Gas Classification Using Time-Series-to-Image Conversion and CNN-Based Analysis on Array Sensor
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- SCIEScopus
- 저널 순위
- JCR Q1Scopus Q1
- 저널
- IEEE SENSORS JOURNAL25(21) · pp.40690 · 2025
- 피인용
- Web of Science 2Scopus 2
- FWCI (Scopus)
- 0.23
- JCR IF
- JCR 2024 4.5
- ISSN
- 1530-437X
저자
- Kim, Chang-Hyun제1저자Korea Inst Ind Technol, Dept Adv Mobil Components Grp, Daegu 42994, South Korea
- 정대웅Pusan Natl Univ, Coll Nanosci & Nanotechnol, Dept Nanomechatron, Busan 46241, South Korea
- 최승환Korea Inst Ind Technol, Dept Adv Mobil Components Grp, Daegu 42994, South Korea
- Choi, SanghunKyungpook Natl Univ, Sch Mech Engn, Daegu 41566, South Korea
- Lee, Suwoong교신저자Korea Inst Ind Technol, Dept Adv Mobil Components Grp, Daegu 42994, South Korea
초록
Gas detection is essential in industrial and domestic environments to ensure safety and prevent hazardous incidents. Traditional single-sensor time-series analysis often suffers from limitations in accuracy and robustness due to environmental variations. To address this issue, we propose an artificial intelligence (AI)-based approach that transforms 1-D time-series data into 2-D image representations, followed by the classification of acetylene (C2H2), ammonia (NH3), and hydrogen (H2) using convolutional neural networks (CNNs). By utilizing image transformation techniques such as recurrence plots (RPs), Gramian angular fields (GAFs), and Markov transition fields (MTFs), our method significantly enhances feature extraction from sensor data. In this study, we utilized sensor array data obtained from ZnO and CuO thin films previously synthesized using a droplet-based hydrothermal method. By exploiting the temperature-dependent response characteristics of these sensors, we aimed to improve classification accuracy. Experimental results indicate that our proposed approach achieves a 6.2% relative improvement over the LSTM baseline model (90.1%) in classification accuracy compared to the conventional LSTM model applied directly to raw time-series data. This study demonstrates that converting time-series data into image representations substantially improves gas detection performance, offering a scalable and efficient solution for various sensor-based applications. Future research will focus on real-time implementation and further optimization of deep learning architectures.
키워드
Classification algorithmsdeep learningfeature detectiongas detectorsgas sensor arrays
식별자
- Scopus EID
- 2-s2.0-105018111543
- WoS UID
- 001606684200004



로그인
연구물 목록으로