• Journal of the Institute of Convergence Signal Processing
• /
• v.25 no.2
• /
• pp.119-126
• /
• 2024

This study aims to evaluate the feasibility of an early warning system for college dropout by machine learning the main patterns that affect college student dropout and to suggest ways to implement a system that can actively prevent it. For this purpose, a performance comparison experiment was conducted using five types of machine learning-based algorithms using data from the Korean Educational Longitudinal Study, 2005, conducted by the Korea Educational Development Institute. As a result of the experiment, the identification accuracy rate of students with the intention to drop out was up to 94.0% when using Random Forest, and the recall rate of students with the intention of dropping out was up to 77.0% when using Logistic Regression. It was measured. Lastly, based on the highest prediction model, we will provide counseling and management to students who are likely to drop out, and in particular, we will apply factors showing high importance by characteristic to the counseling method model. This study seeks to implement a model using IT technology to solve the career problems faced by college students, as dropout causes great costs to universities and individuals.

• Applied Biological Chemistry
• /
• v.14 no.2
• /
• pp.137-148
• /
• 1971

Studies were carried out to investigate the main fermentation microorganisms and their flora changes during Korean native soy-sauce fermentation. Korean native Maeju loaves collected from 5 Do's were separated into surface and inner parts. Four different soy-sauces-the surface part Maeju fermented soy-sauce, the inner part, the surface and inner part combined Maeju fermented soy-sauce, and the semi-Japanese type soy-sauce were fermented and the changes of fermentation microorganism flora and the various chemical components during the period of their fermentations were studied. Besides, 14 home-made soy-sauces collected from 14 different places all over Korea were examined in comparison with the laboratory soy-sauces and to determine the characteristics of Korean native soy-sauce. The results were as follows: 1. The main microorganisms in Korean native soy-sauce fermentation were determined as; Aerobic bacteria: Bacillus subtilis, Bacillus pumilus Lactic acid bacteria: Pediococcus halophilus, Leuconostoc mesenteroides Yeasts: Torulopsis datila, Saccharomyces rouxii 2. Microflora changes during Korean native soy-sauce fermentation were as follows; Aerobic bacteria increased until the 2nd week of fermentation and then gradually decreased. The lactic acid bacteria increased until the 3rd week, after which decreased. When the lactic acid fermentation lowered the pH value to below the 5.4, yeasts were able to grow and participate the fermentation. As the production of organic acids amounted, to a certain height, the growth of all microorganisms lead to the period of decline or death at about the 2nd month of fermentation. After boiling of soy-sauce most microorganisms except a few of Bacillus sp. disappeared. Occosionally yeasts and lactic acid bacteria survived depending upon the composition of soy-sauce. 3. Changes of general chemical components influencing the microflora were investigated for the period of Korean native soy-sauce fermentation. Tetal acidity, salt concentration and total nitrogen were increasing steadily over the entire period of fermentation. pH values were dropping to a certain degree of about 4.5. Salt concentration and pH value seemed to be the important factors influencing the microflora. 4. The microflora were influenced by chemical components of soy-sauce. Aerobic bacteria were able to survive in all soy-sauce as they made spores. Growth of lactic acid bacteria was inhited at 23-26% of salt concentration and pH 4.8. Soy-sauce yeasts started to grow only at pH below 5.4 and seemed to be inhibited at around 26% of salt concentration under pH 4.5-4.7. 5. The open kettle boiling of soy-sauce, the characteristic process of Korean native soy-sauce manufacturing, was effective to sterilize microorganisms, increase the salt concentration, and coagulate proteins. 6. The average viable cell counts of microorganism found in collected samples of home-made Korean native soy-sauces were; Aerobic bacteria: $53{\times}10^2\;cell/ml$ Lactic acid bacteria: 34 cell/ml Yeasts: 14 cell/ml The average values of chemical compositions of samples of home-made Korean native soy-sauce were; Salt concentration: 28.9% pH value: 4.79 Total acidity(lactic acid): 0.91g/100ml Total nitrogen: 1.09g/100ml