Artificial Intelligence (AI), has many benefits, including the ability to find complex patterns, automation, and meaning making. Through these benefits, AI has revolutionized image processing among numerous other disciplines. AI further has the potential to revolutionize other domains; however, this will not happen until we can address the "ilities": repeatability, explain-ability, reliability, use-ability, trust-ability, etc. Notably, many problems with the "ilities" are due to the artistic nature of AI algorithm development, especially hyperparameter determination. AI algorithms are often crafted products with the hyperparameters learned experientially. As such, when applying the same algorithm to new problems, the algorithm may not perform due to inappropriate settings. This research aims to provide a straightforward and reliable approach to automatically determining suitable hyperparameter settings when given an AI algorithm. Results, show reasonable performance is possible and end-to-end examples are given for three deep learning algorithms and three different data problems.
The Internet of Things (IoT) and Industrial IoT (IIoT) is enabled by Wireless Personal Area Network (WPAN) devices. However, these devices increase vulnerability concerns of the IIoT and resultant Critical Infrastructure (CI) risks. Secure IIoT is enabled by both pre-attack security and post-attack forensic analysis. Radio Frequency (RF) Fingerprinting enables both pre-and post-attack security by providing serial-number level identification of devices through fingerprint characterization of their emissions. For classification and verification, research has shown high performance by employing the neural network-based Generalized Relevance Learning Vector Quantization-Improved (GRLVQI) classifier. However, GRLVQI has numerous hyperparameters and tuning requires AI expertise, thus some researchers have abandoned GRLVQI for notionally simpler, but less accurate, methods. Herein, we develop a foolproof approach for tuning AI algorithms. For demonstration, Z-Wave, an insecure low-power/cost WPAN technology, and the GRLVQI classifier are considered. Results show significant increases in accuracy (5% for classification, 50% verification) over baseline methods.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.