Monitoring of mechanical structures is a Big Data challenge concerning Structural Health Monitoring and Non-destructive Testing. The sensor data produced by common measuring techniques, e.g., guided wave propagation analysis, is characterized by a high dimensionality in the temporal domain, and moreover in the spatial domain using 2D scanning. The quality of the results gathered from guided wave analysis depends strongly on the preprocessing of the raw sensor data and the selection of appropriate region of interest windows (ROI) for further processing (feature selection). Commonly, structural monitoring is a task that maps high-dimensional input data on low-dimensional output data (feature extraction of information), e.g., in the simplest case a Boolean output variable “Damaged”. Machine Learning (ML), e.g., supervised learning, can be used to derive such a mapping function. But quality and performance depends strongly on feature selection, too. Therefore, adaptive and reliable input data reduction (feature selection) is required at the first layer of an automatic structural monitoring system. Assuming some kind of one- or two-dimensional sensor data (or n-dimensional in general), image segmentation can be used to identify ROIs. Major difficulties in image segmentation are noise and the differing homogeneity of regions, complicating the definition of suitable threshold conditions for the edge detection or region splitting/clustering. Many traditional image segmentation algorithms are constrained by this issue. In this work, autonomous agents are used as an adaptive and self-organizing software architecture solving the feature selection problem. Agents are operating on dynamically bounded data from different regions of a signal or an image (i.e., distributed with simulated mobility), adapted to the locality, being reliable and less sensitive to noisy sensor data. Finally, adaptive feature extraction (information of structural state and damage) is performed by numerical algorithms and Machine Learning based on ultrasonic measurements of hybrid probes with impact damages.