检索结果-内蒙古大学图书馆

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Linxian Li Yuzhu Hu Yulong Zhao Xiaoqian Xi Jiaxin Chen Wei Wang School of Computer Science Beijing Institute of Technology Beijing China Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU - BIT University Shenzhen China School of Intelligent Systems Engineering Sun Vat-sen University Shenzhen China Faculty of Engineering Shenzhen MSU-BIT University Shenzhen China

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

Collaborative Filtering(CF) is a widely studied recommendation method, and learning high-quality representations is crucial for it. Recent research has focused on improving the quality of learned representations by designing better optimization objectives, such as optimizing alignment and uniformity, which enhance recommendation performance. However, supervised learning alone cannot address inherent issues like sparse supervision signals in recommendation systems. Therefore, many studies use contrastive learning (CL) from self-supervised learning to provide additional self-supervised signals, and often jointly optimize InfoNCE loss from CL and BPR loss from CF. Considering that both InfoNCE and BPR losses can be analyzed through the key properties of alignment and uniformity, we propose a loss function that integrates CL and CF into alignment and uniformity. This integration ensures that the learned representations are both representative and suitable for recommendation tasks. Specifically, we use LightGCN to extract high-order collaborative signals from the user-item interaction graph, and to enable self-supervised learning, we add uniform noise perturbations at each layer. We then optimize the learned representations using our proposed loss function. We conduct experiments on a benchmark dataset to demonstrate the superiority of our framework.

关键词： Collaborative filtering Perturbation methods Supervised learning Noise Collaboration Contrastive learning Information filters Internet of Things Recommender systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Continuous Image Outpainting with Neural ODE

SSRN

引用

SSRN 2023年

作者： Gao, Penglei Yang, Xi Zhang, Rui Huang, Kaizhu Department of Computer Science University of Liverpool United Kingdom School of Advanced Technology Department of Foundational Mathematics Xi’an Jiaotong-Liverpool University China Institute of Applied Physical Sciences and Engineering Duke Kunshan University China

Different from image inpainting, generalised image outpainting aims to extend appealing content all-side around a given image. Existing state-of-the-art outpainting methods often rely on discrete extrapolation to extend the feature map in the bottleneck. They thus suffer from content unsmoothness, especially in circumstances where the outlines of objects in the extrapolated regions are incoherent with the input sub-images. To mitigate this issue, we design a novel bottleneck with Neural ODEs to make continuous extrapolation in latent space, which could be a plug-in for many deep learning frameworks. Our ODE-based network continuously transforms the state and makes accurate predictions by learning the incremental relationship among latent points, leading to both smooth and structured feature representation. Experimental results on three real-world datasets both applied on transformer-based and CNN-based frameworks show that our methods could generate more realistic and coherent images against the state-of-the-art image outpainting approaches. © 2023, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Cassava Syndrome Scan a Pioneering Deep Learning System for Accurate Cassava Leaf Disease Classification 1

引用

6th International Conference on Applied Machine Learning and Data Analytics, AMLDA 2023

作者： Rahat, Irfan Sadiq Ghosh, Hritwik Ramesh, Janjhyam Venkata Naga Kiran, Ajmeera Verma, Poonam VIT-AP University Andhra Pradesh Amaravati India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur522502 India Department of Computer Science and Engineering MLR Institute of Technology Dundigal Telangana Hyderabad500043 India School of Computing Graphic Era Hill University Dehradun R/S Graphic Era Deemed to be University Dehradun248002 India

ISBN: (数字)9783031554865

ISBN: (纸本)9783031554858

Cassava serves as a crucial source of carbohydrates for a vast population globally, playing a significant role in food security. The crop, however, faces threats from a variety of leaf diseases, leading to substantial reduction in yield. Prompt and precise identification of these diseases is essential for implementing effective countermeasures and maintaining adequate food supply. Recently, deep learning methodologies have demonstrated remarkable capabilities in image-based recognition and classification, including the diagnosis of plant diseases. The objective of this research is to construct a dependable cassava leaf disease identification system utilizing deep learning approaches, with an emphasis on achieving exceptional accuracy and dependability. We assess the performance of multiple cutting-edge deep learning architectures, such as ResNet50, DenseNet121, EfficientNet-B0, NasNetLarge, and EfficientNet-V2, in the context of cassava leaf disease classification. The dataset is comprised of nearly 15,000 test images, accompanied by image_id and label data in *** and sample_*** files. Data preprocessing, including resizing, normalization, and augmentation, is conducted before partitioning the data into training, validation, and test sets. Our findings indicate that the EfficientNet-V2 model surpasses its counterparts in performance, attaining the highest validation accuracy of 0.7480 and a comparatively low validation loss of 0.7488. We further explore several strategies to enhance model performance, such as optimizing hyperparameters, employing data augmentation, utilizing early stopping, implementing learning rate scheduling, applying transfer learning, and adopting ensemble techniques. The resulting classifier offers potential benefits to farmers and agricultural specialists in making informed decisions regarding cassava leaf disease management, ultimately leading to improved crop yields and food security. © The Author(s), under exclusive licens

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

Causal Image Synthesis of Brain MR in 3D

arXiv

引用

arXiv 2023年

作者： Li, Yujia Shi, Jiong Zhou, S. Kevin Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China University of Chinese Academy of Sciences China Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei China Department of Neurology Institute on Aging and Brain Disorders The Hospital of Ustc China

Clinical decision making requires counterfactual reasoning based on a factual medical image and thus necessitates causal image synthesis. To this end, we present a novel method for modeling the causality between demographic variables, clinical indices and brain MR images for Alzheimer's Diseases. Specifically, we leverage a structural causal model to depict the causality and a styled generator to synthesize the image. Furthermore, as a crucial step to reduce modeling complexity and make learning tractable, we propose the use of low-dimensional latent feature representation of a high-dimensional 3D image, together with exogenous noise, to build causal relationship between the image and non-image variables. We experiment the proposed method based on 1586 subjects and 3683 3D images and synthesize counterfactual brain MR images intervened on certain attributes, such as age, brain volume and cognitive test score. Quantitative metrics and qualitative evaluation of counterfactual images demonstrates the superiority of our generated images. © 2023, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Distributed optimization for IoT attack detection using federated learning and Siberian Tiger optimizer

引用

ICT Express 2025年第3期11卷 542-546页

作者： Gupta, Brij B. Gaurav, Akshat Alhalabi, Wadee Arya, Varsha Alharbi, Eman Chui, Kwok Tai Department of Computer Science and Information Engineering Asia University Taichung 413 Taiwan Department of Medical Research China Medical University Hospital China Medical University Taichung Taiwan Symbiosis Centre for Information Technology (SCIT) Symbiosis International University Pune India School of Cybersecurity Korea University Seoul South Korea Kyung Hee University 26 Kyungheedae-ro Dongdaemun-gu Seoul South Korea Ronin Institute Montclair NJ United States International Center for AI and Cyber Security Research and Innovations (CCRI) Asia University Taichung 413 Taiwan Department of Computer Science Immersive Virtual Reality Research Group King Abdulaziz University Jeddah Saudi Arabia Hong Kong Metropolitan University Hong Kong SAR China Center for Interdisciplinary Research University of Petroleum and Energy Studies (UPES) Dehradun India Department of Computer Science Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

The rapid growth of IoT devices has heightened the risk of botnet attacks, calling for scalable and distributed detection solutions. In this context, this study proposes a distributed optimization system for IoT attack detection using CNN model utilizing federated learning. After optimizing the hyperparameters of the model at the server, the Siberian Tiger Optimization (STO) method distributes these values to clients for dispersed training. Our model achieves accuracy, recall, and precision of 0.89978, 0.94355, and 0.94455, respectively, using the N-BaIoT dataset. These findings show, in spite of latency issues, the efficiency of federated learning in distributed IoT security systems. © 2025

关键词： CNN model Distributed optimization Federated learning IoT attack detection Siberian Tiger Optimization (STO)

来源：评论

学校读者我要写书评

暂无评论

Maximal coin-walker entanglement in a ballistic quantum walk

引用

Physical Review A 2022年第4期105卷 042216-042216页

作者： Rong Zhang Ran Yang Jian Guo Chang-Wei Sun Jia-Chen Duan Heng Zhou Zhenda Xie Ping Xu Yan-Xiao Gong Shi-Ning Zhu National Laboratory of Solid State Microstructure School of Physics School of Electronic Science and Engineering and Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing 210093 China College of Electronic and Optical Engineering Nanjing University of Posts and Telecommunication Nanjing 210023 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computing National University of Defense Technology Changsha 410073 China

We report that the position-inhomogeneous quantum walk (IQW) can be utilized to produce the maximal high-dimensional entanglement while maintaining the quadratic speedup spread of the wave function. Our calculations show that the maximal coin-walker entanglement can be generated in any odd steps or asymptotically in even steps, and the nearly maximal entanglement can be obtained in even steps after 2. We implement the IQW by a stable resource-saving time-bin optical network, in which a polarization Sagnac loop is employed to realize the precisely tunable phase shift. Our approach opens up an efficient way for high-dimensional entanglement engineering as well as promotes investigations on the role of coin-walker interactions in QW-based applications.

关键词： Entanglement manipulation Optical quantum information processing Quantum optics Quantum walks

来源：评论

学校读者我要写书评

暂无评论

LogiQA: A challenge dataset for machine reading comprehension with logical reasoning 29

LogiQA: A challenge dataset for machine reading comprehensio...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Liu, Jian Cui, Leyang Liu, Hanmeng Huang, Dandan Wang, Yile Zhang, Yue School of Computer Science Fudan University China School of Engineering Westlake University China Institute of Advanced Technology Westlake Institute for Advanced Study China

ISBN: (纸本)9780999241165

Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival human performances on simple QA, and thus increasingly challenging machine reading datasets have been proposed. Though various challenges such as evidence integration and commonsense knowledge have been integrated, one of the fundamental capabilities in human reading, namely logical reasoning, is not fully investigated. We build a comprehensive dataset, named LogiQA, which is sourced from expert-written questions for testing human Logical reasoning. It consists of 8,678 QA instances, covering multiple types of deductive reasoning. Results show that state-of-the-art neural models perform by far worse than human ceiling. Our dataset can also serve as a benchmark for re-investigating logical AI under the deep learning NLP setting. The dataset is freely available at https://***/lgw863/LogiQA-dataset. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Detection of Selfish Nodes based on Node Energy in Mobile Adhoc Networks – MANETs

Detection of Selfish Nodes based on Node Energy in Mobile Ad...

引用

Automation, computing and Renewable Systems (ICACRS), International Conference on

作者： R. Sarumathi V. Jayalakshmi VISTAS Chennai India Dept. of Computer Science RajeswariVedhachalam Govt. Arts College Chengalpet India School of Computing Sciences Vels Institute of Science Technology and Advanced Studies VISTAS Chennai India

ISBN: (纸本)9781665460859

One of the most essential self-configuring and independent wireless networks is the MANET. MANET employs a large number of intermediate nodes to exchange information without the need for any centralized infrastructure. However, some nodes act in a selfish manner, utilizing the network's resources solely for their own benefit and refusing to share with the surrounding nodes. Mobile ad hoc network security is a critical factor that is widely accepted. Selfish nodes are the primary problem of MANET. In a MANET, nodes that are only interested in themselves do not involve in the process of packet forwarding. A node can be identified as selfish or malicious due to some misbehavior reasons. Selfishness on the part of network nodes may be a factor in the low delivery ratio of packets and data loss. A high end-to-end delay is caused by node failure in a MANET network. To study the selfish node attack, a malicious selfish node is put into the network, and a trust-based algorithm for the selfish node attack is also suggested. In order to discover a solution to this issue, we have developed an algorithm called SNRM for the detection of selfish nodes. The routing protocol used in this paper for analysis is AODV. Using a simulation tool, PDR and end-to-end delay are evaluated and compared.

关键词： Renewable energy sources Automation Routing Routing protocols Delays Security AODV

来源：评论

学校读者我要写书评

暂无评论

Enhancing Decision-Making and Operational Efficiency Through Demand Prediction Using Machine Learning

Enhancing Decision-Making and Operational Efficiency Through...

引用

International Conference on Emerging Trends in Networks and computer Communications (ETNCC)

作者： Nilesh Bhaskarrao Bahadure Neelam Singh Jagdish Chandra Patni Rutuja Durge Shailaja Pipalatkar Ramdas Khomane Tanupriya Choudhury Saumya Deshmukh Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Dept. of CSE Graphic Era Deemed to be University Dehradun India Deptt. of CSE Alliance School of Advanced Computing Alliance University Bengaluru India School of Computer Science University of Petroleum and Energy Studies (UPES) Dehradun Uttarakhand India

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

Launching a new product in the market and then getting reviews about the product so that the feasibility of the product can be planned accordingly mainly depends on the survey information or data from the sources. Here, decision-making plays a significant contribution, and this is where demand prediction comes into the picture. Demand prediction will not only help in planning the business and optimizing the operations but will also help get more information about the product's performance in the market. This study mainly focuses on how machine learning algorithms and other techniques can be used to predict the demand for the product. The model proposed in this study can enhance decision-making and efficiency and lead to high-standard market performance.

关键词： Surveys Machine learning algorithms Reviews Decision making Production Pricing Predictive models Market research Scheduling Business

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous Network-based Contrastive Learning Approach for Predicting Drug-Target Interaction

A Heterogeneous Network-based Contrastive Learning Approach ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Junwei Hu Michael Bewong Selasi Kwashie Wen Zhang Vincent M. Nofong Guangsheng Wu Zaiwen Feng College of Informatics Huazhong Agricultural University Wuhan China School of Computing Mathematics & Engineering Charles Sturt University Wagga Wagga NSW Australia Artificial Intelligence & Cyber Futures Institute Charles Sturt University Bathurst NSW Australia Faculty of Engineering University of Mines and Technology Tarkwa Ghana School of Mathematics and Computer Science Xinyu University China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Drug-target interaction (DTI) prediction is crucial for drug development and repositioning. Methods using heterogeneous graph neural networks (HGNNs) for DTI prediction have become a promising approach, with attention-based models often achieving excellent performance. However, these methods typically overlook edge features when dealing with heterogeneous biomedical networks. We propose a heterogeneous network-based contrastive learning method called HNCL-DTI, which designs a heterogeneous graph attention network to predict potential/novel DTIs. Specifically, our HNCL-DTI utilizes contrastive learning to collaboratively learn node representations from the perspective of both node-based and edge-based attention within the heterogeneous structure of biomedical networks. Experimental results show that HNCL-DTI outperforms existing advanced baseline methods on benchmark datasets, demonstrating strong predictive ability and practical effectiveness. The data and source code are available at https://***/Zaiwen/HNCL-DTI.

关键词： Drugs Attention mechanisms Source coding Biological system modeling Contrastive learning Benchmark testing Predictive models Graph neural networks Bioinformatics Diffusion tensor imaging

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：