Explainable Artificial Intelligence (XAI) is an emergent research field which tries to cope with the lack of transparency of AI systems, by providing human understandable explanations for the underlying Machine Learning models. This work presents a new explanation extraction method called LEAFAGE. Explanations are provided both in terms of feature importance and of similar classification examples. The latter is a well known strategy for problem solving and justification in social science. LEAFAGE leverages on the fact that the reasoning behind a single decision/prediction for a single data point is generally simpler to understand than the complete model; it produces explanations by generating simpler yet locally accurate approximations of the original model. LEAFAGE performs overall better than the current state of the art in terms of fidelity of the model approximation, in particular when Machine Learning models with non-linear decision boundaries are analysed. LEAFAGE was also tested in terms of usefulness for the user, an aspect still largely overlooked in the scientific literature. Results show interesting and partly counter-intuitive findings, such as the fact that providing no explanation is sometimes better than providing certain kinds of explanation.
Ultrasonic wave is widely used in Structure Health Monitoring (SHM) systems. A piezoelectric transducer (PZT) is one of the most widely used sensors to acquire the structure's ultrasonic wave. As today's world is digital, it is necessary to digitize the traditional analog PZT sensing system. This paper describes the development and analysis of a digital ultrasonic sensing device (DUSD) for PZT sensors. We removed the complexities of the analog circuit by interfacing the microcontroller directly with the charge amplifier circuit. The microcontroller used in this research is a 32-bit ARM Cortex-M4 with in-built FPU (Floating Point Unit) and DSP (Digital signal processing) instructions. These features make it possible to compute complex signal processing algorithms and methods in the controller itself. The developed sensing device can communicate with the user and other devices using Universal Asynchronous Receiver/Transmitter (UART). The user can select cut-off frequencies of both high pass filters (HPF) and low pass filters (LPF) as well as types of data (ultrasonic waves, damage index) that the user wishes to collect from the device. To illustrate the proficiencies of the device, the ultrasonic wave was collected and evaluated to detect the damage in the test specimen.
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.