The notion of employing a Deep Learning (DL) for gas classification has kindled revolution in the field that has both improved data collection measures and classification performance. Yet, the current literature, with its vast contributions, has potential in enhancing the current state-of-the-art by employing both DL and novel visualization methods to boost classification performance and speed. Therefore, this paper presents a dual classification system for high-performance gas classification: on 1D time series data and on 2D Gramian Angular Field (GAF) data. For the GAF case, 1D data is converted into 2D counterparts by means of normalization, segmentation, averaging, and color-coding. The Gas Sensor Array (GSA) dataset is used for evaluating the implemented AlexNet model for classifying 2D GAF data and an improved version of GasNet for 1D time-based data. Using a cloud-based architecture, the two models are evaluated and benchmarked with the state-of-the-art. Evaluation results of the modified GasNet model on time series data signifies state-of-the-art accuracy of 96.0%, while AlexNet achieved 81.3% test accuracy of GAF classification with near real-time performance on edge computing platforms.
Deep Learning (DL) is empowering technology in a plethora of ways, especially when big data processing is a core requirements. Many challenges, however, arise when solely depending on cloud computing for Artificial Intelligence (AI), such as data privacy, communication latency, and power consumption. Despite increasing popularity of edge computing, the overarching issue in this scope is lack of a comprehensive documentation on how to setup a given edge computing device to run DL algorithms. Due to its specialized nature, installing the full version of TensorFlow DL library on an edge device is a complicated procedure that is seldom successful, due to the many dependent software libraries needed to be compatible with varying architectures of edge computing devices. Henceforth, in this paper, we present a novel guide on how to setup the TensorFlow Lite software library and outline a complete workflow of model training, validation, and testing on the ODROID-XU4. Results are presented for a case study on energy data classification using the outlined model show almost 7 times higher computational performance compared to cloudbased ML.
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.