IRS control

引用

ieee TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第3期24卷 2514-2529页

作者： Bi, Yuanyuan Lau, Vincent K. N. Tsang, Danny H. K. Hong Kong Univ Sci & Technol Acad Interdisciplinary Studies Hong Kong Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Guangzhou Internet Things Thrust Guangzhou 511400 Guangdong Peoples R China

In Intelligent Reflecting Surface (IRS)-assisted massive Multiple-Input Multiple-Output (MIMO) systems, the downlink channel state information (CSI) needs to be fed back to the base station (BS) and utilized to perform the beamforming and IRS control for high spectral efficiency performance. However, the intricate nature of these systems, characterized by a vast number of antennas, subcarriers, and IRS elements, exacerbates the CSI feedback overhead and complicates the optimization of beamforming and IRS parameters, potentially compromising spectral efficiency. Addressing these challenges, this paper introduces a Bayesian Reinforcement learning (BRL)-based approach, named IRS-CSI-BRL, for efficient CSI feedback, beamforming, and IRS control. Firstly, the IRS-CSI-BRL approach utilizes the equivalent CSI for optimization, aligning with current channel estimation protocols without necessitating extensive modifications. Secondly, it employs a practical IRS control model that optimizes the effective capacitance of IRS control circuits rather than IRS reflection coefficients, accurately reflecting the IRS's frequency-responsive behavior to enhance system performance. Additionally, we advocate bypassing the reconstruction of the CSI at the BS to eliminate information irrelevant to beamforming and IRS control, thereby boosting feedback efficiency. Another distinctive feature of the proposed scheme is that its output format is probability distributions, which enables the incorporation of model-assisted knowledge about the latent space and boosts the algorithm's robustness. Simulation results demonstrate that the proposed IRS-CSI-BRL scheme significantly outperforms start-of-the-art solutions in feedback overhead reduction and system data rate enhancement while maintaining exceptional robustness. Furthermore, this approach maintains flexibility, allowing for the incorporation of an additional training loss function for full CSI reconstruction if needed.

关键词： Array signal processing Integrated circuit modeling Optimization Reflection coefficient Channel estimation Capacitance Training Protocols Downlink Circuits IRS massive MIMO CSI feedback beamforming Bayesian reinforcement learning

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：