• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.41-46
• /
• 2023

Human urine is a process of excreting waste products in the blood, and it is easy to collect and contains various substances. Urinalysis is used to check for diseases, health conditions, and urinary tract infections. There are three methods of urinalysis: physical property test, chemical test, and microscopic test, and chemical test results can be easily confirmed using urine test strips. A variety of items can be tested on the urine test strip, through which various diseases can be identified. Recently, with the spread of smart phones, research on reading urine test strips using smart phones is being conducted. There is a method of detecting and reading the color change of a urine test strip using a smartphone. This method uses the RGB values and the color difference formula to discriminate. However, there is a problem in that accuracy is lowered due to various environmental factors. This paper applies a deep learning model to solve this problem. In particular, color discrimination of a urine test strip is improved in a smartphone using a lightweight CNN (Convolutional Neural Networks) model. CNN is a useful model for image recognition and pattern finding, and a lightweight version is also available. Through this, it is possible to operate a deep learning model on a smartphone and extract accurate urine test results. Urine test strips were taken in various environments to prepare deep learning model training images, and a urine test service application was designed using MobileNet V3.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.1
• /
• pp.87-96
• /
• 2009

In conventional method, flight model is discribed to differential equation by linealization of nonlinear object motion equation. As state equation from differential equation of moving object, the controller is designed by transfer functions of each module under discrimination of stability criteria. But this conventional method is designed under limitation of nonlinearity from object's shape and speed. In other word, The greater part of guidance/navigation system was satisfied with the result of good performance for normal figure of flight object, not sudden changed flight condition, not high speed. But it is not able to give full play to its ability on flight object which has abnormal figure, sudden changeable motion, high speed. Therefore, in this paper was presented performance analysis of load control model for navigation/guidance system on flying object being uncertainty, non-linear like abnormal figure, sudden changeable motion, high speed and is presented method of trajectory control(controllability) ahead of controllability and stability to achieve flight mission. In other word, this paper shows the first step of Min-design method and flight control model.

• Korea Journal of Hospital Management
• /
• v.12 no.3
• /
• pp.47-67
• /
• 2007

This paper aims at suggesting several ways lo change financial vulnerability and to improve managerial capability of local public hospitals (LPHs) in Korea through the identification of factors affecting profitability. Several findings of the research are as follows: To begin with, LPHs exhibited a statistically significant difference in their profitability from one another, according to tile analyses of their profitable margins from tile general characteristics. It depends on the number of hospitals in the area, the population of the hospital-built area, the number of competing hospitals, the number of staff per 100 beds, the opening of special clinic, the educational function, and the capacity of rooms. However, there was no variable in the managerial characteristics, presenting a significant difference, in contrast with hospitals which have been managed by private companies and made a great amount of profits. Second, according to the analyses of profit differences in behavioral effort-characteristics, a statistically significant difference was revealed upon the basis of the efforts to improve the clinic service, invite special patients, and shorten the period of being hospitalized. Third, the result of analyses about the difference of profitability from medical care and finance is statistically significant in the rate of labor cost, the rate of management cost, bed-occupancy rate, and the period of being hospitalized. Fourth, according to the analyses of the factors influencing the net profit ratio of the entire capital, Adjusted explanatory power(Adjusted $R^2$) was shown up to 65.2%, which is high. To compare the adjusted explanatory power stage by stage, the first stage model applying only two variables such as structural and strategic characteristics exhibited 23.8%, and the second stage model adding financial characteristics showed 51.5%. The explanatory power was much improved up to 65.2% when the third stage model incorporated the outcome of medical care performance. When the return on investment(ROI) was examined by using the multi-variate linear regression analysis at the final model of third stage, it was found that ROI had a positive relationship with the increase rate of patients, labor costs per doctor, and medical care rate of socially protected inpatients. However, it revealed that ROI had a negative relationship with the ratio of labor costs, the number of patients per managerial staff, and occupancy rate of rooms, respectively. The research suggests that in order for LPHs to increase profitability, LPH, should make efforts not only to attract patients to the hospitals without any discrimination of the patients depending on their financial status, but also to develop efficient management methods to reduce labor costs.

• Journal of Sasang Constitutional Medicine
• /
• v.7 no.1
• /
• pp.69-101
• /
• 1995

Using Bi-Digital O-Ring Test which was developed by Ohmura Toshiaki, constitution classification by the vegetables' was measured by various muscle power measurement meters and the results are as follow : 1. Pinch guage (Model : pc5030HPG, Japan) is the guage to measure finger power between the thumb and second finger, Grip Strength Dynamometer (Model : T.K.K. 5101, Japan) is to measure the hand power (hand dynamometer), Back Strength dynamometer (Model : T.K.K. 5102, Japan)is to measue back muscle strength, Vertical Jump Meter (Model : T.K.K. 5106, Japan) is to measure the height of jump. The above guages were used and its result found that the radish, potato, carrot and cucumber can influence to the muscle strength was not true. 2. When the physical constitution is distinguished vy the O-Ring Test method, Taeyangin's rate appeared as average 21% although it was insistedthat there will be only 0.03-0.1%. This means that the influence power of vegetable doest not appear according to the physical constitution but it appears accidently according to the examinee's emotion about the material such as vegetable etc. as favor or unfavor. 3. It was found that the result of O-Ring Test is the same at any time and at any place was not true. there is no reemergence character. 4. The import of O-Ring Test method to the physical discriminatio disregarded that the mental facor influences absolutely to the physical heath in the ideological physical constitution medicla science. 5. 'O-Ring Test method is a objective judgement method'. is wrong judgement. As you see on the above result, Bi-Digital O-Ring Test set the changeable voluntary muscle as the standard of the judgement, that was first mistake logically, second in spite of leass influence of mental influence by the examiner and examinee than the vegetable discrimination influence, the test disregarded the influence. Thire, only grasp of some material on hand can influence to the voluntary was a wrong theory disregarding the physiology. Finally the misunderstaning his subjective view as an objective view in spite of examiner and examinee's strong influence. Therefore such kind of physical descrimination method must be sublated.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.208-213
• /
• 2021

There is a lack of studies comparing the internal quality of fruit with its external quality. However, issues of internal quality of fruit such as internal browning are important. We propose a method of classifying normal apples and internally browned apples using a near-infrared (NIR) non-destructive system. Specifically, we found the optimal wavelength and characteristics of the spectra for determining the internal browning of Fuji apples. The NIR spectra of apples were obtained in the wavelength range of 470-1150 nm. A group of normal apples and a group of internally browned apples were identified using principal component analysis (PCA), and a partial least squares regression (PLSR) analysis was performed to develop and evaluate the discriminant model. The PCA analysis revealed a clear difference between the normal and internally browned apples. From the PLSR, the correlation coefficient of the predictive model without pretreatment was determined to be 0.902 with an RMSE value of 0.157. The correlation coefficient of the predictive model with pretreatment was 0.906 with an RMSE value of 0.154. The results show that this model is suitable for classifying normal and internally browned apples and that it can be applied for the sorting and evaluation of agricultural products for internal and external defects.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.8
• /
• pp.23-30
• /
• 2021

In this study, we present a comparative analysis of major autoencoder(AE)-based anomaly detection methods for quality determination in the manufacturing process and a new anomaly discrimination criterion. Due to the characteristics of manufacturing site, anomalous instances are few and their types greatly vary. These properties degrade the performance of an AI-based anomaly detection model using the dataset for both normal and anomalous cases, and incur a lot of time and costs in obtaining additional data for performance improvement. To solve this problem, the studies on AE-based models such as AE and VAE are underway, which perform anomaly detection using only normal data. In this work, based on Convolutional AE, VAE, and Dilated VAE models, statistics on residual images, MSE, and information entropy were selected as outlier discriminant criteria to compare and analyze the performance of each model. In particular, the range value applied to the Convolutional AE model showed the best performance with AUC PRC 0.9570, F1 Score 0.8812 and AUC ROC 0.9548, accuracy 87.60%. This shows a performance improvement of an accuracy about 20%P(Percentage Point) compared to MSE, which was frequently used as a standard for determining outliers, and confirmed that model performance can be improved according to the criteria for determining outliers.

• Analytical Science and Technology
• /
• v.29 no.1
• /
• pp.1-9
• /
• 2016

It is believed that traditional Korean medicines can be managed more scientifically through the development of logical criteria to verify their region of cultivation, and that this could contribute to the advancement of the traditional herbal medicine industry. This study attempted to determine such criteria for Sansuyu. The volatile compounds were obtained from 20 samples of domestic Corni fructus (Sansuyu) and 45 samples of Chinese Sansuyu by steam distillation. The metabolites were identified in the NIST Mass Spectral Library via the obtained gas chromatography/mass spectrometer (GC/MS) data of 53 training samples. Data binning at 0.2 min intervals was performed to normalize the number of variables used in the statistical analysis. Multivariate statistical analyses, such as principle component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), and orthogonal partial least squares-discriminant analysis (OPLS-DA) were performed using the SIMCA-P software package. Significant variables with a variable importance in the projection (VIP) score higher than 1.0 were obtained from OPLS-DA, and variables that resulted in a p-value of less than 0.05 through one-way ANOVA were selected to verify the marker compounds. Finally, among the 11 variables extracted, 1-ethylbutyl-hydroperoxide (9.089 min), nonadecane (20.170 min), butylated hydroxytoluene (25.319 min), 5β,7βH,10α-eudesm-11-en-1α-ol (25.921 min), 7,9-bis(2-methyl-2-propanyl)-1-oxaspiro[4.5]deca-6,9-diene-2,8-dione (34.257 min), and 2-decyldodecyl-benzene (54.717 min) were selected as markers to indicate the origin of Sansuyu. The statistical model developed was suitable for the determination of the geographical origin of Sansuyu. The cultivation areas of four Korean and eight Chinese Sansuyu samples were predicted via the established OPLS-DA model, and it was confirmed that 11 of the 12 samples were accurately classified.

• Archives of design research
• /
• v.18 no.4 s.62
• /
• pp.15-24
• /
• 2005

The demand against the house space of the style which is various increases with to join in and the importance which the color does hold gradually is magnified and color meaning from house space is embossed, diversification the necessity of the color plan which hits to the social change which is turning out is recognized. From the research which it sees the importance recognition against the color plan which is must become accomplished variousfrom house space. It analyzes the color tendency of the apartment model house and it presents it does the guide line of house space color design $2001{\sim}2004$ It was sold in lots from the year Busan area in center, the acreage and the space(the wall/the ceiling, the furniture type, the window and door type and the floor type) it used 'The hue&tone 120 color system' and it grasped to the sincere analysis method and the color use present condition which leads a frequency analysis. When it sees the color analysis result of the research which it sees space especially the color plan period for a discrimination compared to the organic enemy the unity which considers a relationship the crisis which will the plan is become accomplished with the direction for, Magnification feeling or high class of the area it is that it shows the color tendency which is discriminated it was with equilibrium general classification.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.6
• /
• pp.731-742
• /
• 2010

Modeling of rubber for design or analysis often requires confusing or complex work because there are a large number of constitutive models to be considered. Some models have few material constants, while others have many. Researchers have to prepare and fit extensive experimental data with caution and discretion. In this paper, we first compared some typical rubber models in which deformation was carried out by stretching up to around eight times the original size. We conclude that continuum-based models and chain molecular models can be used in the study of the small deformation in most engineering applications, but chain molecular models are preferred in the study of the large deformations in most biomaterial applications. As discrimination problems, Treloar's patch and cylindrical balloon stick are tested theoretically and numerically for studying bifurcation. In the case of Treloar's patch, by using the Kearsley's equation, we show that bifurcation exists for continuum-based models but not for chain molecular models. Both models show bifurcation in the cylindrical balloon stick. Therefore, in the analysis of the bifurcation of rubber showed that its existence also depends on the constitutive model selected.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.1 s.307
• /
• pp.17-26
• /
• 2006

This paper proposes a novel hidden Markov model (HMM)-based gesture recognition method and applies it to an HCI to control a computer game. The novelty of the proposed method is two-fold: 1) the proposed method uses a continuous streaming of human motion as the input to the HMM instead of isolated data sequences or pre-segmented sequences of data and 2) the gesture segmentation and recognition are performed simultaneously. The proposed method consists of a single HMM composed of thirteen gesture-specific HMMs that independently recognize certain gestures. It takes a continuous stream of pose symbols as an input, where a pose is composed of coordinates that indicate the face, left hand, and right hand. Whenever a new input Pose arrives, the HMM continuously updates its state probabilities, then recognizes a gesture if the probability of a distinctive state exceeds a predefined threshold. To assess the validity of the proposed method, it was applied to a real game, Quake II, and the results demonstrated that the proposed HMM could provide very useful information to enhance the discrimination between different classes and reduce the computational cost.