Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558950
Murta Kısa, Sercan Demirci, Sibel Arslan, Selçuk Aslan
The new coronavirus or COVID-19 pandemic has focused researchers from various disciplines including computer sciences on existing diagnosis and treatment methods. As a result of this increasing interest, Immune Plasma algorithm (IP algorithm or IPA) that is a new meta-heuristic referencing a treatment method called immune or convalescent plasma has been introduced recently. In this study, IP algorithm was modified by considering the channel assignment problem on cognitive networks and its performance was investigated on solving mentioned problem. Moreover, the results of the IPA based technique were compared with the results of the Brute force search. Comparative studies showed that IP algorithm is capable of obtaining better solutions than the Brute force search.
新型冠状病毒或COVID-19大流行使包括计算机科学在内的各个学科的研究人员集中在现有的诊断和治疗方法上。免疫血浆算法(Immune Plasma algorithm, IP algorithm或IPA)是一种新的元启发式算法，它参考了一种叫做免疫或恢复期血浆的治疗方法。本文考虑了认知网络中的信道分配问题，对IP算法进行了改进，并研究了IP算法在解决信道分配问题时的性能。此外，将基于IPA的搜索结果与蛮力搜索结果进行了比较。比较研究表明，IP算法比蛮力搜索能得到更好的解。
{"title":"Solving Channel Assignment Problem in Cognitive Radio Networks with Immune Plasma Algorithm","authors":"Murta Kısa, Sercan Demirci, Sibel Arslan, Selçuk Aslan","doi":"10.1109/UBMK52708.2021.9558950","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558950","url":null,"abstract":"The new coronavirus or COVID-19 pandemic has focused researchers from various disciplines including computer sciences on existing diagnosis and treatment methods. As a result of this increasing interest, Immune Plasma algorithm (IP algorithm or IPA) that is a new meta-heuristic referencing a treatment method called immune or convalescent plasma has been introduced recently. In this study, IP algorithm was modified by considering the channel assignment problem on cognitive networks and its performance was investigated on solving mentioned problem. Moreover, the results of the IPA based technique were compared with the results of the Brute force search. Comparative studies showed that IP algorithm is capable of obtaining better solutions than the Brute force search.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129767062","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558988
Ercan Atagün, Bengisu Hartoka, A. Albayrak
This paper is a natural language processing study and includes models used in natural language processing. In this paper, topic modeling, which is one of the sub-fields of natural language processing, has been studied. In order to make topic modeling, the data set was obtained by using the data scraping method, which has been very popular in recent years, over social media. The dataset is related to Teknofest competitions. The dataset was created by utilizing the Selenium library, one of the popular libraries used for the data scraping method. In order to be able to analyze on the prepared data set and to ensure the consistency of the clustering process, the text to be used before the analysis was preprocessed. After text preprocessing, clustering was performed on the data set with natural language processing techniques such as BERT and LDA.
{"title":"Topic Modeling Using LDA and BERT Techniques: Teknofest Example","authors":"Ercan Atagün, Bengisu Hartoka, A. Albayrak","doi":"10.1109/UBMK52708.2021.9558988","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558988","url":null,"abstract":"This paper is a natural language processing study and includes models used in natural language processing. In this paper, topic modeling, which is one of the sub-fields of natural language processing, has been studied. In order to make topic modeling, the data set was obtained by using the data scraping method, which has been very popular in recent years, over social media. The dataset is related to Teknofest competitions. The dataset was created by utilizing the Selenium library, one of the popular libraries used for the data scraping method. In order to be able to analyze on the prepared data set and to ensure the consistency of the clustering process, the text to be used before the analysis was preprocessed. After text preprocessing, clustering was performed on the data set with natural language processing techniques such as BERT and LDA.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127638842","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558910
Cansen Çağlayan, M. Karakaya
Today, the text generation subject in the field of Natural Language Processing (NLP) has gained a lot of importance. In particular, the quality of the text generated with the emergence of new transformer-based models has reached high levels. In this way, controllable text generation has become an important research area. There are various methods applied for controllable text generation, but since these methods are mostly applied on Recurrent Neural Network (RNN) based encoder decoder models, which were used frequently, studies using transformer-based models are few. Transformer-based models are very successful in long sequences thanks to their parallel working ability. This study aimed to generate Turkish reviews on the desired topics by using a transformer-based language model. We used the method of adding the topic information to the sequential input. We concatenated input token embedding and topic embedding (control) at each time step during the training. As a result, we were able to create Turkish reviews on the specified topics.
{"title":"Topic-Controlled Text Generation","authors":"Cansen Çağlayan, M. Karakaya","doi":"10.1109/UBMK52708.2021.9558910","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558910","url":null,"abstract":"Today, the text generation subject in the field of Natural Language Processing (NLP) has gained a lot of importance. In particular, the quality of the text generated with the emergence of new transformer-based models has reached high levels. In this way, controllable text generation has become an important research area. There are various methods applied for controllable text generation, but since these methods are mostly applied on Recurrent Neural Network (RNN) based encoder decoder models, which were used frequently, studies using transformer-based models are few. Transformer-based models are very successful in long sequences thanks to their parallel working ability. This study aimed to generate Turkish reviews on the desired topics by using a transformer-based language model. We used the method of adding the topic information to the sequential input. We concatenated input token embedding and topic embedding (control) at each time step during the training. As a result, we were able to create Turkish reviews on the specified topics.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127882394","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558932
Nimet Tülümen, Gökhan Akgün, Ali Nohutçu, Günnur Sevgi Aktoros Genç, S. Genç
Information extraction from text data has always been a tricky and difficult task. This work follows a previous work regarding a designed system that matches job ads with resumes, then assigns them a scoring point. In this system, there are two main parts: information extraction and scoring. For the information extraction part, rule-based methods are efficient when the format of the resumes and job ads are known. In this paper, powerful and efficient methods for information extraction from the mixed resume format and job ads using machine learning and deep learning methods are proposed.
{"title":"Hybrid Job and Resume Matcher","authors":"Nimet Tülümen, Gökhan Akgün, Ali Nohutçu, Günnur Sevgi Aktoros Genç, S. Genç","doi":"10.1109/UBMK52708.2021.9558932","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558932","url":null,"abstract":"Information extraction from text data has always been a tricky and difficult task. This work follows a previous work regarding a designed system that matches job ads with resumes, then assigns them a scoring point. In this system, there are two main parts: information extraction and scoring. For the information extraction part, rule-based methods are efficient when the format of the resumes and job ads are known. In this paper, powerful and efficient methods for information extraction from the mixed resume format and job ads using machine learning and deep learning methods are proposed.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115625029","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558962
Onur Göksel, T. Ovatman
Modeling distributed processes using state machines is gaining importance as the serverless computing becomes more widespread. One of the important issues in distributed state machine execution is to perform better caching approaches. Due to the nature of state machines, the amount of different paths that can be executed by a state machine is limited. This property can be utilized to perform better caching by predicting which path is going to be taken. In this paper, we analyze former execution history of distributed state machines to perform better predictions. We also run experiments to find out if collaboratively using the history of the state machine instances makes any significant improvements on pre-fetching decision. Our results show that pre-fetching significantly decrease the number of cache misses while history sharing between instances provides improvements in a more limited fashion.
{"title":"Collaborative Path Prediction in Cache Pre-fetching for Distributed State Machines","authors":"Onur Göksel, T. Ovatman","doi":"10.1109/UBMK52708.2021.9558962","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558962","url":null,"abstract":"Modeling distributed processes using state machines is gaining importance as the serverless computing becomes more widespread. One of the important issues in distributed state machine execution is to perform better caching approaches. Due to the nature of state machines, the amount of different paths that can be executed by a state machine is limited. This property can be utilized to perform better caching by predicting which path is going to be taken. In this paper, we analyze former execution history of distributed state machines to perform better predictions. We also run experiments to find out if collaboratively using the history of the state machine instances makes any significant improvements on pre-fetching decision. Our results show that pre-fetching significantly decrease the number of cache misses while history sharing between instances provides improvements in a more limited fashion.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124245613","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558898
Ugur Kilic, Nur Hüseym Kaplan, I. Aksakallı, I. Erer
A digital image can be easily manipulated in today’s rapidly boosting technology. Among different types of image forgery methods, Copy-move forgery (CMF) is one of the most popular forgery methods in which a part of the image is copied and pasted into the same image or a different image. Therefore, the development of forgery detection methods has become a hot topic for both researchers and practitioners. In this study, a new CMF method combined with Discrete Cosine Transform (DCT) and optimum parameter Bilateral Filtering (OBF) is proposed to detect copied areas in a digital image. The visual and quantitative comparisons of the proposed hybrid method (DCT-OBF) have been made with traditional DCT based methods. The proposed method outperformed the former bilateral based method as well as the DCT based methods in terms of visual and quantitative analysis. Moreover, comparisons with conventional block-based methods have been carried out for different post-processing attacks such as image blurring and contrast adjustment. Quantitative comparisons demonstrate that the proposed method is better than the conventional block based methods, especially for post-processed images. For blurring post-processed images, the proposed method have provided higher Precision (18% improvement), F1 score (13% improvement), and Recall (5% improvement) rates than the former block based methods.
{"title":"DCT and Optimum Parameter Bilateral Filtering-Based Copy-Move Forgery Detection","authors":"Ugur Kilic, Nur Hüseym Kaplan, I. Aksakallı, I. Erer","doi":"10.1109/UBMK52708.2021.9558898","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558898","url":null,"abstract":"A digital image can be easily manipulated in today’s rapidly boosting technology. Among different types of image forgery methods, Copy-move forgery (CMF) is one of the most popular forgery methods in which a part of the image is copied and pasted into the same image or a different image. Therefore, the development of forgery detection methods has become a hot topic for both researchers and practitioners. In this study, a new CMF method combined with Discrete Cosine Transform (DCT) and optimum parameter Bilateral Filtering (OBF) is proposed to detect copied areas in a digital image. The visual and quantitative comparisons of the proposed hybrid method (DCT-OBF) have been made with traditional DCT based methods. The proposed method outperformed the former bilateral based method as well as the DCT based methods in terms of visual and quantitative analysis. Moreover, comparisons with conventional block-based methods have been carried out for different post-processing attacks such as image blurring and contrast adjustment. Quantitative comparisons demonstrate that the proposed method is better than the conventional block based methods, especially for post-processed images. For blurring post-processed images, the proposed method have provided higher Precision (18% improvement), F1 score (13% improvement), and Recall (5% improvement) rates than the former block based methods.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115669696","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558892
Elmira Daiyrbayeva, A. Yerimbetova, Zhanbolat Maratov, A. Toigozhinova, M. Sambetbayeva
This article is devoted to the issues of steganography, i.e., secure data transmission using an image. The introductory part of the article gives a definition of the concept of steganography, and also describes the use of steganography in graphic images. In this paper, the aim of the researchers is to transfer textual data using an image object using a strip transformation method. The main part of the article shows the results obtained during the experimental work and describes the process of obtaining the results.
{"title":"Learning Steganography with a Strip Transform","authors":"Elmira Daiyrbayeva, A. Yerimbetova, Zhanbolat Maratov, A. Toigozhinova, M. Sambetbayeva","doi":"10.1109/UBMK52708.2021.9558892","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558892","url":null,"abstract":"This article is devoted to the issues of steganography, i.e., secure data transmission using an image. The introductory part of the article gives a definition of the concept of steganography, and also describes the use of steganography in graphic images. In this paper, the aim of the researchers is to transfer textual data using an image object using a strip transformation method. The main part of the article shows the results obtained during the experimental work and describes the process of obtaining the results.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115873171","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558921
Serkan Savaş
The use of social media, which is among the most basic purposes of internet use, has also begun to shape people’s investment tools and investment styles. As a result of increasing interest in recent years, thousands of crypto-currencies have been put into use. Investors invest in these currencies through personal research and referrals. Social media sites, on the other hand, have taken their place among the most effective tools in directing people’s investments in this regard. For this reason, in this study, 10 crypto-currencies with a high market value were determined and people’s reactions on social media were examined. More than 1 million Tweet data were obtained from Twitter with the determined keywords and these data were analyzed by frequency analysis method. In the study, the guidance and manipulation findings of crypto-currencies over social media were also mentioned and the results of the study were explained. Suggestions for areas where the study could be expanded were also made.
{"title":"Analysis of the Social Media Impact on the Popularity of Crypto-currencies","authors":"Serkan Savaş","doi":"10.1109/UBMK52708.2021.9558921","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558921","url":null,"abstract":"The use of social media, which is among the most basic purposes of internet use, has also begun to shape people’s investment tools and investment styles. As a result of increasing interest in recent years, thousands of crypto-currencies have been put into use. Investors invest in these currencies through personal research and referrals. Social media sites, on the other hand, have taken their place among the most effective tools in directing people’s investments in this regard. For this reason, in this study, 10 crypto-currencies with a high market value were determined and people’s reactions on social media were examined. More than 1 million Tweet data were obtained from Twitter with the determined keywords and these data were analyzed by frequency analysis method. In the study, the guidance and manipulation findings of crypto-currencies over social media were also mentioned and the results of the study were explained. Suggestions for areas where the study could be expanded were also made.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131044531","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558981
Meltem Çetiner, Ahmet Yıldırım, Cüneyt Öksüz, Bahadir Onay
Question Answering is a widely studied sub-field of Natural Language Processing (NLP). It studies information retrieval techniques that locate the answer in a corpus for a given query. Recently, deep learning techniques are widely employed in this field. This work uses a transfer learning method on Turkish Tax legislation documents. Experts in Tax-Law domain created 355 question-answer pairs in SQuAD 1.1 (Stanford Question Answering Dataset) format using law documents in UYAP (National Judiciary Informatics System). BERT (Bidirectional Encoder Representations from Transformers) contextual word embedding vectors are used to create a representation that can capture different meanings in word representations. Using both these embeddings and the model obtained from SQuAD 1.1 dataset, a system was deployed. Also, using the failing answers retrieved from the application of this model, a SQuAD 2.0 dataset were created that includes impossible-to-answer questions. New models were obtained by training with this dataset. Our observation is that the most successful model of SQuAD 2.0 dataset outperforms that of SQuAD 1.1 by 11% in exact matching measure and by 5% in F1.
{"title":"Mevzuat Verisetinde Soru Cevaplama Uygulamasi Question Answering Application on Legalisation Dataset","authors":"Meltem Çetiner, Ahmet Yıldırım, Cüneyt Öksüz, Bahadir Onay","doi":"10.1109/UBMK52708.2021.9558981","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558981","url":null,"abstract":"Question Answering is a widely studied sub-field of Natural Language Processing (NLP). It studies information retrieval techniques that locate the answer in a corpus for a given query. Recently, deep learning techniques are widely employed in this field. This work uses a transfer learning method on Turkish Tax legislation documents. Experts in Tax-Law domain created 355 question-answer pairs in SQuAD 1.1 (Stanford Question Answering Dataset) format using law documents in UYAP (National Judiciary Informatics System). BERT (Bidirectional Encoder Representations from Transformers) contextual word embedding vectors are used to create a representation that can capture different meanings in word representations. Using both these embeddings and the model obtained from SQuAD 1.1 dataset, a system was deployed. Also, using the failing answers retrieved from the application of this model, a SQuAD 2.0 dataset were created that includes impossible-to-answer questions. New models were obtained by training with this dataset. Our observation is that the most successful model of SQuAD 2.0 dataset outperforms that of SQuAD 1.1 by 11% in exact matching measure and by 5% in F1.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131609684","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}
Pub Date : 2021-09-15DOI: 10.1109/UBMK52708.2021.9558989
Berkay Özçam, H. Kilinç, A. Zaim
The comfort area created by the fact that people can access everything via the internet has led to an increase in the rate of internet use in recent years. The rise of concepts such as 5G, Internet of Things(IoT), Cloud/Edge/Fog Computing shows that this usage will increase day by day. While this increase brings convenience to humanity, it also increases the appetite of malicious people. Cyber attacks are increasing day by day and many individual or corporate users are harmed. In this study, it is aimed to detect Distributed Denial of Service(DDoS) attacks, which are the most common and most harmful of the bullying we mentioned. We focused on detecting TCP-Flood attacks, which is one of the most preferred DDoS attack types, using various machine learning algorithms. The part that made this job difficult and different was the targeting of real-time detection.
{"title":"Detecting TCP Flood DDoS Attack by Anomaly Detection based on Machine Learning Algorithms","authors":"Berkay Özçam, H. Kilinç, A. Zaim","doi":"10.1109/UBMK52708.2021.9558989","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558989","url":null,"abstract":"The comfort area created by the fact that people can access everything via the internet has led to an increase in the rate of internet use in recent years. The rise of concepts such as 5G, Internet of Things(IoT), Cloud/Edge/Fog Computing shows that this usage will increase day by day. While this increase brings convenience to humanity, it also increases the appetite of malicious people. Cyber attacks are increasing day by day and many individual or corporate users are harmed. In this study, it is aimed to detect Distributed Denial of Service(DDoS) attacks, which are the most common and most harmful of the bullying we mentioned. We focused on detecting TCP-Flood attacks, which is one of the most preferred DDoS attack types, using various machine learning algorithms. The part that made this job difficult and different was the targeting of real-time detection.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"262 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124280288","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：