One-Class Drift Compensation for an Electronic Nose

Abstract

Drift compensation is an important issue in an electronic nose (E-nose) that hinders the development of E-nose’s model robustness and recognition stability. The model-based drift compensation is a typical and popular countermeasure solving the drift problem. However, traditional model-based drift compensation methods have faced “label dilemma” owing to high costs of obtaining kinds of prepared drift-calibration samples. In this study, we have proposed a calibration model for classification utilizing a single category of drift correction samples for more convenient and feasible operations. We constructed a multi-task learning model to achieve a calibrated classifier considering several demands. Accordingly, an associated solution process has been presented to gain a closed-form classifier representation. Moreover, two E-nose drift datasets have been introduced for method evaluation. From the experimental results, the proposed methodology reaches the highest recognition rate in most cases. On the other hand, the proposed methodology demonstrates excellent and steady performance in a wide range of adjustable parameters. Generally, the proposed method can conduct drift compensation with limited one-class calibration samples, accessing the top accuracy among all presented reference methods. It is a new choice for E-nose to counteract drift effect under cost-sensitive conditions.

Review–Modern Data Analysis in Gas Sensors

“…Another domain transfer-based approach proposed by Liang et al 41 utilized external factor interference suppression in classifying gases. A feature transfer-based algorithm was proposed in another article 116 to increase accuracy for drifted E-nose sensors. A joint distribution adaptation-based algorithm was demonstrated in another study 77 where KNN was implemented after minimizing the maximum mean discrepancy (MMD) among features.…”

Model Development for Alcohol Concentration in Exhaled Air at Low Temperature Using Electronic Nose

“…Their disadvantage is that they necessitate a lot of experimentation and make model construction more challenging. Researchers have also developed mathematical models for e-nose drift compensation, but all of them are difficult to use in EN under low-temperature conditions [33][34][35]. The EN may become more popular if a model is researched and applied to it so that it may work in low-temperature conditions without having the aforementioned issues and effectively weaken the effect of temperature.…”