检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Masum, Mohammad Shahriar, Hossain Haddad, Hisham Faruk, Md Jobair Hossain Valero, Maria Khan, Md Abdullah Rahman, Mohammad A. Adnan, Muhaiminul I. Cuzzocrea, Alfredo Wu, Fan School of Data Science Kennesaw State University United States Department of Information Technology Kennesaw State University United States Department of Software Engineering and Game Development Kennesaw State University United States Department Computer Science Kennesaw State University United States Department of Electrical and Computer Engineering Florida International University United States Institute of Natural Sciences United International University United States IDEA Lab University of Calabria Rende Italy LORIA Nancy France Department of Computer Science Tuskegee University United States

Traditional network intrusion detection approaches encounter feasibility and sustainability issues to combat modern, sophisticated, and unpredictable security attacks. Deep neural networks (DNN) have been successfully applied for intrusion detection problems. The optimal use of DNN-based classifiers requires careful tuning of the hyper-parameters. Manually tuning the hyperparameters is tedious, time-consuming, and computationally expensive. Hence, there is a need for an automatic technique to find optimal hyperparameters for the best use of DNN in intrusion detection. This paper proposes a novel Bayesian optimization-based framework for the automatic optimization of hyperparameters, ensuring the best DNN architecture. We evaluated the performance of the proposed framework on NSL-KDD, a benchmark dataset for network intrusion detection. The experimental results show the framework's effectiveness as the resultant DNN architecture demonstrates significantly higher intrusion detection performance than the random search optimization-based approach in terms of accuracy, precision, recall, and f1-score. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Privacy Protection by Particle Swarm Optimization Based Pivot Pixel Modification 1

引用

5th International Conference on Internet of Things, ICIOT 2020, held as part of the Services Conference Federation, SCF 2020

作者： Yang, Jishen Huang, Yan Pang, Junjie Xie, Zhenzhen Li, Wei Department of Computer Science Georgia State University Atlanta30303 United States Department of Software Engineering and Game Development Kennesaw State University Atlanta30144 United States College of Computer Science and Technology Qingdao University Qingdao266000 China College of Computer Science and Technology Jilin University Changchun130012 China

ISBN: (数字)9783030596156

ISBN: (纸本)9783030596149

The image classification models based on neural networks recently have outperformed most of the traditional models, and rapidly been developed and implemented by industry because of the capability of qualifying various computer vision tasks. Hence, the exposure of users image data to unauthorized powerful models causes more information leak in a shorter time. Through experiments, we find that for each input image, the change of the images prediction scores by each pixels RGB value change is different. Also, the pattern of the sensitivity on each pixel is highly related to the category and composition of the input image. By utilizing this feature, we present Pivot Pixel Noise Generator by Particle Swarm Optimization to generate noise points on original images to lower the target models accuracy of correctly predicting the target images label, so to protect the information contained in the target image from the image classification models. The model performs in a semi-black-box manner and balances the number of queries to the target and total number of modified points. We also propose an initialization strategy for the model, PSO Knowledge Transfer, which initializes the models parameters with experience learned from previous runs to further reduce the number of query times and noise points. The model is evaluated using the image classification benchmark model ResNet50 and shows an advantage compared to the baseline algorithm. © 2020, Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Communication efficiency in federated learning: Achievements and challenges

arXiv

引用

arXiv 2021年

作者： Shahid, Osama Pouriyeh, Seyedamin Parizi, Reza M. Sheng, Quan Z. Srivastava, Gautam Zhao, Liang Department of Information Technology Kennesaw State University MariettaGA United States Department of Software Engineering and Game Development Kennesaw State University MariettaGA United States Department of Computing Macquarie University Sydney Australia Department of Math and Computer Science Brandon University Canada Research Centre for Interneural Computing China Medical University Taichung Taiwan

Federated Learning (FL) is known to perform Machine Learning tasks in a distributed manner. Over the years, this has become an emerging technology especially with various data protection and privacy policies being imposed FL allows performing machine learning tasks whilst adhering to these challenges. As with the emerging of any new technology, there are going to be challenges and benefits. A challenge that exists in FL is the communication costs, as FL takes place in a distributed environment where devices connected over the network have to constantly share their updates this can create a communication bottleneck. In this paper, we present a survey of the research that is performed to overcome the communication constraints in an FL setting. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enable an innovative prolonged exposure therapy of attention deficits on autism spectrum through adaptive virtual environments 10

Enable an innovative prolonged exposure therapy of attention...

引用

10th International Conference on Virtual Worlds and games for Serious Applications, VS-games 2018

作者： Mei, Chao Guo, Rongkai Department of Software Engineering and Game Development Kennesaw State University Marietta United States

ISBN: (纸本)9781538671238

A prototype of adaptive virtual environments therapy system (AVET) was developed which will enable innovative Virtual Reality (VR)-based therapy approach for children with attention deficit on the autism spectrum. Many systems have successfully used VR in Autism Spectrum Disorders (ASD) therapies. Most of them use VR as an alternative way to conduct therapies by simulating traditional therapies or real-life experiences. The AVET employed VR-exclusive »impossible experiences» (e.g., a chair that deforms upon the user's gaze, a transparent human) which are not available in real world. The AVET identifies, influences the user's cognition, and delivers a customized Prolonged Exposure (PE)-style VR therapy for children with attention deficits on the autism spectrum. We conducted a preliminary evaluation to the current AVET prototype with the experts. Based on the interview feedbacks, we anticipate the AVET will have a great potential to deliver innovative and effective ASD attention training therapies. © 2018 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A federated approach for fine-grained classification of fashion apparel

arXiv

引用

arXiv 2020年

作者： Mallavarapu, Tejaswini Cranfill, Luke Son, Junggab Kim, Eun Hye Parizi, Reza M. Morris, John Department of Computer Science Kennesaw State University MariettaGA30060 United States Department of Software Engineering and Game Development Kennesaw State University MariettaGA30060 United States Oracle Retail Global Business Unit AtlantaGA United States

As online retail services proliferate and are pervasive in modern lives, applications for classifying fashion apparel features from image data are becoming more indispensable. Online retailers, from leading companies to start-ups, can leverage such applications in order to increase profit margin and enhance the consumer experience. Many notable schemes have been proposed to classify fashion items, however, the majority of which focused upon classifying basic-level categories, such as T-shirts, pants, skirts, shoes, bags, and so forth. In contrast to most prior efforts, this paper aims to enable an in-depth classification of fashion item attributes within the same category. Beginning with a single dress, we seek to classify the type of dress hem, the hem length, and the sleeve length. The proposed scheme is comprised of three major stages: (a) localization of a target item from an input image using semantic segmentation, (b) detection of human key points (e.g., point of shoulder) using a pre-trained CNN and a bounding box, and (c) three phases to classify the attributes using a combination of algorithmic approaches and deep neural networks. The experimental results demonstrate that the proposed scheme is highly effective, with all categories having average precision of above 93.02%, and outperforms existing Convolutional Neural Networks (CNNs)-based schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Integrating Privacy Enhancing Techniques into Blockchains Using Sidechains

Integrating Privacy Enhancing Techniques into Blockchains Us...

引用

2019 IEEE Canadian Conference of Electrical and Computer engineering, CCECE 2019

作者： Parizi, Reza M. Homayoun, Sajad Yazdinejad, Abbas Dehghantanha, Ali Choo, Kim-Kwang Raymond Department of Software Engineering and Game Development Kennesaw State University GA United States Department of Computer Engineering and Information Technology Shiraz University of Technology Shiraz Iran Faculty of Computer Engineering University of Isfahan Iran School of Computer Science University of Guelph ON Canada Department of Information Systems and Cyber Security University of Texas at San Antonio TX United States

ISBN: (纸本)9781728103198

Blockchains are turning into decentralized computing platforms and are getting worldwide recognition for their unique advantages. There is an emerging trend beyond payments that blockchains could enable a new breed of decentralized applications, and serve as the foundation for Internet's security infrastructure. The immutable nature of the blockchain makes it a winner on security and transparency;it is nearly inconceivable for ledgers to be altered in a way not instantly clear to every single user involved. However, most blockchains fall short in privacy aspects, particularly in data protection. Garlic Routing and Onion Routing are two of major Privacy Enhancing Techniques (PETs) which are popular for anonymization and security. Garlic Routing is a methodology using by I2P Anonymous Network to hide the identity of sender and receiver of data packets by bundling multiple messages into a layered encryption structure. The Onion Routing attempts to provide low-latency Internet-based connections that resist traffic analysis, deanonymization attack, eavesdropping, and other attacks both by outsiders (e.g. Internet routers) and insiders (Onion Routing servers themselves). As there are a few controversies over the rate of resistance of these two techniques to privacy attacks, we propose a PET-Enabled Sidechain (PETES) as a new privacy enhancing technique by integrating Garlic Routing and Onion Routing into a Garlic Onion Routing (GOR) framework suitable to the structure of blockchains. The preliminary proposed GOR aims to improve the privacy of transactions in blockchains via PETES structure. © 2019 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Students' motivation in undergraduate courses 9

Students' motivation in undergraduate courses

引用

9th International Multi-Conference on Complexity, Informatics and Cybernetics, IMCIC 2018

作者： Pournaghshband, Hassan Department of Software Engineering and Game Development Kennesaw State University KennesawGA30144 United States

ISBN: (纸本)9781941763698

Education theory suggests that student learning is enhanced when students pay attention to their own learning. There are numerous effective techniques discussed in literature that instructors can employ to encourage their students to pay this attention and enhance their learning. It is important to note that not all these techniques work equally for both, graduate and undergraduate courses. Students vary in culture, socioeconomic status, language, gender, motivation, ability/disability, personal interests and more, and teachers must be aware of these varieties as they plan curriculum. This distinction, specifically considering motivation, ability and personal interests, would even play more significant role when dealing with undergraduate students versus graduate students. In this paper, we address a teaching technique that although it would effectively work for both, graduate and undergraduate courses, but it is better tailored for undergraduate courses. The main idea behind our approach is that it will allow students to grasp the highlights of a topic before its respective lecture is given. The effectiveness of our approach has been evident through higher number of students successfully completing the course as well as the students' feedback at the end of the semester indicating their pleasure about the course. © by the International Institute of Informatics and Systemics 2018.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-based Framework for Detecting Malicious Mobile Applications in App Stores

A Blockchain-based Framework for Detecting Malicious Mobile ...

引用

2019 IEEE Canadian Conference of Electrical and Computer engineering, CCECE 2019

作者： Homayoun, Sajad Dehghantanha, Ali Parizi, Reza M. Choo, Kim-Kwang Raymond Department of Computer Engineering and Information Technology Shiraz University of Technology Shiraz Iran School of Computer Science University of Guelph ON Canada Department of Software Engineering and Game Development Kennesaw State University MariettaGA30060 United States Department of Information Systems and Cyber Security Department of Electrical and Computer Engineering University of Texas at San Antonio San AntonioTX78249 United States

ISBN: (纸本)9781728103198

The dramatic growth in smartphone malware shows that malicious program developers are shifting from traditional PC systems to smartphone devices. Therefore, security researchers are also moving towards proposing novel antimalware methods to provide adequate protection. This paper proposes a Blockchain-Based Malware Detection Framework (B2MDF) for detecting malicious mobile applications in mobile applications marketplaces (app stores). The framework consists of two internal and external private blockchains forming a dual private blockchain as well as a consortium blockchain for the final decision. The internal private blockchain stores feature blocks extracted by both static and dynamic feature extractors, while the external blockchain stores detection results as blocks for current versions of applications. B2MDF also shares feature blocks with third parties, and this helps antimalware vendors to provide more accurate solutions. © 2019 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Internet of Things for Current COVID-19 and Future Pandemics: An Exploratory Study

arXiv

引用

arXiv 2020年

作者： Nasajpour, Mohammad Pouriyeh, Seyedamin Parizi, Reza M. Dorodchi, Mohsen Valero, Maria Arabnia, Hamid R. Department of Information Technology Kennesaw State University MariettaGA United States Department of Software Engineering and Game Development Kennesaw State University MariettaGA United States Department of Computer Science University of North Carolina at Charlotte NC United States Computer Science Department University of Georgia AthensGA United States

In recent years, the Internet of Things (IoT) has drawn convincing research ground as a new research topic in a wide variety of academic and industrial disciplines, especially in healthcare. The IoT revolution is reshaping modern healthcare systems incorporating technological, economic, and social prospects. It is evolving healthcare systems from conventional to more personalized healthcare system where patients can be diagnosed, treated, and monitored more easily. The current global challenge of the COVID-19 pandemic caused by the novel severe contagious respiratory syndrome coronavirus 2 presents the greatest global public health crisis since the pandemic influenza outbreak of 1918. By the moment this paper was written, the number of diagnosed COVID-19 cases around the world reaches more than 14 million. Since then there has been a rapid rise in the different research communities to combating this worldwide threat and IoT technology is one of the pioneers in this area. In the context of COVID-19, IoT enabled /linked devices/applications are utilized to lower the possible spread of COVID-19 to others by early diagnosis, monitoring patients, and practicing defined protocols after patients recovery. This paper surveys the role of IoT-based technologies in facing with COVID-19 and reviews the state-of-the-art architectures, platforms, applications, and industrial IoT-based solutions combating COVID-19 in three main phases including early diagnosis, quarantine time, and after recovery. Copyright © 2020, The Authors. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Join the Fold: Video games, Science Fiction, and the Refolding of Citizen Science

引用

DESIGN ISSUES 2023年第1期39卷 70-87页

作者： Milburn, Colin Buse, Katherine Dhaliwal, Ranjodh Singh Wills, Melissa Aldosari, Raida Camarador, Patrick Miller, Josh Aaron Siegel, Justin Colin Milburn is Gary Snyder Chair in Science and the Humanities and a professor of Science and Technology Studies English and Cinema and Digital Media at the University of California Davis. His research focuses on science literature and media technologies. His books include Nanovision: Engineering the Future (2008) Mondo Nano: Fun and Games in the World of Digital Matter (2015) and Respawn: Gamers Hackers and Technogenic Life (2015). Katherine Buse is an assistant professor of Media Studies at the University of Chicago. Her research focuses on digital media the environmental humanities and the cultures of science and technology. Her current book project Speculative Planetology: Science Culture and the Building of Model Worlds tells the story of how the sciences and the arts co-constructed a toolkit for thinking about planets as whole systems. Ranjodh Singh Dhaliwal is Ruth and Paul Idzik College Chair in Digital Scholarship and an assistant professor of English and Film Television and Theatre at the University of Notre Dame. His work spans media theory science and technology studies and literary criticism. His current book project Rendering: A Political Diagrammatology of Computation shows how our cultural politico-economic and epistemic formulations crystallize into hardware and software architectures. Melissa Wills is a visiting scholar in the Department of Science and Technology Studies at the University of California Davis. She completed her PhD in English at UC Davis in 2021. Her research addresses the relationship between the life sciences and science fiction. Her current book project Ruptures: Life without Germs in the Microbiome Era examines microbiology's debt to the imagination of germ-free worlds. Raida Aldosari is the lead artist on the Foldit: First Contact development team. She received her BS in Nutrition Science from the University of California Davis in 2018. She has experience as a freelance graphic designer and as a project manager for nutrition training and courses.

This article explores the value of science fiction narratives in games for citizen science. Focusing on the protein-folding game Foldit, it describes the process of modifying and redesigning the game to feature a framing narrative and other alterations to the main tutorial campaign. The campaign narrative, Foldit: First Contact, situates the practices of citizen science in an expanded context of meanings and ethical implications, promoting critical self-reflection on the relations of science and civic values. A study of player responses to Foldit: First Contact suggests the significance of science fiction and critical game design for attuning citizen scientists to the collective responsibilities of experimentation and innovation, drawing attention to the intersecting social, technical, and environmental domains in which gamers may contribute to scientific research.

关键词： citizen science science fiction video games narratives

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：