检索结果-内蒙古大学图书馆

Exploring data Geometry for Continual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Zhi Xu, Chen Li, Feng Jia, Yunde Harandi, Mehrtash Wu, Yuwei Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Electrical and Computer Systems Eng. Monash University Data61 Australia

Continual learning aims to efficiently learn from a non-stationary stream of data while avoiding forgetting the knowledge of old data. In many practical applications, data complies with non-Euclidean geometry. As such, the commonly used Euclidean space cannot gracefully capture non-Euclidean geometric structures of data, leading to inferior results. In this paper, we study continual learning from a novel perspective by exploring data geometry for the non-stationary stream of data. Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and prevents forgetting by keeping geometric structures of old data into account. In doing so, making use of the mixed curvature space, we propose an incremental search scheme, through which the growing geometric structures are encoded. Then, we introduce an angular-regularization loss and a neighbor-robustness loss to train the model, capable of penalizing the change of global geometric structures and local geometric structures. Experiments show that our method achieves better performance than baseline methods designed in Euclidean space. Copyright © 2023, The Authors. All rights reserved.

关键词： Geometry

Federated Learning for 6G Communications:Challenges,Methods,and Future Directions

学校读者我要写书评

暂无评论

China Communications 2020年第9期17卷 105-118页

作者： Yi Liu Xingliang Yuan Zehui Xiong Jiawen Kang Xiaofei Wang Dusit Niyato School of Data Science of Technology Heilongjiang UniversityHarbinChina Faculty of Information Technology Monash UniversityAustralia Alibaba-NTU Joint Research Institute and also School of Computer Science and Engineering NTUSingapore Energy Research Institute Nanyang Technological UniversitySingapore College of Intelligence and Computing Tianjin UniversityTianjinChina School of Computer Science and Engineering NTUSingapore

As the 5G communication networks are being widely deployed worldwide,both industry and academia have started to move beyond 5G and explore 6G *** is generally believed that 6G will be established on ubiquitous Artificial Intelligence(AI)to achieve data-driven Machine Learning(ML)solutions in heterogeneous and massive-scale ***,traditional ML techniques require centralized data collection and processing by a central server,which is becoming a bottleneck of large-scale implementation in daily life due to significantly increasing privacy *** learning,as an emerging distributed AI approach with privacy preservation nature,is particularly attractive for various wireless applications,especially being treated as one of the vital solutions to achieve ubiquitous AI in *** this article,we first introduce the integration of 6G and federated learning and provide potential federated learning applications for *** then describe key technical challenges,the corresponding federated learning methods,and open problems for future research on federated learning in the context of 6G communications.

关键词： 6G communication federated learning security and privacy protection

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Haopeng Deng, Andong Liu, Jun Rahmani, Hossein Guo, Yulan Schiele, Bernt Bennamoun, Mohammed Ke, Qiuhong School of Computing and Information Systems University of Melbourne Australia Center for Research in Computer Vision University of Central Florida United States Pillar Singapore University of Technology and Design Singapore School of Computing and Communications Lancaster University United Kingdom School of Electronics and Communication Engineering Sun Yat-sen University China Department of Computer Vision and Machine Learning Max Planck Institute for Informatics Saarland Informatics Campus Germany School of Physics Maths and Computing University of Western Australia Australia Department of Data Science & AI Monash University Australia

Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

Efficient COVID-19 detection using data mining algorithms: a comparison of basic and hybrid approaches

学校读者我要写书评

暂无评论

Soft computing 2025年第3期29卷 1437-1451页

作者： Saidi, Mohammad Gheibi, Mohammad Ghazikhani, Adel Lotfata, Aynaz Chahkandi, Benyamin Familsamavati, Sajad Behzadian, Kourosh Department of Computer Science Imam Reza International University Mashhad Iran MS of Software Engineering Information and Communication Technology Unit Mashhad Municipality Fire and Safety Services Organization Mashhad Iran Big Data Lab Imam Reza International University Mashhad Iran Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Liberec46117 Czech Republic Tallinn10615 Estonia Department of Pathology Microbiology and Immunology School of Veterinary Medicine University of California Davis95616 United States Department of Urban and Regional Planning San Jose State University San Jose95192 United States Faculty of Civil and Environmental Engineering Gdansk University of Technology Narutowicza Street 11/12 80-233 Gdansk Poland Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Monterrey Mexico School of Computing and Engineering University of West London London United Kingdom

Accurate and efficient diagnosis of COVID-19 remains a significant challenge due to the limitations of current detection methods, such as blood tests and chest scans, which can be time-consuming and error-prone. This study aims to compare the performance of basic and hybrid data mining algorithms in diagnosing COVID-19, using blood test results and clinical information to identify the most effective approach. A dataset of 200 records from suspected and infected COVID-19 patients, with 23 characteristics and one diagnostic class, was analysed. Nine data mining algorithms were tested: four basic algorithms (Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor) and five hybrid algorithms (Random Forest, AdaBoost, Majority Voting, XGBoost, Bagging). The study also integrated Response Surface Methodology (RSM) and Adaptive-Network-based Fuzzy Inference System (ANFIS) to enhance model performance. The Bagging algorithm demonstrated superior performance with an accuracy of 88%, sensitivity of 74%, and F-criterion of 78%. The integration of RSM and ANFIS further showed that a smart model could be developed for efficient pandemic crisis management, achieving up to 100% accuracy when considering key factors like AST, Albumin, and CRP. The findings suggest that Bagging and hybrid data mining algorithms can significantly improve COVID-19 detection, reducing time and errors in identifying exposed individuals. The study highlights the potential of combining machine learning techniques with RSM-ANFIS models for effective pandemic management and decision-making in medical settings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Support vector machines

GoMORE: Global Model Reuse for Resource-Constrained Wireless Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yao, Jiacheng Yang, Zhaohui Xu, Wei Chen, Mingzhe Niyato, Dusit Southeast University Nanjing210096 China The Zhejiang Lab Hangzhou311121 China The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The School of Computer Science and Engineering Nanyang Technological University 308232 Singapore

Due to the dynamics of wireless environment and limited bandwidth, wireless federated learning (FL) is challenged by frequent transmission errors and incomplete aggregation from devices. In order to overcome these challenges, we propose a Global MOdel REuse strategy (GoMORE) that reuses the outdated global model to replace the local model parameters once a transmission error occurs. We analytically prove that the proposed GoMORE is strictly superior over the existing strategy, especially at low signal-to-noise ratios (SNRs). In addition, based on the derived expression of weight divergence, we further optimize the number of participating devices in the model aggregation to maximize the FL performance with limited communication resources. Numerical results verify that the proposed GoMORE successfully approaches the performance upper bound by an ideal transmission. It also mitigates the negative impact of non-independent and non-identically distributed (non-IID) data while achieving over 5 dB reduction in energy consumption. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal to noise ratio

Exploring data Geometry for Continual Learning

学校读者我要写书评

暂无评论

Exploring Data Geometry for Continual Learning

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhi Gao Chen Xu Feng Li Yunde Jia Mehrtash Harandi Yuwei Wu Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Electrical and Computer Systems Eng. Monash University and Data61 Australia

Continual learning aims to efficiently learn from a non-stationary stream of data while avoiding forgetting the knowledge of old data. In many practical applications, data complies with non-Euclidean geometry. As such, the commonly used Euclidean space cannot gracefully capture non-Euclidean geometric structures of data, leading to in-ferior results. In this paper, we study continual learning from a novel perspective by exploring data geometry for the non-stationary stream of data. Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and pre-vents forgetting by keeping geometric structures of old data into account. In doing so, making use of the mixed cur-vature space, we propose an incremental search scheme, through which the growing geometric structures are en-coded. Then, we introduce an angular-regularization loss and a neighbor-robustness loss to train the model, capa-ble of penalizing the change of global geometric structures and local geometric structures. Experiments show that our method achieves better performance than baseline methods designed in Euclidean space.

关键词：

Smart Class on Android: A Handy Classroom Scheduling Solution

学校读者我要写书评

暂无评论

Smart Class on Android: A Handy Classroom Scheduling Solutio...

Next Generation Communication & information Processing (INCIP), International Conference on

作者： Vishnuraja Palanisamy M. Thiyagarajan R. Bhavani Arun Anthonisamy K. Manivannan S. Vaishnavi Department of Artificial Intelligence and Data Science Builders Engineering College Kangeyam Tamil Nadu India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamil Nadu India Department of Electronics and Communication Engineering K. Ramakrishnan College of Technology Trichy Tamil Nadu India Department of Computer Science and Business System Panimalar Engineering College Chennai Tamil Nadu India Department of Information Science and Engineering School of Computer Science & Engineering JAIN (Deemed-to-be) University Bengaluru Karnataka India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education (MAHE) Manipal India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Classroom scheduling is vital but difficult for educational institutions, especially those with large student populations and diverse needs. Traditional methods using outdated software or manual processes often cause inefficiencies, disagreements, and administrative workload. In low-resource regions without access to cutting-edge technology and infrastructure, these issues are severe. This paper introduces Android-based SmartClass Mobile to transform classroom scheduling. The program's SOA-based functionality offers flexibility, adaptability, and integration with institution-specific procedures. The Heuristic algorithm and Solution Space Navigation (SSN) tackle scheduling problems such as room availability, multimedia needs, and seating capacities. SSN dynamically resolves conflicts by exploring alternate configurations, while the Heuristic Algorithm assigns time slots and classrooms depending on availability and priority. SmartClass Mobile analysis indicates benefits. The solution reduces conflicts, increases user satisfaction, and decreases scheduling time by 50% compared to manual methods with 85% test user approval. Due to its mobile-first approach, the initiative is open to urban and rural institutions. Dependence on internet access for some functions is a downside, especially in resource-constrained contexts. The findings suggest that SmartClass Mobile provides a scalable, effective, and simple classroom scheduling solution. Mobile technology, advanced algorithms, and SOA concepts make it valuable for school administrators. Additions like AI and machine learning will boost its potential.

关键词： Navigation Heuristic algorithms Software algorithms Manuals Transforms Scheduling Software Real-time systems Mobile applications Reliability

A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Sikun Zha, Hongyuan School of Computing and Information Technology Great Bay University Dongguan523000 China Great Bay Institute for Advanced Study Great Bay University China Dongguan Key Laboratory for Data Science and Intelligent Medicine Great Bay University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China The Chinese University of Hong Kong Shenzhen China

Continuously-observed event occurrences, often exhibit self- and mutually-exciting effects, which can be well modeled using temporal point processes. Beyond that, these event dynamics may also change over time, with certain periodic trends. We propose a novel variational auto-encoder to capture such a mixture of temporal dynamics. More specifically, the whole time interval of the input sequence is partitioned into a set of sub-intervals. The event dynamics are assumed to be stationary within each sub-interval, but could be changing across those sub-intervals. In particular, we use a sequential latent variable model to learn a dependency graph between the observed dimensions, for each sub-interval. The model predicts the future event times, by using the learned dependency graph to remove the non-contributing influences of past events. By doing so, the proposed model demonstrates its higher accuracy in predicting inter-event times and event types for several real-world event sequences, compared with existing state of the art neural point processes. © 2023, CC BY.

关键词： Dynamics

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment