{"title":"MFCC Öznitelikleri ve Adaboost Topluluk Öğrenme Yöntemi Kullanılarak Uyku Seslerinin Sınıflandırılması","authors":"Ensar Arif SAĞBAŞ","doi":"10.53070/bbd.1347221","DOIUrl":"https://doi.org/10.53070/bbd.1347221","url":null,"abstract":"Düzenli ve kaliteli bir gece uykusu insan hayatında hayati önem taşımaktadır. Uyku kalitesi, insanların ve çevrelerindekilerin günlük yaşamları üzerinde büyük bir etkiye sahiptir. Günümüzde birçok insan uyku bozuklukları konusunda sıkıntı çekmektedir. Bu tarz rahatsızlıklar günlük hayatı etkilemekte ve akıl sağlığını bozabilmektedir. Bu çalışma uyku seslerinin otomatik olarak sınıflandırılması için topluluk öğrenme yöntemini kullanan bir yaklaşım önermektedir. Çalışmada 7 farklı uyku sesini içeren bir veri kümesinden faydalanılmıştır. Öncelikli olarak ses dosyalarından MFCC öznitelikleri çıkartılmıştır. Sonrasında çıkartılan öznitelikler ses sınıflandırılmasında sıklıkla kullanılan lojistik regresyon, destek vektör makinesi, kNN ve rastgele orman gibi bilinen yöntemlerle sınıflandırılmıştır. Sınıflandırma başarısını artırmak amacı ile bu temel sınıflandırıcılar Adaboost topluluk öğrenme yöntemi ile birlikte kullanılması yaklaşımı önerilmiştir. Önerilen yaklaşım ile sınıflandırma başarısında artış gözlemlenmiştir. En başarılı sonuç %96.439 ile Adaboost+Rastgele orman yönteminden elde edilmiştir.","PeriodicalId":488052,"journal":{"name":"Bilgisayar bilimleri","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135621348","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 Digital Twin-Based Fault Diagnosis Approach Using Parameter Estimation and Information Entropy","authors":"İlhan AYDIN, Emrullah AYDIN, Erhan AKIN","doi":"10.53070/bbd.1347156","DOIUrl":"https://doi.org/10.53070/bbd.1347156","url":null,"abstract":"Induction motors are one of the important motor types used in industry. Although these motors are generally of robust construction, they are subject to failures due to ambient operating conditions. The traditional diagnostic methods are based on measuring signals such as current, vibration, temperature, and speed from an experimental setup for good and faulty motors. But finding an equivalent motor that can compare with the motor used in the industry is always difficult. Therefore, by constructing a digital twin of the real motor, signals belonging to the healthy motor can be obtained, which is equivalent to the motor in the industry. In this study, motor stator faults were tried to be diagnosed using digital twin and motor signals obtained from a real experimental setup. The faulty frequency region is determined in the spectrum by estimating the parameters related to the motor current, and the faults are determined according to the information entropy. The operation of the proposed system has been tested with data from both the digital twin and the real motor, and successful results have been obtained.","PeriodicalId":488052,"journal":{"name":"Bilgisayar bilimleri","volume":"55 46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135621561","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":"Improved Reptile Search Algorithm for Optimal Design of Solar Photovoltaic Module","authors":"Davut İZCİ, Serdar EKİNCİ, Murat GÜLEYDİN","doi":"10.53070/bbd.1346267","DOIUrl":"https://doi.org/10.53070/bbd.1346267","url":null,"abstract":"This study focuses on the vital role of parameter extraction in optimizing and evaluating solar photovoltaic (PV) systems, as it directly influences their efficiency in converting solar energy to electricity. Researchers have extensively explored the application of various metaheuristic algorithms to accurately estimate solar PV parameters due to their crucial significance, leading to an extensive body of literature on the subject. However, the search for a robust and user-friendly optimizer with high convergence ability remains a challenging task that demands further research. To address this challenge, the study conducts a comprehensive comparative analysis of the RSALF optimizer, an innovative metaheuristic algorithm combining the reptile search algorithm (RSA) with Lévy flight (LF), for parameter extraction of PV model parameters using the Photowatt-PWP201 PV module as a case study. The experimental results demonstrate the RSALF optimizer's remarkable accuracy in parameter estimation, consistently yielding lower root mean square error values and closely aligning with experimental data. Moreover, comparative analysis with other recent optimization approaches highlights the RSALF optimizer's superiority, making it a promising tool for advancing the optimization of PV models and facilitating more efficient and sustainable solar energy utilization.","PeriodicalId":488052,"journal":{"name":"Bilgisayar bilimleri","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135716427","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":"Keystroke Biometric Data for Identity Verification: Performance Analysis of Machine Learning Algorithms","authors":"Erhan YILMAZ, Özgü CAN","doi":"10.53070/bbd.1345519","DOIUrl":"https://doi.org/10.53070/bbd.1345519","url":null,"abstract":"Cyber-attacks are on the rise in today's environment, where traditional security measures are ineffective. As a result, the adoption of cutting-edge tools such as artificial intelligence technology is critical in the fight against cyber threats. User behaviors, such as keyboard dynamics, provide potential data that can be used for protection against cyber-attacks. Keystroke dynamics is one of the fastest and most cost-effective methods that can be used to detect user behaviors, as it can be captured using standard user keyboards. The analysis of this data and protection against cyber-attacks is made possible through machine learning algorithms. Based on keyboard dynamics, this study analyzes the performance of k-Nearest Neighbor (k-NN), Support Vector Machines (SVM), Random Forest (RF), and Neural Network (NN) methods for user behavior analysis and anomaly detection. The findings shed light on the significance of artificial intelligence in cyber security by examining the accomplishments of several machine learning algorithms. The study's findings may serve as a foundation for future research and novel solutions in the realm of cyber security.","PeriodicalId":488052,"journal":{"name":"Bilgisayar bilimleri","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135877189","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}