Show simple item record

dc.contributor.authorÜstündağ, Burak Berk
dc.contributor.authorYücel, Meriç
dc.contributor.authorSERTBAŞ, AHMET
dc.date.accessioned2023-10-10T11:22:49Z
dc.date.available2023-10-10T11:22:49Z
dc.identifier.citationYücel M., SERTBAŞ A., Üstündağ B. B., "High Performance Time Series Anomaly Detection Using Brain Inspired Cortical Coding Method", IEEE ACCESS, cilt.11, ss.8345-8361, 2023
dc.identifier.issn2169-3536
dc.identifier.othervv_1032021
dc.identifier.otherav_12ae9aeb-45a6-48cd-bf20-e74d27beede7
dc.identifier.urihttp://hdl.handle.net/20.500.12627/189692
dc.identifier.urihttps://avesis.istanbul.edu.tr/api/publication/12ae9aeb-45a6-48cd-bf20-e74d27beede7/file
dc.identifier.urihttps://doi.org/10.1109/access.2023.3239212
dc.description.abstractAccurate and automated anomaly detection in time series data sets has an increasingly important role in a wide range of applications. Inspired by coding in the cortical networks of the brain, here we introduce a novel approach for high performance real-time anomaly detection. Cortical coding method is adaptive and dynamic, consisting of self-organized networks. In the cortical coding network introduced herein, the morphological structuring is driven by a brain inspired feature extraction strategy that aims the minimization of the signal energy dissipation while increasing the information entropy of the system. We combine the cortical coding network with transform coding and multi resolution analysis for anomaly detection. As we demonstrate here, the new coding methodology provides high computational efficiency in addition to scalability with respect to target accuracy compared to the traditional clustering algorithms. A wide variety of data sets are used to demonstrate time series anomaly detection performance. In a preliminary work presented here, we detected 77.6% of the present anomalies correctly, using the same hyperparameters for every stage of the method. The results are compared with several clustering algorithms such as K-means and its variants mini-batch K-means, sequential K-means and finally with hierarchical agglomerative clustering. Additionally, the performance of all the clustering methods are compared by memorizing all input data set without performing any clustering. The cortical coding method has shown the best performance compared to the other methods. From the results achieved so far, it appears that there is still a significant room for improvement of the success rate by, specifically, performing hyperparameter and filter optimization according to the characteristics of data sets and using a more advanced fusion model at the output layer. Low time and space complexity, high generalization performance, suitability to real-time anomaly detection, and in-memory processing compatibility are distinct advantages of the cortical coding method in a variety of anomaly detection problems, such as predictive maintenance, cybersecurity, telemedicine, risk management, and transportation safety.
dc.language.isoeng
dc.subjectBilgisayar Ağları ve İletişim
dc.subjectBİLGİSAYAR BİLİMİ, BİLGİ SİSTEMLERİ
dc.subjectBilgisayar Bilimi
dc.subjectMühendislik, Bilişim ve Teknoloji (ENG)
dc.subjectMÜHENDİSLİK, ELEKTRİK VE ELEKTRONİK
dc.subjectMühendislik
dc.subjectTELEKOMÜNİKASYON
dc.subjectBilgi Sistemleri, Haberleşme ve Kontrol Mühendisliği
dc.subjectSinyal İşleme
dc.subjectBilgisayar Bilimleri
dc.subjectBilgi Güvenliği ve Güvenilirliği
dc.subjectMühendislik ve Teknoloji
dc.subjectGenel Mühendislik
dc.subjectElektrik ve Elektronik Mühendisliği
dc.subjectMühendislik (çeşitli)
dc.subjectBilgi sistemi
dc.subjectBilgisayar Bilimi Uygulamaları
dc.subjectBilgisayar Bilimi (çeşitli)
dc.subjectGenel Bilgisayar Bilimi
dc.subjectFizik Bilimleri
dc.titleHigh Performance Time Series Anomaly Detection Using Brain Inspired Cortical Coding Method
dc.typeMakale
dc.relation.journalIEEE ACCESS
dc.contributor.departmentİstanbul Teknik Üniversitesi , ,
dc.identifier.volume11
dc.identifier.startpage8345
dc.identifier.endpage8361
dc.contributor.firstauthorID4310892


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record