检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Wentai He, Ligang Long, Saiqin Abdelmoniem, Ahmed M. Wu, Yingliang Mao, Rui Department of Computer Science College of Information Science Technology Jinan University Guangzhou510632 China Department of Computer Science University of Warwick CoventryCV4 7AL United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom Department of Electronic Business The Institute of Digital Business & Intelligent Logistics South China University of Technology Guangzhou510006 China College of Computer Science and Software Engineering The Shenzhen Institute of Computing Sciences Shenzhen University Shenzhen518060 China

Data, as an observable form of knowledge, has become one of the most important factors of production for the development of Artificial Intelligence (AI). Meanwhile, increasing legislation and regulations on private and proprietary information results in scattered data sources also known as the "data islands". Although some collaborative learning paradigms such as Federated Learning (FL) can enable privacy-preserving training over decentralized data, they have inherent deficiencies in fairness, costs and reproducibility because of being learning-centric, which greatly limits the way how participants cooperate with each other. In light of this, we present a knowledge-centric paradigm termed Knowledge Augmentation in Federation (KAF), with focus on how to enhance local knowledge through collaborative effort. We provide the suggested system architecture, formulate the prototypical optimization objective, and review emerging studies that employ methodologies suitable for KAF. On our roadmap, with a three-way categorization we describe the methods for knowledge expansion, knowledge filtering, and label and feature space correction in the federation. Further, we highlight several challenges and open questions that deserve more attention from the community. With our investigation, we intend to offer new insights for what collaborative learning can bring back to decentralized data. © 2025, CC BY-NC-SA.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Learning Communities from Equilibria of Nonlinear Opinion Dynamics

Learning Communities from Equilibria of Nonlinear Opinion Dy...

引用

IEEE Conference on Decision and Control

作者： Yu Xing Anastasia Bizyaeva Karl H. Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and with Digital Futures Stockholm Sweden Sibley School of Mechanical and Aerospace Engineering Cornell University Ithaca NY USA

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper studies community detection for a nonlinear opinion dynamics model from its equilibria. It is assumed that the underlying network is generated from a stochastic block model with two communities, where agents are assigned with community labels and edges are added independently based on these labels. Agents update their opinions following a nonlinear rule that incorporates saturation effects on interactions. It is shown that clustering based on a single equilibrium can detect most community labels (i.e., achieving almost exact recovery), if the two communities differ in size and link probabilities. When the two communities are identical in size and link probabilities, and the intercommunity connections are denser than intra-community ones, the algorithm can achieve almost exact recovery under negative influence weights but fails under positive influence weights. Utilizing fixed point equations and spectral methods, we also propose a detection algorithm based on multiple equilibria, which can detect communities with positive influence weights. Numerical experiments demonstrate the performance of the proposed algorithms.

关键词： Accuracy Heuristic algorithms Image edge detection Stochastic processes Clustering algorithms Mathematical models Numerical models Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A Study of Noise Reduction Algorithm Using Statistical Optimization in Digital Holographic Microscopy

A Study of Noise Reduction Algorithm Using Statistical Optim...

引用

International Joint Conference on computer science and software engineering (JCSSE)

作者： Jongpil Jeong Hyun–Woo Kim Myungjin Cho Min–Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Fukuoka Japan School of ICT Robotics and Mechanical Engineering IITC. Hankyong National University Anseong Kyonggi-do Republic of Korea

ISBN: (数字)9798350381764

ISBN: (纸本)9798350381771

Recently, due to the coronavirus era, we have a heightened need for fast and accurate diagnostics. To meet these requirements, there are many methods such as polymerase chain reaction, but they also require about from a few hours to a day. In contrast, a three-dimensional model of cells can be observed by simply extracting cells and photographing them with digital holographic microscopy, and in the case of diseases that can be classified b y t he shape of cells, diagnosis i s possible in a few minutes. However, there are precise focal issues and noise in the high-frequency domain, respectively. Therefore, to resolve these issues, we propose an optimization method by modifying the threshold value of the high variance pixel averaging method in digital holographic microscopy.

关键词： Gamma distribution Visualization Three-dimensional displays Shape Microscopy Noise Noise reduction

来源：评论

学校读者我要写书评

暂无评论

Visual Cryptographic Permuted Sampling based Binary Image Watermarking

Visual Cryptographic Permuted Sampling based Binary Image Wa...

引用

International Conference on Circuits, Communication, Control and Computing

作者： Ayesha Shaik A Balasundaram M Nivedita School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai India Center for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai India

This paper proposes a visual cryptography per-muted scrambling (VCPS) based watermarking method for binary images. Binary image (BI), which has only black and white pixels, has a nature of compact storage. Due to the rapid growth of digital technology, a lot of personal information such as health records, hand-written signatures and certificates; book collections and design drawings; cartoon art sketches are stored as digital documents as BIs (white and black pixels) by scanning them. These BIs are communicated through the Internet either for the personal or professional case. Here lies a threat of unauthorized usage of these documents and it is essential to protect them by embedding the watermark (owner information of the binary image). The particularity of the BI makes it more challenging for data hiding because the hiding process is different and only few works are available in this domain. In this paper, the data hiding process is carried out using the coding tables and the encrypted binary watermark shares which is flipped and shuffled using visual cryptography. The proposed technique achieves higher visual quality and less computational cost than the state of the art related techniques.

关键词： Visualization Art Watermarking Encoding Internet Computational efficiency Cryptography

来源：评论

学校读者我要写书评

暂无评论

Impact of Image Sensor Input Faults on Pruned Neural Networks for Object Detection

Impact of Image Sensor Input Faults on Pruned Neural Network...

引用

IEEE International Symposium on Defect and Fault Tolerance in VLSI systems

作者： Yizhi Chen Wenyao Zhu Dejiu Chen Omar Mohammed Parthib Khound Zhonghai Lu School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden School of Industrial Engineering and Management KTH Royal Institute of Technology Stockholm Sweden Chair of Reliability of Technical Systems and Electrical Measurement University of Siegen Siegen Germany

ISBN: (数字)9798350366884

ISBN: (纸本)9798350366891

Object detection is one of the most fundamental problems in computer vision, and image sensors are commonly used for this. In this paper, we present the impact of image sensor faults on pruned neural networks for object detection. We compare the error sensitivities of networks after network slimming, networks after magnitude-based pruning, and native compact models. We also explore different spatial fault types with three intensities. Furthermore, we have developed a temporal error model based on realistic aging image sensor faults. The results illuminate that the performance on clean images is important as the mean Average Precision (mAP) experiences a decrease with an increase in injected faults. Additionally, we demonstrate that the size of the model does not invariably yield a decisive impact on error tolerance when comparing small models such as pruned models and native compact models.

关键词： Image sensors Performance evaluation Fault tolerance Sensitivity Neural networks Fault tolerant systems Object detection Aging Very large scale integration Transformers

来源：评论

学校读者我要写书评

暂无评论

Dual-Scale Enhanced and Cross-Generative Consistency Learning for Semi-Supervised Medical Image Segmentation

SSRN

引用

SSRN 2024年

作者： Gu, Yunqi Zhou, Tao Zhang, Yizhe Zhou, Yi He, Kelei Gong, Chen Zhu, Huafu PCA Lab The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Information Science and Technology Nanjing210094 China School of Computer Science and Engineering Southeast University Nanjing211189 China Medical School Nanjing University National Institute of Healthcare Data Science Nanjing210023 China Institute of High Performance Computing A*STAR Singapore

Medical image segmentation plays a crucial role in computer-aided diagnosis. However, existing methods heavily rely on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations. Moreover, accurately segmenting lesions poses challenges due to variations in shape, size, and location. To address these issues, we propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image Segmentation (DEC-Seg). First, we propose a Cross-level Feature Aggregation (CFA) module that integrates cross-level adjacent layers to enhance the feature representation ability across different resolutions. To address scale variation, we present a scale-enhanced consistency constraint, which ensures consistency in the segmentation maps generated from the same input image at different scales. This constraint helps handle variations in lesion sizes and improves the robustness of the model. Furthermore, we propose a cross-generative consistency scheme, in which the original and perturbed images can be reconstructed using cross-segmentation maps. This consistency constraint allows us to mine effective feature representations and boost the segmentation performance. To produce more accurate segmentation maps, we propose a Dual-scale Complementary Fusion (DCF) module that integrates features from two scale-specific decoders operating at different scales. Extensive experimental results on polyp segmentation from colonoscopy images, skin lesion segmentation from dermoscopic images, and Brain glioma segmentation from MRI images demonstrate the effectiveness of our DEC-Seg against other state-of-the-art semi-supervised segmentation approaches. © 2024, The Authors. All rights reserved.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

FOODwell

FOODwell

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing systems, CHI EA 2023

作者： Hsieh, An-Ting Hsiao, Chih-Ching Tsai, Hsin-Hua Chen, Hung-Hsuan Liu, Jui-Chun Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Institute of Communication Studies National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Applied Arts National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Information Management National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Computer Science and Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9781450394222

Hunger is an often neglected issue, with millions of people worldwide affected by it in 2021 according to the United Nations. This issue also affects minority populations in Taiwan. One solution to this problem is the implementation of suspended meals, which are free meals provided to those in need. Our proposed solution, FOODwell, aims to allow recipients to dwell on better food provision and obtain wellness for their food needs. It is a system that simplifies the process of reserving and collecting suspended meals for recipients by enabling them to interact with the kiosk at the convenience store and cashier at the restaurant, without compromising confidentiality or requiring electronic devices. Overall, FOODwell eliminates obstacles for recipients when reserving and collecting suspended meals. © 2023 Owner/Author.

关键词： interaction design kiosks suspended meals user research zero hunger

来源：评论

学校读者我要写书评

暂无评论

Intent Classification of Nepali Factoid Questions

Intent Classification of Nepali Factoid Questions

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Sushil Timilsina Ashim Khadka Jianchu Lin Faculty of Science and Technology Gandaki College of Engineering and Science Pokhara Nepal Faculty of Science and Technology Nepal College of Information Technology Lalitpur Nepal Faculty of Computer and Software Engineer Huaiyin Institute of Technology Jiangsu China

Question Classification plays a vital role in identifying the accurate answer to any question, and is considered as a core component of Question Answering systems. In Nepali Natural Language Processing, the area of Question Answering has not even been initiated due to a lack of dataset. The dataset of Nepali factual questions has been created by collecting questions from general knowledge books and labelling them with developed taxonomy. The problem of Nepali factoid question classification has been studied with a Support Vector Machine, which works as a baseline classification algorithm and obtained a 0.74 weighted F1-score in the imbalance dataset. The experimental results of the proposed model show the effectiveness of the approach in classifying factoid questions accurately compared with the state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Stock Price Prediction: A Comparative Study of LSTM, RNN, and GRU Models

Deep Learning Approaches for Stock Price Prediction: A Compa...

引用

International Multidisciplinary Conference on computer and Energy science (SpliTech)

作者： Suresh Chavhan Praveen Raj Prayas Raj Ashit Kumar Dutta Joel J.P. C. Rodrigues Department of Computer Science and Engineering Indian Institute of Information and Technology Raichur Karnataka India Department of Computer Science and Information Systems College of Applied Sciences AlMaarefa University Ad Diriyah Riyadh Kingdom of Saudi Arabia Amazonas State University Manaus AM Brazil

ISBN: (数字)9789532901351

ISBN: (纸本)9798350390797

Stock price prediction has been a longstanding challenge in financial markets, and recent advances in deep learning techniques have spurred increased interest in developing accurate and reliable models for forecasting. The comparative study is conducted using historical stock price data from diverse financial markets and periods. The dataset is preprocessed to address issues such as non-linearity, volatility, and noise. Subsequently, the LSTM, RNN, and GRU models are implemented and fine-tuned to optimize their performance in predicting stock prices. Performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) are employed to evaluate and compare the predictive accuracy of each model. Additionally, the study investigates the models' abilities to capture long-term dependencies and adapt to changing market conditions. The results of the comparative analysis provide insights into the relative strengths and weaknesses of LSTM, RNN, and GRU models for stock price prediction. The findings contribute to the ongoing discourse on the applicability of deep learning techniques in financial forecasting and offer practical recommendations for researchers and practitioners seeking to enhance the precision of stock price predictions. In conclusion, the study not only contributes valuable insights into the relative strengths and weaknesses of LSTM, RNN, and GRU models for stock price prediction but also emphasizes the practical utility of the predictions by visually displaying the differences through charts and graphs. This dual approach advances the understanding of deep learning techniques in financial forecasting and provides actionable recommendations for researchers and practitioners seeking to enhance the precision of stock price predictions.

关键词： Deep learning Adaptation models Visualization Recurrent neural networks Accuracy Predictive models Reliability

来源：评论

学校读者我要写书评

暂无评论

Digital Human Techniques for Education Reform 24

Digital Human Techniques for Education Reform

引用

7th International Conference on Educational Technology Management, ICETM 2024

作者： Guo, Peirong Zhang, Qi Tian, Chunwei Xue, Wanli Feng, Xiaocheng School of Software Northwestern Polytechnical University Shaanxi Xi’an China School of Economics and Management Harbin Institute of Technology at Weihai Shandong Weihai China Shenzhen Research Institute of Northwestern Polytechnical University Northwestern Polytechnical University Guangdong Shenzhen China School of Computer Science and Engineering Tianjin University of Technology Tianjin China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Heilongjiang Harbin China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Guangdong Shenzhen China

ISBN: (纸本)9798400717468

The rapid evolution of artificial intelligence, big data, and generative AI models has ushered in significant transformations across various sectors, including education. Digital Human Technique, an innovative technology grounded in advanced computer science and artificial intelligence, is reshaping educational paradigms by enabling virtual humans to simulate human behavior, express emotions, and interact with users. This paper explores the application of Digital Human Technique in education reform, focusing on creating immersive, intelligent classroom experiences that foster meaningful interactions between teachers and students. We define Digital Human Technique and delve into its key technical components such as character modeling and rendering, natural language processing, computer vision, and augmented reality technologies. Our methodology involves analyzing the role of educational digital humans created through these technologies, assessing their impact on educational processes, and examining various application scenarios in educational reform. Results indicate that Digital Human Technique significantly enhances the learning experience by enabling personalized teaching, increasing engagement, and fostering emotional connections. Educational digital humans serve as virtual teachers, interactive learning aids, and facilitators of emotional interaction, effectively addressing the challenges of traditional educational methods. They also promote a deeper understanding of complex concepts through simulated environments and interactive digital content. © 2024 Copyright held by the owner/author(s).

关键词： Digital elevation model

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：