检索结果-内蒙古大学图书馆

4th International Conference on Digital Society and intelligent Systems, DSInS 2024

作者： Wei, Xialong Zhou, Ya School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331528829

Knowledge tracing is fundamental to intelligent educational systems, as it predicts future learning outcomes by analyzing learners' historical performance related to specific knowledge concepts. While advancements have been made through deep learning techniques in the knowledge tracing domain, traditional research faces two significant limitations: insufficient consideration of temporal factors, which impacts the accurate depiction of knowledge retention and mastery dynamics;and the assumption of a one-to-one correspondence between practice and a single knowledge concept, disregarding the complexity of coexisting multiple knowledge concepts. To address these issues, this paper proposes the MulTKT model, which integrates response intervals, response durations, and the synergistic effects of multiple knowledge concepts, while incorporating a temporal decay factor into the self-attention mechanism to precisely capture learning dynamics. Experimental results indicate that MulTKT more accurately represents knowledge states and predicts student performance. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Perturbation Synergy Attack for Person Re-identification 38

Cross-Modality Perturbation Synergy Attack for Person Re-ide...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Gong, Yunpeng Zhong, Zhun Qu, Yansong Luo, Zhiming Ji, Rongrong Jiang, Min School of Informatics Xiamen University China School of Computer Science and Information Engineering Hefei University of Technology China The Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible CulturalHeritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Fujian Xiamen361005 China

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Student Classification with Forgetting Mechanisms on Memory Networks for Knowledge Tracing

Dynamic Student Classification with Forgetting Mechanisms on...

引用

intelligent Computing and Human-Computer Interaction (ICHCI), International Conference on

作者： Guimin Huang Xiangqian Qin Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Knowledge Tracing (KT), a technique for modeling students' knowledge levels and predicting their future question-answering performance based on their historical answer data, is one of the key research areas to strengthen the ability of personalized education. In recent years, memory networks have received more and more attention and application in the field of KT, however, the current KT model based on memory networks ignores the effect of students' learning sequence on the level of forgetting, and fails to model the forgetting behavior of students in the process of learning by using the characteristics of time intervals in the interaction data. Therefore, in this paper, we propose a dynamic student classification with forgetting mechanisms on memory networks model (DSCFMN), which enhance the existing model by dynamically classifying students similar to their learning abilities at specified time intervals, incorporating forgetting factors and introducing a weight decay strategy. Experiments show that our model performs well on online education datasets, and the proposed model achieves better prediction results than existing knowledge tracking methods.

关键词： Knowledge engineering Human computer interaction Computational modeling Education Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Adaptive Finite-Time Control for Switched Cyberphysical Systems With Uncertain Deception Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2023年 1卷 136-146页

作者： Wang, Xin Zhou, Yuhao Luo, Biao Jiang, Yuming Huang, Tingwen Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China School of Automation Central South University Changsha410083 China Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim7491 Norway T&M University at Qatar Doha23874 Qatar

This article is concerned with the event-triggered adaptive finite-time control problem for a class of switched cyber-physical systems (CPSs) subject to uncertain deception attacks. We deploy the finite time command filter to alleviate the possible explosion of complexity rendered by the virtual control signal’s duplicative differentiation. To stabilize the target system with a guaranteed disturbance rejection performance index, a disturbance observer is constructed by using fuzzy logic systems (FLS) with the hope of estimating the unknown external disturbance. Furthermore, the Nussbaum gain is utilized to resist the unknown control efficiency generated by uncertain deception attacks. Based on the common Lyapunov function (CLF) method, sufficient conditions are derived to ensure that all signals in the closed-loop system are uniformly bounded at a finite time. Finally, the simulation example shows the validity and efficacy of the developed control method. © 2023 Institute of Electrical and Electronics Engineers. All rights reserved.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification

Knowledge-Data Fusion Based Source-Free Semi-Supervised Doma...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ruimin Peng Jiayu An Dongrui Wu 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 Wuhan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Electroencephalogram (EEG)-based seizure sub-type classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset with no source data and limited labeled target data, can be used for privacy-preserving seizure subtype classification. This paper considers two challenges in SF-SSDA for EEG-based seizure subtype classification: 1) How to effectively fuse both raw EEG data and expert knowledge in classifier design? 2) How to align the source and target domain distributions for SF-SSDA? We propose a Knowledge-Data Fusion based SF-SSDA approach, KDF-MutuaISHOT, for EEG-based seizure subtype classification. In source model training, KDF uses Jensen-Shannon Diver-gence to facilitate mutual learning between a feature-driven Decision Tree-based model and a data-driven Transformer-based model. To adapt KDF to a new target dataset, an SF-SSDA algorithm, MutualSHOT, is developed, which features a consistency-based pseudo-label selection strategy. Experiments on the public TUSZ and CHSZ datasets demonstrated that KDF-MutualSHOT outperformed other supervised and source-free domain adaptation approaches in cross-subject seizure subtype classification.

关键词： Training Adaptation models Data privacy Fuses Brain modeling Transformers Data models Electroencephalography Decision trees Cybernetics

来源：评论

学校读者我要写书评

暂无评论

BeatKAN: An Efficient and Drum-Attuned Beat Tracking Method Using Kolmogorov-Arnold Networks

BeatKAN: An Efficient and Drum-Attuned Beat Tracking Method ...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhicheng Zhang Ganghui Ru Wei Li School of Computer Science and Technology Fudan University Shanghai China School of Computer Science and Technology Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we propose an efficient and drum-attuned beat tracking method based on Kolmogorov-Arnold networks (KAN). Traditional MLP-based frameworks struggle with complex musical signals due to limited capacity in modeling intricate patterns. Inspired by KAN’s efficient ability to capture complex time-frequency relationships, we leverage it to enhance our model by employing learnable nonlinear activation functions on convolutional kernels. Additionally, we utilize music source separation techniques to extract drum tracks from the original audio, thereby expanding the existing beat datasets and simulating the human perception of beats through drum sounds. Experimental results demonstrate that our approach significantly reduces the parameter count while maintaining high accuracy in beat tracking.

关键词： Time-frequency analysis Accuracy Source separation Convolution Information retrieval Acoustics Kernel Speech processing

来源：评论

学校读者我要写书评

暂无评论

Dual-Domain CLIP-Assisted Residual Optimization Perception Model for Metal Artifact Reduction

arXiv

引用

arXiv 2024年

作者： Zhang, Xinrui Cai, Ailong Wang, Shaoyu Wang, Linyuan Zheng, Zhizhong Li, Lei Yan, Bin The Henan Key Laboratory of Imaging and Intelligent Processing Information Engineering University Zhengzhou450001 China The Key Laboratory of Optoelectronic Technology and Systems Ministry of Education Chongqing University Chongqing400044 China

Metal artifacts in computed tomography (CT) imaging pose significant challenges to accurate clinical diagnosis. The presence of high-density metallic implants results in artifacts that deteriorate image quality, manifesting in the forms of streaking, blurring, or beam hardening effects, etc. Nowadays, various deep learning-based approaches, particularly generative models, have been proposed for metal artifact reduction (MAR). However, these methods have limited perception ability in the diverse morphologies of different metal implants with artifacts, which may generate spurious anatomical structures and exhibit inferior generalization capability. To address the issues, we leverage visual-language model (VLM) to identify these morphological features and introduce them into a dual-domain CLIP-assisted residual optimization perception model (DuDoCROP) for MAR. Specifically, a dual-domain CLIP (DuDoCLIP) is fine-tuned on the image domain and sinogram domain using contrastive learning to extract semantic descriptions from anatomical structures and metal artifacts. Subsequently, a diffusion model is guided by the embeddings of DuDoCLIP, thereby enabling the dual-domain prior generation. Additionally, we design prompt engineering for more precise image-text descriptions that can enhance the model’s perception capability. Then, a downstream task is devised for the one-step residual optimization and integration of dual-domain priors, while incorporating raw data fidelity. Ultimately, a new perceptual indicator is proposed to validate the model’s perception and generation performance. With the assistance of DuDoCLIP, our DuDoCROP exhibits at least 63.7% higher generalization capability compared to the baseline model. Numerical experiments demonstrate that the proposed method can generate more realistic image structures and outperform other SOTA approaches both qualitatively and quantitatively. Copyright © 2024, The Authors. All rights reserved.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Electrospinning of nanofibres

NATURE REVIEWS METHODS PRIMERS

引用

NATURE REVIEWS METHODS PRIMERS 2024年第1期4卷 1页

作者： [Anonymous] Key Laboratory of Textile Science & Technology Ministry of Education College of Textiles Donghua University Shanghai China Center for Nanotechnology & Sustainability Department of Mechanical Engineering College of Design and Engineering National University of Singapore Singapore Singapore School of Engineering Institute for Materials and Processes The University of Edinburgh Edinburgh UK Center for Advanced Intelligent Materials Universiti Malaysia Pahang Al-Sultan Abdullah Kuantan Malaysia Faculty of Industrial Sciences and Technology Universiti Malaysia Pahang Al-Sultan Abdullah Kuantan Malaysia

This PrimeView highlights applications of electrospun nanofibres

关键词：

来源：评论

学校读者我要写书评

暂无评论

Building Semantic Segmentation Through an Ensemble Architecture of UNet and Graph Convolution Networks 22

Building Semantic Segmentation Through an Ensemble Architect...

引用

Proceedings of the 2022 6th International Conference on Electronic Information technology and Computer Engineering

作者： Yuxin Shang Hao Cuib Haitao Guo Shandong Institute of Commerce and Technology China Shandong Institute of Petroleum and Chemical Technology Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9781450397148

Extracting building from remote sensing images remains a challenge because some obstacles, such as trees, cars, farmland, and shadows, disturb the identification accuracy. In recnet years, deep convolution neural networks have shown significant improvements in computer vision, however it is still difficult to extract irregular and small buildings. To develop the extraction accuracy of building, we propose a deep learning model, which combined UNet and graph convolution network, to capture the long-range information. Seven deep convolution neural networks were used on the Massachusetts Buildings Dataset for comparison. And the proposed model, which performed best among these compared models, achieved a building Intersection over Union (IOU) of 71.10%, mean IOU of 81.88%, recall of 81.90%, precision 84.36% and F1 score of 83.11%. This result indicated that the proposed model can accurately extract building objects. The visualization results showed that the proposed model performs better in extracting irregular and small buildings and caneffectively extracts buildings from high-resolution remote-sensing images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

intelligent Test Paper Generation Algorithm Integrating Normal Distribution and Parallel Genetic Algorithm

Intelligent Test Paper Generation Algorithm Integrating Norm...

引用

intelligent Computing and Human-Computer Interaction (ICHCI), International Conference on

作者： Chuangye Liu Guimin Huang Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Genetic algorithms have been widely used in intelligent test paper generation systems. However, traditional genetic algorithms cannot ensure that the difficulty of test questions is normally distributed, and are prone to falling into local optimal solutions. To address the above problems, we proposed an intelligent test paper generation algorithm that combines normal distribution and parallel genetic algorithms. In the population initialization stage, we use the cumulative distribution function (CDF) of the normal distribution to initialize the population. In the subsequent genetic operations, we designed a directed mutation mechanism and added KL divergence as a penalty number in the design of the fitness function to ensure that the difficulty of the test questions is normally distributed. At the same time, in order to speed up the efficiency of the algorithm and escape from the local optimal solution, an adaptive migration strategy was introduced. Experimental results show that the difficulty of the test questions generated by this algorithm is normally distributed, and the algorithm performance is better than other algorithms.

关键词： Human computer interaction Heuristic algorithms Gaussian distribution Genetics Genetic algorithms Distribution functions Convergence

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：