检索结果-内蒙古大学图书馆

Flexible Memory Rotation (FMR): Rotated Representation with Dynamic Regularization to Overcome Catastrophic Forgetting in Continual Knowledge Graph Learning

Flexible Memory Rotation (FMR): Rotated Representation with ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Zhu, Lijing Jeon, Dong Hyun Sun, Wenbo Yang, Li Xie, Yixin Niu, Shuteng Bowling Green State University Computer Science Department Bowling Green United States University of Michigan Transportation Research Institute Ann Arbor United States University of North Carolina at Charlotte Computer Science Department Charlotte United States Kennesaw State University College of Computing and Software Engineering Marietta United States

ISBN: (纸本)9798350362480

As a special type of Knowledge Graph (KG), Continual Knowledge Graph Learning (CKGL) plays a pivotal role in various areas such as recommendation systems, search engines, and personalized services, where knowledge dynamically evolves. A challenging problem in CKGL is catastrophic forgetting, where models forget previously learned knowledge upon being trained on new data. To overcome the challenge, this study proposes Flexible Memory Rotation (FMR), a dual-level regularization technique that focuses on both parameter level and structural level. Our idea is inspired by the natural human learning process, which tends to memorize correctly learned knowledge, leverage the learned to acquire new knowledge, and refine incorrectly learned knowledge with newly obtained information. Commonly, existing regularization-based methods fail to mimic this human nature by having a fixed constraint strategy for all model parameters. To this end, the proposed FMR offers flexible constraints based on qualities of learned knowledge evaluated by the Fisher Information Matrix (FIM). Additionally, we identified a limitation of FIM in CKGL, which is the assumption of independence of time steps does not always hold. To overcome this, FMR rotates the parameter space to diagonalize the FIM. This work has four major contributions: 1) develop a novel regularization technique, FMR, a flexible regularization technique, 2) reveal the unexpected failure of FIM in CKGL and provides an easy remedy via parameter space rotation, 3) the comparison experiments on four benchmark datasets designed for CKGL demonstrates improvement over various state-of-the-art (SOTA) CKGL models, and 4) a comprehensive ablation study investigates each component of the proposed model. The source code is available at https://***/lijingzhu1/FMR. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deep Reinforcement Learning-based Resource Management for Complex Decision Making in Industry Internet of Things Applications 4

Adaptive Deep Reinforcement Learning-based Resource Manageme...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Karne, Niharika Ramagundam, Chandra Shekar Patnala, Ranga Rao Ramagundam, Shashishekhar Tadiboina, Sai Nitisha Sr. Principal Systems Engineer in C&RS Platform Services University of South Alabama Department of Electrical Engineering Masters in Electrical Engineering Amtrak DT United States Software Engineer in Cloud Platform Services City of Philadelphia Pennsylvania United States Vice President Neuberger Berman United States Software Development & Engineering in Content Discovery & AI Troy University Department of Computer Science Masters in Computer Science AL Comcast Montgomery Campus United States Department of Information Technology GEICO - Chevy Chase Chevy ChaseMD20815 United States

An independent industrial system may transform into a connected network through the assistance of Industrial Internet of Things (IIoT). The deployed sensors in the IIoT maintain surveillance of the industrial machinery and equipment. As a result, safety and reliability emerge as the primary concerns in IIoT. This presents a variety of well-known and increasing issues related to the industrial system. The IIoT devices are exposed to a wide range of malware, threats, and assaults. To prevent the IIoT devices from malware effects, effective protection plans must be implemented. But adequate security mechanisms are not be incorporated in IIoT devices with limited resources. It is essential to ensure the accuracy and dependability of information gathered by IIoT devices. Decisions taken with incomplete or inaccurate data might be devastating. To overcome these difficulties deep learning with reinforcement learning for complex decision-making in industry applications is developed in this research work. In this developed model, an Adaptive Deep Reinforcement learning (ADRL)-based resource management is performed to reduce the operation cost associated with IIoT deployments. Energy efficiency is essential in IIoT ecosystem, particularly for the devices that run on batteries. Through dynamic resource allocation based on workload needs and energy limits, ADRL-based resource management optimizes the usage of energy. The reliability of the designed model is enhanced by fine-tuning the parameters from DRL using the Ship Rescue Optimization (SRO) algorithm. Thus, ADRL-based resource management systems make real-time decisions based on current environmental conditions and system requirements. This helps the IIoT systems to react quickly to change demands and optimize resource allocation. Finally, the experimental analysis is performed to find the success rate of the developed resource management system via various metrics. Throughout the validation, the statistical analysis of the

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The 23andMe Data Breach: Analyzing Credential Stuffing Attacks, Security Vulnerabilities, and Mitigation Strategies

arXiv

引用

arXiv 2025年

作者： Holthouse, Ryan Owens, Serena Bhunia, Suman Department of Computer Science and Software Engineering Miami University OxfordOH45056 United States

In October 2023, 23andMe, a prominent provider of personal genetic testing, ancestry, and health information services, suffered a significant data breach orchestrated by a cybercriminal known as "Golem." Initially, approximately 14,000 user accounts were compromised by a credential smear attack, exploiting reused usernames and passwords from previous data leaks. However, due to the interconnected nature of 23andMe’s DNA Relatives and Family Tree features, the breach expanded exponentially, exposing sensitive personal and genetic data of approximately 5.5 million users and 1.4 million additional profiles. The attack highlights the increasing threat of credential stuffing, exacerbated by poor password hygiene and the absence of robust security measures such as multi-factor authentication (MFA) and rate limiting. In response, 23andMe mandated password resets, implemented email-based two-step verification, and advised users to update passwords across other services. This paper critically analyzes the attack methodology, its impact on users and the company, and explores potential mitigation strategies, including enhanced authentication protocols, proactive breach detection, and improved cybersecurity practices. The findings underscore the necessity of stronger user authentication measures and corporate responsibility in safeguarding sensitive genetic and personal data. © 2025, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Survey on Mobile Edge Computing Architectures for Deep Learning Models 13

A Survey on Mobile Edge Computing Architectures for Deep Lea...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Lee, Jaehwan Na, Woongsoo Kongju National University Department of Computer Science and Engineering Korea Republic of Kongju National University Department of Software Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

With the development of mobile devices and communication technology, the IoT paradigm has recently been gaining attention. Various sensors and high-speed communication technology are equipped by various mobile devices, making it possible to collect a large amount of environmental data. Accordingly, many attempts have been made to process data collected from mobile devices into deep learning models. Since mobile devices have relatively insufficient computing resources and battery constrains to directly execute large-scale deep learning models, these tasks are offloaded to a cloud computing platform instead. In addition, mobile edge computing (MEC) or fog computing architecture has been proposed in order for the heavy tasks to be processed in a nearby computing node, thereby address the latency limits of cloud computing architecture. The deep learning inferencing can be performed with low latency on the surrounding edge computing nodes by applying the MEC paradigm, however, finding the optimal offloading node selection has been challenging problem, which triggered various studies have been conducted. In this paper, communication technologies and edge computing architectures for offloading deep learning models are examined and comparatively analyzed. © 2022 IEEE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Systematic Analysis of Several Deep Learning Approaches for COVID-19 Detection Using X-ray Images 3

Systematic Analysis of Several Deep Learning Approaches for ...

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Shakil, Rashiduzzaman Akter, Bonna Javed Mehedi Shamrat, F.M. Jahan, Nusrat Hasan, Shakibe Khater, Ankit Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Daffodil International University Department of Software Engineering Dhaka Bangladesh Daffodil International University Department of Information Technology & Management Dhaka Bangladesh European University of Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh Jadavpur University Department of Computer Science and Engineering India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

COVID-19 is a virus-borne malady. A clinical study of infected COVID-19 patients found that most COVID-19 patients suffered lung infection after contracting the disease. Consequently, chest X-rays are a more effective and lower-cost imaging technique for diagnosing lung-related problems. This study used deep learning models, including MobileNetV2,DenseNet201, ResNet50, and VGG19, for COVID-19 prediction. For the study, we used chest X-ray image data for binary classification of COVID-19. 7207 chest X-ray image data were obtained from the Kaggle repository, with 5761 being utilized for training and 1446 being used for validation. A comparative analysis was conducted among the models and examined their accuracy. It has been determined that the DenseNet201 models achieved the highest accuracy of 93.02% for detecting COVID-19 in the lowest compilation time of 27secs. The models, MobileNetV2, ResNet50, and VGG19 had the accuracy rate of 77.28%, 65.86% and 74.92%, respectively. The research indicates that the DenseNet201 model is the most effective in detecting COVID-19 using x-ray imaging. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Contrastive Self-supervised EEG Representation Learning for Emotion Classification 46

Contrastive Self-supervised EEG Representation Learning for ...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Hu, Keya Dai, Ren-Jie Chen, Wen-Tao Yin, Hao-Long Lu, Bao-Liang Zheng, Wei-Long Tongji University School of Software Engineering China Shanghai Jiao Tong University Department of Computer Science and Engineering China Shanghai Jiao Tong University School of Medicine RuiJin-Mihoyo Laboratory Clinical Neuroscience Center RuiJin Hospital China

ISBN: (纸本)9798350371499

Self-supervised learning provides an effective approach to leverage a large amount of unlabeled data. Numerous previous studies have indicated that applying self-supervision to physiological signals can yield better representations of the signals. In the paper, we aim to apply this method to the crucial field of emotion recognition. We perform the experiment with several state-of-the-art contrastive self-supervised methods to explore their effectiveness in pre-training feature encoders on raw electroencephalography (EEG) signals and fine-tuning the pre-trained encoders on the downstream emotion classification tasks. We attempt to vary the proportion of labeled data used during fine-tuning and find that the improvement from self-supervised methods is more pronounced when the proportion of labeled data is small. Additionally, we explore the transferability of the feature encoders pre-trained on various datasets and observe that most self-supervised methods exhibit a certain degree of transferability. Methods that effectively utilize the temporal information in EEG signals show superior stability, accuracy, and transferability. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Risk Mitigation in Global software Development: Leveraging Agile Practices and Seven Risk Management Principles

Enhancing Risk Mitigation in Global Software Development: Le...

引用

International Conference on Communication Technologies (ComTech)

作者： Maria Javed Muhammad Haroon Alam Muhammad Sohail Fahim Arif Department of Computer Software Engineering MCS National University of Science and Technology (NUST) Islamabad Pakistan

ISBN: (数字)9798331515331

ISBN: (纸本)9798331515348

Management of geographically dispersed teams introduces several challenges, particularly the risk during the Global software Development (GSD) process. It impacts the aim of organizations of cost reduction, benefits of global talent, and rapid product development. Failure to identify and mitigate risks can cause delays in the development process, budget overruns, and compromised quality. In our research the RMMM (Risk Mitigation, Monitoring, and Management) framework was developed, combining seven core risk management principles with agile practices to improve risk handling and enhance team communication and collaboration. The framework focuses on identifying, analyzing, and mitigating risks while ensuring clear communication protocols, realistic project timelines, appropriate tools, and skilled team members. The framework is validated through expert feedback, after results and analysis, the proposed framework demonstrates a 66.7% comprehensive rate. Over 75% of industry specialists support its implementation, with more than 55% considering it feasible for GSD projects. This approach has proven effective in minimizing risks and ensuring successful project delivery in complex, distributed development environments.

关键词： Industries Protocols Costs Organizations software Product development Delays Monitoring software development management Risk mitigation

来源：评论

学校读者我要写书评

暂无评论

The Design of Continuous Surgical Robotic Arms with Variable Stiffness Material and Magnetic Guidance 5

The Design of Continuous Surgical Robotic Arms with Variable...

引用

5th International Conference on Signal Processing and Machine Learning, CONF SPML 2025

作者： Zhang, Yixin Department of Computer Science and Software Engineering Hebei University of Technology Hebei Langfang065000 China

ISBN: (纸本)9781837243235

In recent years, with the aging population and the increasing incidence of natural cavity diseases and cancer tumors, the demand for minimally invasive surgery has risen. This, in turn, requires robotic arms with greater flexibility and precision. However, traditional rigid surgical robotic arms make it difficult to meet these needs. This paper includes an illustration of the invention related to a continuous surgical robotic arm which is combined with magnetic guidance and a variable stiffness material. This paper aims to explore the advantages of continuum robots based on Phase Change Materials (PCMs) in surgical applications, especially through the stiffness adjustability of the material and the combination of magnetic materials to improve positioning accuracy. In this study, low-melting-point alloys were chosen as the variable stiffness material. This paper analyzed a flexible and precise surgical robotic arm by summarizing and combining previous experiments on the properties of low-melting alloys under different conditions and simulating magnetic navigation in complex environments. Through this design, the robots can enhance the safety, versatility and collaboration ability among the continuous robots, opening up new ways for endocavitary robotic surgery. © The Institution of engineering & Technology 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Fast Second-order Method for Neural Networks under Small Treewidth Setting

Fast Second-order Method for Neural Networks under Small Tre...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Li, Xiaoyu Long, Jiangxuan Song, Zhao Zhou, Tianyi Stevens Institute of Technology Department of Computer Science HobokenNJ United States South China University of Technology School of Software Engineering Guangzhou China University of California Berkeley The Simons Institute for the Theory of Computing BerkeleyCA United States University of Southern California Department of Computer Science Los AngelesCA United States

ISBN: (纸本)9798350362480

Training neural networks is a fundamental problem in theoretical machine learning. Second-order methods are rarely used in practice due to their high computational cost, even they converge much faster than first-order methods. The state-of-the-art result for the second-order method to train an over-parameterized neural network can run in O(log(1/ϵ)) iterations and each iteration has O(mnd + n3) running time, where n represent the number of data points, d is the dimension of the feature space of each data and m is the width of the neural network [Brand, Peng, Song and Weinstein ITCS 2021]. In this work, we further improve the convergence rate and the running time for each iteration to O(loglog(1/ϵ)) and O(mdτ2) respectively, where m = Ω(n4) and τ is the treewidth of the data matrix and usually very small. Our algorithm has a quadratic convergence rate, so it can be regarded as a truly second-order algorithm. To the best of our knowledge, our algorithm is the first to achieve a quadratic convergence rate for neural network training, with a per-iteration running time of O(mdτ2). © 2024 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence (XAI) from a user perspective: A synthesis of prior literature and problematizing avenues for future research

引用

Technological Forecasting and Social Change 2023年 186卷

作者： Haque, AKM Bahalul Islam, A.K.M. Najmul Mikalef, Patrick Department of Software Engineering LUT University Finland Department of Computer Science Norwegian University of Science and Technology Norway

The rapid growth and use of artificial intelligence (AI)-based systems have raised concerns regarding explainability. Recent studies have discussed the emerging demand for explainable AI (XAI);however, a systematic review of explainable artificial intelligence from an end user's perspective can provide a comprehensive understanding of the current situation and help close the research gap. The purpose of this study was to perform a systematic literature review of explainable AI from the end user's perspective and to synthesize the findings. To be precise, the objectives were to 1) identify the dimensions of end users' explanation needs;2) investigate the effect of explanation on end user's perceptions, and 3) identify the research gaps and propose future research agendas for XAI, particularly from end users' perspectives based on current knowledge. The final search query for the Systematic Literature Review (SLR) was conducted on July 2022. Initially, we extracted 1707 journal and conference articles from the Scopus and Web of science databases. Inclusion and exclusion criteria were then applied, and 58 articles were selected for the SLR. The findings show four dimensions that shape the AI explanation, which are format (explanation representation format), completeness (explanation should contain all required information, including the supplementary information), accuracy (information regarding the accuracy of the explanation), and currency (explanation should contain recent information). Moreover, along with the automatic representation of the explanation, the users can request additional information if needed. We have also described five dimensions of XAI effects: trust, transparency, understandability, usability, and fairness. We investigated current knowledge from selected articles to problematize future research agendas as research questions along with possible research paths. Consequently, a comprehensive framework of XAI and its possible effects on user behavio

关键词： Transparency

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：