2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)最新文献

{"title":"An Approach to Terrain Trafficability Evaluation Based on a Neural Network for Emergency Decision-Support Systems","authors":"A. Pershutkin, A. Dukhanov, Petr Gladilin","doi":"10.1109/AICT47866.2019.8981782","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981782","url":null,"abstract":"This paper deals with a new method to evaluate the velocity of a transport unit based on static and dynamic data on terrain relief, urban objects, and the values of hydrometeorological parameters. We considered the existing and available approaches to off-road routes based on the parameters mentioned above (considering velocity reduction depending on terrain parameters) and defined the problem statement. Then, we designed the method to evaluate the velocity on a terrain surface using an artificial neural network. Our method considers the static data (e.g., type of surface) and dynamic hydro-meteorological parameters of the terrain. To determine the efficiency of the method, we conducted the experiment using data from the Leningrad region. The experiment shows significantly increased accuracy in the velocity evaluation of the transport unit.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132296168","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}

{"title":"A Conceptual Model of an Intelligent Platform for Security Risk Assessment in SMEs","authors":"Laura Arenda, O. Popov","doi":"10.1109/AICT47866.2019.8981796","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981796","url":null,"abstract":"SMEs are increasingly targeted by cyberattacks and usually less in control of their Information Security Management System than larger organizations due to a lack of resources. Risk assessment can help them to determine which changes are needed bearing in mind their constraints. However, common frameworks for risk assessments are more suitable for large organizations. Some of them have been designed specifically for SMEs but still target an audience of information security experts and are considered as time-consuming by SMEs. This article aims at tackling those issues by introducing a conceptual model of an Intelligent Platform for supporting SMEs in security risk assessment process. The design research method was used to develop a model taking into account the inputs from relevant stakeholders collected via interviews. The model was validated and improved with case studies where quick security risk assessments in three different SMEs have been performed following the activities that the proposed model is supposed to perform.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"303 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115405052","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}

{"title":"Machine Learning and Advanced Analytics in Tax Fraud Detection","authors":"A. Adamov","doi":"10.1109/AICT47866.2019.8981758","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981758","url":null,"abstract":"We all are passing through Big Data Renaissance right now. Academic literature shows increasing interest to subject of application of Big Data technology to cross-sectoral business and relevant scientific research. But portion of research papers devoted to application of Big Data to Taxation is relatively small, despite of the fact that tax generates huge amounts of Data and has enormous potential to benefit from Big Data Analytics. This paper is a conceptual approach to build theoretical and methodological foundation for Data Analytics application in taxation. It is described how tax authorities can benefit from their operational data. Primary prerequisites for efficient application of Advanced Data Analytics are revealed.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116923375","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}

{"title":"Performance Comparison of Convolutional Neural Network Models on GPU","authors":"M. M. Yapıcı, Adem Tekerek, Nurettin Topaloglu","doi":"10.1109/AICT47866.2019.8981749","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981749","url":null,"abstract":"Deep learning methods are used in many popular areas such: image processing, computer vision, autonomous vehicles, character recognition, audio and video processing. These methods require high processing power, such as graphics cards (GPUs), to obtain successful results in the solution of NP hard problems which have big data. In this study, performance comparison of convolutional neural network (CNN) architectures were performed on GPU. ResNet, VGGNet19 and DenseNet CNN models, and GPDS signature dataset were used for comparison. According to the obtained results, ResNet50 took up the least amount of GPU memory space. The best classification results were obtained with DenseNet121 and the second one was from ResNet50.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131623695","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}

{"title":"Another Generalization of $3mathrm{x}+1$ Problem: Existence of periodicity in the construction of numbers in periodic version of generalized Collatz’ problem and its computational aspects","authors":"Y. Aliyev","doi":"10.1109/AICT47866.2019.8981720","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981720","url":null,"abstract":"In the paper, another generalization of Collatz's Syracuse problem was discussed. For a given initial integer number, each next integer number is obtained by dividing the previous integer by 2 (T operation), or multiplying it by 3, adding 1 and then dividing by 2 (S operation), or finally, multiplying by 3, adding 2 and then dividing by 2 (V operation), provided that all of these divisions by 2 are possible. The presence of this last operation V makes the problem more general. We ask the following question: How can one find from the given sequence of T, S, V operations whether an initial integer exists which after all these operations, applied in the given order, will end up with the same initial number? We found an algorithm that can quickly find that integer or determine if such an integer doesn't exist. We also discuss relationship of this problem with 3-adic numbers which we use to represent the elements of the periodic sequence.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"98 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133801672","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}

{"title":"Performance Analysis of Topology and Destination Based Routing Protocols in Mobile Ad-Hoc Network Using NS2","authors":"A. A. Ajibesin, M. Kah, A. T. Ishaq, Caleb A. Ajibesin","doi":"10.1109/AICT47866.2019.8981772","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981772","url":null,"abstract":"In this paper, three MANET routing protocols were simulated. One is the DSDV which is a destination-based proactive protocol. Others are DSR and AODV which are topology-based reactive protocols. Also, three metrics namely, Throughput, Packet delivery ratio (PDR) and Jitter were considered for the performance evaluation. The protocols were simulated using network simulator 2. The results showed that the average Throughput, the PDR and average Jitter of the protocols increased as the number of network topology (nodes) increased. Overall, AODV protocol outperformed the other two protocols for all the observed metrics when the network exceeds 35 nodes while the DSR is the better protocol in smaller networks. Thus, the two reactive protocols (DSR Topology-based and AODV Destination-based) have shown better performance over the DSDV Destination-based proactive protocol. Furthermore, the trend analysis based on the cumulative performance in different network scenarios is useful information for the network designers.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127661567","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}

{"title":"Sentiment Analysis of Azerbaijani twits Using Logistic Regression, Naive Bayes and SVM","authors":"Huseyn Hasanli, S. Rustamov","doi":"10.1109/AICT47866.2019.8981793","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981793","url":null,"abstract":"In the work, the roadmap of sentiment analysis of twits in Azerbaijani language has been developed. The principles of collecting, cleaning and annotating of twits for Azerbaijani language are described. Machine learning algorithms, such as Linear regression, Naïve Bayes and SVM applied to detect sentiment polarity of text based on bag of word models. Our suggested approach for data processing and classification can be easily adapted and applied to other Turkish language. Achieved results from different machine learning algorithm have been compared and defined optimal parameters for the classification of twits.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127231538","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}

{"title":"Influence of Interlingual Homonymy on How People Mutually Understand and Visually Perceive Oral Speech","authors":"M. Myasoedova, M. Farkhadov, Z. P. Myasoedova","doi":"10.1109/AICT47866.2019.8981786","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981786","url":null,"abstract":"In this paper we study interlingual homonymy. We compare the Russian language with the languages of other language groups and how homonymy influences the process of speech communication and how speakers understand each other. Interlanguage correspondences attract interest, since if people inaccurately recognize words, the utterance can change its meaning. To a greater extent this is relevant for visual perception of homonyms. Examples of interlanguage homonyms of various linguistic structures are given. We implemented the basis module of the «Chitaem s gub» multimedia program; the program was developed by the authors to teach users to distinguish individual speech elements with similar visemes.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124872501","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}

{"title":"The role of Increasing the Number of Iterations for Numerical Methods upon Digital Image","authors":"Fatin E. M. Al-Obaidi, Ali Jassim Mohamed Ali, Khalid G. Mohammed","doi":"10.1109/AICT47866.2019.8981760","DOIUrl":"https://doi.org/10.1109/AICT47866.2019.8981760","url":null,"abstract":"Due to its numerical procedure, an expected error occurred in applying the numerical algorithms. A challenging attempt toward using such approximation methods on digital image has been utilized here. Bisection, Newton Raphson, and secant methods are some numerical techniques which have been used here for certain considerations to test their evaluation upon a digital image through investigating the role of increasing the number of iterations each time. Results show that Bisection method is the best numerical technique than other used techniques in its approximated use upon an image with least and stable absolute and relative errors. Increasing the number of iterations didn't affect its numerical procedure while an alternative errors with a bell shape resulted in the case of Newton- Raphson and secant methods. Absolute error seems to be more sensitive estimator than relative one toward detecting the suitable number of iterations that caused a least significant error","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131730960","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}

{"title":"A New Bandwidth Management Model using Software-Defined Networking Security Threats","authors":"K. Nisar, Emilia Rosa Jimson, Mohd. Hanafi bin Ahmad Hijazi, Ag. Asri Ag. Ibrahim, Yong-Jin Park, I. Welch","doi":"10.1109/aict47866.2019.8981784","DOIUrl":"https://doi.org/10.1109/aict47866.2019.8981784","url":null,"abstract":"Available bandwidth in network is limited, it is very critical to manage the network bandwidth efficiently. In this research, bandwidth management model based on Software-Defined Networking (SDN) architecture is examined. Through the recommended model, real-time traffic over network was given importance to approach the restricted bandwidth over non real-time traffic. SDN promises the simplification of network management compared to the traditional network. SDN architecture breaks the vertically integrated current network design and it introduces centralized network control through the SDN controller, which is considered as the greatest contribution of SDN in networking area. SDN architecture is adopted in this paper since it promotes centralized control features which enable grid programmability and supports improve network resources administration. Simulation was conducted using the EstiNet network simulator. Two groups of experiments with different situations have been conducted. Each experiment consisted of five simulations with different number of sender and receiver nodes. The first experiment simulated the traffics in a traditional networking; and the second experiment simulated the traffics in a proposed network model. In addition, bulk of the existing bandwidth was reserved to real-time traffic and the remaining quantity was reserved for non-real-time traffic. The real-time throughput results of the two different experiments have been compared to estimate the performance of the proposed SDN research model. The experiment results presented that the recommended model has successfully given urgency to real-time network traffic to approach the limited network bandwidth. As the number of nodes increases, the conventional real-time throughput of setup one and setup two decreases linearly. When nodes reach 10, the real-time ordinary throughput of setup one and setup two are 63SKBps and 473KBps respectively.","PeriodicalId":329473,"journal":{"name":"2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130684041","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}