In this paper we propose a strategy based on past/present values provided by each sensor of a network for detecting their malicious activity. Basically, we will compare at each moment the sensor's output with its estimated value computed by an autoregressive predictor. In case the difference between the two values is higher then a chosen threshold, the sensor node becomes suspicious and a decision block is activated.

During their task accomplishment, autonomous unmanned aerial vehicles are facing more and more threats coming from both ground and air. In such adversarial environments, with no a priori information about the threats, a flying robot in charge with surveilling a specified 3D sector must perform its tasks by evolving on misleading and unpredictable trajectories to cope with enemy entities. In our view, the chaotic dynamics can be the cornerstone in designing unpredictable paths for such missions, even though this solution was not exploited until now by researchers in the 3D context. This paper addresses the flight path-planning issue for surveilling a given volume in adversarial conditions by proposing a proficient approach that uses the chaotic behaviour exhibited by the 3D Arnold’s cat map. By knowing the exact location of the volume under surveillance before take-off, the flying robot will generate the successive chaotic waypoints only with onboard resources, in an efficient manner. The method is validated by simulation in a realistic scenario using a detailed Simulink model for the X-4 Flyer quadcopter.

Because of numerous possible causes involved, it isn't easy for general physicians to identify the precise reason of the psychiatric diseases and to decide the correct treatment. Bayesian networks are recognized as efficient graphical models with significant capabilities for investigating biomedical data either to obtain relationships between variables, either for medical predictions. Our paper provides a Bayesian network-based analysis of psychiatric patient data, which have been gathered from a Romanian specialized clinic during a couple of years. The development of this Bayesian network led us to the identification of most significant factors that affect some important diseases and their correlations.

Living organisms have developed and optimized ingenious defense strategies based on positional entropy. One of the most significant examples in this respect is known as protean behavior, where a prey animal under threat performs unpredictable zig-zag movements in order to confuse, delay or escape the predator. This kind of defensive behavior can inspire efficient strategies for patrolling robots evolving in the presence of adversaries. The main goal of our proposed bioinspired method is to implement the protean behavior by altering the reference path of the robot with sudden and erratic direction changes without endangering the robot’s overall mission. By this, a foe intending to target and destroy the mobile robot from a distance has less time for acquiring and retaining the proper sight alignment. The method uses the chaotic dynamics of the 2D Arnold’s cat map as a primary source of positional entropy and transfers this feature to every reference path segment using the kinematic relative motion concept. The effectiveness of this novel biologically inspired method is validated through extensive and realistic simulation case studies.