检索结果-内蒙古大学图书馆

3DGCformer: 3-Dimensional Graph Convolutional transformer for multi-step origin–destination matrix forecasting

Applied Intelligence 2025年第6期55卷 1-18页

作者： Huang, Yiou Deng, Hao Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

Forecasting Human mobility is of great significance in the simulation and control of infectious diseases like COVID-19. To get a clear picture of potential future outbreaks, it is necessary to forecast multi-step Origin–Destination (OD) matrices for a relatively long period in the future. However, multi-step Origin–Destination Matrix Forecasting (ODMF) is a non-trivial problem. First, previous ODMF models only forecast the OD matrix for the next time-step, and they cannot perform well on long-term multi-step forecasts due to error accumulation. Second, many ODMF methods capture spatial and temporal dependencies with separate modules, which is insufficient to model spatio-temporal correlations in the time-varying OD matrix sequence. To address the challenges in multi-step ODMF, we propose 3-Dimensional Graph Convolutional Transformer (3DGCformer). As an enhancement of the original 3DGCN, we propose a novel Origin–Destination Feature Propagation (ODFP) rule between 3DGCN layers and integrate 2 3DGCNs with different spatio-temporal graphs and corresponding feature propagation rules to model the formation of OD flows in a more comprehensive way. For multi-step forecasts, 3DGCformer uses Transformer to capture long-term global temporal dependency, and adapt its decoder using labeled tokens to avoid error accumulation and improve time efficiency. To avoid information loss as the number of regions increases, we propose a patch embedding approach to convert data from 3DGCNs to the Transformer module. We perform extensive experiments on 4 real-world human mobility datasets, and the results show that our proposed model outperforms the state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Interpretable CNN-Based Lithographic Hotspot Detection Through Error Marker Learning

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 1031-1044页

作者： Sun, Haoyang Jiang, Cong Ye, Xun Feng, Dan Tan, Benjamin Ma, Yuzhe Liu, Kang Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Wuhan430074 China University of Calgary Department of Electrical and Software Engineering CalgaryABT2N 1N4 Canada With Microelectronics Thrust Guangzhou510530 China

As the technology node develops toward its physical limit, lithographic hotspot detection has become increasingly important and ever-challenging in the computer-aided design (CAD) flow. In recent years, convolutional neural networks (CNNs) have achieved great success in hotspot detection. However, the interpretability of their hotspot prediction has yet to be considered. Compared with conventional lithography simulation and pattern matching-based methods, the black-box nature of CNNs wavers their practical applications with confidence. In this article, we propose the first interpretable CNN-based hotspot detector capable of providing high-detection accuracy and reliable explanations for hotspot identification. Specifically, we augment the training dataset with expanded error markers obtained and preprocessed from lithography simulation, which are then learned by an encoder-decoder architecture as intermediate features. We additionally introduce coordinate attention in the encoder to facilitate better-feature extraction. By learning these error markers and part of their surrounding metals as root cause hotspot features, our architecture achieves the highest-hotspot accuracy of 99.78% and the lowest-false positive rate of 5.29% compared to all prior work. Moreover, our method demonstrates the best visual and quantitative interpretability results when applying CNN interpretation methods. © 2024 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

TangibleMoments: Embedding XR Memories onto Physical Objects

TangibleMoments: Embedding XR Memories onto Physical Objects

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Khan, Omar Ahmed, Zaid Nam, Hyeongil Kim, Kangsoo University of Calgary Department of Computer Science Canada Engineering University of Calgary Department of Electrical and Software Canada

ISBN: (纸本)9798331514846

The increasing prevalence of Extended Reality (XR) and head-mounted displays (HMDs), alongside rapid advancements in 3D reality capture technology, unlocks a new paradigm for capturing and reliving past memories/experiences through XR. Current methods for accessing and interacting with these "XR Memories"still lack the ability to fully leverage the range of capabilities afforded by XR and HMDs. We introduce TangibleMoments, a novel framework that enables users to embed XR memories onto physical objects, transforming those objects into "Moments"- tangible user interfaces for accessing and interacting with XR memories. We describe and illustrate five interaction methods as part of this framework: Creating Moments, Recalling Moments, Sharing Moments, Copying Moments, and Clearing Moments. We showcase an initial prototype and discuss possible extensions. © 2025 IEEE.

关键词： gaussian splatting Mixed reality spatial memory tangible user interfaces virtual reality

来源：评论

学校读者我要写书评

暂无评论

Investigating Visual Guide Cues in VR: Impacts of Virtual Humans and Symbol-Based Navigation on Real-World Performance and Experience

Investigating Visual Guide Cues in VR: Impacts of Virtual Hu...

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Khan, Omar Nguyen, Anh Nam, Hyeongil Kim, Kangsoo University of Calgary Department of Computer Science Canada University of Calgary Department of Electrical and Software Engineering Canada

ISBN: (纸本)9798331514846

Virtual experiences can significantly influence our perception and behavior in the real world, shaping how we interact with and navigate physical environments. In this paper, we examine the impact of learning navigation routes in an immersive virtual environment (IVE) on navigation performance and user experience in a corresponding real-world indoor setting. We developed a guide system with two distinct audiovisual representations: a human agent guide and a symbol-based guide. A preliminary user study (N = 10) was conducted to evaluate the system. While no significant differences were observed between the two guide conditions, the findings reveal valuable insights into user-perceived confidence and enjoyment during real-world navigation tasks. Contrary to our expectations, the symbol-based guide elicited slightly higher positive scores compared to the human agent guide. We discuss these findings and outline directions for future research. © 2025 IEEE.

关键词： confidence enjoyment navigation Real-Virtual influence task load virtual human visual cues

来源：评论

学校读者我要写书评

暂无评论

Attention-Driven Emotion Recognition in EEG: A Transformer-Based Approach With Cross-Dataset Fine-Tuning

引用

IEEE Access 2025年 13卷 69369-69394页

作者： Ghous, Ghulam Najam, Shaheryar Alshehri, Mohammed Alshahrani, Abdulmonem AlQahtani, Yahya Jalal, Ahmad Liu, Hui Riphah International University Department of Electrical and Computer Engineering Islamabad44000 Pakistan Bahria University Department of Electrical Engineering Islamabad44000 Pakistan King Khalid University Department of Computer Science Abha61421 Saudi Arabia King Khalid University Department of Informatics and Computer Systems Abha61421 Saudi Arabia Air University Faculty of Computer Science and AI Islamabad44000 Pakistan Korea University College of Informatics Department of Computer Science and Engineering Seoul02841 Korea Republic of University of Bremen Cognitive Systems Laboratory Bremen28359 Germany Guodian Nanjing Automation Company Ltd. Nanjing210032 China

Emotion recognition from EEG (electroencephalogram) signals is crucial in mental health diagnostics and human-computer interaction but is often hindered by high dimensionality, noise, and complex temporal dependencies in the data. This paper presents a novel approach that integrates transformer models, attention mechanisms, and transfer learning to enhance emotion recognition accuracy from EEG signals. The proposed methodology consists of two phases: Attention Enhanced Base Model Development (AE-BMD) and Cross-Dataset Fine Tuning Adaptation (CD-FTA). In the AE-BMD phase, the base model is developed and trained on the SEED-IV dataset (15 participants, 62 EEG channels), achieving an accuracy of 84%, with an average precision of 84.75%, recall of 84% and F1-score of 84%. This phase employs optimized feature extraction from key EEG frequency bands (Delta, Theta, Alpha, Beta, Gamma) using techniques such as MFCC, GFCC, power spectral density, and Hjorth parameters. A transformer encoder with integrated spectral and temporal attention mechanisms captures intricate patterns and long-range dependencies within the EEG signals. In the CD-FTA phase, the model undergoes fine-tuning on the SEED-V dataset (20 participants, 62 channels) leading to an improved accuracy of 90%, with an average precision of 90.6%, recall of 90.6%, and F1-score of 90.6%. The model’s generalization is further validated on the MPED dataset (23 participants, 62 channels, seven emotion classes), achieving 79%, with an average precision of 79.3%, recall of 79.3% and F1-score of 79.1% across diverse emotional states. This cross-dataset adaptation leverages transfer learning to enhance the model’s generalization across different emotional states and EEG datasets. Experimental results show that the proposed approach outperforms traditional methods, achieving superior accuracy and robustness in emotion recognition tasks. This work advances emotion recognition systems by addressing challenges in EEG signal proc

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Klotski v2: Improved DNN Model Orchestration Framework for Dataflow Architecture Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 1045-1058页

作者： Bai, Chen Wei, Xuechao Zhuo, Youwei Cai, Yi Zheng, Hongzhong Yu, Bei Xie, Yuan The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Hong Kong Alibaba DAMO Academy Computing Technology Laboratory Hangzhou311121 China Peking University School of Integrated Circuits Beijing100871 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong

Dataflow architecture accelerators are a new kind of scalable DNN accelerators. For an instruction, the availability of input operands solely determines the beginning of executions. DNN model orchestration determines how to partition, schedule, and map the computation to the underlying hardware. In this article, we propose the Klotski v2 framework to solve DNN model orchestration for dataflow architecture accelerators. First, a Bayesian optimization-based entropy-directed partition algorithm is proposed to transform a DNN model into μ ops. Second, a unified formal formulation for μ ops scheduling and mapping is presented. Third, a two-stage methodology is proposed to decouple the scheduling and mapping. Fourth, a Hilbert curve-based mapping heuristic is proposed to enhance problem-solving efficiency, improving the tradeoff between solution quality and algorithm runtime. Extensive results show that Klotski v2 can achieve an average of 21.57% higher execution performance improvement than the previous methodologies. With the Hilbert curve-based mapping heuristic, we improve the algorithm efficiency by an average of 63.50% across different DNN workloads. © 1982-2012 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Speed Harmonic based Saturation Free Inductance Modeling and Estimation of Interior PMSM Using Measurements Under One Load Condition

引用

CES Transactions on Electrical Machines and Systems 2025年第1期9卷 91-99页

作者： Guodong Feng Yuting Lu Zhe Tong Beichen Ding Guishan Yan Chunyan Lai the School of Intelligent Systems Engineering Sun Yat-sen UniversityShenzhenChina the School of Advanced Manufacturing Sun Yat-sen University the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) China the Department of Electrical and Computer Engineering Concordia UniversityQCCanada

For permanent magnet synchronous machines(PMSMs),accurate inductance is critical for control design and condition *** to magnetic saturation,existing methods require nonlinear saturation model and measurements from multiple load/current conditions,and the estimation is relying on the accuracy of saturation model and other machine parameters in the *** harmonic produced by harmonic currents is inductance-dependent,and thus this paper explores the use of magnitude and phase angle of the speed harmonic for accurate inductance *** estimation models are built based on either the magnitude or phase angle,and the inductances can be from d-axis voltage and the magnitude or phase angle,in which the filter influence in harmonic extraction is considered to ensure the estimation *** inductances can be estimated from the measurements under one load condition,which is free of saturation ***,the inductance estimation is robust to the change of other machine *** proposed approach can effectively improve estimation accuracy especially under the condition with low current *** and comparisons are conducted on a test PMSM to validate the proposed approach.

关键词： PMSM Inductance estimation Speed harmonic High frequency signal injection

来源：评论

学校读者我要写书评

暂无评论

Topology entropy: Enhancing graph partitioning for TAD identification and single-cell clustering

引用

Computational and Structural Biotechnology Journal 2025年 27卷 1864-1886页

作者： Liang, Qiushi Zhao, Shengjie Chen, Lingxi Li, Shuai Cheng School of Computer Science and Technology Tongji University Shanghai201804 China Department of Computer Science City University of Hong Kong 999077 Hong Kong Department of Biomedical Sciences City University of Hong Kong 999077 Hong Kong Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education China

Entropy quantifies the limits of information compression and provides a theoretical foundation for exploring complex structures in large-scale graphs. However, effective metrics are needed to capture the intricate structural details in biological graphs. In this paper, we introduce the topology entropy encoding tree to quantify the complexity of biological graphs and show that minimizing the associated entropy is equivalent to optimal graph partitioning. We develop two methods, TEC-O and TEC-U, for partitioning ordered and unordered biological graphs. TEC-O is applied to identify Topologically Associated Domains (TADs) in Hi-C contact maps, while TEC-U is used for cell clustering in single-cell sequencing data. Results from simulated datasets demonstrate that topology entropy is robust to noise and effectively captures structural information, outperforming existing methods. Experiments on Hi-C data from five cell lines and ten single-cell sequencing datasets show that TEC-O and TEC-U achieve the highest accuracy in TAD detection and cell clustering, respectively, providing biologically meaningful insights. © 2025 The Authors

关键词： Cell culture

来源：评论

学校读者我要写书评

暂无评论

A survey of artificial intelligence models for wireless capsule endoscopy videos for superior automatic diagnosis: problems and solutions

引用

Multimedia Tools and Applications 2025年 1-35页

作者： El-Gammal, Eman M. El-Shafai, Walid Taha, Taha E. El-Fishawy, Adel S. Abd El-Samie, Fathi E. Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Center of Advanced Software and Biomedical Clinical Engineering Consultations Faculty of Engineering Cairo University Giza Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University 84428 Riyadh11671 Saudi Arabia

Wireless Capsule Endoscopy (WCE) emerged as an innovative and patient-centric approach for non-invasive and painless examination of the gastrointestinal (GI) tract. It serves as a pivotal tool in helping medical practitioners in the early detection of anomalies within the intricate domain of the human GI tract. The automated identification of aberrations assumes paramount significance, contributing not only to temporal efficiency but also to timely diagnosis. Within the realm of academic literature, a plethora of Artificial Intelligence (AI) methodologies have been proposed to effectuate the automatic classification, segmentation, and synthesis of anomalies inherent in WCE images. This scholarly endeavor undertakes a comprehensive and meticulous survey, elucidating the spectrum of anomaly classification, summarization, and detection techniques harnessed for computer-Aided Diagnosis (CAD) in the context of WCE images. The survey begins by delineating the methodologies underpinning WCE image classification and video processing. Subsequently, an exhaustive evaluation of techniques for analyzing WCE images is furnished, accompanied by an in-depth exploration of pertinent surveys, in addition to a judicious assessment of their merits and demerits. Furthermore, this study undertakes a rigorous evaluation of prevailing datasets utilized to benchmark the efficacy of various WCE techniques. In summary, this survey serves as a vanguard, delineating promising avenues for future investigations in the realm of WCE image analysis models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Gupacker: Generalized Unpacking Framework for Android Malware

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4338-4352页

作者： Zheng, Tao Hou, Qiyu Chen, Xingshu Ren, Hao Li, Meng Li, Hongwei Shen, Changxiang Sichuan University School of Cyber Science and Engineering Chengdu610065 China Sichuan University School of Cyber Science and Engineering Cyber Science Research Institute Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province School of Computer Science and Information Engineering Hefei230002 China University of Padua Department of Mathematics HIT Center Padua35131 Italy University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Sichuan University Cyber Science Research Institute Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China

Android malware authors often use packers to evade analysis. Although many unpacking tools have been proposed, they face two significant challenges: 1) They are easily impeded by anti-analysis techniques employed by packers, preventing efficient collection of hidden Dex data. 2) They are typically designed to unpack a specific packer and cannot handle malware packed with mixed packers. Consequently, many packed malware samples evade detection. To bridge this gap, we propose Gupacker , a novel generalized unpacking framework. Gupacker offers a generic solution for first-generation holistic packer by customizing the Android system source code. It identifies the type of packer and selects an appropriate unpacking function, constructs a deeper active call chain to achieve generic unpacking of second-generation function extraction packers, and uses JNI function and instruction monitoring to handle third-generation virtual obfuscation packer. On this basis, we counteract a diverse array of anti-analysis techniques. We conduct extensive experiments on 5K packed Android malware samples, comparing Gupacker with 2 commercial and 4 state-of-the-art academic unpacking tools. The results demonstrate that Gupacker significantly improves the efficiency of Android malware unpacking with acceptable system overhead. We analyze real packed applications based on Gupacker and found several are second-packed by attackers, including WPS for Android, with tens of millions of users. We receive and responsibly report 13 0day vulnerabilities and also assist in the remediation of all vulnerabilities. © 2005-2012 IEEE.

关键词： Android malware

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：