Until now, we were determining stable data gathering (DG) trees for mobile sensor networks (MSNs) using a link stability metric (computationally-light or computationally-heavy) that is directly computed on the egocentric edge network. Among such DG trees, the BPI' (complement of bipartivity index)-based DG trees were observed to be the most stable, but the BPI' metric is also computationally-heavy. Hence, we seek to build a multi-variable linear regression model to predict the BPI' values for the egocentric networks of edges using three computationally-light metrics (neighborhood overlap: NOVER, one-hop two-hop neighborhood: OTH, and normalized neighbor degree: NND) that are also computed on the egocentric edge networks. The training and testing are conducted as part of a single simulation run (i.e., in-situ). The training dataset comprises of the BPI', NOVER, OTH and NND values of randomly sampled egocentric edge networks during the first phase of the simulation (1/5th of the total simulation time). We observe the R-square values for the prediction to be above 0.85 for both low density and high density networks. We also observe the lifetimes of the predicted BPI'-based DG trees to be 87-92% and 55-75% of the actual BPI'-based DG trees for low-moderate and moderate-high density networks respectively.
{"title":"Multi-Variable Linear Regression-Based Prediction of A Computationally-Heavy Link Stability Metric for Mobile Sensor Networks","authors":"N. Meghanathan","doi":"10.5121/csit.2019.91103","DOIUrl":"https://doi.org/10.5121/csit.2019.91103","url":null,"abstract":"Until now, we were determining stable data gathering (DG) trees for mobile sensor networks (MSNs) using a link stability metric (computationally-light or computationally-heavy) that is directly computed on the egocentric edge network. Among such DG trees, the BPI' (complement of bipartivity index)-based DG trees were observed to be the most stable, but the BPI' metric is also computationally-heavy. Hence, we seek to build a multi-variable linear regression model to predict the BPI' values for the egocentric networks of edges using three computationally-light metrics (neighborhood overlap: NOVER, one-hop two-hop neighborhood: OTH, and normalized neighbor degree: NND) that are also computed on the egocentric edge networks. The training and testing are conducted as part of a single simulation run (i.e., in-situ). The training dataset comprises of the BPI', NOVER, OTH and NND values of randomly sampled egocentric edge networks during the first phase of the simulation (1/5th of the total simulation time). We observe the R-square values for the prediction to be above 0.85 for both low density and high density networks. We also observe the lifetimes of the predicted BPI'-based DG trees to be 87-92% and 55-75% of the actual BPI'-based DG trees for low-moderate and moderate-high density networks respectively.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116322507","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}
Insider threat has become a serious issue to the many organizations. Various companies are increasingly deploying many information technologies to prevent unauthorized access to getting inside their system. Biometrics approaches have some techniques that contribute towards controlling the point of entry. However, these methods mainly are not able to continuously validate the users reliability. In contrast behavioral profiling is one of the biometrics technologies but it focusing on the activities of the users during using the system and comparing that with a previous history. This paper presents a comprehensive analysis, literature review and limitations on behavioral profiling approach and to what extent that can be used for mitigating insider misuse.
{"title":"The Feasibility of Using Behavioural Profiling Technique for Mitigating Insider Threats: Review","authors":"Gaseb Alotibi, N. Clarke, Fudong Li, S. Furnell","doi":"10.5121/csit.2019.91106","DOIUrl":"https://doi.org/10.5121/csit.2019.91106","url":null,"abstract":"Insider threat has become a serious issue to the many organizations. Various companies are increasingly deploying many information technologies to prevent unauthorized access to getting inside their system. Biometrics approaches have some techniques that contribute towards controlling the point of entry. However, these methods mainly are not able to continuously validate the users reliability. In contrast behavioral profiling is one of the biometrics technologies but it focusing on the activities of the users during using the system and comparing that with a previous history. This paper presents a comprehensive analysis, literature review and limitations on behavioral profiling approach and to what extent that can be used for mitigating insider misuse.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133301685","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}
MatBase is a prototype intelligent data and knowledge base management system based on the Relational, Entity-Relationship, and (Elementary) Mathematical Data Models, having two current versions (MS SQL Server and C#, MS Access and VBA). Users may work with it only at one or any combination of these conceptual levels, without any programming knowledge (be it SQL, C#, VBA, etc.), to create, populate, update, and delete databases and corresponding management software applications. The paper introduces the MatBase architecture and the principles used to transparently program while modelling data at these three conceptual levels with this tool. A real-life example illustrates them.
MatBase是一个基于关系、实体-关系和(初级)数学数据模型的智能数据和知识库管理系统的原型，目前有两个版本(MS SQL Server和c#， MS Access和VBA)。用户可以只在这些概念级别的一个或任何组合上使用它，而不需要任何编程知识(无论是SQL, c#， VBA等)来创建，填充，更新和删除数据库和相应的管理软件应用程序。本文介绍了MatBase的体系结构以及使用该工具在这三个概念层对数据建模时透明编程的原则。一个现实生活中的例子说明了这一点。
{"title":"Matbase – A Tool for Transparent Programming While Modelling Data at Conceptual Levels","authors":"Christian Mancas","doi":"10.5121/csit.2019.91102","DOIUrl":"https://doi.org/10.5121/csit.2019.91102","url":null,"abstract":"MatBase is a prototype intelligent data and knowledge base management system based on the Relational, Entity-Relationship, and (Elementary) Mathematical Data Models, having two current versions (MS SQL Server and C#, MS Access and VBA). Users may work with it only at one or any combination of these conceptual levels, without any programming knowledge (be it SQL, C#, VBA, etc.), to create, populate, update, and delete databases and corresponding management software applications. The paper introduces the MatBase architecture and the principles used to transparently program while modelling data at these three conceptual levels with this tool. A real-life example illustrates them.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124292515","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}
The evolving complexity of modern technologies brings new concepts, solutions, tools, but also new needs and problems. We review a computing and communication model inspired in physics, to examine complex systems under a perspective of physics-inspired principles like symmetry and conservation-laws. Aiming to help design, build, and control systems, we apply concepts like Information-Symmetry, propagation of information, or inertia to model communications. Modelling computing under physics reactions and conservation laws gives tools to automatically audit each process and create side effects on deviations, bringing advantages in verification, security, and to gain reliability. We review the Feynman-diagrams in computing, rotating diagrams to obtain reversible operations from one formula, and using the diagrams to verify consistency against a unique computing expression. Applications include dealing with data uncertainty, we show advantages to control fuzzy systems and reduce dataset needing further screening. Model and diagrams are proposed as tools to help automate and refine designs, and to gain in reliability.
{"title":"Information –Symmetry and Feynman-Diagrams Applied to Computing Models","authors":"Carlos Martinez, A. González, Ewa Nieminsky","doi":"10.5121/csit.2019.91108","DOIUrl":"https://doi.org/10.5121/csit.2019.91108","url":null,"abstract":"The evolving complexity of modern technologies brings new concepts, solutions, tools, but also new needs and problems. We review a computing and communication model inspired in physics, to examine complex systems under a perspective of physics-inspired principles like symmetry and conservation-laws. Aiming to help design, build, and control systems, we apply concepts like Information-Symmetry, propagation of information, or inertia to model communications. Modelling computing under physics reactions and conservation laws gives tools to automatically audit each process and create side effects on deviations, bringing advantages in verification, security, and to gain reliability. We review the Feynman-diagrams in computing, rotating diagrams to obtain reversible operations from one formula, and using the diagrams to verify consistency against a unique computing expression. Applications include dealing with data uncertainty, we show advantages to control fuzzy systems and reduce dataset needing further screening. Model and diagrams are proposed as tools to help automate and refine designs, and to gain in reliability.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130784020","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}
This paper presents a novel methodology for automatically extracting pragmatic markers from large streams of texts and repositories of documents. Pragmatic markers typically are implications, innuendos, suggestions, contradictions, sarcasms or references that are difficult to define objectively, but that are subjectively evident. Our methodology uses a two-stage augmented learning model applied to a specific use case, extracting from a repository of over 1500 Article IV country reports prepared for government officials by International Monetary Fund (IMF) staff. The model uses principles of evidence theory to train a machine to decipher the textual patterns of suggested actions for government officials and to extract those suggestions from the country reports at scale. We demonstrate the effectiveness of the model with impressive precision and recall metrics that over time outperform even the human trainers.
{"title":"An Augmented Intelligence Model to Extract Pragmatic Markers","authors":"V. Perincherry, David White, Staci Warden","doi":"10.5121/csit.2019.91110","DOIUrl":"https://doi.org/10.5121/csit.2019.91110","url":null,"abstract":"This paper presents a novel methodology for automatically extracting pragmatic markers from large streams of texts and repositories of documents. Pragmatic markers typically are implications, innuendos, suggestions, contradictions, sarcasms or references that are difficult to define objectively, but that are subjectively evident. Our methodology uses a two-stage augmented learning model applied to a specific use case, extracting from a repository of over 1500 Article IV country reports prepared for government officials by International Monetary Fund (IMF) staff. The model uses principles of evidence theory to train a machine to decipher the textual patterns of suggested actions for government officials and to extract those suggestions from the country reports at scale. We demonstrate the effectiveness of the model with impressive precision and recall metrics that over time outperform even the human trainers.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116758293","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}
Empirical Mode Decomposition is an adaptive and local tool that extracts underlying analytical components of a non-linear and non-stationary process, in turn, is the basis of Hilbert Huang transform, however, there are problems such as interfering modes or ensuring the orthogonality of decomposition. Three variants of the algorithm are evaluated, with different experimental parameters and on a set of 10 time series obtained from surface electromyography. Experimental results show that obtaining low error in reconstruction with the analytical signals obtained from a process is not a valid characteristic to ensure that the purpose of decomposition has been fulfilled (physical significance and no interference between modes), in addition, freedom must be generated in the iterative processes of decomposition so that it has consistency and does not generate biased information. This project was developed within the framework of the research group DIGITI of the Universidad Distrital Francisco Jose de Caldas.
{"title":"Inspection of Methods of Empirical Mode Decomposition","authors":"Roberto Hern'andez Santander, E. Casallas","doi":"10.5121/csit.2019.91104","DOIUrl":"https://doi.org/10.5121/csit.2019.91104","url":null,"abstract":"Empirical Mode Decomposition is an adaptive and local tool that extracts underlying analytical components of a non-linear and non-stationary process, in turn, is the basis of Hilbert Huang transform, however, there are problems such as interfering modes or ensuring the orthogonality of decomposition. Three variants of the algorithm are evaluated, with different experimental parameters and on a set of 10 time series obtained from surface electromyography. Experimental results show that obtaining low error in reconstruction with the analytical signals obtained from a process is not a valid characteristic to ensure that the purpose of decomposition has been fulfilled (physical significance and no interference between modes), in addition, freedom must be generated in the iterative processes of decomposition so that it has consistency and does not generate biased information. This project was developed within the framework of the research group DIGITI of the Universidad Distrital Francisco Jose de Caldas.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126583439","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}
Nowadays, road traffic accidents are one of the leading causes of deaths in this world. It is a complex phenomenon leaving a significant negative impact on human’s life and properties. Classification techniques of data mining are found efficient to deal with such phenomena. After collecting data from Lebanese Internal Security Forces, data are split into training and testing sets using 10-fold cross validation. This paper aims to apply two different algorithms of Decision Trees C4.5 and CART, and various Artificial Neural Networks (MLP) in order to predict the fatality of road accidents in Lebanon. Afterwards, a comparative study is made to find the best performing algorithm. The results have shown that MLP with 2 hidden layers and 42 neurons in each layer is the best algorithm with accuracy rate of prediction (94.6%) and area under curve (AUC 95.71%).
{"title":"Comparative Study Between Decision Trees and Neural Networks to Predictfatal Road Accidents in Lebanon","authors":"Z. Farhat, Ali Karouni, B. Daya, P. Chauvet","doi":"10.5121/csit.2019.91101","DOIUrl":"https://doi.org/10.5121/csit.2019.91101","url":null,"abstract":"Nowadays, road traffic accidents are one of the leading causes of deaths in this world. It is a complex phenomenon leaving a significant negative impact on human’s life and properties. Classification techniques of data mining are found efficient to deal with such phenomena. After collecting data from Lebanese Internal Security Forces, data are split into training and testing sets using 10-fold cross validation. This paper aims to apply two different algorithms of Decision Trees C4.5 and CART, and various Artificial Neural Networks (MLP) in order to predict the fatality of road accidents in Lebanon. Afterwards, a comparative study is made to find the best performing algorithm. The results have shown that MLP with 2 hidden layers and 42 neurons in each layer is the best algorithm with accuracy rate of prediction (94.6%) and area under curve (AUC 95.71%).","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134068735","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}
The Named Data Networking (NDN) immunes to most of the attacks which exist in today’s Internet. However, this newborn network architecture may still subject to Distributed Denial of Service (DDOS) attacks if less evaluation is paid. In this paper, we firstly give a survey of the state of art works on the mitigations of the Content Poisoning Attack (CPA) in NDN and discuss their limitations as well. After this, we give out our mitigation and the results from simulations show that with the implementation of our mitigation, the Interest Satisfaction Rate (ISR) of all Consumers maintains a highly acceptable rate even when network is under CPA.
{"title":"Mitigate Content Poisoning Attack in NDN by Namespace Authorization","authors":"Pengfei Yue, Bin Pang","doi":"10.5121/csit.2019.91109","DOIUrl":"https://doi.org/10.5121/csit.2019.91109","url":null,"abstract":"The Named Data Networking (NDN) immunes to most of the attacks which exist in today’s Internet. However, this newborn network architecture may still subject to Distributed Denial of Service (DDOS) attacks if less evaluation is paid. In this paper, we firstly give a survey of the state of art works on the mitigations of the Content Poisoning Attack (CPA) in NDN and discuss their limitations as well. After this, we give out our mitigation and the results from simulations show that with the implementation of our mitigation, the Interest Satisfaction Rate (ISR) of all Consumers maintains a highly acceptable rate even when network is under CPA.","PeriodicalId":285934,"journal":{"name":"5th International Conference on Computer Science, Information Technology (CSITEC 2019)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372496","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：