In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).
Much greater surface-to-volume ratio of hierarchical nanostructures renders them with promising potential for high performance chemical sensing. In this work, crystalline nanocombs were synthesized via chemical vapor deposition and fabricated into resistive gas sensors. Particularly, NO2 sensing performance of these devices has been systematically characterized, showing higher sensitivity as compared to their nanobelt counterparts. Through device simulation, it was discovered that the teeth part of a nanocomb could serve as a "negative-potential gate" after accumulating electrons captured by surface adsorbed NO2 molecules. This self-gating effect eventually results in a greater reduction of nanocomb device channel conductance upon NO2 exposure, as compared to a nanobelt device, leading to a much higher NO2 detection sensitivity. This study not only sheds light on the mechanism of performance enhancement with hierarchical nanostructures, but also proposes a rational approach and a simulation platform to design nanostructure based chemical sensors with desirable performance.
The accelerated evolution of communication platforms including Internet of Things (IoT) and the fifth generation (5G) wireless communication network makes it possible to build intelligent gas sensor networks for real-time monitoring chemical safety and personal health. However, this application scenario requires a challenging combination of characteristics of gas sensors including small formfactor, low cost, ultralow power consumption, superior sensitivity, and high intelligence. Herein, self-powered integrated nanostructured-gas-sensor (SINGOR) systems and a wirelessly connected SINGOR network are demonstrated here. The room-temperature operated SINGOR system can be self-driven by indoor light with a Si solar cell, and it features ultrahigh sensitivity to H2, formaldehyde, toluene, and acetone with the record low limits of detection (LOD) of 10, 2, 1, and 1 ppb, respectively. Each SINGOR consisting of an array of nanostructured sensors has the capability of gas pattern recognition and classification. Furthermore, multiple SINGOR systems are wirelessly connected as a sensor network, which has successfully demonstrated flammable gas leakage detection and alarm function. They can also achieve gas leakage localization with satisfactory precision when deployed in one single room. These successes promote the development of using nanostructured-gas-sensor network for wide range applications including smart home/building and future smart city.
In this work, we present a high-performance smart electronic nose (E-nose) system consisting of a multiplexed tin oxide (SnO) nanotube sensor array, read-out circuit, wireless data transmission unit, mobile phone receiver, and data processing application (App). Using the designed nanotube sensor device structure in conjunction with multiple electrode materials, high-sensitivity gas detection and discrimination have been achieved at room temperature, enabling a 1000 times reduction of the sensor's power consumption as compared to a conventional device using thin film SnO. The experimental results demonstrate that the developed E-nose can identify indoor target gases using a simple vector-matching gas recognition algorithm. In addition, the fabricated E-nose has achieved state-of-the-art sensitivity for H and benzene detection at room temperature with metal oxide sensors. Such a smart E-nose system can address the imperative needs for distributed environmental monitoring in smart homes, smart buildings, and smart cities.
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.