检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yuan, Haonan Sun, Qingyun Fu, Xingcheng Zhang, Ziwei Ji, Cheng Peng, Hao Li, Jianxin Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China School of Computer Science and Engineering Beihang University China Key Lab of Education Blockchain and Intelligent Technology Guangxi Normal University China Department of Computer Science and Technology Tsinghua University China

Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribution shifts, which are common in real-world scenarios. As the generation of dynamic graphs is heavily influenced by latent environments, investigating their impacts on the out-of-distribution (OOD) generalization is critical. However, it remains unexplored with the following two major challenges: (1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? (2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatiotemporal invariant patterns. Specifically, we first design the environment-aware EA-DGNN to model environments by multi-channel environments disentangling. Then, we propose an environment instantiation mechanism for environment diversification with inferred distributions. Finally, we discriminate spatio-temporal invariant patterns for out-of-distribution prediction by the invariant pattern recognition mechanism and perform fine-grained causal interventions node-wisely with a mixture of instantiated environment samples. Experiments on real-world and synthetic dynamic graph datasets demonstrate the superiority of our method against state-of-the-art baselines under distribution shifts. To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of TB from Chest X-ray: A Study with EfficientNet

Detection of TB from Chest X-ray: A Study with EfficientNet

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： A. Rama M. P. Rajakumar N. Mythili S. Arunmozhi Mazin Abed Mohammed V. Rajinikanth Department of CSE Saveetha School of Engineering SIMATS Chennai TN India Department of Artificial Intelligence and Data Science St.Joseph's College of Engineering Chennai TN India Department of Computer Science and Engineering St.Joseph's Institute of Technology Chennai TN India Department of Electronics and Communication Engineering Manakula Vinayagar Institute of Technology Puducherry TN India Department of Artificial Intelligence College of Computer Science and Information Technology University of Anbar Anbar Iraq Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai TN India

The lung is one of the prime organs, and any disease in the lung causes mild to severe breathing problems; untreated lung disease will lead to several complications. Tuberculosis (TB) is a lung ailment that needs premature recognition and handling. The primary objective is to employ the deep-learning (DL) based TB detection using chest $X$ -rays. Various stages of the proposed scheme consist of (i) data collection and resizing, (ii) DL-supported feature extraction, (iii) binary classification and five-fold cross-validation, and (iv) comparison with earlier results and confirming the merit of the scheme. This research implements EfficientNet (EN) variants to classify the chosen $\mathrm{X}$ -rays into healthy/TB classes using the SoftMax classifier. The proposed scheme with EN_B2 (ENB2) has been successful in providing an accuracy of $96{\% }$ as far as detection accuracy is considered when compared to other methods. The superiority of the suggested strategy is also confirmed by an analysis using the most recent technology, which confirms the worth of the proposed system on the chosen $\mathrm{X}$ -ray imagery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protecting Deep Neural Networks in Cloud-Based Environments Towards Backdoor Assaults

Protecting Deep Neural Networks in Cloud-Based Environments ...

引用

Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), International Conference on

作者： Manjunatha R Naresh Kaushik Yaduvir Singh Department of Data analytics and Mathematical Sciences School of Sciences JAIN (Deemed to be University) Bangalore Karnataka India Department of uGDX ATLAS SkillTech University Mumbai Maharashtra India Department of Computer Science and Engineering (AI) Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India

ISBN: (数字)9798350355338

ISBN: (纸本)9798350355345

When it comes to training deep neural networks, especially those with complicated architectures, the accompanying financial and temporal costs often force resource-constrained customers to outsource their learning process via cloud service providers. But there's a risk that dishonest cloud providers may include backdoors and jeopardise the security of the overall model. Users may examine the model closely and utilise state-of-the-art defence techniques to reduce this danger. The goal of this research is to create a robust backdoor attack technique called RobNet that can circumvent current defences from the perspective of malevolent cloud providers. Furthermore, multi-trigger backdoor assaults are introduced, which enlarge the attack area by misclassifying inputs with different triggers into target labels that are either identical or dissimilar. RobNet is tested against four popular defence techniques (Pruning, NeuralCleanse, Strip, and ABS) using datasets from MNIST, GTSRB, and CIFAR-10. RobNet has a higher attack success rate and more robustness against possible defensive measures when compared to two state-of-the-art baselines: Hidden Backdoors and BadNets.

关键词： Training Technological innovation Strips Neurons Artificial neural networks Robustness Service-oriented architecture Security Biological neural networks Resilience

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery

arXiv

引用

arXiv 2023年

作者： Liu, Jin Mao, Junbin Lin, Hanhe Kuang, Hulin Pan, Shirui Wu, Xusheng Xie, Shan Liu, Fei Pan, Yi Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830000 China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Science and Engineering University of Dundee DundeeDD1 4HN United Kingdom School of Information and Communication Technology Griffith University Gold CoastQLD4215 Australia Shenzhen Health Development Research and Data Management Center Shenzhen518109 China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology. The source code will be available at https://***/yutian0315/MMKGL. © 2023, CC BY-NC-ND.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Relation Matrix Bidirectional Approach for Relational Triple Extraction

Hybrid Deep Relation Matrix Bidirectional Approach for Relat...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yushuai Hu Jing Zhao Ming Li Lin Yuan Qingzhi Zou Ronghuan Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Relation extraction is a crucial task within information extraction, and numerous models have demonstrated impressive results. However, most of the tagging-based relation triple extraction methods employ unidirectional approaches to extract subjects, objects, and relations, which may overlook crucial information. In this paper, we introduce a novel deep matrix-based bidirectional relation extraction model. Firstly, we extract forward and backward entity pairs. During the bidirectional extraction process,there may be some redundant relationships,so we use a shared encoder to connect and enhance the extraction process. Secondly, we design a low-complexity relation extraction matrix to allocate all possible relations. We assess our model using diverse benchmark datasets, and comprehensive experiments show that our approach effectively addresses subsequent triple extraction issues stemming from entity extraction failures.

关键词： Learning systems Federated learning Computational modeling Benchmark testing Information retrieval data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Alzheimer’s Disease Using EfficientNet-B3 Architecture with Transfer Learning

Automated Detection of Alzheimer’s Disease Using EfficientN...

引用

Information Technology (ACIT)

作者： Ahmad Aburomman Suhaila Abuowaida Adai Al-Momani Esraa Al Henawi Esraa Abu Elsoud Zaher Salah Haneen Alzoubi Huah Yong Chan Mohammed Khouj Department of Data Science and AI Zarqa University Zarqa Jordan Department of Computer Science AI Al-Bayt University Mafraq Jordan Department of Computer Science Zarqa University Zarqa Jordan Department of Information Technology The Hashemite University Zarqa Jordan Faculty of Information Technology Applied Science Private University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Gelugor Pulau Pinang Malaysia Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

In order to bring forward expansion in both the accuracy and the processing speed of the detection of Alzheimer’s disease, an automated approach for Alzheimer’s disease diagnosis with passable EfficientNet-B3 neural network and transfer learning techniques is provided in this work. After direct fitness on a large number of annotated brain images, the model of EfficientNet-B3 is further trained, in an effort to obtain worse depicted quality connected with Alzheimer’s Disease. To hasten the process of training and to make the model fit for this specific task, transfer learning was employed. The results of these experiments prove the efficiency of our approach to the diagnostic Alzheimer’s disease compared to the most advanced and regular deep learning methods. Thus, the model may also withstand the test amidst diverse clinical populations by performing well in dementia classification with precision and recall performance coupled with over 99% accuracy. These findings demonstrate how the EfficientNet-B3 architecture and transfer learning enhance generalization across.

关键词： Training Deep learning Accuracy Transfer learning Brain modeling Medical diagnosis Alzheimer's disease Information technology Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

FaaSTube: Optimizing GPU-oriented data Transfer for Serverless Computing

arXiv

引用

arXiv 2024年

作者： Wu, Hao Deng, Junxiao Yu, Minchen Yu, Yue Liu, Yaochen Fan, Hao Wu, Song Wang, Wei National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Hong Kong University of Science and Technology Hong Kong The Chinese University of Hong Kong Shenzhen China

Serverless computing has gained significant traction for machine learning inference applications, which are often deployed as serverless workflows consisting of multiple CPU and GPU functions with data dependency. However, existing data-passing solutions for serverless computing primarily reply on host memory for fast data transfer, mandating substantial data movement and resulting in salient I/O overhead. In this paper, we present FaaSTube, a GPU-efficient data passing system for serverless inference. FaaSTube manages intermediate data within a GPU memory pool to facilitate direct data exchange between GPU functions. It enables fine-grained bandwidth sharing over PCIe and NVLink, minimizing data-passing latency for both host-to-GPU and GPU-to-GPU while providing performance isolation between functions. Additionally, FaaSTube implements an elastic GPU memory pool that dynamically scales to accommodate varying data-passing demands. Evaluations on real-world applications show that FaaSTube reduces end-to-end latency by up to 90% and achieves up to 12x higher throughput compared to the state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： computer graphics equipment

来源：评论

学校读者我要写书评

暂无评论

Exploring the Use of Machine Learning Techniques for Enhancing Real-Time data Access

Exploring the Use of Machine Learning Techniques for Enhanci...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Sourav Rampal Shreenidhi H S Manish Shrivastava Akhilendra Pratap Singh Reena R Santosh D. Kumar Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune INDIA

Actual-time statistics to date has updated, increasingly vital as the quantity of virtual information maintains updated growth. Effective choice-making depends on the capability to update access and analyze records. Device up-to-date techniques provide the capacity up-to-date enhance actual-time statistics up-to-date by using offering insights from disparate pieces of information. This paper addresses the potential benefits of using a system with date knowledge and updated, up-to-date strategies to broaden extra clever statistics up to date updated systems. It summarizes the contemporary nation of the art and highlights studies in machine learning and up-to-date imaginative and prescient real-time information up-to-date. It additionally discusses present-day challenges and shows viable instructions for future studies. The studies network up-to-date recall how gadgets are up to date know that updated strategies may be used to facilitate real-time get entry updated the maximum precious pieces of facts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IOT based Machine Learning Algorithms for data science on Quality Control Process

IOT based Machine Learning Algorithms for Data Science on Qu...

引用

Intelligent & Innovative Practices in engineering & Management (IIPEM), International Conference on

作者： Lingarasu Kittusamy G. Prasanna Lakshmi Pravin B Khatkale P. William Onkar Ghige Bhagyashree Ashok Tingare Quality Engineering Lead Compunnel Inc Morgan Plainsboro NJ School of Computer Science and Engineering Sandip University Nashik Maharashtra Sanjivani University Kopargaon Maharashtra India Deaprtment of Information Technology Sanjivani College of Engineering Kopargaon Amity University Dubai UAE Department of Elecrical Engineering Sanjivani College of Engineering Kopargaon MH India Department of Artificial Intelligence and Data Science D Y Patil College of Engineering Akurdi Pune

ISBN: (数字)9798350390049

ISBN: (纸本)9798350390056

Because of the combination of Internet of Things (IoT) technology and machine learning (ML) algorithms, quality control methods in the industrial sector are undergoing a revolution. This is because real-time monitoring, predictive maintenance, and anomaly detection are now entirely feasible. Conventional quality control methods, which often rely on random inspections and sampling, are being phased out in favour of these cutting-edge technologies, which provide continuous data collection and analysis. The purpose of this research is to get a better understanding of how it is possible for IoT and ML to enhance quality control by examining their applications, benefits, and challenges in industrial settings. In this work, we demonstrate how machine learning algorithms that are based on the Internet of Things (IoT) have the potential to significantly improve defect detection rates, reduce downtime, and optimise manufacturing processes by using a multidimensional research approach that combines empirical analysis and case studies. The findings illustrate how these technologies have a considerable and beneficial impact on decision-making in data-driven quality control processes, as well as on the efficiency of operations and the quality of products available.

关键词： Machine learning algorithms Process control Quality control Machine learning Solids Real-time systems Internet of Things Anomaly detection Predictive maintenance Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Open-Set Object Detection via Conditional Evidence Decoupling

arXiv

引用

arXiv 2024年

作者： Wu, Zhaowei Su, Binyi Zhang, Hua Zhou, Zhong The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300401 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Zhongguancun Laboratory Beijing100190 China

Few-shot Open-set Object Detection (FOOD) poses a significant challenge in real-world scenarios. It aims to train an open-set detector under the condition of scarce training samples, which can detect known objects while rejecting unknowns. Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous. To mitigate this issue, we develop a two-stage open-set object detection framework with prompt learning, which delves into conditional evidence decoupling for the unknown rejection. Specifically, we propose an Attribution-Gradient-based Pseudo-unknown Mining (AGPM) method to select region proposals with high uncertainty, which leverages the discrepancy in attribution gradients between known and unknown classes, alleviating the inadequate unknown distribution coverage of training data. Subsequently, we decouple known and unknown properties in pseudo-unknown samples to learn distinct knowledge with proposed Conditional Evidence Decoupling (CED), which enhances separability between knowns and unknowns. Additionally, we adjust the output probability distribution through Abnormal Distribution Calibration (ADC), which serves as a regularization term to establish robust decision boundaries for the unknown rejection. Our method has achieved superior performance over previous state-of-the-art approaches, improving the mean recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

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：