检索结果-内蒙古大学图书馆

International Conference on e-health Networking, Applications and Services (HealthCom)

作者： Boyuan Peng Yiyang Liu Xin Zhu Jie Huang Wenwen Wang Li Fang Qin Zhou Graduate Department of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Fukushima Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Chiyodaku Tokyo Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Aizu-Wakamatsu Fukushima Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350350548

ISBN: (纸本)9798350350555

Semi-supervised learning (SSL) is a promising solution for the problem of insufficient medical labeled data. However, it is still a challenging task to segment transvaginal ultrasound (TVUS) images because of their poor contrast and speckle noise. In this study, we propose Multi-StudentNet, a semi-supervised deep-learning framework for endometrial segmentation in TVUS images. This method employs multiple student models to effectively integrate labeled and unlabeled data, improving the reliability and performance of segmentation while significantly reducing the need for extensive manual labeling. By leveraging the weights of multiple models, our framework facilitates feature sharing, which enhances model robustness. Specifically, Multi-StudentNet achieves a Dice coefficient (DSC) of 0.81 and a specificity of 0.99. Our multi-student models consistently outperform single-student models across various conditions, including normal, polyp, and cancer cases. Extensive experiments demonstrate that Multi-StudentNet achieves state-of-the-art performance in both accuracy and robustness.

关键词： Image segmentation Ultrasonic imaging Accuracy Manuals Speckle Semisupervised learning Robustness Data models Optimization Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Novel Approach for Enhancing Mental Well-Being Through Machine Learning Techniques

Novel Approach for Enhancing Mental Well-Being Through Machi...

引用

Advancements in Computing (ICAC), International Conference on

作者： O.V.D.E Roshani H.M.K.J.J Ayuwardhana P.H.M.S Rodrigo R.U Hewageegana Harinda Fernando Dilshan I. de Silva Department of Computer Science and Software Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Systems Engineering Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

Frequently, individuals undergo specific episodes of mental health challenges throughout their lifetime. But the COVID pandemic has triggered a surge in mental health disorders arising from isolation, monotonous routines, demanding workloads, financial disparities, and disruptions to daily schedules. Furthermore, the global pandemic has induced constant anxiety and stress. Beyond the pandemic, the competition and intense pressure of the modern world impact mental health. Access to advanced mental health solutions and the necessary familiarity remain limited for most of the population. Given the integration of technology into daily life, diverse remedies, including mobile and web applications, have emerged to tackle the escalating challenge of mental health disorders. This study proposes an accessible and cost-effective approach that employs machine learning to detect stress levels and discern user emotions from journal entries and facial expressions while integrating self-journaling, video recommendations, and visual content generation to stimulate positive emotions and relieve stress.

关键词：

来源：评论

学校读者我要写书评

暂无评论

INVESTIGATION OF THE ACCELERATION INFLUENCE ON FRICTION IN BEARINGS IN DUAL-SPIN MISSILE 38

INVESTIGATION OF THE ACCELERATION INFLUENCE ON FRICTION IN B...

引用

38th Danubia-Adria Symposium on Advances in Experimental Mechanics, DAS 2022

作者： Todić, Ivana Kuzmanović, Vladimir University of Belgrade Faculty of Mechanical Engineering Weapon Systems Department Kraljice Marije 16 Belgrade11120 Serbia University of Belgrade Faculty of Mathematics Department for Computer Science and Informatics Studentski Trg 16 Belgrade11000 Serbia

ISBN: (纸本)9786188627802

Rockets and missiles fired from a tube usually have aerodynamic surfaces that are packed when the rocket is in the tube. One of the common fins folding solutions is the wrap-around fins. The wrap-around fins are usually separated from the rocket's body by a bearing;thus the characteristics and the type of bearings used will have an effect on roll stabilization and the performance of roll stabilization autopilot. Also, during the flight, many forces act upon the missile thus affecting its exposed components. In turn, this may also affect the performance of the bearings that allow the wrap-around fins to rotate independently around the missile's body. This dual-spin concept increases roll stabilization efficiency and reduces induced roll from lateral control. For this design to be effective and achieve the desired performance, it is critical to analyze how the movements of the missile affect the bearing separating the body from the wrap-around fins. Since the sections are separated by the bearing, various imperfections of the joint such as friction, misalignment, etc. combined with the acceleration of the missile may have a transitional influence on the performance of the wrap-around fins and thus roll stabilization. In this paper, we will first identify and explain the problem of acceleration influence on friction in bearings. Next, the laboratory equipment and experimental procedures for examining friction in bearings will be described in detail. We will then present and analyze the results obtained from the experiments. Finally, we will draw conclusions and present the design modification this investigation has led to as well as the improved roll autopilot performance achieved by using the appropriate bearing. © 2023 Elsevier Ltd. All rights reserved.

关键词： acceleration-induced dual-spin fins friction missile wrap-around

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Satellite and Debris Detection: YOLO in Action

A Deep Learning Approach for Satellite and Debris Detection:...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Md Younus Ahamed Md Asif Bin Syed Paroma Chatterjee Al Zadid Sultan Bin Habib Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown USA Department of Industrial and Management Systems Engineering West Virginia University Morgantown USA

Satellite detection refers to the identification and recognition of satellites in satellite images. This task is crucial for various applications, including space surveillance, satellite tracking, and space debris monitoring. Several studies have been conducted to develop methods and techniques for satellite detection. The intricacy and scale of satellite images make satellite detection incredibly challenging. The process of manual identification and classification necessitates a significant amount of time. Recently, Deep Learning (DL) has emerged as a highly promising approach in computer Vision (CV) tasks. This study evaluates the effectiveness of three widely employed DL-based object detection algorithms, specifically YOLOv4, YOLOv5, and YOLOv8, within the field of satellite detection. The algorithms have undergone training utilizing a dataset of satellite photos comprising both satellites and debris. The evaluation of the algorithm’s performance involved the utilization of broadly accepted metrics, including Precision, Recall, Mean Average Precision (mAP), Box Loss, and Class Loss. The findings indicated that all three algorithms exhibited a high level of accuracy in detecting and precisely determining the location of objects inside satellite data. The performance of YOLOv5 and YOLOv8 surpassed that of YOLOv4 across various measures, with a notable advantage observed in detecting tiny objects. Overall, this study demonstrates the capabilities of DL algorithms in the context of satellite detection and classification techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Defeating Proactive Jammers Using Deep Reinforcement Learning for Resource-Constrained IoT Networks

arXiv

引用

arXiv 2023年

作者： Ali, Abubakar Sani Naser, Shimaa Muhaidat, Sami Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi127788 United Arab Emirates Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada

Traditional anti-jamming techniques like spread spectrum, adaptive power/rate control, and cognitive radio, have demonstrated effectiveness in mitigating jamming attacks. However, their robustness against the growing complexity of internet-of-thing (IoT) networks and diverse jamming attacks is still limited. To address these challenges, machine learning (ML)based techniques have emerged as promising solutions. By offering adaptive and intelligent anti-jamming capabilities, ML-based approaches can effectively adapt to dynamic attack scenarios and overcome the limitations of traditional methods. In this paper, we propose a deep reinforcement learning (DRL)-based approach that utilizes state input from realistic wireless network interface cards. We train five different variants of deep Q-network (DQN) agents to mitigate the effects of jamming with the aim of identifying the most sample-efficient, lightweight, robust, and least complex agent that is tailored for power-constrained devices. The simulation results demonstrate the effectiveness of the proposed DRL-based anti-jamming approach against proactive jammers, regardless of their jamming strategy which eliminates the need for a pattern recognition or jamming strategy detection step. Our findings present a promising solution for securing IoT networks against jamming attacks and highlights substantial opportunities for continued investigation and advancement within this field. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hash Tag-Based Sentiment Analysis Using A Deep Learning Approach

Hash Tag-Based Sentiment Analysis Using A Deep Learning Appr...

引用

International Conference on Advanced Computing and Communication systems (ICACCS)

作者： R. Venkatesan M. Sangeetha S. Nivedha M. Selvakumar K.S. Chandru P. Parthasarathi Department of Information Technology Bannari Amman Institute of Technology Erode India Department of Information Technology K S Rangasamy College of Technology Namakkal India Dept. of Computer Science & Engineering Hindusthan College of Engg and Technology Coimbatore India Dept. Computer Science & Business Systems Bannari Amman Institute of Technology Erode India Dept. Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

Social commerce uses a variety of social networking sites like Facebook, Instagram, Twitter, Pinterest, and business Whatsapp as a platform to promote products and services. Since advertising, a product, or service in s-comm will reach as high as a possible number of users on networking sites. Ads will spread virally by sharing among friends and friends of friends. So that wider reachability is possible and shortly will get the customer for our business. The success of an s-comm campaign is measured by the degree to which consumers interact with the sellers through review comments, likes, and shares between friends. Customer behavior analysis is needed for s-comm marketing because social commerce can significantly boost economic growth. The sentiment analysis of customer recommendations was investigated using a dataset of women's s-comm apparel hashtags and reviews. So for such reviews are experimented with different machine learning algorithms (Decision tree, SVM, Random Forest, KNN, Naïve Bayes and LSTM). These models handled the common English reviews and compared the metrics (Accuracy, Sensitivity and Specificity) with one another. Instead of working with individual model, this paper introduces a novel hybrid approach that integrates CNN and Ada Boost LSTM algorithms to provide better results in sentiment analysis when compared to other machine learning algorithms mentioned above. While considering the hash tag with common review comments the hybrid system is out performed. The comparison analysis is done for performance matrices namely accuracy of 98%, specificity of 98.1%, and sensitivity of 98.1%. In the s-commerce transaction industry, this hybrid approach will help to create a deeper understanding of consumer sentiment analysis and psychologically attract clients.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Sensitivity Machine learning algorithms Reviews Social networking (online) Biological system modeling Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Blockchain Integrated Federated Learning in Edge-Fog-Cloud systems for IoT based Healthcare Applications: A Survey

arXiv

引用

arXiv 2024年

作者： Rajagopal, Shinu M. Supriya, M. Buyya, Rajkumar Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India CLOUDS Lab School of Computing and Information Systems The University of Melbourne Australia

Modern Internet of Thing (IoT) applications generate enormous amount of data. To prototype the incoming data from such applications, data-driven machine learning has emerged as a viable method which can help to develop precise and reliable statistical models. Existing data is not effectively utilized by machine learning as it is stored in data silos and technology businesses are now required to treat user data carefully in accordance with user-privacy legislation in many regions of the world. It is self-evident that the samples in the typical machine learning centralized server paradigm have different probability distributions of data supplied. As a result, the common model fails to personalize. Without sufficient data, machine learning is unlikely to reach its full potential. Hence the new distributed paradigm, federated learning has gained popularity that supports collaborative learning while preserving privacy. IoT applications with cryptography characteristics will be capable of storing and transmitting data securely over networks by maintaining data consistency. Therefore, federated learning and blockchain integration are particularly beneficial for IoT applications that manage sensitive data such as healthcare. Although several studies have focused on various applications of blockchain technology and federated learning, a thorough examination of these technologies in edge-fog-cloud based IoT computing systems and healthcare applications is yet to be performed. The basic architecture, structure, types, functions, and characteristics of federated learning and blockchain are addressed at the outset of this survey article. This article also considers the wide range of applications to which federated learning and blockchain has been implemented, including edge, fog, cloud and IoT computing paradigms. Lastly, it evaluates the different implementations of federated learning in healthcare applications. © 2024, CC BY-NC-ND.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Towards Threat Modelling of IoT Context-Sharing Platforms

Towards Threat Modelling of IoT Context-Sharing Platforms

引用

IEEE International Symposium on Network Computing and Applications

作者： Mohammad Goudarzi Arash Shaghaghi Simon Finn Burkhard Stillerd Sanjay Jha School of Computer Science and Engineering UNSW Sydney Australia Cyber Security Cooperative Research Centre (CSCRC) Department of Informatics Communication Systems Group University of Zurich Switzerland

ISBN: (数字)9798331510183

ISBN: (纸本)9798331510190

The Internet of Things (IoT) involves complex, interconnected systems and devices that depend on contextsharing platforms for interoperability and information exchange. These platforms are, therefore, critical components of real-world IoT deployments, making their security essential to ensure the resilience and reliability of these “systems of systems.” In this paper, we take the first steps toward systematically and comprehensively addressing the security of IoT context-sharing platforms. We propose a framework for threat modelling and security analysis of a generic IoT context-sharing solution, employing the MITRE ATT&CK framework. Through an evaluation of various industry-funded projects and academic research, we identify significant security challenges in the design of IoT context-sharing platforms. Our threat modelling provides an in-depth analysis of the techniques and sub-techniques adversaries may use to exploit these systems, offering valuable insights for future research aimed at developing resilient solutions. Additionally, we have developed an open-source threat analysis tool that incorporates our detailed threat modelling, which can be used to evaluate and enhance the security of existing context-sharing platforms.

关键词： Threat modeling Industries Interconnected systems Security Internet of Things Reliability Interoperability Information exchange System of systems Resilience

来源：评论

学校读者我要写书评

暂无评论

Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation

arXiv

引用

arXiv 2024年

作者： Wu, Xinghao Niu, Jianwei Liu, Xuefeng Shi, Mingjia Zhu, Guogang Tang, Shaojie School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Sichuan University Sichuan China Department of Management Science and Systems University at Buffalo United States

In traditional Federated Learning approaches like FedAvg, the global model underperforms when faced with data heterogeneity. Personalized Federated Learning (PFL) enables clients to train personalized models to fit their local data distribution better. However, we surprisingly find that the feature extractor in FedAvg is superior to those in most PFL methods. More interestingly, by applying a linear transformation on local features extracted by the feature extractor to align with the classifier, FedAvg can surpass the majority of PFL methods. This suggests that the primary cause of FedAvg’s inadequate performance stems from the mismatch between the locally extracted features and the classifier. While current PFL methods mitigate this issue to some extent, their designs compromise the quality of the feature extractor, thus limiting the full potential of PFL. In this paper, we propose a new PFL framework called FedPFT to address the mismatch problem while enhancing the quality of the feature extractor. FedPFT integrates a feature transformation module, driven by personalized prompts, between the global feature extractor and classifier. In each round, clients first train prompts to transform local features to match the global classifier, followed by training model parameters. This approach can also align the training objectives of clients, reducing the impact of data heterogeneity on model collaboration. Moreover, FedPFT’s feature transformation module is highly scalable, allowing for the use of different prompts to tailor local features to various tasks. Leveraging this, we introduce a collaborative contrastive learning task to further refine feature extractor quality. Our experiments demonstrate that FedPFT outperforms state-of-the-art methods by up to 7.08%. Copyright © 2024, The Authors. All rights reserved.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media 16th

Impact of COVID-19 on Predicting 2020 US Presidential Electi...

引用

16th International Conference on Information Technology and Applications, ICITA 2022

作者： Khan, Asif Zhang, Huaping Boudjellal, Nada Hayat, Bashir Dai, Lin Ahmad, Arshad Al-Hamed, Ahmed School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China The Faculty of New Information and Communication Technologies University Abdelhamid Mehri Constantine 2 Constantine25000 Algeria Institute of Management Sciences Peshawar Peshawar Pakistan Institute of Software Systems Engineering Johannes Kepler University Linz4040 Austria Department of IT and Computer Science Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology Mang Khanpur Road Haripur22620 Pakistan

ISBN: (纸本)9789811993305

By the beginning of 2020, the world woke up to a global pandemic that changed people’s everyday lives and restrained their physical contact. During those times Social Media Platforms (SMPs) were almost the only mean of individual-to-individual and government-to-individuals communications. Therefore, people’s opinions were more expressed on SM. On the other hand, election candidates used SM to promote themselves and engage with voters. In this study, we investigate how COVID-19 affected voters’ opinions through the months of the US presidential campaign and eventually predict the 2020 US Presidential Election results using Twitter’s data. Mainly two types of experiments were conducted and compared;(i) transformer-based, and (ii) rule-based sentiment analysis (SA). In addition, vote shares for the presidential candidates using both approaches were predicted. The results show that the rule-based approach nearly predicts the right winner, Joe Biden with MAE 2.1, outperforming the predicted results from CNBC, Economist/YouGov, and transformer-based (BERTweet) approach, except for RCP (MAE 1.55). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19

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：