Transactions on Networks and Communications最新文献_第6页

Interpretable machine learning approach for predicting COVID-19 risk status of an individual 预测个体COVID-19风险状态的可解释机器学习方法

Transactions on Networks and Communications Pub Date : 2021-04-04 DOI: 10.14738/TNC.92.9760

A. Onoja, M. Ejiwale, Ayesan Rewane

{"title":"Interpretable machine learning approach for predicting COVID-19 risk status of an individual","authors":"A. Onoja, M. Ejiwale, Ayesan Rewane","doi":"10.14738/TNC.92.9760","DOIUrl":"https://doi.org/10.14738/TNC.92.9760","url":null,"abstract":"This study aimed to ascertained using Statistical feature selection methods and interpretable Machine learning models, the best features that predict risk status (“Low”, “Medium”, “High”) to COVID-19 infection. This study utilizes a publicly available dataset obtained via; online web-based risk assessment calculator to ascertain the risk status of COVID-19 infection. 57 out of 59 features were first filtered for multicollinearity using the Pearson correlation coefficient and further shrunk to 55 features by the LASSO GLM approach. SMOTE resampling technique was used to incur the problem of imbalanced class distribution. The interpretable ML algorithms were implored during the classification phase. The best classifier predictions were saved as a new instance and perturbed using a single Decision tree classifier. To further build trust and explainability of the best model, the XGBoost classifier was used as a global surrogate model to train predictions of the best model. The XGBoost individual’s explanation was done using the SHAP explainable AI-framework. Random Forest classifier with a validation accuracy score of 96.35 % from 55 features reduced by feature selection emerged as the best classifier model. The decision tree classifier approximated the best classifier correctly with a prediction accuracy score of 92.23 % and Matthew’s correlation coefficient of 0.8960. The XGBoost classifier approximated the best classifier model with a prediction score of 99.7 %. This study identified COVID-19 positive, COVID-19 contacts, COVID-19 symptoms, Health workers, and Public transport count as the five most consistent features that predict an individual’s risk exposure to COVID-19.","PeriodicalId":448328,"journal":{"name":"Transactions on Networks and Communications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126756095","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

Novel Multifunction Filter using Current Feedback Amplifier 新型电流反馈放大器多功能滤波器

Transactions on Networks and Communications Pub Date : 2021-03-01 DOI: 10.14738/TNC.91.8122

Nisha Walde, Prashant Kumar Mavi

引用次数: 0

Nelder-Mead Algorithm in Solving Ordinary Differential Equations Whose Solutions Possess Singularities 求解具有奇异性常微分方程的Nelder-Mead算法

Transactions on Networks and Communications Pub Date : 2021-02-28 DOI: 10.14738/TNC.91.9772

A. Wusu, O. Olabanjo

引用次数: 1

Low-cost Wireless Personal Weather Station for Rural Farmers 面向农民的低成本无线个人气象站

Transactions on Networks and Communications Pub Date : 2021-02-28 DOI: 10.14738/TNC.91.9647

André Rodrigue Tchamda, K Merlain Boris Djousse, Anselme Maffo Koumetio, M. Fonteh, F. B. Pelap, R. Tchitnga, M. Kom

引用次数: 0

A Comparison of Fair Sharing Algorithms for Regulating Search as a Service API 规范搜索即服务API的公平共享算法比较

Transactions on Networks and Communications Pub Date : 2021-02-11 DOI: 10.14738/TNC.86.9633

S. Bagui, Evorell Fridge

{"title":"A Comparison of Fair Sharing Algorithms for Regulating Search as a Service API","authors":"S. Bagui, Evorell Fridge","doi":"10.14738/TNC.86.9633","DOIUrl":"https://doi.org/10.14738/TNC.86.9633","url":null,"abstract":"Providers of a Search as a Service (SaaS) environment must ensure that their users will not monopolize the service or use more than their fair share of resources. Fair sharing algorithms have long been used in computer networking to balance access to a router or switch, and some of these algorithms have also been applied to the control of queries submitted to search engine APIs. If a search query’s execution cost can be reliably estimated, fair sharing algorithms can be applied to the input of a SaaS API to ensure everyone has equitable access to the search engine. \u0000The novelty of this paper lies in presenting a Single-Server Max-Min Fair Deficit Round Robin algorithm, a modified version of the Multi-Server Max-Min Fair Deficit Round Robin algorithm. The Single-Server Max-Min Fair Deficit Round Robin algorithm is compared to three other fair sharing algorithms, token-bucket, Deficit Round Robin (DRR), and Peng and Plale’s [1] Modified Deficit Round Robin (MDRR) in terms of three different usage scenarios, balanced usage, unbalanced usage as well as an idle client usage, to determine which is the most suitable fair sharing algorithm for use in regulating traffic to a SaaS API. This research demonstrated that the Single-Server Max-Min Fair DRR algorithm provided the highest throughput of traffic to the search engine while also maintaining a fair balance of resources among clients by re-allocating unused throughput to clients with saturated queues so a max-min allocation was achieved.","PeriodicalId":448328,"journal":{"name":"Transactions on Networks and Communications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127453962","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

Characteristics of Nanopositioning Electroelastic Digital-to-Analog Converter for Communication Systems 通信系统纳米定位电弹性数模转换器特性研究

Transactions on Networks and Communications Pub Date : 2020-12-31 DOI: 10.14738/TNC.86.9699

S. Afonin

引用次数: 0

Practical generation of common random strings for secure multiparty computations over the Internet 在Internet上安全多方计算的通用随机字符串的实际生成

Transactions on Networks and Communications Pub Date : 2020-12-31 DOI: 10.14738/TNC.86.9447

I. Vajda

引用次数: 0

Preserving Privacy Location in 5G by Using Variable Pseudonym 通过使用可变假名保护5G中的隐私位置

Transactions on Networks and Communications Pub Date : 2020-10-31 DOI: 10.14738/TNC.85.9571

Mamoon M. Saeed, R. Saeed, R. Mokhtar, H. Alhumyani, Elmustafa Syed Ali

{"title":"Preserving Privacy Location in 5G by Using Variable Pseudonym","authors":"Mamoon M. Saeed, R. Saeed, R. Mokhtar, H. Alhumyani, Elmustafa Syed Ali","doi":"10.14738/TNC.85.9571","DOIUrl":"https://doi.org/10.14738/TNC.85.9571","url":null,"abstract":"User privacy is one of the most issues addressed extensively in mobile communications evolutions, research literature, and standardization. Location privacy is a key parameter and crucial aspect for user privacy, where most of the tracking, Unsolicited advertising, malicious activities, and location-based terrorism attacks are depending on the location of the victims. For preserving location privacy, various methods in previous mobile networks use a pseudonym instead of permanent identity i.e. Cell Radio Network Temporary Identifiers (C-RNTI), However, these methods based on C-RNII have been proofed that faces many vulnerable due to the clear text used for C-RNII exchange. A man-in-the-middle attack can easily trace users and collect information. The main objective of this paper is to propose a new location privacy algorithm that can greatly enhance the capabilities of the 5G architecture. The proposed algorithm introduces a novel variable pseudonym (V-RNTI) as an identifier for the user radio channel. Also, it provides an enhanced pseudonyms allocation procedure for identification. A new procedure that enabling UE to use different values for V-RNTI changed frequently using agreed equations to generate the values of the identifier. The proposed scheme is compatible with 3GPP standards architecture, where minor modifications/upgrades are needed for UEs eNB. Specifically, we build our model of the 5G V-RNTI authentication protocol and perform an automated security verification tool analysis of the protocol model by using the ProVerif model checker. Our analysis results show that the proposed procedure is working without flaws.","PeriodicalId":448328,"journal":{"name":"Transactions on Networks and Communications","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124507406","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

The Impact of Emerging Wireless Network System and Cybersecurity in A Global Community 新兴无线网络系统和网络安全对全球社区的影响

Transactions on Networks and Communications Pub Date : 2020-10-31 DOI: 10.14738/TNC.85.9628

B. Ele, O. J. Adinya, I. O. Obono

引用次数: 2

Development of an Improved Network Security System using Firewall for Securing Organisational Data 开发使用防火墙保护机构数据的网络安全系统

Transactions on Networks and Communications Pub Date : 2020-10-31 DOI: 10.14738/TNC.85.9605

B. Ele, E. E. Umoh, D. O. Egete

{"title":"Development of an Improved Network Security System using Firewall for Securing Organisational Data","authors":"B. Ele, E. E. Umoh, D. O. Egete","doi":"10.14738/TNC.85.9605","DOIUrl":"https://doi.org/10.14738/TNC.85.9605","url":null,"abstract":"It is eminent that the Internet is far from being secure. Insecure networks have caused organizations to lose lots of money as a result of data loss or data corruption, and even worse, some organizations have also lost their reputation hence reduce the client’s confidence. Therefore, this research focused on the development of an improved network security system using a firewall that can secure both the internal and external network of an organization. The system was developed using both packet filtering and proxy server architectures to prevent unauthorized connection or access to the organization server or resources thereby reducing the risk of attacks to the network and loss of organizational data. The system was implemented using PHP and python programming languages and the backend was developed using MySQL as the database server; HTML, CSS, and JavaScript for the frontend layout. The implementation of this firewall system includes a monitoring admin interface from where most activities within the private network can be monitored and also this system can prevent or deny the unauthorized request of services either by an intruder from an external network or personnel within the network. Based on the findings of this study, the developed system is recommended for any organization that depends on computer networks for the running of their daily activities.","PeriodicalId":448328,"journal":{"name":"Transactions on Networks and Communications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127625648","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