• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.243-249
• /
• 2012

These days it is becoming more and more common to find electronic medical screening systems installed in Oriental hospitals and clinics. This is a relatively new development for the practice of traditional Oriental medicine. Specifically, Pulse detection machines are being utilized in order to help determine a patient's disease scientifically. However, identifying and diagnosing the specific disease correctly for each patient is still very difficult in Oriental medicine. The intention of this paper is to propose a solution which uses two separate Electronic systems working together to produce a better likelihood of finding the correct diagnosis for each patient. It is proposed that an EMR intelligent electronic chart system be developed and employed, which would utilize both Pulse wave system and a tongue detection system at the same time, in order to solve the problem. Computer simulation results have proven to show that EMR systems used in hospitals and clinics are more efficient and yield a more accurate diagnosis than traditional methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.213-218
• /
• 2011

In this paper, we have developed a tongue diagnosis system using fuzzy rules. A healthy person's tongue is red in color and has less tongue coating. However, when a person suffers from a disease, the color of their tongue changes from red to white, blue, or black. Therefore, it can analyze patient's health if analyze color and coated tongue of tongue. Medical diagnosis system can automatically determines the symptoms of the disease of a patient and their and calculate the optimal acupuncture time on the basis of the patient's physical conditions, illness conditions, and age from any place and at any time. The computer simulation results have shown that electro-acupuncture administered by using the medical diagnosis system developed in this study is more effective than the conventional method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.6 no.2
• /
• pp.149-158
• /
• 2005

In this paper, we have designed and implemented a portable e-tongue (electronic tongue) system using MACS (multi array chemical sensor) and PDA. The system embedded in PDA has merits such as comfortable user interface and data transfer by internet from on-site to remote computer. MACS was made up 7 electrodes (${NH_4}^+$, $Na^+$, $Cl^-$, ${NO_3}^-$, $K^+$, $Ca^{2+}$, $Na^+$, pH) and a reference electrode. For learning the system, we adapted the Levenberg-Marquardt algorithm based on the back-propagation, which could iteratively learned the pre-determined standard patterns, in e-tongue system. Conclusionally, the relationship between the standard patterns and unknown pattern can be easily analyzed. The e-tongue was applied to whiskeys and cognac (one high level whisky, one low level whiskey, two cognac) and 2 sample whiskeys for each standard patterns and unknown patterns. The relationship between the standard patterns and unknown patterns can be easily analyzed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.313-322
• /
• 2020

A large volume of data will improve the robustness of deep learning models and avoid overfitting problems. In automatic tongue segmentation, the availability of annotated tongue images is often limited because of the difficulty of collecting and labeling the tongue image datasets in reality. Data augmentation can expand the training dataset and increase the diversity of training data by using label-preserving transformations without collecting new data. In this paper, augmented tongue image datasets were developed using seven augmentation techniques such as image cropping, rotation, flipping, color transformations. Performance of the data augmentation techniques were studied using state-of-the-art transfer learning models, for instance, InceptionV3, EfficientNet, ResNet, DenseNet and etc. Our results show that geometric transformations can lead to more performance gains than color transformations and the segmentation accuracy can be increased by 5% to 20% compared with no augmentation. Furthermore, a random linear combination of geometric and color transformations augmentation dataset gives the superior segmentation performance than all other datasets and results in a better accuracy of 94.98% with InceptionV3 models.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.921-926
• /
• 2022

Sugar solutions (5%, 10%, 15% and 20%) were tested by seven sensors of Astree E-Tongue for selecting a sensor for sweetness. NMS sensor was chosen as a sensor for sweetness among two sensors (PKS and NMS sensors selected in first stage) by considering precision, linearity and accuracy. Sugar, fructose, glucose and xylitol (5%, 10% and 15%) were tested by E-tongue. The principal component analysis (PCA) result by E-Tongue with seven sensors at 5% concentration level of four sweetners was not satisfactory (Discrimination index was -0.1). On the other hand, the relative NMS sensor response values were derived as 1.08 (fructose), 0.99 (glucose) and 1.00 (xylitol) comparing to sugar. Only the E-Tongue relative glucose response 0.99 was different from 0.5~0.75 of the relative sweetness range reported as the human sensory test results. Considering the excellent precision (%RSD, 1.53~3.64%) of E-Tongue using NMS single sensor for three types of sweeteners compared to sugar in the concentration range of 5% to 15%, replacing sensory test of sweetened beverages by E-Tongue might be possible for new product development and quality control.

• Korean Journal of Food Science and Technology
• /
• v.49 no.4
• /
• pp.349-354
• /
• 2017

The geographical origins of raw ginseng (RG) were discriminated using an electronic tongue. Taste screening, DFA (discriminant function analysis), and CDA (canonical discriminant analysis) were used to statistically analyze the data. The taste profile patterns of umami, bitterness, and sweetness of the Korean RG was different from those of the Chinese RG. The Korean RG was stronger than the Chinese RG regarding the taste of umami. DFA discriminated the geographical origins of 154 samples, with a few overlapping samples, between the Korean and Chinese RG. CDA showed that the accuracy of origin discrimination for the Korean and Chinese RGs were 87.01 and 94.81%, respectively. The final accuracy of origin discrimination was 90.91%. The distance between the centroids of each group was 2.7463. Thus, the electronic tongue analysis can be used to efficiently differentiate the geographical origins of RG.

• Food Science of Animal Resources
• /
• v.39 no.3
• /
• pp.379-387
• /
• 2019

The effects of dry-aging on changes in taste compounds and electronic taste sensing traits of pork were investigated. Ten pork belly and shoulder blade cuts were divided into wet-aging and dry-aging treatments and stored for 21 days at $2^{\circ}C$. The contents of nucleotides and free amino acids, and electronic tongue analysis were investigated at different aging periods (1, 7, 14, and 21 days). The contents of inosine and hypoxanthine of dry-aged pork cuts increased more rapidly, and they were significantly (p<0.05) higher than wet-aged pork cuts. Total free amino acids of dry-aged pork cuts were also significantly (p<0.05) higher than those of wet-aged pork cuts after 21 days of aging. Consequently, umami intensity of dry-aged pork cuts increased more rapidly and the values were significantly (p<0.05) higher than those of wet-aged pork during 21 days of aging. Results suggested that the better palatability of dry-aged pork cuts might be due to higher umami intensity in relation to higher contents of inosine, hypoxanthine, and free amino acids.

• Korean Journal of Food Science and Technology
• /
• v.53 no.5
• /
• pp.585-592
• /
• 2021

This study compared the quality characteristics of commercial Cheddar cheese of dairy types (DT) and vegan types (VT) using electronic sensory evaluation (nose and tongue) and texture profile analysis (TPA). The electronic nose detected acetaldehyde, 2-methylbutanal, and n-butanol in all samples, whereas 2,3-pentanedione and pentan-2-one were detected in DT1, VT1, and VT3. The electronic tongue detected various intensities of six tastes in the two types, regardless of the raw material. Principal component analysis by electronic sensory evaluation revealed the differences between the pattern for VT. The TPA results showed that the textures of DT and VT were not classified according to the raw material. However, the protein content affecting texture was <0.6% for VT compared with that for DT. These results are expected to be useful for establishing quality indicators in developing vegan cheese products with characteristics similar to those of dairy cheese.

• Korean Journal of Food Science and Technology
• /
• v.48 no.5
• /
• pp.430-436
• /
• 2016

Solid phase microextraction and gas chromatography-mass spectrometry (SPME/GC-MS), electronic nose, and electronic tongue were used to characterize the sensory profiles of cider vinegars from Korea (K1-2), China (C1-2), Japan (J1-2), and US (U1-2). SPME-GC/MS detected acetic acid as the common volatile compound in all vinegars, in addition to isovaleric acid, octanoic acid, and phenethyl acetate. Acids and acetic esters were the major components of Korean and US vinegar samples, respectively. Chinese vinegars had high ethyl acetate content, while Japanese samples were characterized by a low content of acetic acid. Principal component analysis (PCA) pattern provided a clear categorical discrimination of Chinese vinegars by E-nose and E-tongue analyses. The instrumental sensory scores and the taste attributes for flavor ($r^2=0.9431$), sourness ($r^2=0.9515$), and sweetness ($r^2=0.8325$) were highly correlated. Therefore, SPME/GC-MS, E-nose, and E-tongue analyses may be useful tools to discriminate the sensory profiles of cider vinegars of different origins.

• Proceedings of the Korean Society of Tobacco Science Conference
• /
• 2004.05a
• /
• pp.33-34
• /
• 2004