• Biotechnology and Bioprocess Engineering:BBE
• /
• v.11 no.5
• /
• pp.432-441
• /
• 2006

2D fluorescence sensors produce a great deal of spectral data during fermentation processes, which can be analyzed using a variety of statistical techniques. Principal component analysis (PCA) and a self-organizing map (SOM) were used to analyze these 2D fluorescence spectra and to extract useful information from them. PCA resulted in scores and loadings that were visualized in the score-loading plots and used to monitor various fermentation processes with recombinant Escherichia coli and Saccharomyces cerevisiae. The SOM was found to be a useful and interpretative method of classifying the entire gamut of 2D fluorescence spectra and of selecting some significant combinations of excitation and emission wavelengths. The results, including the normalized weights and variances, indicated that the SOM network is capable of being used to interpret the fermentation processes monitored by a 2D fluorescence sensor.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.17-24
• /
• 2020

In this paper, we present a movie rating prediction architecture based on a convolutional neural network (CNN). Our prediction architecture extends TextCNN, a popular CNN-based architecture for sentence classification, in three aspects. First, character embeddings are utilized to cover many variants of words since reviews are short and not well-written linguistically. Second, the attention mechanism (i.e., squeeze-and-excitation) is adopted to focus on important features. Third, a scoring function is proposed to convert the output of an activation function to a review score in a certain range (1-10). We evaluated our prediction architecture on a movie review dataset and achieved a low MSE (e.g., 3.3841) compared with an existing method. It showed the superiority of our movie rating prediction architecture.

• International Journal of Contents
• /
• v.11 no.2
• /
• pp.20-30
• /
• 2015

We propose a new method that specifies objective image quality factors by evaluating an image quality measurement model using random images. In other words, No-Reference variables are used to evaluate the quality of an original image without using any reference for comparison. 1000 portrait images were collected from a web gallery with votes constituting over 30 recommendation values. The bottom-up data collecting process was used to calculate the following image quality factors: total range, average, standard deviation, normalized distribution, z-score, preference percentage. A final grade is awarded out of 100 points, and this method ranks and grades the final estimated image quality preference in terms of total image quality factors. The results of the proposed image quality evaluation model consist of the specific dynamic range, skin tone R, G, B, L, A, B, and RSC contrast. We can present the total for the expected preference points as the average of the objective image qualities. Our proposed image quality evaluation model can measure the preferences for an actual image using a statistical analysis. The results indicate that this is a practical image quality measurement model that can extract a subject's preferred image quality.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.55 no.4
• /
• pp.73-82
• /
• 2013

The main objective of this study was to evaluate Representative Concentration Pathways (RCP) scenarios-based flood risk at a Si-Gun level. A bias correction using a quantile mapping method with the Generalized Extreme Value (GEV) distribution was performed to correct future precipitation data provided by the Korea Meteorological Administration (KMA). A series of proxy variables including CN80 (Number of days over 80 mm) and CX3h (Maximum precipitation during 3-hr) etc. were used to carry out flood risk assessment. Indicators were normalized by a Z-score method and weighted by factors estimated by principal component analysis (PCA). Flood risk evaluation was conducted for the four different time periods, i.e. 1990s, 2025s, 2055s, and 2085s, which correspond to 1976~2005, 2011~2040, 2041~2070, and 2071~2100. The average flood risk indices based on RCP4.5 scenario were 0.08, 0.16, 0.22, and 0.13 for the corresponding periods in the order of time, which increased steadily up to 2055s period and decreased. The average indices based on RCP8.5 scenario were 0.08, 0.23, 0.11, and 0.21, which decreased in the 2055s period and then increased again. Considering the average index during entire period of the future, RCP8.5 scenario resulted in greater risk than RCP4.5 scenario.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.32 no.4
• /
• pp.167-175
• /
• 2019

Objetives : The purpose of this study is to report the effect of Oryeong-san on adult whole-body atopic dermatitis. Methods : We treated a 21-year-old male patient who have adult whole-body atopic dermatitis by Korean medicine. This treatment was enforced from 2019.5.25 to 2019.6.29. And we have confirmed the improvement of itching, rashes and oozing. We recorded photos that includes change of symptoms. Results : After the treatments was done, the grade of VAS and SCORAD was decreased. The VAS grade was decreased from grade 8 to grade 2. The SCORAD score was decreased from 72.1 to 52.1. And itching, rashes, oozing were clearly decreased. Conclusions : Oryeong-san has effect on decreasing itching, rashes and oozing. Also, sleeping time reduced due to itchness was normalized. Thus, It is able that Oryeong-san works on skin desease like atopic dermatitis.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.27 no.2
• /
• pp.47-53
• /
• 2019

The development of the aviation industry and the changes in the military operation mission environment are demanding more long - distance operation (long - time flight), and such a flying environment is a risk factor for fatigue - related accidents. For the aviation related organizations such as ICAO and FAA, fatigue risk management system (FRMS) are applied along with flight time restriction regulations to prevent fatigue related accidents. The most important process in FRMS is fatigue risk management. Fatigue risk management systematically manages fatigue through scientific fatigue risk data collection and fatigue risk assessment. The purpose of this study is to applicate the assessment of scientific fatigue risk management to pilots of airplanes engaged in long flight. We reviewed the current state of risk management and FRMS through previous research. We also developed fatigue risk management indicators and examined the validity of internationally recognized fatigue risk data collection methods and fatigue risk assessment tools. There are 134 mission (flight) data used for development. In order to verify the indicators, the fatigue risk score between the items was assigned through pair-wise comparison. In addition, the verify test results were normalized.

• Journal of Sasang Constitutional Medicine
• /
• v.34 no.4
• /
• pp.68-80
• /
• 2022

Objectives This study is to report a significant improvement in a Taeeumin patient with systemic contact dermatitis after eating urushiol chicken by herbal medicine treatment. Methods The patient had complaints of erythema, swelling, pruritus, scaly skin, and facial flushing. We treated the patient with an herbal medicine 'Galgeunhaegi-tang' for three months. We evaluated the treatment outcome of systemic contact dermatitis using the Three Item Severity(TIS) score every visit and facial flushing by Image color summarizer at the first and last visit. Results After the treatment, the severity of the patient's skin complaints lessened from moderate to mild. The Image color summarizer showed a minor decrease in the normalized red color level and a significant increase in the brightness level and facial color percentage. Conclusions The patient diagnosed with systemic contact dermatitis, treated with Galgeunhaegi-tang for three months, showed a significant improvement in skin complaints with brighter and even facial color.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1708-1717
• /
• 2023

The grade analysis of lead-zinc ore is the basis for the optimal development and utilization of deposits. In this study, a method combining Prompt Gamma Neutron Activation Analysis (PGNAA) technology and machine learning is proposed for lead-zinc mine borehole logging, which can identify lead-zinc ores of different grades and gangue in the formation, providing real-time grade information qualitatively and semi-quantitatively. Firstly, Monte Carlo simulation is used to obtain a gamma-ray spectrum data set for training and testing machine learning classification algorithms. These spectra are broadened, normalized and separated into inelastic scattering and capture spectra, and then used to fit different classifier models. When the comprehensive grade boundary of high- and low-grade ores is set to 5%, the evaluation metrics calculated by the 5-fold cross-validation show that the SVM (Support Vector Machine), KNN (K-Nearest Neighbor), GNB (Gaussian Naive Bayes) and RF (Random Forest) models can effectively distinguish lead-zinc ore from gangue. At the same time, the GNB model has achieved the optimal accuracy of 91.45% when identifying high- and low-grade ores, and the F₁ score for both types of ores is greater than 0.9.

• Annals of Hepato-Biliary-Pancreatic Surgery
• /
• v.27 no.1
• /
• pp.63-69
• /
• 2023

Methods: Patients who underwent cholecystectomy were classified into two groups according to their GBWT status (GBWT+ vs. GBWT-). Results: Among 1,211 patients who underwent cholecystectomy, GBWT+ was seen in 177 (14.6%). The GBWT+ group was significantly older with more males, higher ASA score, higher alkaline phosphatase level, higher international normalized ratio, and lower albumin level than the GBWT- group. On ultrasound, GBWT+ patients had larger stone size, more pericholecystic fluid, more common bile duct stone, and more biliary pancreatitis. Compared with the GBWT- group, the GBWT+ group had more urgent surgeries (12.4% vs. 3.2%, p = 0.001), higher conversion rate (4.5% vs. 0.3%, p = 0.001), prolonged operative time (67 ± 38 vs. 54 ± 29 min; p = 0.001), more bleeding (3.4% vs. 0.5%, p = 0.002), and more need of drain (21.5% vs. 10.5%, p = 0.001). By multivariate analysis, factors associated with increased length of hospital stay were GBWT+ (HR: 1.97, 95% CI: 1.19-3.25, p = 0.008), urgent surgery (HR: 10.2, 95% CI: 4.07-25.92, p = 0.001), prolonged surgery (HR: 1.01, 95% CI: 1.0-1.02, p = 0.001), and postoperative drain (HR: 11.3, 95% CI: 6.40-20.0, p = 0.001). Conclusions: Variables such as GBWT ≥ 5 mm, urgent prolonged operation, and postoperative drains are independent predictors of extended hospital stay. GBWT+ patients are twice likely to stay in hospital for more than 72 hours and more prone to develop complications than GBWT- patients.

• Journal of Veterinary Science
• /
• v.25 no.2
• /
• pp.27.1-27.12
• /
• 2024

Background: A urethral obstruction (UO) is an emergency commonly observed in male cats, which can result in significant clinical and laboratory alterations, leading to complications and death. Objectives: This study aimed to correlate symmetric dimethylarginine (SDMA) with the urea, creatinine, potassium, and bicarbonate levels in cats with UO. In addition, the correlation between clinical score and time of obstruction was evaluated. Methods: Thirty male cats were selected and allocated into a control group (CG, n = 13) and an obstruction group (OG, n = 17). The laboratory analyses were conducted before treatment (M0) and at different times after treatment (12 h [M12], 24 h [M24], and 48 h [M48]). Correlations were established between SDMA and creatinine, urea, bicarbonate, potassium, time of obstruction, and the clinical score. Results: A strong correlation (r > 0.6) was observed between SDMA and creatinine, urea, and potassium in the OG. Furthermore, there was substantial agreement (kappa value) between SDMA and creatinine at M24. A higher clinical score was associated with a longer time of obstruction. In the OG, at M48, the SDMA and creatinine levels were 50% and 41.2% higher, respectively. Conclusions: A correlation was observed between SDMA and creatinine in obstructed cats, and significant agreement between these values was observed 24 h after the unblocking treatment. A correlation among SDMA, urea, and potassium was observed. Approximately 9% more cats continued to have elevated SDMA levels after 48 h of treatment compared to creatinine. This suggests a slightly lower sensitivity of the latter biomarker but does not exclude the possibility of congruent and normalized values after a longer evaluation period.