发布求助
文献互助 智能选刊 最新文献

2021 6th International Conference on Computer Science and Engineering (UBMK)最新文献

筛选
英文 中文
A Comparative Study of Machine Learning Approaches for Non Performing Loan Prediction 不良贷款预测的机器学习方法比较研究
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558894
Sefik Ilkin Serengil, Salih Imece, U. Tosun, Ege Berk Buyukbas, B. Koroglu
{"title":"A Comparative Study of Machine Learning Approaches for Non Performing Loan Prediction","authors":"Sefik Ilkin Serengil, Salih Imece, U. Tosun, Ege Berk Buyukbas, B. Koroglu","doi":"10.1109/UBMK52708.2021.9558894","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558894","url":null,"abstract":"Credit risk estimation and the risk evaluation of credit portfolios are crucial to financial institutions which provide loans to businesses and individuals. Non-performing loan (NPL) is a loan type in which the customer has a delinquency; because they have not made the scheduled payments for a time period. NPL prediction has been widely studied in both finance and data science. In addition, most banks and financial institutions are empowering their business models with the advancements of machine learning algorithms and analytical big data technologies. In this paper, we studied on several machine learning algorithms to solve this problem and we propose a comparative study of some of the mostly used non performing loan models on a customer portfolio dataset in a private bank in Turkey. We also deal with a class imbalance problem using class weights. A dataset, composed by 181.276 samples, has been used to perform the analysis considering different performance metrics (i.e. Precision, Recall, F1 Score, Imbalance Accuracy (IAM), Specificity). In addition to these, we evaluated the performance of the algorithms and compared the obtained results. According to these performance metrics, LightGBM gave the best results among the logistic regression, SVM, random forest, bagging classifier, XGBoost and LSTM for the dataset.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"13 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":"130901484","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: 6
Object Annotation Using Cost-Effective Active Learning 使用成本效益高的主动学习的对象注释
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9559028
Nuh Hatipoglu, Esra Çinar, H. K. Ekenel
{"title":"Object Annotation Using Cost-Effective Active Learning","authors":"Nuh Hatipoglu, Esra Çinar, H. K. Ekenel","doi":"10.1109/UBMK52708.2021.9559028","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9559028","url":null,"abstract":"Deep learning models require large amount of training data to reach high accuracies. However, labeling large volumes of training data is a labor-intensive and time-consuming process. Active learning is an approach that seeks to maximize the performance of a model with the least possible amount of labeled data. It is of great practical importance to develop a framework by combining deep learning and active learning methods that transfer features from a small number of unlabeled training data to classifiers. With this study, we combine active learning and deep learning models, which allows for fine-tuning deep learning models with a small number of training data. We use images of shelf products belonging to the same product group with 13 classes and examine them using different deep learning classifier models. Experimental results show that we are able to achieve higher performance by annotating and using a part of the data for training compared to annotating and using the entire dataset. This way, we save from the annotations costs, and at the same time reach an improved object classification system.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"24 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":"134149494","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: 1
Two Level Document Image Classification 二级文档图像分类
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558895
Adnan Öncevarlık, Akın Akön, Kemal Doruk Yıldız, E. Adali
{"title":"Two Level Document Image Classification","authors":"Adnan Öncevarlık, Akın Akön, Kemal Doruk Yıldız, E. Adali","doi":"10.1109/UBMK52708.2021.9558895","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558895","url":null,"abstract":"Classifying documents is an important process for organizations that are responsible for keeping a large number of documents in a digital archive. In this paper, a two-level method was used to classify approximately 253 class of documents. In the first stage, the documents were visually classified. In the second stage, unclassifiable documents were tried to be classified using natural language processing (NLP). Training set was created by classifying approximately 28.000 documents by hand. Studies were carried out on single-page documents. Performances were measured by making experiments on the full, 1/2 and 1/3 of document using AlexNet for image classification, bag-of-words and LSTM algorithm for NLP. The performances of the study were measured according to different options. The success rate was 75% and 85% at the end of first and second stages respectively","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"186 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":"133684387","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: 1
SSH and Telnet Protocols Attack Analysis Using Honeypot Technique : *Analysis of SSH AND TELNET Honeypot 基于蜜罐技术的SSH和Telnet协议攻击分析:* SSH和Telnet蜜罐分析
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558948
Melike Başer, Ebu Yusuf Güven, M. Aydin
{"title":"SSH and Telnet Protocols Attack Analysis Using Honeypot Technique : *Analysis of SSH AND TELNET Honeypot","authors":"Melike Başer, Ebu Yusuf Güven, M. Aydin","doi":"10.1109/UBMK52708.2021.9558948","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558948","url":null,"abstract":"Generally, the defense measures taken against new cyber-attack methods are insufficient for cybersecurity risk management. Contrary to classical attack methods, the existence of undiscovered attack types called’ zero-day attacks’ can invalidate the actions taken. It is possible with honeypot systems to implement new security measures by recording the attacker’s behavior. The purpose of the honeypot is to learn about the methods and tools used by the attacker or malicious activity. In particular, it allows us to discover zero-day attack types and develop new defense methods for them. Attackers have made protocols such as SSH (Secure Shell) and Telnet, which are widely used for remote access to devices, primary targets. In this study, SSHTelnet honeypot was established using Cowrie software. Attackers attempted to connect, and attackers record their activity after providing access. These collected attacker log records and files uploaded to the system are published on Github to other researchers1. We shared the observations and analysis results of attacks on SSH and Telnet protocols with honeypot.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"3 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":"117053533","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: 4
Geospatial Radar Deployment Optimization 地理空间雷达部署优化
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558967
Osman Abul, Furkan Şavşatlı
{"title":"Geospatial Radar Deployment Optimization","authors":"Osman Abul, Furkan Şavşatlı","doi":"10.1109/UBMK52708.2021.9558967","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558967","url":null,"abstract":"With the advancement of technology, many services have been developed that cover certain regions and provide benefits on various issues. Examples of these are internet providers, mobile hospitals, weather balloons and radars used by the army or navy. As the geography grows and the number of specified systems increases, it is expected that these will act as a whole and be optimally distributed. In this paper, the problem of optimal distribution of military air defense system radars to critical areas has been addressed. First of all, the problem definitions are given and then the solutions to these problems are developed. Experimental evaluation has been made on the designed data sets.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"29 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":"115629963","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
Implementation of Semantic Web in the Companies: Human Resources Ontology 语义网在企业中的实现:人力资源本体
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558937
Erinç Cibil, Murat Komesli
{"title":"Implementation of Semantic Web in the Companies: Human Resources Ontology","authors":"Erinç Cibil, Murat Komesli","doi":"10.1109/UBMK52708.2021.9558937","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558937","url":null,"abstract":"Today, data which is growing exponentially; has become very important in the both backup and analysis phase. For this reason, it is necessary to store, transfer and examine the data in a correct structure according to the semantic web principles. In addition, the aim of the computers to automatically infer some operations without the need for human intervention and to be more beneficial to people in this state is being worked on. An example of the human resources ontology developed with the Protégé tool is described in order to accelerate and correct the semantic network processes with the ontologies created for this purpose. In addition, the developed ontology was queried using SPARQL language. In this study, it is aimed to query different types of heterogeneous data together with RDF queries. Thus, in addition to relational databases, which are still indispensable today, many heterogeneous data will be queried and inferences can be made by computers.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"72 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":"115564438","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: 1
A Region Alignment and Matching Method for Fractured Object Reassembly 断裂物体重组的区域对齐与匹配方法
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9559005
O. Cakir, Vasif Nabivev
{"title":"A Region Alignment and Matching Method for Fractured Object Reassembly","authors":"O. Cakir, Vasif Nabivev","doi":"10.1109/UBMK52708.2021.9559005","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9559005","url":null,"abstract":"Reassembling fractured objects has many popular applications, such as relics restoration and solving puzzle. Mostly corrosions are encountered on the shared regions of the fractured object pieces and this data loss makes the reassembly process much more difficult. In this study a minimum bounding box (MBB) based alignment and key-point based matching method is proposed. Our method first divides every single fractured object piece into regions and generates MBB for each region. Then the key-points are determined based on the distances of the middle surface computed from two opposing surfaces of the MBB of the base region. Matching between the base and the candidate regions is carried out depending on similarities of the distances computed according to key-points. The alignment surface is one of the MBB surfaces of the base region and candidate regions are also regenerated on the alignment surface, so the base and the candidate regions are aligned in this manner. We have tested our alignment and matching method on sample fractured corroded objects. The similarity results show that the proposed method aligns and matches right candidate region from other candidates accurately.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"46 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":"127062034","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: 1
Anomaly Detection on Bitcoin Values 比特币价值的异常检测
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9559002
Ekin Ecem Tatar, Murat Dener
{"title":"Anomaly Detection on Bitcoin Values","authors":"Ekin Ecem Tatar, Murat Dener","doi":"10.1109/UBMK52708.2021.9559002","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9559002","url":null,"abstract":"Bitcoin has received a lot of attention from investors, researchers, regulators, and the media. It is a known fact that the Bitcoin price usually fluctuates greatly. However, not enough scientific research has been done on these fluctuations. In this study, long short-term memory (LSTM) modeling from Recurrent Neural Networks, which is one of the deep learning methods, was applied on Bitcoin values. As a result of this application, anomaly detection was carried out in the values from the data set. With the LSTM network, a time-dependent representation of Bitcoin price can be captured, and anomalies can be selected. The factors that play a role in the formation of the model to be applied in the detection of anomalies with the experimental results were evaluated.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"36 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":"123294302","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
UBMK 2021 Committees
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558987
{"title":"UBMK 2021 Committees","authors":"","doi":"10.1109/UBMK52708.2021.9558987","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558987","url":null,"abstract":"","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"83 4 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":"123277033","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
Multi-Class Sentiment Analysis from Turkish Tweets with RNN 基于RNN的土耳其语推文多类情感分析
2021 6th International Conference on Computer Science and Engineering (UBMK) Pub Date : 2021-09-15 DOI: 10.1109/UBMK52708.2021.9558958
Ayşe Gül Eker, Kadir Eker, N. Duru
{"title":"Multi-Class Sentiment Analysis from Turkish Tweets with RNN","authors":"Ayşe Gül Eker, Kadir Eker, N. Duru","doi":"10.1109/UBMK52708.2021.9558958","DOIUrl":"https://doi.org/10.1109/UBMK52708.2021.9558958","url":null,"abstract":"Twitter is a social media platform where users can post their messages called ‘tweets’. Comment on a product, person, or event on Twitter; It takes reading and interpreting thousands of tweets to find out what emotion it represents. With sentiment analysis, it is possible to perform this process automatically in a short time. In this study; A data set consisting of Turkish tweets divided into 5 different emotion categories was used. Sentiment analysis was carried out using RNN architecture, which is a deep learning method. In the dataset, there are equal numbers of tweets for each of the emotions “angry”, “fear”, “happy”, “surprise”, “sad”. The success of the models established by performing multi-class sentiment analysis with LSTM, BiLSTM and GRU based on RNN architecture was compared. Highest accuracy; It has been in the model established with bidirectional LSTM, that is, BiLSTM, which is very successful in past and future word contexts.","PeriodicalId":106516,"journal":{"name":"2021 6th International Conference on Computer Science and Engineering (UBMK)","volume":"126 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":"124586010","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: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信