检索结果-内蒙古大学图书馆

6th International Conference on computer Science and Educational Informatization, CSEI 2024

作者： Li, Chao Xu, Zixuan Jing, Weipeng College of Computer and Control Engineering Northeast Forestry University Harbin150040 China

ISBN: (纸本)9789819637379

In this paper, we propose a novel AI-based model that combines a GPT-2 language model with a natural language generation component to generate Customized Narrative Fragments for Personalized Recommendations(CNFPR) in education. Our approach builds on the existing literature on AI-based learning content generation and learning pathway augmentation, but introduces a new component that leverages the power of GPT-2 and an innovative Conceptual Definition Extractor to generate high-quality natural language text. By integrating this component into our model, we aim to create a more personalized and engaging learning experience for students, one that is tailored to their individual needs and preferences. Experimental results show that compared with the Zero-shot evaluation with GPT-2, our CNFPRNet model demonstrates a 23.5% increase in ROUGE scores. This improves the accuracy of recommended content and enables teaching resources to better meet the individual needs of users. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Report generators

来源：评论

学校读者我要写书评

暂无评论

FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training

FlashMix: Fast Map-Free LiDAR Localization via Feature Mixin...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Raktim Gautam Goswami Naman Patel Prashanth Krishnamurthy Farshad Khorrami Department of Electrical and Computer Engineering Control/Robotics Research Laboratory (CRRL) NYU Tandon School of Engineering Brooklyn NY USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long training times hinder rapid adaptation to new environments. To address this, we propose FlashMix, which uses a frozen, scene-agnostic backbone to extract local point descriptors, aggregated with an MLP mixer to predict sensor pose. A buffer of local descriptors is used to accelerate training by orders of magnitude, combined with metric learning or contrastive loss regularization of aggregated descriptors to improve performance and convergence. We evaluate FlashMix on various LiDAR localization benchmarks, examining different regularizations and aggregators, and demonstrating its effectiveness for rapid and accurate LiDAR localization in real-world scenarios. The code is available at https://***/raktimgg/FlashMix.

关键词： Location awareness Training Measurement Point cloud compression Laser radar Accuracy Pose estimation Benchmark testing Mixers Convergence

来源：评论

学校读者我要写书评

暂无评论

Split Cost Function based Single-Horizon Finite-Set Model Predictive control for Boost Converter with Loading Current Estimation

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Tatari, Fatemeh Rezayof Bizhani, Hamed Iwanski, Grzegorz Warsaw University of Technology Faculty of Electrical Engineering Warsaw Poland Kielce University of Technology Faculty of Electrical Engineering Automatic Control and Computer Science Kielce Poland

This paper presents a robust single-horizon finite-set model predictive control (FS-MPC) method for controlling the output voltage of boost converters. Unlike the long-horizon FS-MPC approach, which addresses the non-minimum phase (NMP) behavior of the converter by extending the prediction horizon (thereby increasing computational effort), the proposed method ensures stable voltage regulation by incorporating inductor current regulation into the cost function. To achieve this, the desired inductor current is calculated based on input-output power balance theory. Unlike recent studies that require an additional sensor to measure the loading current, this paper develops a loading current estimation approach to eliminate the need for extra current sensors, thereby enhancing the robustness of the proposed FS-MPC method. Additionally, over-current protection, which is typically absent in conventional FS-MPC used for direct voltage regulation, is also incorporated into the proposed method. The conventional cost function is also modified to tackle the NMP behavior more effectively. The performance of the proposed method in regulating the output voltage is evaluated through simulation results. Finally, its effectiveness across a wide range of output power and various load characteristics, including resistive, constant power, and constant current loads, is validated via experimental results. The results demonstrate that the proposed method is not only able to eliminate the overshoot and undershoot, but can also improve the settling time by 41% compared to a well-tuned conventional cascaded PI controller. In addition, the proposed method can reduce the computational burden by 84% compared to the conventional long-horizon FS-MPC approach. © 2013 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Switching event-triggered self-adjusting prescribed performance force control of electrohydraulic load simulator

引用

ISA Transactions 2025年

作者： Li, Jiafeng Ji, Ruihang Yan, Hao Shan, Jiefeng Chen, Zanwei School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China Department of Electrical and Computer Engineering National University of Singapore 117576 Singapore

This paper addresses the problem of switching event-triggered self-adjusting prescribed performance force control of electro-hydraulic load simulator (EHLS). A reduced-order fuzzy speed state observer for speed estimation is designed and a self-adjusting performance boundary is devised to mitigate the commutation jitter problem. The switching event-triggered mechanism dynamically adjusts the triggering conditions to optimize resource utilization. To reduce the complexity of the traditional inverse stepping control, the dynamic surface technique is adopted. The results demonstrate that the proposed control method guarantees the boundedness of the closed-loop system states and confines the tracking error to a small range near the equilibrium point within a finite time horizon. Finally, the effectiveness of the proposed method is demonstrated through experimentation. © 2025 International Society of Automation

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Crowdsourcing Task Recommendation Method Based on Heterogeneous Graph Feature Anomaly Detection 18th

Crowdsourcing Task Recommendation Method Based on Heterogen...

引用

18th China Conference on Wireless Sensor Networks, CWSN 2024

作者： Wei, Kai Pan, Qingxian Yu, Song Fan, Zequn Li, Jinru School of Computer and Control Engineering Yantai University Yantai264005 China School of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9789819621859

The crowdsourcing task recommendation method addresses worker selection overload by intelligently matching workers with tasks. However, existing research often overlooks the inherent characteristics of workers and tasks, the long-term behavioral preferences of workers, and abnormal information about workers and tasks, which impacts the accuracy of recommendations. To address these issues, we propose a novel crowdsourcing task recommendation method based on anomaly detection using multi-attribute heterogeneous graph features. This method first establishes the connection relationships between crowdsourcing workers and tasks to construct a worker-task heterogeneous graph. DeepWalk generates initial node features, and the message-passing mechanism in the graph neural network is employed to explore the feature information of workers and task nodes. During message transmission, the graph convolutional autoencoder drives the detection of worker and task feature information. Finally, Bi-GRU captures the long-term behavioral preferences of workers, and link prediction constructs links based on node similarity to complete the recommendation of sensing tasks. We evaluate nine real datasets, and the experimental results demonstrate that the proposed method outperforms the baseline method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Community Membership Hiding via Gradient-based Optimization

arXiv

引用

arXiv 2025年

作者： Silvestri, Matteo Gabrielli, Edoardo Silvestri, Fabrizio Tolomei, Gabriele Department of Computer Science Sapienza University of Rome Rome Italy Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

We tackle the problem of community membership hiding, which involves strategically altering a network’s structure to obscure a target node’s membership in a specific community identified by a detection algorithm. We reformulate the original discrete counterfactual graph objective as a differentiable constrained optimization task. To solve this, we propose ∇- CMH, a gradient-based method that modifies the network’s structure within the feasible bounds for an individual target node, effectively concealing its membership. Experimental results across multiple datasets and community detection algorithms show that our approach surpasses existing baselines, offering a better balance between accuracy and computational efficiency. © 2025, CC BY.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Decoupling While Coupling: Towards More Accurate Stereo Image Sand Removal Beyond Certainty

Decoupling While Coupling: Towards More Accurate Stereo Imag...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Bingcai Liu, Hui Qian, Chuang Jia, Yi Wu, Wangyu Li, Zhishan School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool United Kingdom School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns. © 2025 IEEE.

关键词： Cross-view Inter-view Sand removal Stereo image Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Robust Residual Compensation control for Disturbance Suppression to Enhance Performance of Grid-Forming Inverter

引用

International Journal of Circuit Theory and Applications 2025年第0期

作者： Zhang, Shufeng Liu, Changan Shi, Yuntao School of Control and Computer Engineering North China Electric Power University Beijing China School of information North China University of Technology Beijing China School of Electrical and Control Engineering North China University of Technology Beijing China

Grid-forming (GFM) inverter has been proposed as a practical solution for improving the stability and resilience of modern power systems. However, the GFM inverter exhibits low inertia characteristic and is susceptible to external disturbance and uncertainty. Motivated by this, this paper presents a residual compensation control strategy to improve the performance of the GFM inverter. To address the impact of measurement noise with outliers on state estimation and residual generation, the Huber function is employed as a cost function in the design of a robust Kalman filter-based residual generator. Subsequently, a robust residual compensation controller is developed to achieve effective disturbance suppression. The generalized system model of the GFM inverter is established based on the model matching theory. Two algebraic Riccati equations corresponding to the full-information system and output feedback system are then formulated based on the generalized model to facilitate the solution of the robust residual compensation controller. Simulation and experiment results demonstrate that the robust Kalman filter-based residual generator and the robust residual compensation controller, as presented, effectively suppress measurement noise and load-side disturbance, thereby improving the performance of the GFM inverter. © 2025 John Wiley & Sons Ltd.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

FusionGCNN: An IoT-Based Novel Spatiotemporal Graph Convolutional Network for ECG Arrhythmia Detection

引用

IEEE Internet of Things Journal 2025年

作者： Iqbal, Saeed Zhong, Xiaopin Alhussein, Musaed Wu, Zongze Aurangzeb, Khursheed Liu, Weixiang Zhang, Yudong Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11543 Saudi Arabia Henan Polytechnic University School of Computer Science and Technology Henan Jiaozuo China

Electrocardiogram (ECG) arrhythmia identification is critical for early cardiovascular disease diagnosis and monitoring in Internet of Things (IoT) industry. Still, it is difficult due to complicated waveforms, individual variability, and the requirement for real-time analysis on resource-limited equipment. Traditional approaches sometimes fail to detect complicated spatial-temporal correlations in ECG data, limiting their efficiency in identifying arrhythmias. Furthermore, deploying these models in tinyML contexts, such as edge and IoT devices limited by large computational and memory needs, emphasizes the importance of lightweight, accurate models for real-time applications. Our suggested solution consists of three main components: SigNet, DualGCNN, and FusionGCNN. SigNet uses Separable Convolution layers to effectively extract local spatial features, making it ideal for IoT-based healthcare deployment. DualGCNN combines dual Graph Convolutional layers with spatial attention, allowing the model to capture local and global dependencies for better classification of arrhythmia. FusionGCNN combines the capabilities of GCN and SigNet with an effective feature fusion technique to improve feature representation while remaining computationally economical. Ablation tests show that FusionGCNN improves performance considerably, with greater accuracy (0.9641), lower training error (0.0004), and a higher F1 Score (0.9645) across a variety of ECG patterns. FusionGCNN, with its low training error, high stability, and computational economy, is well-suited to tinyML requirements, allowing implementation on edge and IoT devices for scalable, real-time ECG monitoring in healthcare. © 2014 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Immoral post detection using a one-dimensional convolutional neural network-based LSTM network

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Saqia, Bibi Khan, Khairullah Rahman, Atta Ur Khan, Aurangzeb Jain, Deepak Kumar Department of Computer Science University of Science and Technology Bannu28100 Pakistan Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China Symbiosis Institute of Technology Symbiosis International University Pune India

In text mining and Natural Language Processing (NLP), extracting emotions from textual data is gaining rapid attraction. The proliferation of online content and the freedom of expression on social media platforms has compelled the advancement of more sophisticated methods for the automatic identification of unwanted content. The One-Dimensional Convolutional Neural Network (1D-CNN) performs best for feature extraction, while the Long Short-Term Memory Network (LSTM) is well-known for extracting sequential features and classification of textual data. This study proposes a novel solution by combining 1D-CNN with LSTM. Utilizing a context-aware model, this study aims to enhance the detection of immoral posts, including hate speech and other forms of immoral content on social media platforms. Various posts are extracted from social media, which are then processed using Glove word embedding models. It depicts the word representations in the text, which yields the form of a real-valued vector determining the words' meaning. The 1D convolution utilizes a filter window over the input time-series data to extract features. Relying on the acquired parameters of the filters, they act as feature extractors. This feature extraction technique allows the model to distinguish detailed patterns and nuances from the textual contents of posts. The sequential processing capabilities of the LSTM network enable an in-depth examination of the text, capturing temporal relationships and context, which is critical for successful content categorization. To validate the proposed model, we utilized a benchmark dataset, called the Twitter dataset. The proposed model achieved the highest accuracy of 95.37% and outperforms state-of-the-art works. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

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：