• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.76-88
• /
• 2019

With advances in olfactory sensor technologies, the number of reports on various intelligent applications using multiple sensors (sensor arrays) are continuously increasing for fields such as medicine, environment, security, etc. For intelligent and point-of-care applications, it is not only important for the sensor technology to perform chemical or physical measurements rapidly and accurately, but it is also important for artificial intelligence technology to recognize and quantify specific chemicals or diagnose diseases such as lung cancer and diabetes. In particular, great advances in pattern recognition technologies, including deep learning algorithms, as well as sensor array technologies, are expected to enhance the potential of various types of olfactory intelligence applications, including early cancer diagnosis, drug seeking, military operations, and air pollution monitoring.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.405-405
• /
• 2000

We designed the artificial olfactory sensing system (Electronic Nose) using MOS type sensor array fur recognizing and analyzing odour. The response of individual sensors of sensor array, each processing a slightly different response towards the sample volatiles, can provide enough information to discriminate between sample odours. In this paper, we applied clustering algorithm for dimension reduction, such as linear projection mapping (PCA method), nonlinear mapping (Sammon mapping method) and the combination of PCA and Sammon mapping having a better discriminating ability. The odours used are VOC (Volatile chemical compound) and Toxic gases.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1997.04a
• /
• pp.99-102
• /
• 1997

An electronic nose system is an instrument designed far mimicking human olfactory system. It consists generally of gas (odor) sensor array corresponding to olfactory receptors of human nose and artificial neural network pattern recognition technique based on human biological odor sensing mechanism. Considerable attempts to develop the electronic nose system have been made far applications in the fields of floods, drinks, cosmetics, environment monitoring, etc. A portable electronic nose system has been fabricated by using oxide semiconductor gas sensor array and pattern recognition technique such as principal component analysis (PCA) and back propagation artificial neural network The sensor array consists of six thick film gas sensors whose sensing layers are Pd-doped WO$_3$ Pt-doped SnO$_2$ TiO$_2$-Sb$_2$O$_3$-Pd-doped SnO$_2$ TiO$_2$-Sb$_2$O$_{5}$-Pd-doped SnO$_2$+Pd filter layer, A1$_2$O$_3$-doped ZnO and PdCl$_2$-doped SnO$_2$. As an application the system has been used to identify CO/HC car exhausting gases and the identification has been successfully demonstrated.d.

• Journal of Sensor Science and Technology
• /
• v.27 no.2
• /
• pp.118-125
• /
• 2018

An evaluation system for an electronic-nose concept using three types of metal oxide gas sensors that react similarly to the human olfactory cells was constructed for the quantitative and qualitative evaluation of aroma fragrances. Four types of aroma fragrances (lavender, orange, jasmine, and Roman chamomile), which are commonly used in aromatherapy, were evaluated. All the gas sensors reacted remarkably to the aroma fragrances and the good correlation of r=0.58-0.88 with the aromatic odor intensities by olfaction was confirmed. From the results of the analysis of an electronic-nose concept for classifying the characteristics of aroma oil fragrances, aroma oils could be classified using the fragrance characteristics and oil extraction methods with the cumulative variability contribution rate of 95.65% (F1: 69.65%, F2: 26.03%) by principal component analysis. In the pattern recognition based on the artificial neural network, the four aroma fragrances were 100% recognized through the training data of 56 cases (70%) out of 80 cases, and the pattern recognition rate was 57.1%-71.4% through the validation and testing data of 24 cases (30%). The pattern recognition success rate through all confusion matrices was 82.1%, indicating that the classification of aroma oil fragrances using the three types of gas sensors was successful.