{"title":"Analysis of Popularity Degradation in P2P Overlay Topology","authors":"Gurhan Gunduz","doi":"10.1109/ubmk55850.2022.9919512","DOIUrl":"https://doi.org/10.1109/ubmk55850.2022.9919512","url":null,"abstract":"","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114993320","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":"Android Malware Variant Detection by Comparing Traditional Antivirus","authors":"Mahamat Hassan, I. Sogukpinar","doi":"10.1109/UBMK55850.2022.9919458","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919458","url":null,"abstract":"Android is gradually becoming malware targeting it. According to the recent Symantec threat reports, the number of newly discovered mobile malware variants grew by 54% from 2016 to 2017. Malware writers used obfuscation techniques to create malware variants to evade detection by some tools detections or antivirus companies. it is difficult for antivirus to detect the signature of these variants if the database does not update. It is, therefore, essential to explore new ways to prevent, detect and counter cyberattacks. In these detection mechanisms, machine learning uses to create classifiers that determine whether an application is dangerous or not. In the research, we focus on Android malware detection in Android APK. We analyze obfuscation techniques used by malware writers to create malware variants. We analyze permission and API Calls from Android APK. We compare techniques and how it is not easy for traditional antivirus to detect malware variants.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125513045","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":"Mixed-Method Quantization of Convolutional Neural Networks on an Adaptive FPGA Accelerator","authors":"Hadee Madadum, Y. Becerikli","doi":"10.1109/UBMK55850.2022.9919597","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919597","url":null,"abstract":"Research on quantization of Convolutional Neural Networks (ConNN) has gained attention recently due to the increasing demand for using ConNN models on embedded devices. The quantization method involves compressing the ConNN model to simplify complex computing and reduce resource requirements. Despite this, simply mapping a 32-bit ConNN model to a lower bit can have a negative impact on accuracy. One of the limitations of the quantization is the diversity of parameters in the ConNN model. Different layers have different structures. Thus, using the same quantization method for all layers in the ConNN model can lead to sub-optimal performance. Therefore, we propose a mixed-method quantization, a compression technique that uses different quantization approaches for a single ConNN model. We also propose an adaptive accelerator for quantized ConNN where its architecture is reconfigured during runtime using partial reconfiguration capability. The experimental results show that the proposed design achieves accuracy close to 32-bit models when quantizing ConNN models to 4 bits without retraining. In addition, the adaptive accelerator can achieve the highest resource efficiency of 1.11 GOP/s/DSP and 1.49 GOP/s/kLUT.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122092407","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 Effect of Statistical Attributes on the Determination of Stock Trading Actions","authors":"Zinnet Duygu Akşehir, E. Kılıç","doi":"10.1109/UBMK55850.2022.9919544","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919544","url":null,"abstract":"In this study, the methods used for the position/trade action (buy/sell/hold) estimates of financial assets, especially in the literature, were examined. As a result of the examinations, it was determined that the data imbalance problem arose when performing position labeling on stock price data. In this context, the positions of the four stocks in the BIST30 index after one month were estimated using the k-nearest neighbor and support vector machines methods. The data imbalance problem that occurred during the labeling of stock data as buy/sell/hold was resolved using the SMOTE approach. In addition, the effect of using various attributes based on time series characteristics in addition to price data and technical indicators to predict the position of stock data on model performance was also investigated. We created four different input sets for the prediction models in this context. In two of these sets, monthly data of stocks and 15 technical indicator values were used in addition to these data. In the other two, respectively, the daily data of stocks and, in addition to these data, statistical attributes obtained from 15 technical indicator values are discussed. The results showed that using these statistical features increased the model's performance by 15-20% and reached an Fl-score value of 0.97.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128362304","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}
G. Bekmanova, A. Nazyrova, Nurzada Amangeldy, A. Sharipbay, S. Kudubayeva
{"title":"A New Approach to Developing a Terminological Dictionary of School Subjects in the Kazakh Language","authors":"G. Bekmanova, A. Nazyrova, Nurzada Amangeldy, A. Sharipbay, S. Kudubayeva","doi":"10.1109/UBMK55850.2022.9919581","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919581","url":null,"abstract":"In the context of inclusive education, there is a change in the requirements for electronic educational resources. They can be integrated, and their content and design should correspond to the individual characteristics of the trainees, including trainees with disabilities and special educational needs. Electronic educational resource selection, application, and development are urgent and global problems. One of the crucial directions in the inclusive education system is the development of electronic resources to provide equal access to information and communication for all parties, regardless of which language (verbal or sign) they use. It also forms a barrier-free environment in both formal and informal communication. The most widely needed such resources are secondary school students, who are in the majority. This article discusses a new approach to developing a terminological dictionary of school subjects in the Kazakh language, accompanied by sign language translation and methods of searching for words in the dictionary. The database of school terms is the direction of project № BR11765535, funded by the Ministry of Science and Higher Education due to the need for such digital resources.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129130086","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}
A. Gatiatullin, Lenara Kubedinova, N. Prokopyev, Abduramanov Ibraim
{"title":"Toolset of “Turkic Morpheme” Portal for Creation of Electronic Corpora of Turkic Languages in a Unified Conceptual Space","authors":"A. Gatiatullin, Lenara Kubedinova, N. Prokopyev, Abduramanov Ibraim","doi":"10.1109/UBMK55850.2022.9919449","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919449","url":null,"abstract":"Sphere of electronic corpora creation as a way of preservation and development of natural languages as well as a resource base for developers of NLP technologies and language researchers experience a rapid increase in number and volume of electronic corpora for many languages, including Turkic languages. However, a lot of Turkic languages has no corpus due to their developers having problems with implementation and supporting the operation of such large, technically demanding resources. This paper presents the toolset for creation of Turkic corpora within the “Turkic Morpheme” web-portal, the multilingual resource with language-independent grammatical, syntactic and semantic level models and language-dependent data for Turkic language family. Use of this toolset will help to solve corpus annotation and NLP processing unification problem and enrich the portal resources by creating a unified conceptual space of Turkic electronic corpora.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114170203","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":"Supporting the Student-Lesson Relationship with Petri Nets and Prediction Model with Inverse Proportion Approach","authors":"Osman Karcioğlu, Mehmet Göktürk","doi":"10.1109/UBMK55850.2022.9919590","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919590","url":null,"abstract":"Uncertainty is disturbing. Eliminating uncertainty is important for people to proactively make the right decisions about the future. Therefore, the calculation of probabilities allows situation analysis to be made in order to make the most accurate decision for the future. It has been determined that models with a “concurrent” structure created with Petri Nets can perform situation analysis. In order for this analysis to be more rational, it is envisaged to support the Petri Nets model with an inverse proportionality approach. In this case study, the probability of students being successful in the courses they take was estimated with petri nets, and then, in addition to this analysis, it was formulated that more rational estimations could be made with the Inverse Proportion approach.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134181037","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":"Intelligent Microclimate Control System Using PLC and SCADA","authors":"Boltaboyeva Assiya, Akhmetova Ardak, Mansurova Madina, Amirkhanova Gulshat, Abdikarov Ramzat","doi":"10.1109/UBMK55850.2022.9919585","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919585","url":null,"abstract":"Automation of various types of production is an important direction in the scientific and technical development of society. Automation brings the quality of labor productivity, freeing a person from the production process, improving the quality of products and better meeting needs to a higher level in society. The basis of modern automation is the concept of technology, flexible and without human help. Technology without human help is considered as a mode of highly automated production processes without human involvement (or minimal). Flexible technology contributes to the removal of restrictions on the nature of products (or their significant reduction) and a sharp reduction in the required volume of preparatory work during the transition to a new technology. Flexible technology leads to high automation of the production of many products, which allows you to master the production of new products in a short time and in an automated mode. Therefore, the system development architecture is an urgent scientific task.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131112560","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":"An Anomaly Detection Study for the Smart Home Environment","authors":"Mehmet Erhan Bilgin, H. Kilinç, A. Zaim","doi":"10.1109/UBMK55850.2022.9919448","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919448","url":null,"abstract":"Unusual sensor data in smart homes may herald different problems based on sensor errors, security vulnera-bilities, activity and behavior changes. This study focuses on detecting anomalies and unusual situations in 7 different sensor data in a house. For this, a model created with a combination of unsupervised and supervised machine learning algorithms is used. The sensor data are labeled using Isolation Forest which is one of the unsupervised algorithms. Then, the data is trained with the supervised algorithms Decision Tree, Extra Trees, Random Forest and XGBoost classification algorithms. Anomaly decisions are made with an accuracy of over 99 percent.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132695788","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":"Infinite Spaces Using Recursive Portals","authors":"Ali Emre Gülcü, F. B. Atalay","doi":"10.1109/UBMK55850.2022.9919479","DOIUrl":"https://doi.org/10.1109/UBMK55850.2022.9919479","url":null,"abstract":"One of the strongest aspects of virtual reality (VR) hardware and applications is the immersion it provides to the user. While combination of techniques such as real-walking for locomotion, head movement for gaze direction and hand detection for controls are great for immersive experience; when the real space and the virtual environment does not match, developers must resort to alternative locomotion techniques such as teleportation, controller-assisted movement or in-place walking via external devices. Despite lifting the restrictions on physical spaces, these techniques may need expensive or cumbersome hardware, cause nausea and dizziness on the user or simply diminish the immersion. We propose a portal based environment design method and a modern rendering engine to visualize the created scenes. Our method uses the same physical space by overlapping multiple regions of the virtual environment on top of each other while keeping the affine properties of the scene. The user can walk between different virtual rooms while staying in a limited physical space. We also conduct a user study to compare user experience to state-of-the-art physical-virtual environment mapping method; in which, the users strongly favored our method.","PeriodicalId":417604,"journal":{"name":"2022 7th International Conference on Computer Science and Engineering (UBMK)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123997004","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}