Nondestructive testing techniques for the diagnosis of defects in solid materials can follow three steps, i.e., detection, location, and characterization. The solutions currently on the market allow for good detection and location of defects, but their characterization in terms of the exact determination of defect shape and dimensions is still an open question. This paper proposes a method for the reliable estimation of crack shape and dimensions in conductive materials using a suitable nondestructive instrument based on the eddy current principle and machine learning system postprocessing. After the design and tuning stages, a performance comparison between the two machine learning systems [artificial neural network (ANN) and support vector machine (SVM)] was carried out. An experimental validation carried out on a number of specimens with different known cracks confirmed the suitability of the proposed approach for defect characterization.

Monitoring of aquatic ecosystems has been historically accomplished by intensive campaigns of direct measurements (by probes and other boat instruments) and indirect extensive methods such as aero-photogrammetry and satellite detection. These measurements characterized the research in the last century, with significant but limited improvements within those technological boundaries. The newest advances in the field of smart devices and increased networking capabilities provided by emerging tools, such as the Internet of Things (IoT), offer increasing opportunities to provide accurate and precise measurements over larger areas. These perspectives also correspond to an increasing need to promptly respond to frequent catastrophic impacts produced by drilling stations and intense transportation activities of dangerous materials over ocean routes. The shape of coastal ecosystems continuously varies due to increasing anthropic activities and climatic changes, aside from touristic activities, industrial impacts, and conservation practices. Smart buoy networks (SBNs), autonomous underwater vehicles (AUVs), and multi-sensor microsystems (MSMs) such as smart cable water (SCW) are able to learn specific patterns of ecological conditions, along with electronic “noses”, permitting them to set innovative low-cost monitoring stations reacting in real time to the signals of marine environments by autonomously adapting their monitoring programs and eventually sending alarm messages to prompt human intervention. These opportunities, according to multimodal scenarios, are dramatically changing both the coastal monitoring operations and the investigations over large oceanic areas by yielding huge amounts of information and partially computing them in order to provide intelligent responses. However, the major effects of these tools on the management of marine environments are still to be realized, and they are likely to become evident in the next decade. In this review, we examined from an ecological perspective the most striking innovations applied by various research groups around the world and analyzed their advantages and limits to depict scenarios of monitoring activities made possible for the next decade.

Early diagnosis of neurodegenerative disorders, such as Alzheimer's Disease (AD), is very important to reduce their effects and to improve both quality and life expectancy of patients. In this context, it is generally agreed that handwriting is one of the first skills altered by the onset of such diseases. For this reason, the analysis of handwriting and the study of its alterations have become of great interest in order to formulate the diagnosis as soon as possible. A fundamental aspect for the use of these techniques is the definition of effective features, which allows the system to distinguish the natural alterations of handwriting due to age, from those caused by neurodegenerative disorders. Starting from these considerations, the aim of our study is to verify whether the combined use of both shape and dynamic features allows a decision support system to improve performance for AD diagnosis. To this purpose, starting from a database of on-line handwriting samples, we generated for each of them an off-line synthetic color image, where the color of each elementary trait encodes, in the three RGB channels, the dynamic information associated with that trait. In order to verify the importance and the specific role played by shape information, we also generated an off-line synthetic binary image for each handwriting sample, where background pixels have white color, while those corresponding to the traits have black color. Finally, we exploited the ability of Convolutional Neural Network (CNN) to automatically extract features on both color and binary images. We carried out a large set of experiments for comparing the results obtained by using on-line features with those obtained by using the off-line features provided by CNN on both color and binary images.