检索结果-内蒙古大学图书馆

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

Organizational governance: Resolving insufficient practice and quality expectation in Small software Companies. 22

Organizational governance: Resolving insufficient practice a...

引用

Proceedings of the 2022 European Symposium on software engineering

作者： Micheal Tuape Petrus Iiyambo Jussi Kasurinen Department of Software Engineering Lappeenranta-Lahti University of Technology Finland Dept of Computing Maths and Statistical Sciences University of Namibia Namibia

ISBN: (纸本)9781450397308

The quality of software products is among the most prevalent challenges threatening the software development primarily in small software companies (SSCs). These challenges are associated with insufficient practices affecting the production of software and the development processes. This paper explores the role of governance in streamlining software processes and practices to produce better quality software products. In a cross-sectional survey (n = 127), we reached out to software practitioners working in SSCs from four countries. We examined how SSCs engage in oversight and accountability and how SSCs perform management roles and activities, such as controlling, directing, and guiding in the process of developing software. Our findings indicate that although the SSCs minimally embrace governance practices, the smaller companies have a more challenging task embracing governance practices from the complexities arising out of these companies' structures. This study highlights the aspects of governance that need attention in the smaller category of SSCs. It proposes an organizational governance model to facilitate the SSCs in developing governance strategies to take advantage of the benefits of governance during software development.

关键词： software Organizational governance Small software Companies software processes

来源：评论

学校读者我要写书评

暂无评论

Recognition of Abnormal Human Behavior in Elevators based on CNN 26

Recognition of Abnormal Human Behavior in Elevators based on...

引用

26th International Conference on Automation and computing, ICAC 2021

作者： Shi, Yajing Guo, Benjun Xu, Yuanping Xu, Zhijie Huang, Jian Lu, Jun Yao, Dengguo Chengdu University of Information Technology School of Software Engineering Chengdu China University of Huddersfield School of Computing and Engineering Huddersfield Queensgate United Kingdom

ISBN: (纸本)9781860435577

This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN (S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior. © 2021 Chinese Automation and computing Society in the UK-CACSUK.

关键词： Elevators

来源：评论

学校读者我要写书评

暂无评论

Fall Detection in Elevator Cages Based on XGBoost and LSTM 26

Fall Detection in Elevator Cages Based on XGBoost and LSTM

引用

26th International Conference on Automation and computing, ICAC 2021

作者： Xu, Caorong Xu, Yuanping Xu, Zhijie Guo, Benjun Zhang, Chaolong Huang, Jian Deng, Xin Chengdu University of Information Technology School of Software Engineering Chengdu China University of Hudderseld School of Computing and Engineering HudderseldQueensgate United Kingdom

ISBN: (纸本)9781860435577

Fall detection has always been challenging. There are many current works that have achieved good results in fall detections, but most of the existing works only consider single feature dimension (i.e., temporal features or spatial features). This study proposes a method that combines LSTM and XGBoost model to detect human body falls through fusing both temporal and spatial features. It starts with extracting bond points on human body in each frame of the video by using AlphaPose. In the second step, three features of the human body (i.e., vertical height, aspect ratio of the human external rectangle and angle of the knee joint) are calculated as spatial features through the extracted bone point information. Then use LSTM to learn these three kinds of features on both the temporal and spatial dimension. Furthermore, this model integrates the XGBoost to learn multiple features to improve the recognition rate. Finally, various human body fall detections in elevator cabs are applied to test the usability and validity of this study. The experimental results of the whole model reach 92.11% recognition accuracy, and 93.33% on the the F1-measure index. © 2021 Chinese Automation and computing Society in the UK-CACSUK.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Improved Census Transform Method for Semi-Global Matching Algorithm 26

Improved Census Transform Method for Semi-Global Matching Al...

引用

26th International Conference on Automation and computing, ICAC 2021

作者： Pan, Xie Jun, Guoben Xu, Yuanping Xu, Zhijie Li, Tukun Huang, Jian Qiao, Wenbo Chengdu University of Information Technology School of Software Engineering Chengdu China University of Hudderseld School of Computing and Engineering Hudderseld Queensgate United Kingdom

ISBN: (纸本)9781860435577

In order to solve the problem that the original Census transform algorithm is easily affected by the gray value of the central pixel, and further improvement of the matching accuracy of SGM algorithm, this study proposes an improved Census transform algorithm based on the sequence template. It divides the pixel values in the Census window into sequential sequences from the outside to inside, and then constructs Census encoding templates within and between sequences according to predefined rules in this study, such that the Census value of the center pixel can contain more information within the window, and can further improve the matching accuracy of SGM. Experimental results show that the improved sequence template-based Census transform method can enhance average 16.26% matching accuracy of SGM algorithm, while preserving its efficiency. © 2021 Chinese Automation and computing Society in the UK-CACSUK.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Expressive Completeness of Two-Variable First-Order Logic with Counting for First-Order Logic Queries on Rooted Unranked Trees

Expressive Completeness of Two-Variable First-Order Logic wi...

引用

Annual Symposium on Logic in Computer Science

作者： Jelle Hellings Marc Gyssens Jan Van Den Bussche Dirk Van Gucht Department of Computing and Software McMaster University Hamilton Canada Data Science Institute Hasselt University Diepenbeek Belgium Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

We consider the class of finite, rooted, unranked, unordered, node-labeled trees. Such trees are represented as structures with only the parent-child relation, in addition to any number of unary predicates for node labels. We prove that every unary first-order query over the considered class of trees is already expressible in two-variable first-order logic with counting. Somewhat to our surprise, we have not seen this result being conjectured in the extensive literature on logics for trees. Our proof is based on a global variant of local equivalence notions on nodes of trees. This variant applies to entire trees, and involves counting ancestors of locally equivalent nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Chen, Xi Li, Qin Cai, Haibin Wang, Ting MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China

Federated Learning (FL) empowers multiple clients to collaboratively train machine learning models without sharing local data, making it highly applicable in heterogeneous Internet of Things (IoT) environments. However, intrinsic heterogeneity in clients’ model architectures and computing capabilities often results in model accuracy loss and the intractable straggler problem, which significantly impairs training effectiveness. To tackle these challenges, this paper proposes a novel Heterogeneity-aware Personalized Federated Learning method, named HAPFL, via multi-level Reinforcement Learning (RL) mechanisms. HAPFL optimizes the training process by incorporating three strategic components: 1) An RL-based heterogeneous model allocation mechanism. The parameter server employs a Proximal Policy Optimization (PPO)-based RL agent to adaptively allocate appropriately sized, differentiated models to clients based on their performance, effectively mitigating performance disparities. 2) An RL-based training intensity adjustment scheme. The parameter server leverages another PPO-based RL agent to dynamically fine-tune the training intensity for each client to further enhance training efficiency and reduce straggling latency. 3) A knowledge distillation-based mutual learning mechanism. Each client deploys both a heterogeneous local model and a homogeneous lightweight model named LiteModel, where these models undergo mutual learning through knowledge distillation. This uniform LiteModel plays a pivotal role in aggregating and sharing global knowledge, significantly enhancing the effectiveness of personalized local training. Experimental results across multiple benchmark datasets demonstrate that HAPFL not only achieves high accuracy but also substantially reduces the overall training time by 20.9%-40.4% and decreases straggling latency by 19.0%-48.0% compared to existing solutions. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

eDEM-CONNECT: An Ontology-Based Chatbot for Family Caregivers of People with Dementia 12th

eDEM-CONNECT: An Ontology-Based Chatbot for Family Caregive...

引用

12th International Conference on Mobile Communication and Healthcare, MobiHealth 2023

作者： Boiting, Maurice Tschorn, Niklas Suravee, Sumaiya Yordanova, Kristina Halek, Margareta Jagoda, Franziska A. Lüdtke, Stefan Burmann, Anja Fraunhofer Institute for Software and Systems Engineering ISST Dortmund44147 Germany Institute for Data Science Universität Greifswald Greifswald17489 Germany School of Nursing Science Faculty of Health Universiät Witten/Herdecke Witten58453 Germany Institute for Visual and Analytic Computing Universät Rostock Rostock18059 Germany

ISBN: (纸本)9783031606649

Home care of people with dementia (PwD) is mainly organized and carried out by non-professional family caregivers, who struggle to interpret the needs of PwD correctly and are confronted with the challenging behavior of their relatives. Although support services for family caregivers are widespread in Germany, they are rarely used due to the fact that information is poorly organized and relatives are faced with a flood of disorganized, outdated, and confusing content. Due to the technical development of chatbot technologies (ChatGPT), chatbots gain more and more relevance. Based on the new technological possibilities, we developed an online communication and service platform with an integrated chatbot within the eDEM-CONNECT project, with the aim of making structured and easily understandable information accessible for family caregivers. This work focuses on the development of a chatbot pipeline that has broad domain knowledge through a provided ontology on the topic of agitation of PwD. This allows the chatbot to provide relevant and peer-reviewed information to family members. In our approach, a patient history is first taken based on several diagnostic questions so that relevant information can be output in a later step. For this purpose, we demonstrate that agitations in natural language can be correctly recognized by the used BERT model and that our developed chatbot is able to select further diagnostic questions based on the predictions of a Markov logic network. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A Testbed Implementation of Microservices-based In-Network computing Framework for Information-Centric IoVs

A Testbed Implementation of Microservices-based In-Network C...

引用

2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022

作者： Ud Din, Muhammad Salah Ur Rehman, Muhammad Atif Imran, Muhammad Nadeem, Muhammad Kim, Byung-Seo Hongik University Department of Electronics and Computer Engineering Sejong City30016 Korea Republic of Manchester Metropolitan University Department of Computing and Mathematics United Kingdom Hongik University Department of Software and Communications Engineering Sejong City30016 Korea Republic of

ISBN: (数字)9781665464345

ISBN: (纸本)9781665464345

In this paper, we design and implement a multi-layered microservices-centric in-network computing framework aiming to reduce latency and bandwidth consumption that mainly occur due to frequent handovers in a highly mobile vehicular environment. The framework comprised NDN-enabled vehicular nodes in NDNsim Environment, resourceful Edge computing, and the Cloud server. We modified the NDNsim codebase and develop the fundamentals of microservices execution and nodes' resource management. In addition, we also implemented the Microservices in Dotnet and placed them on Edge and Cloud nodes. NDN communication stack is utilized for the communication in simulations while the Restful APIs are developed to enable NDNsim and Edge communication, inter Edge communication, and Edge-cloud communication. Extensive experimentation reveals that the proposed microservice architecture highly optimized bandwidth consumption compared with the conventional monolithic system. © 2022 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Discrete Geometric Coded Data Layout for Large-scale Object Storage Systems 21

Discrete Geometric Coded Data Layout for Large-scale Object ...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud computing, 16th IEEE International Conference on Social computing and Networking and 13th International Conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Tian, Yi Xu, Guangping Yang, Hongzhang Ni, Yue Cao, JiaXin Yang, Lei Tianjin University of Technology School of Computer Science and Engineering Tianjin China Novel Software Technology Tianjin Key Laboratory of Intelligence Computing Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Information Technology Co. Ltd. China

ISBN: (纸本)9798350329223

Regenerating codes are new network codes proposed to reduce the data required for fault repair, which can improve the recovery efficiency of faulty nodes in data storage systems. However, unlike Reed-Solomon code, which repairs at the granularity of bytes, regenerating codes require data stored in large chunks but leads to severe read amplification, which reads out excess data when degraded read objects and increases degraded read time. That reflects a mutual constraint between improving recovery efficiency and degraded read performance, as manifested in the amplification of data reads, a vital issue considered in this *** solve this problem, we propose a new type of data layout - discrete geometric, which splits the object into a series of geometric sequences of data blocks. They are placed discretely into corresponding containers on the disks at different nodes, with containers of the same size made into a strip for encoding. The discrete characteristic ensures lower repair costs for degraded reads. The geometric characteristic ensures the repair performance of regenerating codes by large blocks, and read amplification can be mitigated through small blocks. To reduce IOPS for discrete geometric, we propose Discrete Geometric-Locally Regenerating Codes (DG-LRCs), guaranteeing lower degraded read latency while improving recovery *** results show that the degraded read time of DG-LRCs compared to regenerating codes combined with geometric partitioning is 22.56% lower at 2Gbpsand 60.56% lower at 4Gbps, and the recovery performance is 7.04 times better than that of RS code. © 2023 IEEE.

关键词： Efficiency

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：