Main Page
Biography
CV
 Research
 Publications
 People
 Teaching
 Contact
Context-aware Anomaly Detection System Based on Big Data
 
 

Recent developments in information and detection technologies, and increasing use of intelligent mobile devices and internet have bolstered the capacity and capabilities of data acquisition systems beyond expectation. Today, many sources of information from shares on social networks to blogs, from intelligent device activities to security camera recordings are easily accessible. In our project, we will design state-aware anomaly detection and event prediction systems based on data from diverse sources acquired rapidly under unstationary conditions and quality. The problem of anomaly (or irregularity) detection and subsequent event prediction is a critical topic of national importance, particularly due to increasing border violations and cyber attacks in recent years. However, traditional techniques show insufficient performance in real-life applications due to several reasons: (1) Data acquired from diverse sources are too large in size to be adequately processed by conventional feature extraction, signal processing and machine learning methods. (2) The performance of conventional methods is further impaired by the highly variable properties, structure and quality of text, sound and video data acquired at high speeds. Therefore, highly innovative approaches are urgently needed to cast the full potential of big data on anomaly detection and event prediction applications.

In this project, we design novel algorithms that process text on social media, usage statistics of mobile devices and surveillance camera recordings in real time, and subsequently leverage these data for context-dependent anomaly detection and event prediction. The main aims of the project are: 1) Design of techniques that will scan text in Turkish on social media platforms, and that will extract text features for event detection and prediction; 2) Design of systems that will extract visual features from surveillance camera recordings using deep-learning methods; 3) Design of techniques that will process communication data as well as user information (such as location and time) from mobile devices to perform anomaly detection and event prediction; 4) Design of systems that will perform context-dependent processing and interpretation of data acquired at various dimensions, times and quality from written, audio and visual sources, as well as extracted features; 5) Development of a theoretical foundation for anomaly detection in big data applications.

We will first study anomaly detection problems that are dependent on the state or context of application. In this regard, detection of context-dependent irregularity is of greater relevance for national security than point irregularity. Context-dependent anomaly arises in cases where an event may be considered irregular at certain times and normal at other instances. As a result, detection of real-life anomalies is compromised due to the time-varying properties of the information medium, and state, time and context-dependent variations in the anomaly definition. In this project, for the first time in literature, we will design optimal anomaly-detection approaches based on content, context and location-dependent processing of text, sound and video sequences. The proposed algorithm will select the most informative data types and volumes, and the most effective prediction techniques to process the selected data in a state-dependent manner.

Sample publications on this topic include:

-- H. Ozkan, F. Ozkan and S. S. Kozat, ``Online Anomaly Detection under Markov Statistics with Controllable Type-I Error,'' IEEE Transactions on Signal Processing, Accepted, 2015

-- H. Ozkan, O. Pelvan and S. S. Kozat, ``Data Imputation through the Identification of Local Anomalies,'' IEEE Transactions on Neural Networks and Learning Systems, Accepted, 2015.

-- H. Ozkan, F. Ozkan, I. Delibalta and S. S. Kozat, ``Online Anomaly Detection with Constant False Alarm Rate" IEEE Workshop on Machine Learning for Signal Processing, Boston, 2015.

-- M. O. Sayin, N. D. Vanli, I. Delibalta and S. S. Kozat, ``Efficient and Distributed Tracking of Evolving State," IEEE Workshop on Machine Learning for Signal Processing, Boston, 2015.

-- N. D. Vanli and S. S. Kozat, ``A Comprehensive Approach to Universal Nonlinear Regression Based on Trees,'' IEEE Transactions on Signal Processing, 2013.