Recent Progress in Smart Electronic Nose Technologies Enabled with Machine Learning Methods

Machine learning methods enable the electronic nose (E-Nose) for precise odor identification with both qualitative and quantitative analysis. Advanced machine learning methods are crucial for the E-Nose to gain high performance and strengthen its capability in many applications, including robotics, food engineering, environment monitoring, and medical diagnosis. Recently, many machine learning techniques have been studied, developed, and integrated into feature extraction, modeling, and gas sensor drift compensation. The purpose of feature extraction is to keep robust pattern information in raw signals while removing redundancy and noise. With the extracted feature, a proper modeling method can effectively use the information for prediction. In addition, drift compensation is adopted to relieve the model accuracy degradation due to the gas sensor drifting. These recent advances have significantly promoted the prediction accuracy and stability of the E-Nose. This review is engaged to provide a summary of recent progress in advanced machine learning methods in E-Nose technologies and give an insight into new research directions in feature extraction, modeling, and sensor drift compensation.

Drift Compensation on Massive Online Electronic-Nose Responses

Gas sensor drift is an important issue of electronic nose (E-nose) systems. This study follows this concern under the condition that requires an instant drift compensation with massive online E-nose responses. Recently, an active learning paradigm has been introduced to such condition. However, it does not consider the “noisy label” problem caused by the unreliability of its labeling process in real applications. Thus, we have proposed a class-label appraisal methodology and associated active learning framework to assess and correct the noisy labels. To evaluate the performance of the proposed methodologies, we used the datasets from two E-nose systems. The experimental results show that the proposed methodology helps the E-noses achieve higher accuracy with lower computation than the reference methods do. Finally, we can conclude that the proposed class-label appraisal mechanism is an effective means of enhancing the robustness of active learning-based E-nose drift compensation.

Drift Characteristics of DONET Pressure Sensors Determined From In-Situ and Experimental Measurements

DONET, the dense ocean-floor network system for earthquakes and tsunamis, began operations in the Nankai Trough, SW Japan, in 2010. The present study focuses on pressure sensors that are being used as tsunami meters to measure changes in hydraulic pressure. Pressure sensors typically show a drift in their readings over their operational lifespan. DONET pressure sensors can act as geodetic sensors measuring vertical crustal deformation change over time if the sensor drift can be accurately corrected. Monitoring crustal deformation before the occurrence of megathrust earthquakes is performed by discriminating between the vertical crustal deformation and the sensor drift of the pressure sensors. Therefore, in this study, we evaluated the sensor drift shown by the DONET pressure sensors since their deployment into the deep-sea, by removing the tidal component and confirming the occurrence of sensor drift. We evaluated the initial behavior of pressure sensors before deep-sea deployment using our own high-accuracy pressure standard. Our experiment involved 20-MPa pressurization for the pressure sensors under an ambient temperature of 2°C for a duration of 1 month. Some sensor drifts in our experiment correspond in rate and direction to those from the in-situ measurements determined to be in the initial stage. Our experiment suggests that the pre-deployment pressurization of pressure sensors can be an effective procedure to determine the sensor drift after sensor deployment into the deep-sea.