检索结果-内蒙古大学图书馆

5th International Conference on Emerging Systems and Intelligent computing, ESIC 2025

作者： Thanalakshmi, S. Geethamahalakshmi, G. Azath, H. Prabu, K. Kumanan, T. Srinivasan, C. Gojan School of Business and Technology Department of Management Studies Redhills Tamil Nadu Chennai India Easwari Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology School of Computing Tamil Nadu Chennai India Gojan School of Business and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Dr Mgr Educational and Research Institute Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331522100

Eye strain and its effects on general health have become more pressing issues due to the pervasive nature of digital devices in modern life. This work offers a new approach by combining the Internet of Things (IoT) with Naive Bayes classification for smart eyewear that reduces eye strain. The proposed system aims to reduce digital eye strain by adapting the lens's characteristics in real-time to user behavior and ambient factors. Using the IoT architecture, data like screen time, distance from the device, and ambient lighting conditions may be captured in real-time when users interact with digital displays. Using Naive Bayes classification, this data is processed to identify probable causes of eye strain and suggest suitable eyewear changes to reduce pain. The proposed system provides a preventative method of fostering digital well-being using software and hardware components, such as sensors, microcontrollers, and machine learning algorithms. These smart glasses provide hope for a future free of the negative impacts of digital device use on eye health by making personal recommendations based on each user's unique requirements. © 2025 IEEE.

关键词： Ambient Sensing Eye Health Personalized Recommendations Smart Glasses User Interaction Analysis Wearable Technology

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

SELF-Clustering Graph Transformer Approach to Model Resting State Functional Brain Activity

SELF-Clustering Graph Transformer Approach to Model Resting ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Bishal Thapaliya Esra Akbas Ram Sapkota Bhaskar Ray Vince Calhoun Jingyu Liu Department of Computer Science Georgia State University Atlanta USA Tri-Institutional Center for Translational Research in Neuroimaging and Data Science School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Resting-state functional magnetic resonance imaging (rs-fMRI) offers valuable insights into the human brain's functional organization and is a powerful tool for investigating the relationship between brain function and cognitive processes as it allows for the functional organization of the brain to be captured without relying on a specific task or stimuli. In this study, we introduce a novel attention mechanism for graphs with subnetworks, named Self Clustering Graph Transformer (SCGT), designed to handle the issue of uniform node updates in graph transformers. By using static functional connectivity (FC) correlation features as input to the transformer model, SCGT effectively captures the sub-network structure of the brain by performing cluster-specific updates to the nodes unlike uniform node updates like vanilla graph transformers, further allowing us to learn and interpret the sub clusters. We validate our approach on the Adolescent Brain Cognitive Development (ABCD) dataset, comprising 7,957 participants, for the prediction of total cognitive score and gender classification. Our results demonstrate that SCGT outperforms the vanilla graph transformer method, and other recent models, offering a promising tool for modeling brain functional connectivity and interpreting the underlying subnetwork structures.

关键词： Biometrics Correlation Cognitive processes Biological system modeling Organizations Predictive models Functional magnetic resonance imaging Transformers Brain modeling Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars

arXiv

引用

arXiv 2025年

作者： Hua, Yuncheng Qu, Lizhen Li, Zhuang Xue, Hao Salim, Flora D. Haffari, Gholamreza Department of Data Science & AI Monash University Australia School of Computer Science Engineering University of New South Wales Australia School of Computing Technologies Royal Melbourne Institute of Technology Australia

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting aspects of LLM alignment—factuality and safety. We packaged the restyled examples as prompts to trigger few-shot learning, improving LLM alignment. Compared to the best baseline approach, with an average score of 5.00 as the maximum, our method achieves a maximum 0.10 increase on the Alpaca-eval task (from 4.50 → 4.60), a 0.22 enhancement on the just-eval-instruct benchmark (from 4.34 → 4.56), and a maximum improvement of 0.32 (from 3.53 → 3.85) on the MT-Bench dataset. We release the code and data at https://***/AnonymousCode-computerscience/RIDE. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Contemporary Survey on Semantic Communications: Theory of Mind, Generative AI, and Deep Joint Source-Channel Coding

arXiv

引用

arXiv 2025年

作者： Nguyen, Loc X. Raha, Avi Deb Aung, Pyae Sone Niyato, Dusit Han, Zhu Hong, Choong Seon Department of Computer Science and Engineering Kyung Hee University Gyeonggi-do Yongin-si17104 Korea Republic of College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of Houston HoustonTX77004 United States Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of

Semantic Communication is becoming the next pillar in wireless communication technology due to its various capabilities. However, it still encounters various challenging obstacles that need to be solved before real-world deployment. The major challenge is the lack of standardization across different directions, leading to variations in interpretations and objectives. In the survey, we provide detailed explanations of three leading directions in semantic communications, namely Theory of Mind, Generative AI, Deep Joint Source-Channel Coding. These directions have been widely studied, developed, and verified by institutes worldwide, and their effectiveness has increased along with the advancement in technology. We first introduce the concepts and background of these directions. Firstly, we introduce the Theory of Mind, where the communication agents interact with each other, gaining understanding from observations and slowly forming a common language. Secondly, we present generative AI models, which can create new content and offer more freedom to interpret the data beyond the limitation of semantic meaning compression of raw data before transmitting it. The received signal is then decoded by another generative AI model to execute the oriented task. Thirdly, we review deep learning models to jointly optimize the source and channel coding modules. Then, we present a comprehensive survey of existing works in each direction, thereby offering readers an overview of past achievements and potential avenues for further contribution. Moreover, for each direction, we identify and discuss the existing challenges that must be addressed before these approaches can be effectively deployed in real-world scenarios. These challenges encompass a range of technical, computational, and practical issues. For instance, scalability and adaptability remain critical barriers in real-world deployment, particularly in dynamic environments with diverse user demands. Additionally, the possibility

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

Empirical Privacy Variance

arXiv

引用

arXiv 2025年

作者： Hu, Yuzheng Wu, Fan Xian, Ruicheng Liu, Yuhang Zakynthinou, Lydia Kamath, Pritish Zhang, Chiyuan Forsyth, David Siebel School of Computing and Data Science University of Illinois Urbana-Champaign United States Institute of Automation Chinese Academy of Sciences China Department of Electrical Engineering and Computer Science University of California Berkeley United States Google Research United States

We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrated to the same (Ε, δ)-DP guarantee using DP-SGD with different hyperparameter configurations can exhibit significant variations in empirical privacy, which we quantify through the lens of memorization. We investigate the generality of this phenomenon across multiple dimensions and discuss why it is surprising and relevant. Through regression analysis, we examine how individual and composite hyperparameters influence empirical privacy. The results reveal a no-free-lunch trade-off: existing practices of hyperparameter tuning in DP-SGD, which focus on optimizing utility under a fixed privacy budget, often come at the expense of empirical privacy. To address this, we propose refined heuristics for hyperparameter selection that explicitly account for empirical privacy, showing that they are both precise and practically useful. Finally, we take preliminary steps to understand empirical privacy variance. We propose two hypotheses, identify limitations in existing techniques like privacy auditing, and outline open questions for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Autonomous Microscopy for Scalable and Intelligent Characterization of 2D Materials

arXiv

引用

arXiv 2025年

作者： Yang, Jingyun Yin, Ruoyan Avery Jiang, Chi Hu, Yuepeng Zhu, Xiaokai Hu, Xingjian Kumar, Sutharsika Wang, Xiao Zhai, Xiaohua Rong, Keran Zhu, Yunyue Zhang, Tianyi Yin, Zongyou Kong, Jing Gong, Neil Zhenqiang Ren, Zhichu Wang, Haozhe Department of Electrical and Computer Engineering Duke University United States School of Computing National University of Singapore Singapore Google Deepmind United Kingdom Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States School of Chemistry Australian National University Australia Department of Materials Science and Engineering Massachusetts Institute of Technology United States

Characterization of atomic-scale materials traditionally requires human experts with months to years of specialized training. Even for trained human operators, accurate and reliable characterization remains challenging when examining newly discovered materials such as two-dimensional (2D) structures. This bottleneck drives demand for fully autonomous experimentation systems capable of comprehending research objectives without requiring large training datasets. In this work, we present ATOMIC (Autonomous Technology for Optical Microscopy & Intelligent Characterization), an end-to-end framework that integrates foundation models to enable fully autonomous, zero-shot characterization of 2D materials. Our system integrates the vision foundation model (i.e., Segment Anything Model), large language models (i.e., ChatGPT), unsupervised clustering, and topological analysis to automate microscope control, sample scanning, image segmentation, and intelligent analysis through prompt engineering, eliminating the need for additional training. When analyzing typical MoS2 samples, our approach achieves 99.7% segmentation accuracy for single layer identification, which is equivalent to that of human experts. In addition, the integrated model is able to detect grain boundary slits that are challenging to identify with human eyes. Furthermore, the system retains robust accuracy despite variable conditions including defocus, color temperature fluctuations, and exposure variations. It is applicable to a broad spectrum of common 2D materials—including graphene, MoS2, WSe2, SnSe—regardless of whether they were fabricated via top-down or bottom-up methods. This work represents the implementation of foundation models to achieve autonomous analysis, establishing a scalable and data-efficient characterization paradigm that fundamentally transforms the approach to nanoscale materials research. © 2025, CC BY.

关键词： Layered semiconductors

来源：评论

学校读者我要写书评

暂无评论

SWIPTNet: a Unified Deep Learning Framework for SWIPT Based on GNN and Transfer Learning

引用

IEEE Transactions on Mobile computing 2025年

作者： Han, Hong Lu, Yang Song, Zihan Zhang, Ruichen Chen, Wei Ai, Bo Niyato, Dusit Kim, Dong In Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Beijing Jiaotong University School of Electronics and Information Engineering Beijing100044 China Sungkyunkwan University Department of Electrical and Computer Engineering Suwon16419 Korea Republic of

This paper investigates the deep learning based approaches for simultaneous wireless information and power transfer (SWIPT). The quality-of-service (QoS) constrained sumrate maximization problems are, respectively, formulated for power-splitting (PS) receivers and time-switching (TS) receivers and solved by a unified graph neural network (GNN) based model termed SWIPT net (SWIPTNet). To improve the performance of SWIPTNet, we first propose a single-type output method to reduce the learning complexity and facilitate the satisfaction of QoS constraints, and then, utilize the Laplace transform to enhance input features with the structural information. Besides, we adopt the multi-head attention and layer connection to enhance feature extracting. Furthermore, we present the implementation of transfer learning to the SWIPTNet between PS and TS receivers. Ablation studies show the effectiveness of key components in the SWIPTNet. Numerical results also demonstrate the capability of SWIPTNet in achieving nearoptimal performance with millisecond-level inference speed which is much faster than the traditional optimization algorithms. We also show the effectiveness of transfer learning via fast convergence and expressive capability improvement. © 2002-2012 IEEE.

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures

arXiv

引用

arXiv 2025年

作者： Yin, Ming Wang, Mengdi Wang, Yu-Xiang The Department of Electrical and Computer Engineering Princeton University United States The Halıcıoğlu Data Science Institute UC San Diego United States

This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline RL is the appropriate model for almost any real-life ML problems, even if they have nothing to do with the recent AI breakthroughs that use RL. Then we will zoom into two fundamental problems of offline RL: offline policy evaluation (OPE) and offline policy learning (OPL). It may be surprising to people that tight bounds for these problems were not known even for tabular and linear cases until recently. We delineate the differences between worst-case minimax bounds and instance-dependent bounds. We also cover key algorithmic ideas and proof techniques behind near-optimal instance-dependent methods in OPE and OPL. Finally, we discuss the limitations of offline RL and review a burgeoning problem of low-adaptive exploration which addresses these limitations by providing a sweet middle ground between offline and online RL. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design of Nonlinear Delay Differential System for Analyzing Vulnerabilities in Nanoscale Hardware Implants: A Deep Dive into Intelligent computing Networks

引用

Nano 2025年第3期20卷

作者： Asif Raja, Muhammad Junaid Ali Masood, Zaheer Hussain, Ijaz Zameer, Aneela Mehmood, Ammara Raja, Muhammad Asif Zahoor Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Electrical Engineering Capital University of Science and Technology Islamabad Pakistan Department of Computer and Information Sciences Pakistan Institute of Engineering & Applied Sciences Islamabad Pakistan School of Electrical and Data Engineering University of Technology Sydney Australia Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan

In the annals of contemporary innovation, the study of miniature marvels nanoscale hardware implants emerged as a pivotal instrument, scarcely perceptible to the naked eye, embodies a prowess of cutting-edge technologies and clandestine intrigue. The objective of this research is to introduce a time delay nonlinear system for nanoscale hardware implants vulnerabilities that portray the exploitation of a system by utilizing the stupendous knacks of advanced deep bidirectional long short-term memory (LSTM) networks for time series predictions. Firmware-level bugs present the potential for escalating privileges and executing of code remotely beneath the operating system, allowing for infiltration or complete intervention within a computer system. The designed deep bidirectional LSTM is configured to precisely predict and forecast the dynamic states of time delay differential system, offering a robust framework for mimicking delays that commonly manifest in the real cyber-physical systems. To orchestrate the system compromises in real scenarios through the activation of bugged hardware, time delay factors τ1 and τ2 are introduced to account the time delays necessary for exploiting the bugged and patched nodes, respectively. Synthetic data is generated to train the LSTM network for all scenarios of the model for the dynamics of bugged, compromised, patched nodes and these acquired information is used for training, testing and validation purposes regarding exploitation of the bugged hardware. Comparative analysis on exhaustive simulations revealed a minimal difference between the LSTM's predictions and those from the numerical outcomes with MSE in the range of 10-7, underscoring the network's effectiveness, robustness and stability in modeling complex system dynamics of hardware vulnerabilities. © 2025 World Scientific Publishing Company.

关键词： Firmware

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：