Trafik Verilerinde Genetik Algoritmalar ve Meta Optimizasyonla Güçlendirilmiş Exponential Smoothing Modeli ile Anomali Tespiti ve Performans Analizi

dc.contributor.author Guler, Ali Kerem
dc.contributor.author Arsan, Taner
dc.contributor.author Fuat Alsan, Huseyin
dc.contributor.author Arsan, Taner
dc.contributor.other Computer Engineering
dc.date.accessioned 2024-11-15T17:48:01Z
dc.date.available 2024-11-15T17:48:01Z
dc.date.issued 2025
dc.department Lisansüstü Eğitim Enstitüsü / Bilgisayar Mühendisliği Ana Bilim Dalı
dc.department Kadir Has University en_US
dc.department-temp [Guler, Ali Kerem; Fuat Alsan, Huseyin; Arsan, Taner] Kadir Has Univ, Dept Comp Engn, TR-34083 Istanbul, Turkiye en_US
dc.description.abstract Bu çalışma, Numenta Anomaly Benchmark'ın (NAB) gerçek zamanlı trafik veri setleri üzerinde tahminleme yapan Third Order Exponential Smoothing modelinin parametrelerini optimize etmek amacıyla genetik algoritma kullanmaktadır. Ayrıca, genetik algoritma optimizasyon sürecini daha verimli hale getirmek için meta-optimizasyon tekniklerinden yararlanılarak anomali tespitindeki doğruluğu önemli ölçüde artıran yenilikçi bir yaklaşım sunmaktadır. Önerilen metodoloji, trafik yönetim sistemlerinde kritik olan veri akışlarındaki sapmaları tespit etmek için çeşitli trafik veri senaryolarına karşı farklı veri setleri üzerinde test edilmiştir. NAB'nin skorlama sistemini kullanarak yapılan karşılaştırmalı performans analizi, bu araştırmada geliştirilen yöntemin mevcut NAB algoritmalarının çoğundan üstün olduğunu ve NAB'nin önde gelen algoritmalarıyla rekabet edebildiğini göstermektedir. 'standart' için 54.32, 'reward_low_FP' için 53.73 ve 'reward_low_FN' için 69.54 skorları elde eden önerilen yaklaşım, sırasıyla NAB algoritmalarının ortalamasına göre %3.13, %2.70 ve %3.24 oranında bir iyileşme sağlamış, önemli bir gelişme kaydetmiştir. Bulgular, önerilen yaklaşımın sadece yüksek hassasiyetle anormallikleri tespit etmekle kalmayıp, aynı zamanda manuel yeniden kalibrasyon gerektirmeden değişen veri özelliklerine dinamik olarak uyum sağladığını göstermektedir. Bu çalışma, güvenilir izleme sağlayan ve potansiyel olarak etkin trafik yönetimi ve planlamayı kolaylaştıran sağlam bir trafik anomali tespit yöntemi önermektedir. Çalışmanın sonuçları, gerçek zamanlı veri izleme ve anormallik tespiti gerektiren diğer alanlara da genişletilebilir, farklı bağlamlar ve gereksinimlere uyum sağlayabilen ölçeklenebilir bir çözüm sunmaktadır.
dc.description.abstract This study employs a genetic algorithm to optimize the parameters of the Third Order Exponential Smoothing model for predicting on the real-time traffic datasets of the Numenta Anomaly Benchmark (NAB). Moreover, it suggests a new approach to apply meta-optimization techniques to make the genetic algorithm optimization process more efficient so as to get improved accuracy in anomaly detection. The proposed methodology has been tested on various traffic data scenarios across different datasets to detect deviations critical to traffic management systems. Comparisons in performance using NAB's scoring system clearly show that the method developed in this research outperforms most of the existing NAB algorithms and competes with the leading algorithms in NAB. Achieving scores of 54.32 for 'standard', 53.73 for 'reward_low_FP', and 69.54 for 'reward_low_FN', the proposed approach shows an improvement of 3.13%, 2.70%, and 3.24% respectively over the average NAB algorithms, marking a significant enhancement. The findings indicate that the proposed approach not only detects anomalies with high precision but also dynamically adapts to changing data characteristics without requiring manual recalibration. This study proposes a robust traffic anomaly detection method that ensures reliable monitoring and potentially facilitates effective traffic management and planning. The results of the study can be extended to other areas requiring real-time data monitoring and anomaly detection, offering a scalable solution adaptable to different contexts and requirements. en
dc.description.abstract This study employs a genetic algorithm to optimize the parameters of the Third Order Exponential Smoothing model for predicting on the real-time traffic datasets of the Numenta Anomaly Benchmark (NAB). The genetic algorithm process was executed with different population sizes and gene sets. In addition, a parameter sensitivity analysis was conducted, through which the ideal number of genes and population size providing the best results within the specified range were determined. Moreover, a novel approach incorporating meta-optimization techniques is proposed to enhance the efficiency of the genetic algorithm optimization process, aiming to achieve improved accuracy in anomaly detection. The proposed methodology has been tested on various traffic data scenarios across different datasets to detect deviations critical to traffic management systems. Performance comparisons using the NAB scoring system demonstrate that the method developed in this study outperforms the majority of existing NAB algorithms, as well as the contemporary approaches of Isolation Forest, Multi-Layer Perceptron Regressor (MLPRegressor), and hybrid K-Nearest Neighbors - Gaussian Mixture Models (KNN + GMM), and is competitive with leading algorithms. The proposed approach, which achieved scores of 54.41 for 'Standard', 53.95 for 'reward_low_FP_rate', and 69.61 for 'reward_low_FN_rate', indicates improvements of 3.67%, 4.45%, and 2.63%, respectively, compared to the average scores of the NAB algorithms. The findings indicate that the proposed approach not only detects anomalies with high precision but also dynamically adapts to changing data characteristics without requiring manual recalibration. This study proposes a robust traffic anomaly detection method that ensures reliable monitoring and potentially facilitates effective traffic management and planning.The results of the study can be extended to other areas requiring real-time data monitoring and anomaly detection, offering a scalable solution adaptable to different contexts and requirements. en_US
dc.description.woscitationindex Science Citation Index Expanded
dc.identifier.doi 10.1109/ACCESS.2025.3543030
dc.identifier.endpage 69
dc.identifier.endpage 33378 en_US
dc.identifier.issn 2169-3536
dc.identifier.scopus 2-s2.0-85218776623
dc.identifier.scopusquality Q1
dc.identifier.startpage 33361 en_US
dc.identifier.uri https://doi.org/10.1109/ACCESS.2025.3543030
dc.identifier.volume 13 en_US
dc.identifier.wos WOS:001438222500036
dc.identifier.wosquality Q2
dc.language.iso en
dc.language.iso en en_US
dc.publisher IEEE-Inst Electrical Electronics Engineers inc en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 0
dc.subject Anomaly Detection en_US
dc.subject Time Series Analysis en_US
dc.subject Benchmark Testing en_US
dc.subject Genetic Algorithms en_US
dc.subject Real-Time Systems en_US
dc.subject Optimization en_US
dc.subject Accuracy en_US
dc.subject Smoothing Methods en_US
dc.subject Streams en_US
dc.subject Predictive Models en_US
dc.subject Third Order Exponential Smoothing en_US
dc.subject Genetic Algorithms en_US
dc.subject Time Series Analysis en_US
dc.subject Numenta Anomaly Benchmark en_US
dc.title Trafik Verilerinde Genetik Algoritmalar ve Meta Optimizasyonla Güçlendirilmiş Exponential Smoothing Modeli ile Anomali Tespiti ve Performans Analizi
dc.title Anomaly Detection and Performance Analysis With Exponential Smoothing Model Powered by Genetic Algorithms and Meta Optimization en_US
dc.type Article en_US
dc.wos.citedbyCount 0
dspace.entity.type Publication
relation.isAuthorOfPublication 7959ea6c-1b30-4fa0-9c40-6311259c0914
relation.isAuthorOfPublication.latestForDiscovery 7959ea6c-1b30-4fa0-9c40-6311259c0914
relation.isOrgUnitOfPublication fd8e65fe-c3b3-4435-9682-6cccb638779c
relation.isOrgUnitOfPublication.latestForDiscovery fd8e65fe-c3b3-4435-9682-6cccb638779c

Files