Performance and high availability have become increasingly important drivers, amongst other drivers, for user retention in the context of web services such as social networks, and web search. Exogenic and/or endogenic factors often give rise to anomalies, making it very challenging to maintain high availability, while also delivering high performance. Given that service-oriented architectures (...

Human crowd behavior analysis is a subject of great interest in research now days. Great advantage of investigating dense human crowds in places like mosques and temples to perform automatic surveillance for any unusual activity detection that might be a subject of interest and must be addressed on earliest to avoid accident. We present robust statistical skeleton for modeling a dense crowded s...

The use of statistical methods for anomaly detection has become of interest to researchers in many subject areas. Structural health monitoring in particular has benefited from the versatility of statistical damage-detection techniques. We propose modeling structural vibration sensor output data using nonlinear time-series models. We demonstrate the improved performance of these models over curr...

The state of classifier incongruence in decision making systems incorporating multiple classifiers is often an indicator of anomaly caused by an unexpected observation or an unusual situation. Its assessment is important as one of the key mechanisms for domain anomaly detection. In this paper, we investigate the sensitivity of Delta divergence, a novel measure of classifier incongruence, to est...

We propose using side information to further inform anomaly detection algorithms of the semantic context of the text data they are analyzing, thereby considering both divergence from the statistical pattern seen in particular datasets and divergence seen from more general semantic expectations. Computational experiments show that our algorithm performs as expected on data that reflect real-worl...

Support vector machine are among the most well known supervised anomaly detection technique, which are very efficient in handling large and high dimensional dataset. SVM, a powerful machine method developed from statistical learning and has made significant achievement in some field. This Technique does not suffer the limitations of data dimensionality and limited samples. In this present study...

This paper presents a new approach, based on polynomial optimization and the method of moments, to the problem of anomaly detection. The proposed technique only requires information about the statistical moments of the normal-state distribution of the features of interest and compares favorably with existing approaches (such as Parzen windows and 1-class SVM). In addition, it provides a succinc...

Various applications rely on a continuous processing of data streams originating from a network of interconnected and collaborated sensors. The processing of those streams has turned out to be a difficult task as sensors only have limited resources and the data they produce is inherently uncertain and unreliable. In order to bridge the gap from raw, uncertain sensor readings to a meaningful mod...

Social network analysis has attracted intensive interests by researchers from multiple disciplines. However most of the existing work is descriptive nature, and statistical network analysis remains an active area of research. In this paper, we model and study two facets of the social networks in short message services (SMS). One is the structure of the contact networks of mobile users, the othe...

The JiNao project at MCNC/NCSU focuses on detecting intrusions, especially insider attacks, against OSPF (Open Shortest Path First) routing protocol. This paper presents the implementation and experiments of the JiNao’s statistical intrusion detection module. Our implementation is based upon the algorithm developed in SRI’s NIDES (Next-generation Intrusion Detection Expert System) project. Some...