ARFA: Automated real-time flight data analysis using evolving clustering, classifiers and recursive density estimation

Kolev, Denis; Angelov, Plamen; Markarian, Garik; Suvorov, Mikhail; Lysanov, Sergey

doi:10.1109/eais.2013.6604110

Cited by 10 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, these quantities are applicable online and can be calculated recursively for certain type of distances (such as Euclidean [7,10], Mahalonobis [11,12]). For example, if use Euclidean distance we have):…”

Section: Basic Concepts Of Tedamentioning

confidence: 99%

Anomaly detection based on eccentricity analysis

Angelov

2014

2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)

Self Cite

127

View full text Add to dashboard Cite

In this paper, we propose a new eccentricity-based anomaly detection principle and algorithm. It is based on a further development of the recently introduced data analytics framework (TEDA -from typicality and eccentricity data analytics). We compare TEDA with the traditional statistical approach and prove that TEDA is a generalization of it in regards to the well-known "nσ σ σ σ" analysis (TEDA gives exactly the same result as the traditional "nσ σ σ σ" analysis but it does not require the restrictive prior assumptions that are made for the traditional approach to be in place). Moreover, it offers a nonparametric, closed form analytical descriptions (models of the data distribution) to be extracted from the real data realizations, not to be pre-assumed. In addition to that, for several types of proximity/similarity measures (such as Euclidean, cosine, Mahalonobis) it can be calculated recursively, thus, computationally very efficiently and is suitable for real time and online algorithms. Building on the per data sample, exact information about the data distribution in a closed analytical form, in this paper we propose a new less conservative and more sensitive condition for anomaly detection. It is quite different from the traditional "nσ σ σ σ" type conditions. We demonstrate example where traditional conditions would lead to an increased amount of false negatives or false positives in comparison with the proposed condition. The new condition is intuitive and easy to check for arbitrary data distribution and arbitrary small (but not less than 3) amount of data samples/points. Finally, because the anomaly/novelty/change detection is very important and basic data analysis operation which is in the fundament of such higher level tasks as fault detection, drift detection in data streams, clustering, outliers detection, autonomous video analytics, particle physics, etc. we point to some possible applications which will be the domain of future work.

show abstract

Section: Basic Concepts Of Tedamentioning

confidence: 99%

Anomaly detection based on eccentricity analysis

Angelov

2014

2014 IEEE Symposium on Evolving and Autonomous Learning Systems (EALS)

Self Cite

127

View full text Add to dashboard Cite

show abstract

“…The ARTOT method, described in [47] and [54], aims to avoid the parameters dependency, such as the ℎ parameter, as well as recursive incremental description. It estimates data density value according to the equation…”

Section: Non-parametric Density Estimation Techniques For Trackingmentioning

confidence: 99%

“…In ARTOT method [47], [54], the density is calculated for each of the pixels, also the mean and variance of the density are calculated:…”

Section: Non-parametric Density Estimation Techniques For Trackingmentioning

confidence: 99%

Intelligent Video Surveillance

Neves¹

2019

View full text Add to dashboard Cite

The author is pleased to thank Denis Kolev and Mikhail Suvorov, discussions with whom, as well the co-operation on the articles and book chapter, have contributed significantly to this thesis. The discussions, article co-operation and various help and assistance of my supervisors, Professor Plamen Angelov and Professor Garik Markarian, helped me enormously. Also I need to praise Professor George Kolev for all discussions and help. Also, many appreciation go to my colleagues in Rinicom, to fellows of the EU FP7 TRAX project for object tracking, in which I am happy to participate, and to my parents, Nikolay and Lyudmila, and my sister Evgenia.

show abstract