检索结果-内蒙古大学图书馆

7th International Conference on Machine Learning and Machine Intelligence, MLMI 2024

作者： Zhang, Zhen Abraham, Samuel Lee, Alex Li, Yichen Morota, Gota Ha, Dong Sam Shin, Sook BlacksburgVA United States The Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA United States School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan China School of Animal Sciences Virginia Tech BlacksburgVA United States

ISBN: (纸本)9798400717833

SegIt is a novel, user-friendly, and highly efficient sensor data labeling tool designed to tackle critical challenges such as data privacy, synchronization accuracy, and memory efficiency inherent in existing labeling tools. While many current sensor data labeling tools provide free online services, they typically necessitate users to upload unlabeled sensor data, alongside video or audio references, to cloud storage for labeling. Nevertheless, such third-party storage exposes user data to potential security risks. SegIt, an innovative open-source tool, provides a software solution for tagging unlabeled sensor data directly on a local computer, ensuring enhanced accuracy, convenience, and, most importantly, data security. © 2024 Copyright held by the owner/author(s).

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

DERLight: A Deep Reinforcement Learning Traffic Light Control Algorithm with Dual Experience Replay

引用

Journal of Internet Technology 2024年第1期25卷 79-86页

作者： Yang, Zhichao Kong, Yan Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

In recent years, with the increasingly severe traffic environment, most cities are facing various traffic congestion problems, and the demand for intelligent regulation of traffic signals is also increasing. In this study, we propose a new intelligent traffic light control algorithm, dual experience replay light (DERLight), which innovatively and efficiently designs a dual experience replay training mechanism based on the classic deep Q network (DQN) framework and considers the dynamic epoch function. As results show that compared with some state-of-the-art algorithms, DERLight can shorten the average travel time of vehicles, increase the throughput at intersections, and also speed up the convergence of the network. In addition, the design of this algorithm framework is not only limited to the field of intelligent transportation, but also has transferability for some other fields. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Usage of Blockchain Technology for Improving computer Security 25

Usage of Blockchain Technology for Improving Computer Securi...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Almomani, Adai Al Refai Mohammed, N. Aburomman, Ahmad Alidmat, Omar Khair Alla Saber, Qotadeh Alshariedeh, Fuad Khouj, Mohammed Zarqa University Department of Computer Science Zarqa Jordan Zarqa University Software Engineering Dep. Zarqa Jordan Zarqa University Department of Data Science and A Zarqa Jordan Univeristy of Business and Technology Department of Electronic Enginnering Jeddah Saudi Arabia

ISBN: (纸本)9798331540012

Cyber threats have grown increasingly sophisticated, surpassing the capabilities of traditional security measures. Blockchain technology, with its decentralized and immutable structure, offers a potential solution to these challenges. This study examines the role of blockchain tools such as smart contracts, decentralized identity management, and secure data sharing in enhancing cybersecurity. A review of key literature and analysis of survey data from cybersecurity professionals demonstrate blockchain's effectiveness in improving data integrity, access control, and secure communications. The results show significant correlations between the adoption of blockchain technologies and the mitigation of threats like data breaches and unauthorized access. While blockchain presents promising advancements, scalability, regulatory barriers, and energy consumption remain challenges. The study provides valuable insights for researchers, practitioners, and policymakers on how blockchain can be integrated into modern cybersecurity strategies to create more secure digital environments. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Action Classification Using One-Shot Object Detection

引用

computers, Materials & Continua 2023年第8期76卷 1343-1359页

作者： Hyun Yoo Seo-El Lee Kyungyong Chung Contents Convergence Software Research Institute Kyonggi UniversitySuwon-si16227Korea Department of Public Safety Bigdata Kyonggi UniversitySuwon-si16227Korea Division of Computer Science and Engineering Kyonggi UniversitySuwon-si16227Korea

Deep learning-based action classification technology has been applied to various fields,such as social safety,medical services,and *** an action on a practical level requires tracking multiple human bodies in an image in real-time and simultaneously classifying their *** are various related studies on the real-time classification of actions in an ***,existing deep learning-based action classification models have prolonged response speeds,so there is a limit to real-time *** addition,it has low accuracy of action of each object ifmultiple objects appear in the ***,it needs to be improved since it has a memory overhead in processing image *** learning-based action classification using one-shot object detection is proposed to overcome the limitations of multiframe-based analysis *** proposed method uses a one-shot object detection model and a multi-object tracking algorithm to detect and track multiple objects in the ***,a deep learning-based pattern classification model is used to classify the body action of the object in the image by reducing the data for each object to an action *** to the existing studies,the constructed model shows higher accuracy of 74.95%,and in terms of speed,it offered better performance than the current studies at 0.234 s per *** proposed model makes it possible to classify some actions only through action vector learning without additional image learning because of the vector learning feature of the posterior neural ***,it is expected to contribute significantly to commercializing realistic streaming data analysis technologies,such as CCTV.

关键词： Human action classification artificial intelligence deep neural network pattern analysis video analysis

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Asthma Prediction Model in Children

Federated Learning-Based Asthma Prediction Model in Children

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Henshaw, Ekpo Raphael Chukwudi Osamor, Victor Azeta, Ambrose A. Covenant University Department of Computer and Information Sciences Canaanland km10 Idiroko Road Ogun State Ota Nigeria Namibia University of Science and Technology Department of Software Engineering Windhoek Namibia

ISBN: (纸本)9798350358155

The traditional (logistic regression, risk factor) as well as machine learning asthma prediction models exist. However, using a centralized machine learning methods in healthcare need training of the first-class learning models on various datasets, moreso, it is difficult to get access to patients' health data because health records are generally not easily licensed or approved. Besides cost, data privacy and security represent the main challenges with centralized machine learning which requires sensitive information from users such as medical diagnoses and health records data. The objective of this study is to provide a federated learning-based asthma prediction in children to derive answers to the problems associated with the existing asthma prediction model for children. Symmetrical uncertainty and normalization interaction were employed for feature selection. The model was trained using Federated Artificial Intelligence (AI) Technology Enabler (FATE) and was extended to the XGBoost model and one central server for federated algorithm averaging. The result of the study showed that the model achieved 0.74 accuracy, precision (0.87%), recall (0.77%) and F1-score (0.82%) for the non-asthmatic class and precision of 0.49%, recall of 0.66 %, as well as F1-score of 0.56% for the asthmatic class respectively. The study concludes that the model performance was on the same level as some of the existing machine learning models. It also enables a collaborative model sharing with other hospitals as well as meets the criteria of healthcare data protection regulations. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Considering Multiple Stakeholders Perspectives for interval-based Goal Oriented Requirements Prioritization in agile development 6

Considering Multiple Stakeholders Perspectives for interval-...

引用

6th International Conference on computer, software and Modeling, ICCSM 2022

作者： Fadel, Shaimaa Abdelmoez, Walid Saad, Amani A. Arab Academy for Science and Technology Computer Engineering Department Alexandria Egypt Arab Academy for Science and Technology Software Engineering Department Alexandria Egypt

ISBN: (数字)9781665454865

ISBN: (纸本)9781665454865

Addressing the importance of the requirements prioritization, recent research introduced 'A value-based approach for reasoning with goal models', which allows stakeholders to set an importance estimate for each element in a goal model, that relates the requirements with the business objectives. These estimates are then propagated by means of their relationships (dependencies, contributions and decompositions) to get a prioritized list of all requirements. In this paper, a methodology that extends the aforementioned technique is presented. It uses Goal Oriented Requirements Language (GRL) to prioritize requirements in an agile environment, taking into consideration the opinion of many Stakeholders. As the static value of the estimate is never accurate and does not give the stakeholders enough flexibility, the proposed methodology enables each stakeholder to provide for each requirement its importance as an estimated interval instead of a static value. Then, for each requirement the mean value of the estimation interval is calculated, the information asymmetry and confidence level per requirement are demonstrated, so that a prioritized list can then be generated. The analyst can choose to use the prioritized list based on one of these criteria. This methodology is demonstrated on a case study. © 2022 IEEE.

关键词： Computational modeling Estimation software Cognition Stakeholders Business

来源：评论

学校读者我要写书评

暂无评论

IBATree: A Novel Method for Interpretable Cancer Cell Diagnosis Using Information Bottleneck Attribution

IBATree: A Novel Method for Interpretable Cancer Cell Diagno...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Raza, Muhammad Umair Chen, Jie Nawaz, Adil Saeed, Faisal Leung, Victor C.M. Li, Jianqiang Wang, Zhaoxia Shenzhen University College of Computer Science and Software Engineering China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology China Shenzhen Children's Hospital Department of Gastroenterology China

ISBN: (纸本)9798350386226

Deep Neural Networks (DNNs) have demonstrated remarkable performance in classification and regression tasks on RGB-based pathological inputs. The network's prediction mechanism must be interpretable to establish trust in the clinical routine. One principal approach to interpretation is feature attribution. Feature attribution methods identify the importance of input features for the output prediction. Building on the Information Bottleneck Attribution (IBA) method, we recognize the RGB's input regions with high mutual information with the network's output for each prediction. IBA identifies input regions that have sufficient predictive information. In this paper, we introduce "IBATree", a novel approach that combines IBA with decision trees to enhance both the interpretability and accuracy of DNNs in cancer cell classification. Our method leverages the information bottleneck framework to inject noise into feature maps and then isolates the most informative features for model predictions while maintaining high classification performance. We evaluated our proposed approach on three datasets - CNMC, ISBI2016, and BreaKHis - demonstrating competitive accuracy and producing clear interpretations. This makes IBATree particularly suitable for clinical applications, where understanding the rationale behind predictions is crucial. Our results show that IBATree provides reliable predictions and valuable insights into feature importance, paving the way for its application in various biomedical domains. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Broadcasting in interconnection networks based on node partitioning 3

Broadcasting in interconnection networks based on node parti...

引用

3rd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2023

作者： Harutyunyan, Hovhannes A. Hovhannisyan, Narek Concordia University Department of Computer Science and Software Engineering MontrealQCH3G 1M8 Canada

ISBN: (纸本)9798350333732

Broadcasting is one of the information dissemination primitives where a message is passed from one node (called originator) to all other nodes in the network. With the increasing interest in interconnection networks, an extensive amount of research was dedicated to broadcasting. Two main research goals of this area are finding inexpensive network structures that maintain efficient broadcasting and finding the broadcast time for well-known and widely used network *** the scope of this paper, we will mainly focus on determining the broadcast time and near-optimal broadcasting schemes in networks. Determination of the broadcast time of any node in an arbitrary network is known to be NP-hard. Polynomial time solutions are known only for a few network topologies. There also exist various heuristic and approximation algorithms for different network topologies. In this paper, we will present an efficient heuristic for the broadcast time problem in networks, where the nodes can be partitioned into two groups. © 2023 IEEE.

关键词： Broadcasting

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-based conditional optimal transport generative adversarial network for medical image generation

引用

Visual Informatics 2024年第1期8卷 15-25页

作者： Jun Wang Bohan Lei Liya Ding Xiaoyin Xu Xianfeng Gu Min Zhang School of Software Technology Zhejiang UniversityNingboZhejiangChina College of Computer Science&Technology Zhejiang UniversityHangzhouZhejiangChina Department of Pathology Sir Run Run Shaw HospitalZhejiang University School of MedicineHangzhouZhejiangChina College of Biomedical Engineering&Instrument Science Zhejiang UniversityHangzhouZhejiangChina Department of Computer Science State University of New York at Stony BrookStony BrookNYUSA

Medical image generation has recently garnered significant interest among ***,the primary generative models,such as Generative Adversarial Networks(GANs),often encounter challenges during training,including mode *** address these issues,we proposed the AECOT-GAN model(Autoencoder-based Conditional Optimal Transport Generative Adversarial Network)for the generation of medical images belonging to specific *** training process of our model comprises three fundamental *** training process of our model encompasses three fundamental ***,we employ an autoencoder model to obtain a low-dimensional manifold representation of real ***,we apply extended semi-discrete optimal transport to map Gaussian noise distribution to the latent space distribution and obtain corresponding labels *** procedure leads to the generation of new latent codes with known ***,we integrate a GAN to train the decoder further to generate medical *** evaluate the performance of the AE-COT-GAN model,we conducted experiments on two medical image datasets,namely DermaMNIST and *** model’s performance was compared with state-of-the-art generative *** show that the AE-COT-GAN model had excellent performance in generating medical ***,it effectively addressed the common issues associated with traditional GANs.

关键词： Medical image generation Mode collapse Mode mixing Optimal transport Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

CP-Steering: CDN- and Protocol-Aware Content Steering Solution for HTTP Adaptive Video Streaming 23

CP-Steering: CDN- and Protocol-Aware Content Steering Soluti...

引用

2nd Mile-High Video Conference, MHV 2023

作者： Farahani, Reza Bentaleb, Abdelhak Shojafar, Mohammad Hellwagner, Hermann Alpen-Adria-Universität Klagenfurt Austria Department of Computer Science and Software Engineering Concordia University Canada University of Surrey United Kingdom

ISBN: (纸本)9798400701603

In recent years, HTTP Adaptive Streaming (HAS)-based technologies, such as Dynamic Adaptive Streaming over HTTP (DASH), have become the predominant video delivery paradigm over the Internet. HAS-based content providers frequently employ multiple Content Delivery Network (CDNs) to distribute their content to the end users. Recently, Apple and DASH-IF standardization introduced content steering technique to enable content providers to switch the content source that a player utilizes at start-up or midstream. Due to diverse adaptive video streaming demands for latency-sensitive and/or bandwidth-sensitive streams, satisfying end users with a pleasant Quality of Experience (QoE) poses a new challenge for redesigning the current content steering strategies. This paper leverages the recent popular Quick UDP Internet Connections (QUIC) transport protocol and introduces a CDN- and Protocol-aware content Steering solution for HTTP Adaptive Streaming (CP-Steering). We discuss the details of CP-Steering strategy and then give directions for future work. © 2023 Owner/Author(s).

关键词： HTTP

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：