2021 International Conference on Computational Science and Computational Intelligence (CSCI)最新文献_第4页

Analysis of Routing Entropy in Hyperbolic Trees 双曲树路由熵的分析

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00161

Zalán Heszberger, András Majdán, A. Gulyás, András Bíró, László Balázs, J. Bíró

{"title":"Analysis of Routing Entropy in Hyperbolic Trees","authors":"Zalán Heszberger, András Majdán, A. Gulyás, András Bíró, László Balázs, J. Bíró","doi":"10.1109/CSCI54926.2021.00161","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00161","url":null,"abstract":"Recent results have shown that the memory requirements of destination-based hop-by-hop routing in largescale communication networks can efficiently be estimated by the information theoretic!! entropy of the forwarding tables placed at the nodes. For calculating and analyzing the memory usage the forwarding tables are to be inferred according to the routing algorithm, then the entropy values can be established. This could be a computationally intensive task, especially in case of large networks operated along complex routing policies making the analysis hard and less tractable. In this paper we focus on a special case, when the routing is based on a spanning tree the so called hyperbolic tree. We show that the routing entropy can efficiently be computed in this case without generating the forwarding tables. Based on this computation, analytical results on routing scalability with respect to memory usage can also be derived, which confirms observations on numerical investigations. These network theoretical results will expectedly have significance in the forthcoming 5th generation (5G) and the future 6th generation (6G) complex communication systems. The representation and modelling power of hyperbolic complex networks may greatly help in mastering the complexity of rapidly expanding systems like 5G and 6G communication networks.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"78 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133931292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Circular Framework from Branding to Recruitment in Perspective of Higher Education : Type of the submission: Full/Regular Research Paper Symposium acronyms is: CSCI-ISED 从高等教育的角度来看，从品牌推广到招聘的循环框架:提交类型:完整/定期研究论文研讨会缩写为:CSCI-ISED

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00067

Miao Chen, Ali A. Al-Babawat, A. Alsadoon, Srujal Patel, R. M. Salah, P. Prasad

引用次数: 0

Redesigning An Undergraduate Course: Principles of Programming Languages 重新设计本科课程:程序设计语言原理

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00015

Xuguang Chen

引用次数: 0

Evaluation of the security level of Aruba wireless networks in an educational center 某教育中心Aruba无线网络安全等级评估

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00275

De La Cruz De La Cruz Paola, Rúsbel Domínguez Domínguez

引用次数: 1

Design of Network Forensics Labs for Teaching-oriented Institutions 面向教学院校的网络取证实验室设计

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00213

Kewei Sha, Wei Wei, Arpit Jain

{"title":"Design of Network Forensics Labs for Teaching-oriented Institutions","authors":"Kewei Sha, Wei Wei, Arpit Jain","doi":"10.1109/CSCI54926.2021.00213","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00213","url":null,"abstract":"Network-related cyber crimes including Phishing attacks, DDoS attacks, Identity Theft, etc. increase significantly with the extension of networked devices and systems. Cyber crime investigation conducted by network forensic professionals is critical not only to discover the source of security attacks but also to prevent future crimes. Although colleges and universities start involving forensics in education programs and forensics professionals training based on well-designed and effective curricula, there is still a significant gap between the supply of qualified network forensics professionals and what the market demands. As a highly technical subject, network forensics requires practitioners to obtain necessary knowledge and skills through both theoretical learning hands-on labs. However, survey of existing curricula shows the lack of hands-on network forensics labs. Therefore, we aim to develop a suite of initial hands-on network forensics labs that can be easily integrated into a Network Forensics course. The design focuses on addressing two major issues, building an isolated lab environment from the existing campus network and creating labs that provide realistic and practical experiences. In this paper, we first discuss the challenges of developing network forensics labs, then we describe our approaches to overcome those challenges. In addition, we also present the design of three typical network forensics labs. We believe that our designed labs, as well as the lessons learned, can help other institutions to develop effective network forensics courses.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131151077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Sentiment Analysis Approach for Abusive Content Detection using Improved Dataset 一种基于改进数据集的滥用内容检测情感分析方法

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00283

Aziz L. Ngou Njikam Abdou, Elie Fute Tagne

引用次数: 0

Lateral Flow Test Interpretation with Residual Networks 用残余网络解释横向流动试验

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00261

Dena F. Mujtaba, N. Mahapatra

{"title":"Lateral Flow Test Interpretation with Residual Networks","authors":"Dena F. Mujtaba, N. Mahapatra","doi":"10.1109/CSCI54926.2021.00261","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00261","url":null,"abstract":"Lateral flow tests (LFTs) are a cost-effective, quick, and frequently used testing method in many domains such as food safety and environmental and clinical applications. However, a major challenge is accurate interpretation of LFT results. Often, if a low level of target substance is present in the input liquid, the test line indicator may appear faint, causing a test interpreter to read the test result as a false negative. Therefore, to address this problem, we propose a deep-learning-based method to interpret images of LFT results. Our model is based on ResNet-101, a state-of-the-art image classification model that uses residual networks, or skip-connections between layers to improve learning on the training dataset. We further improve our model by using data augmentation to generate additional and more difficult images of LFTs for the model to learn from, thereby improving its performance and reducing overfitting to the training dataset. Our approach is also trained and tested on a dataset of SARS-CoV-2 LFT images, containing both positive and negative results. We compare our ResNet approach to a baseline convolutional neural network model. Our results show the ResNet model achieves a higher specificity and sensitivity than the baseline model to interpret LFT results.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131995421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Quantifying the Impact of Vulnerabilities of the Components of an Information System towards the Composite Rise Exposure 量化信息系统组件脆弱性对复合上升暴露的影响

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00193

Yanzhen Qu, Adam English, Brace Hannon

引用次数: 0

Weakly Supervised Crowdsourcing Learning Based on Adversarial Consensus 基于对抗共识的弱监督众包学习

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00052

Menglong Wei, Shao-Yuan Li, Sheng-Jun Huang

引用次数: 0

Model-Based Security Testing of Vehicle Networks 基于模型的车辆网络安全测试

2021 International Conference on Computational Science and Computational Intelligence (CSCI) Pub Date : 2021-12-01 DOI: 10.1109/CSCI54926.2021.00179

Florian Sommer, R. Kriesten, F. Kargl

{"title":"Model-Based Security Testing of Vehicle Networks","authors":"Florian Sommer, R. Kriesten, F. Kargl","doi":"10.1109/CSCI54926.2021.00179","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00179","url":null,"abstract":"Modern vehicles consist of a large number of electronic information technology components, which communicate with each other and external components. To protect vehicles against security attacks, automotive-specific standards and regulations require an integration of security concepts and measures in vehicles. Security testing techniques, such as penetration tests, are used to verify and validate those measures. However, these methods are usually carried out manually in late phases of development. Thus, identified vulnerabilities can only be eliminated at a late stage leading to a high investment of time and resources. This paper presents a model-based security testing approach which aims to enable security tests early on in the vehicle development process in an automated way. This allows vulnerabilities to be identified and eliminated at an early stage during development. Therefore, we show our concept to create a security model based on a vehicle network. This model can be used to automatically derive attack paths for security testing. We further illustrate our approach by applying it to a real-world vehicle network.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131272753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3