检索结果-内蒙古大学图书馆

Integrating a Sequential Model Into GNN-Based Social Recommendation for Relieving Over-Smoothing Problem

IEEE Access 2025年 13卷 100219-100233页

作者： Janekhwan Kitsupapaisan Saranya Maneeroj Atsuhiro Takasu Department of Mathematics and Computer Science Faculty of Science Advanced Virtual and Intelligent Computing Center Chulalongkorn University Bangkok Thailand National Institute of Informatics Tokyo Japan

In recent years, social recommendation systems have increasingly integrated Graph Neural Networks (GNNs) to capture social relationships among users from both direct and higher-order neighbors. However, these state-of-the-art models face limitations regarding the number of iterations they can propagate across the graph. Messages from higher-order neighbors often dilute the unique characteristics of the target node. This causes node representations to become similar and indistinguishable, leading to a phenomenon known as the over-smoothing problem. Several works have attempted to address this problem with the expectation of preserving user characteristics. They add auxiliary information to the GNN-based social recommendation models without considering the dynamic preferences of users, which frequently change over time. Therefore, those works still struggle with the same problem after propagating in a few iterations. To mitigate this phenomenon, we propose a novel approach to integrate user characteristics extracted from users’ historical interactions using a sequential model to slow down node convergence. Integrating user characteristics into the GNN-based social recommendation will allow the model to capture user preferences that dynamically change over time. Consequently, the proposed model will be able to leverage informative data from higher-order neighbors over social networks for user representation learning, leading to better performance and effectiveness of the recommendations. Our experimental results demonstrate that the proposed model outperforms state-of-the-art social recommendation models across three benchmark datasets.

关键词： Representation learning Graph neural networks Social networking (online) Convergence Redundancy Recommender systems Diffusion processes Smoothing methods Nickel Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Hybrid cloud storage system with enhanced multilayer cryptosystem for secure deduplication in cloud

引用

International Journal of Intelligent Networks 2023年第1期4卷 301-309页

作者： Mageshkumar, Nagappan Swapna, J. Pandiaraj, A. Rajakumar, R. Krichen, Moez Ravi, Vinayakumar Department of Computer Science and Technology Madanapalle Institute of Technology and Science Madanapalle India Department of Computer Science & Engineering Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Computing Technology SRM Institute of Science and Technology Kattankulathur chennai India Al-Baha University Alaqiq 65779-7738 Saudi Arabia ReDCAD Laboratory University of Sfax Sfax3038 Tunisia Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar34754 Saudi Arabia Centre for Automation School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai India

Data deduplication is a crucial technique in the field of data compression that aims to eliminate redundant copies of recurring data. This technique has gained significant popularity in the realm of cloud storage due to its ability to effectively reduce storage requirements and optimize bandwidth utilization. To ensure the safeguarding of sensitive data while simultaneously facilitating deduplication, researchers have put forth the concept of convergent encryption as a potential solution. This technique involves encrypting the data prior to its outsourcing, thereby enhancing the confidentiality of the information. In this work, an earnest endeavor is undertaken to formally tackle the issue of authorized data deduplication, with the aim of enhancing data security. Our approach combines the Diffie-Hellman algorithm and symmetrical external decision to protect and popularize information, ensuring end-to-end encryption to encourage user adoption of cloud storage. The proposed model employs block-level deduplication and guarantees the randomness of ciphertexts by generating encryption keys using the Diffie-Hellman algorithm. This method effectively counters both internal and external brute-force attacks, enhancing data security while reducing computational costs. An extensive experimentation is carried out to demonstrate that our approach is particularly beneficial in scenarios with multiple privilege sets. Overall, the proposed model offers an elaborate framework that maintains data privacy and strengthens security measures, contributing to a more efficient and secure cloud-based document search. © 2023 The Author(s)

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

3L-AODV: Three Layer Security Protocol for Grayhole Attack Mitigation in MANET 8th

3L-AODV: Three Layer Security Protocol for Grayhole Attack ...

引用

8th International Congress on Information and Communication Technology, ICICT 2023

作者： Kamel, Mohammed B. M. Abdullah, Wisam Dawood Hamoud, Alaa Khalaf Valadares, Dalton C. G. Shareiyat, Ammar Ligeti, Peter Department of Computer Algebra Eotvos Lorand University Budapest Hungary Institute for Data Science Cloud Computing and IT Security Furtwangen University of Applied Sciences Furtwangen im Schwarzwald Germany Department of Computer Science University of Kufa Najaf Iraq Department of Computer Science University of Tikrit Tikrit Iraq Department of Computer Information Systems University of Basrah Basrah Iraq Virtus RDI Center Federal University of Campina Grande Campina Grande Brazil Federal Institute of Pernambuco Pernambuco Caruaru Brazil Department of CSS University of Stockholm Stockholm Sweden Department of Vulnerability Operations Center Orange Cyberdefense Stockholm Sweden

ISBN: (纸本)9789819930425

As the mobile ad hoc networks infrastructure has no centralized points of connections, the traffic from a source to a destination passes through number of intermediate nodes. When more than one neighbor node is available, the traffic passes through one of them based on some criteria. If a node behaves maliciously in all of the connections and drops the traffic, it creates a security blackhole, while a malicious node that behaves normally is some of the connections creates a security grayhole. Since the malicious node behaves normally in some connections, mitigating this attack is challenging. In this paper, we proposed 3L-AODV, a security protocol that uses three layers of protection and detection to mitigate the grayhole attack. As it does not require any modification on the AODV protocol, it can be implemented on any network that its routing is based on AODV. The analysis of our results shows that 3L-AODV could mitigate the grayhole attack without affecting the performance of the network. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Portability and Scalability of OpenMP Offloading on State-of-the-Art Accelerators 38th

Portability and Scalability of OpenMP Offloading on State...

引用

38th International Conference on High Performance computing, ISC High Performance 2023

作者： Fridman, Yehonatan Tamir, Guy Oren, Gal Department of Computer Science Ben-Gurion University of the Negev Be’er Sheva Israel Department of Physics Nuclear Research Center - Negev Be’er Sheva Israel Scientific Computing Center Nuclear Research Center - Negev Be’er Sheva Israel Intel Corporation Santa Clara United States Department of Computer Science Technion - Israel Institute of Technology Haifa Israel

ISBN: (纸本)9783031408427

Over the last decade, most of the increase in computing power has been gained by advances in accelerated many-core architectures, mainly in the form of GPGPUs. While accelerators achieve phenomenal performances in various computing tasks, their utilization requires code adaptations and transformations. Thus, OpenMP, the most common standard for multi-threading in scientific computing applications, introduced offloading capabilities between host (CPUs) and accelerators since v4.0, with increasing support in the successive v4.5, v5.0, v5.1, and the latest v5.2 versions. Recently, two state-of-the-art GPUs – the Intel Ponte Vecchio Max 1100 and the NVIDIA A100 GPUs – were released to the market, with the oneAPI and NVHPC compilers for offloading, correspondingly. In this work, we present early performance results of OpenMP offloading capabilities to these devices while specifically analyzing the portability of advanced directives (using SOLLVE’s OMPVV test suite) and the scalability of the hardware in representative scientific mini-app (the LULESH benchmark). Our results show that the coverage for version 4.5 is nearly complete in both latest NVHPC and oneAPI tools. However, we observed a lack of support in versions 5.0, 5.1, and 5.2, which is particularly noticeable when using NVHPC. From the performance perspective, we found that the PVC1100 and A100 are relatively comparable on the LULESH benchmark. While the A100 is slightly better due to faster memory bandwidth, the PVC1100 reaches the next problem size (4003 ) scalably due to the larger memory size. The results are available at: https://***/Scientific-computing-Lab-NRCN/Accel-OpenMP-Portability-Scalability. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Learning to Rank Patches for Unbiased Image Redundancy Reduction

Learning to Rank Patches for Unbiased Image Redundancy Reduc...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yang Luo Zhineng Chen Peng Zhou Zuxuan Wu Xieping Gao Yu-Gang Jiang Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Fudan University University of Maryland College of Information Science and Engineering Hunan Normal University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods rely on supervisory signals. They may compel models to preserve content that aligns with labeled categories and discard content belonging to unlabeled categories. This categorical inductive bias makes these methods less effective in real-world scenarios. To address this issue, we propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches (LTRP). We observe that image reconstruction of masked image modeling models is sensitive to the removal of visible patches when the masking ratio is high (e.g., 90%). Building upon it, we implement LTRP via two steps: inferring the semantic density score of each patch by quantifying variation between reconstructions with and without this patch, and learning to rank the patches with the pseudo score. The entire process is self-supervised, thus getting out of the dilemma of categorical inductive bias. We design extensive experiments on different datasets and tasks. The results demonstrate that LTRP outperforms both supervised and other self-supervised methods due to the fair assessment of image content. Code is available at https://***/irsLu/1trp.

关键词： visualization Accuracy Semantic segmentation Redundancy Semantics Self-supervised learning Object detection

来源：评论

学校读者我要写书评

暂无评论

Hyper Elliptic Curve Based Certificateless Signcryption Scheme for Secure IIoT Communications

引用

computers, Materials & Continua 2022年第5期71卷 2515-2532页

作者： Usman Ali Mohd Yamani Idna Idris Jaroslav Frnda Mohamad Nizam Bin Ayub Roobaea Alroobaea Fahad Almansour Nura Modi Shagari Insaf Ullah Ihsan Ali Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala Lumpur50603Malaysia Department of Computer Science University of SwatSaidu Sharif19130Pakistan Center for Research in Mobile Cloud Computing University of MalayaKuala Lumpur50603Malaysia Department of Quantitative Methods and Economic Informatics Faculty of Operation and Economics of Transport and CommunicationsUniversity of Zilina01026 ZilinaSlovakia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science College of Sciences and Arts in RassQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science Hamdard Institute of Engineering and TechnologyIslamabad44000Pakistan

Industrial internet of things (IIoT) is the usage of internet of things(IoT) devices and applications for the purpose of sensing, processing andcommunicating real-time events in the industrial system to reduce the unnecessary operational cost and enhance manufacturing and other industrial-relatedprocesses to attain more profits. However, such IoT based smart industriesneed internet connectivity and interoperability which makes them susceptibleto numerous cyber-attacks due to the scarcity of computational resourcesof IoT devices and communication over insecure wireless channels. Therefore, this necessitates the design of an efficient security mechanism for IIoTenvironment. In this paper, we propose a hyperelliptic curve cryptography(HECC) based IIoT Certificateless Signcryption (IIoT-CS) scheme, with theaim of improving security while lowering computational and communicationoverhead in IIoT environment. HECC with 80-bit smaller key and parameterssizes offers similar security as elliptic curve cryptography (ECC) with 160-bitlong key and parameters sizes. We assessed the IIoT-CS scheme security byapplying formal and informal security evaluation techniques. We used Realor Random (RoR) model and the widely used automated validation of internet security protocols and applications (AVISPA) simulation tool for formalsecurity analysis and proved that the IIoT-CS scheme provides resistance tovarious attacks. Our proposed IIoT-CS scheme is relatively less expensivecompared to the current state-of-the-art in terms of computational cost andcommunication overhead. Furthermore, the IIoT-CS scheme is 31.25% and 51.31% more efficient in computational cost and communication overhead,respectively, compared to the most recent protocol.

关键词： IoT security authentication protocols hyperelliptic curve cryptography certificateless public key cryptography

来源：评论

学校读者我要写书评

暂无评论

CloudyFL: A Cloudlet-Based Federated Learning Framework for Sensing User Behavior Using Wearable Devices 6

CloudyFL: A Cloudlet-Based Federated Learning Framework for ...

引用

6th International Workshop on Embedded and Mobile Deep Learning, EMDL 2022 - Part of MobiSys 2022

作者： Gong, Qingyuan Ruan, Hui Chen, Yang Su, Xiang School of Computer Science Fudan University China BirenTech Research China Department of Computer Science Norwegian University of Science and Technology Norway Center for Ubiquitous Computing University of Oulu Finland

ISBN: (纸本)9781450394048

Wearable devices have been widely utilized by the general public for tracking physical activities. Many complex machine learning models leverage wearable devices to address application problems, such as predicting pedestrian behaviors and health management. These models often incur heavy computing load and energy cost, which is challenging for wearable devices. However, aggregating the data from different wearable devices to a central server introduces privacy concerns. To address these challenges, we propose an architecture, CloudyFL, by deploying cloudlets close to wearable devices. In CloudyFL, each cloudlet forms a trusted zone covering a subset of nearby wearable devices. Models are trained in this trusted zone, and then, only the model parameters are transmitted to a centralized aggregator using a federated learning framework. We additionally propose an LSTM-based model for user behavior sensing, with a neural network design to adjust to the non-IID data distribution on multiple cloudlets. Experimental results show that our training model within the CloudyFL architecture can achieve a performance better than existing methodologies. © 2022 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Towards Context-aware Support for Color Vision Deficiency: An Approach Integrating LLM and AR 13

Towards Context-aware Support for Color Vision Deficiency: A...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Morita, Shogo Zhang, Yan Yamauchi, Takuto Chen, Sinan Li, Jialong Tei, Kenji Tokyo Institute of Technology School of Computing Tokyo Japan University of Tokyo International Research Center for Neurointelligence Tokyo Japan Waseda University Department of Computer Science and Engineering Tokyo Japan Kobe University Center of Mathematical and Data Sciences Kobe Japan

ISBN: (纸本)9798350355079

People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly focus on presentation-based aids, like the color vision modes found in iPhone accessibility settings. However, offering context-aware support, like indicating the doneness of meat, remains a challenge since task-specific solutions are not cost-effective for all possible scenarios. To address this, our paper proposes an application that provides contextual and autonomous assistance. This application is mainly composed of: (i) an augmented reality interface that efficiently captures context;and (ii) a multi-modal large language model-based reasoner that serves to cognitize the context and then reason about the appropriate support contents. Preliminary user experiments with two color vision deficient users across five different scenarios have demonstrated the effectiveness and universality of our application. © 2024 IEEE.

关键词： Color vision

来源：评论

学校读者我要写书评

暂无评论

Data and Ensemble Machine Learning Fusion Based Intelligent Software Defect Prediction System

引用

computers, Materials & Continua 2023年第6期75卷 6083-6100页

作者： Sagheer Abbas Shabib Aftab Muhammad Adnan Khan Taher MGhazal Hussam Al Hamadi Chan Yeob Yeun School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Software Faculty of Artificial Intelligence and SoftwareGachon UniversitySeongnam13120Korea Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan School of Information Technology Skyline University CollegeUniversity City SharjahSharjahUAE Center for Cyber Security Faculty of Information Science and TechnologyUKMBangiSelangor43600Malaysia College of Engineering and IT University of Dubai14143UAE EECS Department Center for Cyber Physical SystemsKhalifa UniversityAbu Dhabi127788UAE

The software engineering field has long focused on creating high-quality software despite limited *** defects before the testing stage of software development can enable quality assurance engineers to con-centrate on problematic modules rather than all the *** approach can enhance the quality of the final product while lowering development *** defective modules early on can allow for early corrections and ensure the timely delivery of a high-quality product that satisfies customers and instills greater confidence in the development *** process is known as software defect prediction,and it can improve end-product quality while reducing the cost of testing and *** study proposes a software defect prediction system that utilizes data fusion,feature selection,and ensemble machine learning fusion techniques.A novel filter-based metric selection technique is proposed in the framework to select the optimum features.A three-step nested approach is presented for predicting defective modules to achieve high *** the first step,three supervised machine learning techniques,including Decision Tree,Support Vector Machines,and Naïve Bayes,are used to detect faulty *** second step involves integrating the predictive accuracy of these classification techniques through three ensemble machine-learning methods:Bagging,Voting,and ***,in the third step,a fuzzy logic technique is employed to integrate the predictive accuracy of the ensemble machine learning *** experiments are performed on a fused software defect dataset to ensure that the developed fused ensemble model can perform effectively on diverse *** NASA datasets are integrated to create the fused dataset:MW1,PC1,PC3,PC4,and *** to the results,the proposed system exhibited superior performance to other advanced techniques for predicting software defects,achieving a remarkable accuracy rate of 92.08%.

关键词： Ensemble machine learning fusion software defect prediction fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

AS-Det: Active Sampling for Adaptive 3D Object Detection in Point Clouds 39

AS-Det: Active Sampling for Adaptive 3D Object Detection in ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ding, Ziheng Zhang, Xiaze Jing, Qi Cheng, Ying Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)157735897X

3D object detection in point clouds is critical in 3D computer vision, autonomous driving, and robotics. Existing point-based detectors, tailored to handle unstructured raw point clouds, often rely on simplistic sampling strategies to select a subset of points for local representation learning and detection. However, the diverse patterns exhibited by multiple types of point cloud data present a significant challenge to the universality of current detectors, particularly those captured by varied sensors (e.g., LiDAR and 4D Imaging Radar). In response to this challenge, we introduce an adaptable point-based single-stage 3D detector, AS-Det, engineered to excel on both LiDAR and 4D Radar point clouds. Specifically, we propose a novel active sampling strategy that actively mines object-related information to achieve efficient sampling and representation across different types of point clouds through end-to-end training. Additionally, we introduce a lightweight multi-scale center feature aggregation module to exploit multi-scale object context for precise and low-cost detection. By integrating the abovementioned modules, AS-Det achieves highly adaptive detection on various point clouds, encompassing different sensors and scales. Experimental results demonstrate the superior performance and adaptability of AS-Det on both LiDAR and 4D Radar point clouds. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Object detection

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：