기본 정보
연구 분야
프로젝트
발행물
구성원
article|
gold
·인용수 1
·2025
A Reproducible Benchmark for Gas Sensor Array Classification: From FE-ELM to ROCKET and TS2I-CNNs
Chang‐Hyun Kim, Seung-Hwan Choi, Seung-Hwan Choi, Sanghun Choi, Sanghun Choi, Suwoong Lee
IF 3.5Sensors
초록

Classifying low-concentration Gas Sensor Array (GSA) data is hard due to low SNR, sensor heterogeneity, drift, and small samples. We benchmark time-series-to-image (TS2I) CNNs against time-series classifiers, after reproducing a strong FE-ELM baseline under a shared fold manifest. Using the GSA-LC and GSA-FM datasets, we compare FE-ELM, vector baselines, time-series methods, and TS2I-CNNs with 20 × 5 repeated stratified cross-validation (<i>n</i> = 100). ROCKET delivers the best accuracy on both datasets and is significantly better than TCN and MiniROCKET (paired tests with Holm-Bonferroni, <i>p</i> < 0.05): on GSA-FM, accuracy 0.9721 ± 0.0480 (95% CI [0.9627, 0.9815]) with Macro-F1 0.9757; on GSA-LC, 0.9578 ± 0.0433 (95% CI [0.9493, 0.9663]) with Macro-F1 0.9555. Among image-based models, CNN-RP is the most robust, whereas CNN-GASF lags, especially on GSA-LC. RGB fusion strategies (e.g., with MTF) are dataset-dependent and often inconsistent, and transfer learning with ResNet-18 offers no consistent advantage. Overall, ROCKET ranks first across folds, while CNN-RP is the most reliable TS2I alternative under low-concentration conditions. These results provide a reproducible, fair benchmark for e-nose applications and practical guidance for model selection, while clarifying both the potential and limitations of TS2I.

키워드
Benchmark (surveying)Rocket (weapon)Sensor fusionBaseline (sea)Sensor arrayRGB color modelTransfer of learning
타입
article
IF / 인용수
3.5 / 1
게재 연도
2025