• Journal of Korea Multimedia Society
• /
• v.13 no.8
• /
• pp.1171-1182
• /
• 2010

In this paper, odor classification and source analysis methods are proposed to trace odor sources in th air at the specific place and period. It is necessary to generate representative patterns in order to classify the various odors efficiently. We, therefore, create 67 kinds of odor representative patterns measured from the main sources. considering the air mixed with various odors, several mixed representative patterns for odor sources are generated with the combination of two or three different odors. In addition, the weight of odor sources for an odor from a civil complaint region are computed using pseudo inverse method. As a result, we can trace and identify the odor sources to lead to a specific odor and the contribution of each source. The results of this study will be useful for settling the civil complaint related with odors.

• Journal of Sensor Science and Technology
• /
• v.24 no.6
• /
• pp.368-372
• /
• 2015

In this paper, we proposed a post-processing technique for improving classification performance of electronic nose (E-Nose) system which may be occurred drift signals from sensor array. An adaptive radial basis function network using stochastic gradient (SG) and singular value decomposition (SVD) is applied to process signals from sensor array. Due to drift from sensor's aging and poisoning problems, the final classification results may be showed bias and fluctuations. The predicted classification results with drift are quantized to determine which identification level each class is on. To mitigate sharp fluctuations moving-averaging (MA) technique is applied to quantized identification results. Finally, quantization and some edge correction process are used to decide levels of the fluctuation-smoothed identification results. The proposed technique has been indicated that E-Nose system was shown correct odor identification results even if drift occurred in sensor array. It has been confirmed throughout the experimental works. The enhancements have produced a very robust odor identification capability which can compensate for decision errors induced from drift effects with sensor array in electronic nose system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.698-703
• /
• 2006

This paper proposes an approach to search for the odor source using an autonomous mobile robot equipped with vision and odor sensors. The robot is initially navigating around the specific area with vision system until it looks for an object in the camera image. The robot approaches the object found in the field of view and checks it with the odor sensors if it is releasing odor. If so, the odor is classified and localized with the classification algorithm based on neural network The AMOR(Autonomous Mobile Olfactory Robot) was built up and used for the experiments. Experimental results on the classification and localization of odor sources show the validity of the proposed algorithm.

• Journal of Sensor Science and Technology
• /
• v.25 no.3
• /
• pp.161-172
• /
• 2016

The use of a chemical sensor array can help discriminate between chemicals when comparing one sample with another. The ability to classify pattern characteristics from relatively small pieces of information has led to growing interest in methods of sensor recognition. A variety of pattern recognition algorithms, including the adaptive radial basis function network (RBFN), may be applicable to gas and/ or odor classification. In this paper, we provide a broad review of approaches for various types of gas and/or odor identification techniques based on RBFN and drift compensation techniques caused by sensor poisoning and aging.

• Journal of Korean Medical classics
• /
• v.13 no.1
• /
• pp.345-360
• /
• 2000

I In the rearch of the principle of herb classification based on constitution I have recognised Lee Jae Ma(李濟馬)'s medical thought on the herb. He had believed that herb must be used when needed, also had opposed taking overdose of medicine. And he had prescribed to a patient based on constitution. The results were summerized as follow; 1. In the classification of herb according to constitution, Although Gimilon(氣味論) that empasized in the herbal medicine have had reference value but cannot be absolute classific standard. The medicinal portion of herb was not significant. And through research the past prescription that were qouted by Lee Jae Ma cannot find a meaningful result. 2. Lee Jae Ma denied the tradtional GuiKyung(歸經) theory, and classified into Iung(肺), spleen(脾), liver(肝), kidney(腎). And when he gave medical teatment, he has used the methods of the supplement to weakned organ. 3. On the principle of herb classification based on constitution, Lee Jae Ma had presented general rule that are fragrance(馨), odor(臭), liquid(液), taste(味). Although it had suitable tendency but cannot complitely coinside with the actual. Therefore I interpreted fragrance(馨), odor(臭), liquid(液), taste(味) into the symbol that represent the chief effect. On these conception it's necessary more study.

• Journal of Environmental Impact Assessment
• /
• v.4 no.1
• /
• pp.59-64
• /
• 1995

Environmental Impact Assesment(EIA) is composed of various procedures, such as screening, scoping, inventory survey, prediction, assessment, mitigation measure, alternative assessment, and post management. Remote sensing introduced lately begins to be applied ecosystem and land use in inventory survey and assessment of EIA. This study explains on land use classification, buffering analysis of residential area, and overlaying analysis of odor predictive data with residential area for application to EIA with remote sensing data. Residential area extracted from land use classification of remote sensing provides effectively buffering analysis of residential area in selection of landfill site with GIS. It could assess also residential effect to an offensive odor by overlaying analysis. Application methods in EIA should be enlarged to assess effectively.

• Science of Emotion and Sensibility
• /
• v.16 no.2
• /
• pp.207-220
• /
• 2013

For video reality improvement, there has been much advancement in the methods of providing visual, auditory, and tactile information. On the other hand, there is little research on olfaction for video reality because it is difficult to define and knotty to manipulate. As a first step for video reality improvement using olfactory information, this research investigated users' acceptability of smell when they watch videos of various kinds and then classified the video clips based on their acceptability of different criteria. To do so, we first selected three questions of whether the scene in the video appears to have an odor (odor presence), whether a matching odor is likely to improve a sense of reality (effect on sense of reality), and whether s/he would like a matching odor to be present (preference for the matching odor). Then after collecting 51 video clips of various genres that would receive either high or low ratings for the questions above, we had participants to watch the videos and rate them for the above three questions on 7-point scale. For video classification, we paired each two questions to construct 2D space to draw scatterplot of video clips where the scales of the two questions represent X or Y axis. Clusters of video clips that locate at different quadrants of the 2D space would provide important insights in providing olfactory information for video reality improvement.

• Journal of Biosystems Engineering
• /
• v.29 no.4
• /
• pp.317-322
• /
• 2004

This study was conducted to evaluate the feasibility of identifying freshness of beef using a surface acoustic wave (SAW) sensor based electronic nose. The beef was stored at 5$^{\circ}C$ and aroma was measured with the passage of time. Chromatographic analysis of the odor showed that number of volatile components and their amounts were rapidly increased after 19 days of storage. Classifying beefs according to their storage days was possible using principle component analysis (PCA). Classifying beefs processed from four different origins was also possible with PCA analysis of odor. This study shows that electronic nose can be applied to beef freshness evaluation and classification of its origin.

• ETRI Journal
• /
• v.28 no.1
• /
• pp.59-66
• /
• 2006

Learning behaviors of a radial basis function network (RBFN) using a singular value decomposition (SVD) and stochastic gradient (SG) algorithm, together named RBF-SVD-SG, for odor sensing systems are analyzed, and a fast training method is proposed. RBF input data is from a conducting polymer sensor array. It is revealed in this paper that the SG algorithm for the fine-tuning of centers and widths still shows ill-behaving learning results when a sufficiently small convergence coefficient is not used. Since the tuning of centers in RBFN plays a dominant role in the performance of RBFN odor sensing systems, our analysis is focused on the center-gradient variance of the RBFN-SVD-SG algorithm. We found analytically that the steadystate weight fluctuation and large values of a convergence coefficient can lead to an increase in variance of the center-gradient estimate. Based on this analysis, we propose to use the least mean square algorithm instead of SVD in adjusting the weight for stable steady-state weight behavior. Experimental results of the proposed algorithm have shown faster learning speed and better classification performance.

• Science of Emotion and Sensibility
• /
• v.5 no.2
• /
• pp.1-9
• /
• 2002

It is already known that olfactory susceptibility differ with races and sex. Moreover, with aging both detection and identification about olfactory information were impaired. For researches about evaluation of the odor with aging, although the subject used, from infants to elderly, was various, the kinds of odor used were restricted to simple alcohol and acetic acid. Also, the evaluation methods were mainly used olfactory test. From over respects , this research was done as follows. Subjects were 19 to 72 years (n=50) whose sense-of-smell functions are normal. They were taken as stability and closed eye state. The odor stimuli were used 100% natural odor of six kinds of Basil, Lavender, Lemon, Jasmine, Ylangylang oil and Skatole , during 60 seconds using olfactometer. ECG, GSR and subjective evaluation were measured, and examined their relevance. Twenty and 40 ages group evaluated Lemon and 60 ages group did Lavender affirmatively. Correlation was seen among RRI, HR, GSR and subjective evaluation for 40 ages group, and it turns out that it is the group which a mature olfactory function most. These results are fully applied not only to development of the classified cosmetics for the age group but to development of the artificial smell and taste.