In many applications, an anomaly detection system presents the most anomalous data instance to a human analyst, who then must determine whether the instance is truly of interest (e.g. a threat in a security setting). Unfortunately, most anomaly detectors provide no explanation about why an instance was considered anomalous, leaving the analyst with no guidance about where to begin the investigation. To address this issue, we study the problems of computing and evaluating sequential feature explanations (SFEs) for anomaly detectors. An SFE of an anomaly is a sequence of features, which are presented to the analyst one at a time (in order) until the information contained in the highlighted features is enough for the analyst to make a confident judgement about the anomaly. Since analyst effort is related to the amount of information that they consider in an investigation, an explanation's quality is related to the number of features that must be revealed to attain confidence. One of our main contributions is to present a novel framework for large scale quantitative evaluations of SFEs, where the quality measure is based on analyst effort. To do this we construct anomaly detection benchmarks from real data sets along with artificial experts that can be simulated for evaluation. Our second contribution is to evaluate several novel explanation approaches within the framework and on traditional anomaly detection benchmarks, offering several insights into the approaches.
The widespread use of internet services over the wireless links is expeditiously grown in recent years. The reinforcement of portable computing platform and technological elevation of wireless communication evokes substantial prosperity in the design and development of integrated environment such as cellular mobile environments. The repercussion of packet losses due to corruption and mobility is the radical circumstances of deteriorating TCP performance in the wireless ambience. Uniform and Multistate error model are both used in wireless environment; Uniform error model provides packet losses at a constant rate which consequence an imprecise results during simulation as in wireless environment packet losses are arbitrary, bursty and time diversify in nature. However Multistate error model imitates the behavior of the wireless packet loss in real environment and produce infallible outcome. In this paper we constitute a realistic Cellular Mobile Environment by considering multistage error model in the design of wireless packet losses. Mobility in structure is also conceived to estimate the actual performance of TCP. Moreover the behavior of TCP Tahoe, Reno, New Reno, Sack and Vegas in Cellular Mobile network is simulated to perceive the impact of wireless link on the behavior of these TCP variants. Finally from the result of our simulation we conclude the best TCP variants for different circumstances.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.