检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Wan, Guancheng Tian, Yijun Huang, Wenke Chawla, Nitesh V. Ye, Mang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Department of Computer Science University of Notre Dame United States Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

Graph Contrastive Learning (GCL) has emerged as a highly effective self-supervised approach in graph representation learning. However, prevailing GCL methods confront two primary challenges: 1) They predominantly operate under homophily assumptions, focusing on low-frequency signals in node features while neglecting heterophilic edges that connect nodes with dissimilar features. 2) Their reliance on neighborhood aggregation for inference leads to scalability challenges and hinders deployment in real-time applications. In this paper, we introduce S3GCL, an innovative framework designed to tackle these challenges. Inspired by spectral GNNs, we initially demonstrate the correlation between frequency and homophily levels. Then, we propose a novel cosine-parameterized Chebyshev polynomial as low/high-pass filters to generate biased graph views. To resolve the inference dilemma, we incorporate an MLP encoder and enhance its awareness of graph context by introducing structurally and semantically neighboring nodes as positive pairs in the spatial domain. Finally, we formulate a cross-pass GCL objective between full-pass MLP and biased-pass GNN filtered features, eliminating the need for augmentation. Extensive experiments on real-world tasks validate S3GCL proficiency in generalization to diverse homophily levels and its superior inference efficiency. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

EMARec: a sequential recommendation with exponential moving average

引用

Neural Computing and Applications 2024年第21期36卷 12917-12933页

作者： Chen, Rui Wang, Zonglin Tang, Cundong Zhang, Jianwei Li, Pu Kong, Xiangjie Huang, Min College of Software Engineering Zhengzhou University of Light Industry Zhengzhou450001 China Henan Joint International Research Laboratory of Computer Animation Implementation Technologies Zhengzhou450001 China School of Information Science and Technology Northwest University Xi’an710127 China Faculty of Information and Engineering Xuchang Vocational Technical College Xuchang461000 China College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China

Capturing dynamic preference features from user historical behavioral data is widely applied to improve the accuracy of recommendations in sequential recommendation tasks. However, existing deep neural network-based sequential recommendation methods often ignore the noise information in user behavioral data that influence recommendation effectiveness, making recommendation models sensitive to noisy data. Additionally, these deep learning-based recommendation models often require a large number of parameters to capture user behavior patterns, leading to higher time complexity and susceptibility to overfitting due to noise fluctuations. To address these issues, in this paper, we apply the moving average concept from the field of time-series analysis to sequential recommendation tasks. The approach smooths sequence data, removes noise, making the data more stable and reliable, increases the model’s insensitivity to noise information, and better understands the evolution of user interests and behavioral patterns. Specifically, in our experiments, the moving average algorithm effectively denoises sequential data with low time complexity. Therefore, we propose a Sequential Recommendation with Exponential Moving Average with MLP architecture that makes the model more competitive in terms of time complexity. Experimental results conducted on two datasets demonstrate that EMARec outperforms state-of-the-art sequential recommendation methods across various common evaluation metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

IoT Based Drip Infusion Monitoring System

IoT Based Drip Infusion Monitoring System

引用

2022 IEEE Delhi Section Conference, DELCON 2022

作者： Maniktalia, Riddhi Tanwar, Satwik Billa, Ritvik Deepa, K. School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Department of Software Systems Vellore India

ISBN: (纸本)9781665458832

During recent years, we have seen many technological advancements which help to take better care of patient's health and assure them fast and safe recovery. The most basic item necessary is competent patient care in hospitals, as well as proper management of fluid and electrolytes. In hospital almost all patients, mainly ICU patients, have to regulate the volume of fluids and electrolyte into the bloodstream 247 which is done using drip. These drips need regular monitoring or changing to maintain constant flow of fluids or to prevent any infection to patients. Though this system is simple, overcrowded hospitals and the risk of deficiency of nurses can put patients at health risk which can deteriorate patients' health more aggressively or in worse case it can lead to death. Almost in all hospitals, nurses or the hospital staff are responsible for monitoring the drip level. But unfortunately, because of their hectic schedule, the observer may forget to change the bottle at the appropriate time. During the pandemic, hospitals were overrun with patients, and nurses were unable to do manual regular checks on the drip conditions and drip level of every patient, even after working extra shifts. Many patients even died due to not being able to get proper care from nurses. The next step in providing more effective and easy healthcare is to automate such vital procedures. To overcome this critical situation, we are proposing an IoT (Internet of Things) based Drip Monitor System using Arduino UNO which eases the process of measuring and solves the issues of bubble formation in drips. © 2022 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

The Open Source Threat Intelligence Relational Dataset and Its Optimal Implementation

The Open Source Threat Intelligence Relational Dataset and I...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Yang, Yaru Li, Junyu Zhang, Ronghua Sah, Abhishek Pratap Yadav, Amit Khan, Asif Chengdu Neusoft University Department of Computer and Software Chengdu China University of Electronic Science and Technology of China School of Management Science and Engineering Chengdu China Charles Darwin University College of Engineering IT and Environment NT Australia Integral University Department of Computer Application Lucknow India

ISBN: (纸本)9798350361537

Threat intelligence provides a platform for cybersecurity engineers for attack traceability, which provides substantial knowledge database logs to defend against future security threats. Threat intelligence relationship extraction based on deep learning solves the challenge of threat knowledge construction to a certain extent but still faces problems such as lack of open-source datasets and the inability of the model to accurately correlate threat entities with potential relationships. Therefore, for cybersecurity research work, this paper designs a threat ontology, constructs the threat relationship dataset TreatRE by remote supervision, and opens this dataset. The dataset contains 12000 utterances and 12 threat relations from 500 CTIs, and it performs well in multiple relation models trained on deep learning methods. Meanwhile, we propose a multisensory attention-based threat intelligence relationship extraction method MAtt, which combines location perception, self-attention perception, and neuronal memory perception to further improve the threat relationship extraction effect. Experimental results show that the trained model based on TreatRE can more accurately extract the knowledge objects and their relationships described in threat intelligence. An accuracy score of 95.4% can be obtained using the MAtt method, which is 3.48% more than the best baseline compared with the same type of relationship extraction model. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Research on Improved Quick Sort Algorithm with Duplicate Value Handling 8

Research on Improved Quick Sort Algorithm with Duplicate Val...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Hemin Yadav, Amit Khan, Asif Sah, Abhishek Pratap Chengdu Neusoft University College of Computer and Software Chengdu China Charles Darwin University College of Engineering It and Environment NT Australia Integral University Department of Computer Application Lucknow India University of Electronic Science and Technology of China School of Management Science and Engineering Chengdu China

ISBN: (纸本)9798350376425

An improved algorithm based on Quick Sort algorithm research method is proposed to deal with prevailing duplicate values in the sorting of data. The duplicate values are specially processed, which effectively reduces the number of division and greatly reduces the number of recursions. The experimental results show that the time efficiency is improved by more than 50% when dealing with large data than the traditional Quick Sort algorithm without reducing the space efficiency. © 2024 IEEE.

关键词： Duplicate Value Quick Sort Recursion

来源：评论

学校读者我要写书评

暂无评论

Graph-in-Graph Convolutional Network for Hyperspectral Image Classification

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第1期35卷 1157-1171页

作者： Jia, Sen Jiang, Shuguo Zhang, Shuyu Xu, Meng Jia, Xiuping College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Key Laboratory for Geo-Environmental Monitoring of Coastal Zone Shenzhen University Ministry of Natural Resources Shenzhen518060 China School of Engineering and Information Technology University of New South Wales CanberraACT 2612 Australia

With the development of hyperspectral sensors, accessible hyperspectral images (HSIs) are increasing, and pixel-oriented classification has attracted much attention. Recently, graph convolutional networks (GCNs) have been proposed to process graph-structured data in non-Euclidean domains and have been employed in HSI classification. But most methods based on GCN are hard to sufficiently exploit information of ground objects due to feature aggregation. To solve this issue, in this article, we proposed a graph-in-graph (GiG) model and a related GiG convolutional network (GiGCN) for HSI classification from a superpixel viewpoint. The GiG representation covers information inside and outside superpixels, respectively, corresponding to the local and global characteristics of ground objects. Concretely, after segmenting HSI into disjoint superpixels, each one is converted to an internal graph. Meanwhile, an external graph is constructed according to the spatial adjacent relationships among superpixels. Significantly, each node in the external graph embeds a corresponding internal graph, forming the so-called GiG structure. Then, GiGCN composed of internal and External graph convolution (EGC) is designed to extract hierarchical features and integrate them into multiple scales, improving the discriminability of GiGCN. Ensemble learning is incorporated to further boost the robustness of GiGCN. It is worth noting that we are the first to propose the GiG framework from the superpixel point and the GiGCN scheme for HSI classification. Experiment results on four benchmark datasets demonstrate that our proposed method is effective and feasible for HSI classification with limited labeled samples. For study replication, the code developed for this study is available at https://***/ShuGuoJ/***. © 2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Short Review of Truck and Drone Collaborative Delivery Problem 10

A Short Review of Truck and Drone Collaborative Delivery Pro...

引用

10th IEEE International Conference on Cyber Security and Cloud Computing and 9th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Zhu, Yena Liu, Min Jin, Dongyao Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China Hunan Key Laboratory for Service computing and Novel Software Technology Xiangtan China

ISBN: (纸本)9798350312461

With the emergence of efficient logistics models and the development of drone technology, the last-mile delivery problem has become a focus of attention for scholars in various fields. The advantages of drones, such as low cost, energy saving, and independence from road conditions, have made them increasingly popular in the delivery industry. However, drones have shortcomings such as short endurance, small payload capacity, and susceptibility to interference. Therefore, the cooperative delivery model of vehicles and drones has important theoretical research significance and practical application value. Existing literature reviews focus on static truck-drone delivery problems (TDDPs) and methods such as exact algorithms, heuristics, and metaheuristics. However, real-life truck-drone delivery problems are easily affected by dynamic environmental changes. Accordingly, this article introduces some new dynamic variants of TDDPs proposed in recent years, which consider variable drone flight endurance, urban crowded road conditions, stochastic customer demands, and the influence of weather changes. In recent years, some new methods for solving TDDPs have been introduced, such as the increasingly popular machine learning and reinforcement learning methods. Finally, the possible future research directions and development trends of TDDPs are presented. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Soft Hand and Wrist Rehabilitation Robot Utilizing Lattice Structure Actuators

Development of a Soft Hand and Wrist Rehabilitation Robot Ut...

引用

2024 International Convention on Rehabilitation engineering and Assistive Technology and World Rehabilitation Robot Convention, i-CREATE and WRRC 2024

作者： Lai, Jianwei Song, Aiguo Zhang, Wenbin Lu, Ye Wang, Jiajin Li, Ye School of Instrument Science and Engineering Southeast University State Key Laboratory of Digital Medical Engineering Jiangsu Key Laboratory of Remote Measurement and Control Nanjing210096 China College of Computer Science and Software Engineering Hohai University Nanjing210024 China

ISBN: (纸本)9798350355123

Soft robots offer promising solutions for rehabilitation due to their inherent attributes such as suppleness, lightweight construction, and safety features. However, prevalent soft actuators face limitations in output force and bending angle, impeding their effective application in rehabilitation. This paper proposes a novel design approach employing a two-layer lattice structure actuator, comprising flexion, guiding, and extension layers. This innovative design facilitates supple and efficient bi-directional rehabilitation training for fingers and wrists. Experimental results demonstrate the efficacy of the proposed dual-layer lattice structure actuator. At an air pressure of 150 kPa, it achieves an end force of 14.88 N, marking a remarkable 906% increase compared to its single-layer counterpart. Additionally, the dual-layer structure exhibits a minimum bending radius of 2.77 cm under 60 kPa, representing a 38.5% reduction relative to the single-layer actuator. Leveraging these actuators, a hand and wrist rehabilitation robot was developed and subjected to a clinical trial involving two healthy subjects. The trial outcomes reveal significant improvements in finger grasping ability and wrist range of motion with the assistance of the rehabilitation robot. These results underscore the practical usability and effectiveness of the soft hand and wrist rehabilitation robot, thereby holding promise for enhancing patient rehabilitation outcomes. © 2024 IEEE.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

A CTR Prediction Model Based on Attention Mechanism and Logarithmic Transformation 2

A CTR Prediction Model Based on Attention Mechanism and Loga...

引用

2nd International Conference on Digital Signal and computer Communications, DSCC 2022

作者： Meng, Lu Shi, Tian-Wei Chang, Guang-Ming Qiang, Jiao-Feng Cui, Wen-Hua School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China

ISBN: (纸本)9781510656734

To address the problems of inadequate feature interaction and lack of targeting in feature combination in the click-through rate prediction model. We propose a click-through prediction model called SELFM. It based on attention mechanism and logarithmic transformation structure. The model first incorporates the attention mechanism in the feature embedding stage to distinguish the importance of different features and avoids the effects of invalid features. Then the field-aware factorization machine is used to learn low-order feature interactions. The logarithmic transformation structure is used to convert the power of each feature in the feature combination into the coefficients to be learned and combined with the hidden layer for higher-order nonlinear feature interactions. The final output layer is processed with the Sigmoid function to get the click-through rate prediction results. The experimental results show that the AUC and Logloss of this paper's model are better than the existing click-through rate prediction models, which effectively improves the prediction accuracy and enhances the ability of the recommendation system to process data. © 2022 SPIE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on NetPad Teaching Mode Based on ARCS Motivational Model 17th

Research on NetPad Teaching Mode Based on ARCS Motivational ...

引用

17th International Conference on computer science and Education, ICCSE 2022

作者： Zhang, Jing Gao, Jinghui Lei, Siran Chen, Ruxian Li, Ya Rao, Yongsheng Institute of Computing Science and Technology Guangzhou University Guangzhou China Software Engineering Institute of Guangzhou Guangzhou China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

ISBN: (纸本)9789819924455

Stimulating and maintaining students’ learning motivation is the key to fully mobilizing the enthusiasm of students’ active participation and realizing the unity of students’ learning and teachers’ teaching. The ARCS motivational model is an instructional design model proposed by Professor Keller that focuses on motivating and sustaining students’ learning motivation. Additionally, NetPad is a web-based dynamic mathematics software with powerful functions and user-friendly interface, it can be organically integrated with teaching, enrich the teaching style, and strengthen students’ learning motivation. In this paper, we propose the NetPad motivational teaching mode based on the ARCS model and NetPad. This mode consists of four procedures: interesting cases introduction, detailed cases explanation, group inquiry, and mutual evaluation and sharing. Each procedure is progressive and complementary, reflecting the hierarchy of motivational teaching from shallow to deep and the synergy of motivation stimulating and maintaining. The teaching practice under the guidance of this mode has verified its effectiveness. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motivation

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：