Sensor fusion for intrusion detection under false alarm constraints

Abstract

Sensor fusion algorithms allow the combination of many heterogeneous data types to make sophisticated decisions. In many situations, these algorithms give increased performance such as better detectability and/or reduced false alarm rates. To achieve these benefits, typically some system or signal model is given. This work focuses on the situation where the event signal is unknown and a false alarm criterion must be met. Specifically, the case where data from multiple passive infrared (PIR) sensors are processed to detect intrusion into a room while satisfying a false alarm constraint is analyzed. The central challenge is the space of intrusion signals is unknown and we want to quantify analytically the probability of false alarm. It is shown that this quantification is possible by estimating the background noise statistics and computing the Mahalanobis distance in the frequency domain. Using the Mahalanobis distance as the decision metric, a threshold is computed to satisfy the false alarm constraint.978-1-4799-6117-7/15/$31.00 ©2015 IEEE This full text paper was peer-reviewed at the direction of IEEE Instrumentation and Measurement Society prior to the acceptance and publication.

Investigation of Flash Floods on Early Basis: A Factual Comprehensive Review

“…Fusion algorithm of sensors permits the combination of different data type of sensors to achieve higher accuracy and precision. Particularly if we take an example of PIR (Passive infrared sensors) in which many sensors output from PIR sensors were taken to investigate the presence of the real target and to identify the false alarm [15]. The evacuation announcements in emergency situation are affected due to the false alarm.…”

“…The PCA dimension was selected to record at least 95 % of the variance and PCA coefficients were Gaussian distributed. The results were taken from post processing data that was recorded and observed by the test bed particularly analysis was performed on MATLAB [15]. Nistara was a device interfaced with different sensors (thermal, fire, seismic) was installed at different points for sending signals to the main computer which implemented the fuzzy logic-based decisions.…”

Recognizing Foreign Object Debris (FOD): False Alarm Reduction Implementation

“…Highly autentic imaging technology is esse for the dense vigilance of airport runways and railway traction systems; therefore, carrier frequency was enhanced to a higher frequency like W-band (75-110 GHz) [8]. A sensory network system was connected by optical fiber [6][7][8]. Radio over fiber distributed frequencies to the radar systems [8].…”

“…Birds, mini nut and bolts, tiny falling chunk or scrap have various sizes and shapes therefore it would be more difficult to observe FOD manually as it will have high false alarm rates due to the poor analysis of human being [4][5]. Several sensors based fusion algorithms have been developed to mitigate the fake alerts [6]. In large field infrared system needed high data rate bandwidth for the images.…”