• Proceedings of the KAIS Fall Conference
• /
• 2010.11b
• /
• pp.1014-1016
• /
• 2010

우리나라 쌀 생산량은 해마다 증가되고 있으나, 1인당 쌀 소비량은 급격히 감소되고 있는 수급 불균형을 이루고 있다. 특히 충청남도는 최근 6년간 전국 쌀 생산량 1위를 차지해 오고 있어서 쌀 소비의 확대방안이 더욱 절실히 요구되고 있는 지역적 특성을 지니고 있다. 취반용 쌀 소비량 확대만으로는 쌀 소비량 증대에 한계점이 있으므로, 소비자의 요구에 맞는 고 기능성, 간편식으로 다양한 기호성을 지닌 쌀 가공식품 형태의 개발이 필요하게 되었다. 이러한 요구에 적합한 제품개발로 쌀을 이용한 쌀국수를 개발하고자 하였으며, 이러한 쌀국수 제품개발은 쌀을 이용한 제품개발은 또다른 시도가 되어 쌀 소비촉진이 향상될 것으로 기대된다. 기능성 쌀국수 개발을 위하여 천연물 중 연잎 소재를 첨가하였다. 연잎은 차와 사찰음식을 대표하는 소재중 하나이다. 연잎에는 비타민 C와 섬유소가 매우 풍부하다. 이러한 성분은 미용식품으로써의 응용이 가능하며, 식이 섬유소는 배변작용에도 도움이 될 수 있다. 또한 항산화제인 quercetin이 다량 함유되어 있다. 이 quercetin은 플라보이드 배당체이며, 우리 몸의 세포의 노화를 유발하는 유해 활성 산소를 제거하는 기능을 가지고 있다. 따라서 이러한 유해 활성산소를 억제하는 것이 항산화 활성이 높은 연잎을 이용하여 고 기능성 쌀가공품 제품 개발이 가능할 것으로 기대한다. 쌀가루 50%를 기준으로하여 연잎가루는 3% 첨가하였으며, 전분의 종류를 달리하여 최종 제품을 개발한 결과, texture analyser로 물성을 측정한 결과 타피오카 전분과 쌀가루 혼한 쌀국수의 물성이 좋은 결과를 나타내었다. 관능검사 결과도 타피오카 전분과 쌀가루 혼합 쌀국수가 소비자들의 기호도가 높은 선호도를 나타내었고, 감자전분과 밀가루는 다소 낮은 선호도를 나타내었다. 본 연구를 기초로 하여 쌀제품 개발시 쌀의 가공적성 및 기능성 소재의 첨가 비율 확립하고, 연잎과 같은 쌀국수에 첨가 가능한 다양한 기능성 소재 발굴 및 첨가 가능성을 제시하고자 하였다.

• Journal of Korean Society of Transportation
• /
• v.22 no.7 s.78
• /
• pp.147-154
• /
• 2004

The purpose of this paper is to improve the existing phase split algorithm considering the minimum green time in COSMOS. In the case of a signalized intersection where two wide and narrow streets intersect each other, the time required for the pedestrian crossing is frequently longer than the time alloted to the through traffic on a minor street. In order to meet the minimum green time requirement for the pedestrian less time in alloted automatically to the left-turn traffic, creating heavy congestion on the left-turn approach. To solve this problem, this study suggests a new algorithm which shares the barrier using minimum green time and shares the burden with signal phases alloted to the crossing street traffic on the basis of the equal ratio of the degree of saturation, while maintaining the minimum green time requirement. The new algorithm was compared with the existing algorithm by using a microscopic simulation model for COSMOS evaluation developed at Ajou University. The simulation results show that the new algorithm produces better performance than the existing one.

• Journal of Korean Society of Transportation
• /
• v.33 no.1
• /
• pp.1-13
• /
• 2015

This study aims to develop a mainline metering strategy considering queue imbalance among lanes that can reduce congestion at a toll plaza section by managing queue caused by mainline metering. The suggested strategy considers simultaneously optimizing the number of cars in merging area and managing queue by lane. This study analyzes the effectiveness of the strategy with respect to the average travel time and the occurrence rate of spillback using the PARAMICS. The results show that the suggested strategy has an effect on reducing congestion and improving operation efficiency at toll plaza. In particular, the congestion become more intensified when the length of waiting space is shorter; however, this study shows that the suggested strategy can relieve the congestion in that condition.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.8 no.6
• /
• pp.469-477
• /
• 2003

This paper proposes a Carrier-Rotation (CR) PWM technique that is a new solution for the voltage unbalancing problem of flying capacitors in the Flying Capacitor Multi-level Inverter (FCMI). The proposed technique equalizes the utilization of phase leg voltage redundancies corresponding to the charging and the discharging state of individual flying capacitors during each switching period of all the switches. Therefore, the charging and the discharging quantity of flying capacitors are equal, which makes the average variation of flying capacitor voltages become zero and keeps their voltage stable during minimum specified period. It also has the reduced harmonic contents of output voltage and the same switch utilization since all the carrier signals are in phase and the switching frequency of each switch is identical. The proposed technique is analyzed precisely in flying capacitor 3-level inverter and then it has expanded to the FCMI (N-level, N>3). Experimental results on the laboratory prototype flying capacitor 3-level inverter confirm the validity of the proposed technique.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.140-140
• /
• 2018

다수의 자연 하천은 사행의 형태를 가지고 있으며 자연 상태에서의 직선 하천 형태는 비율이 20% 이하이다. 이러한 하천의 사행 형상으로 인하여 편수위 발달, 횡방향 압력의 불균형, 그리고 수심차에 의한 원심력이 발생하여 이차류 흐름이 발생된다. 정확한 이차류 구현을 위해서는 3차원 모형을 사용하는 것이 바람직하나, 3차원 모형의 격자 구성과 사용에서는 상당한 시간 및 노력이 요구되기 때문에 수심적분 2차원 모형을 사용하면서도 이차류의 영향을 구현하기 위한 연구들이 이루어졌다. 본 연구에서는 이러한 이차류의 영향을 2차원 모형으로 구현하고자 하였으며 이를 위해 이차류 연직 분포에 대한 기존 연구를 검토하여 새로운 이차류 공식을 개발하였다. 그리고 한국건설기술연구원 하천실험센터의 실규모 실험을 통해서 이차류 공식에 사용되는 계수를 보정하였다. 이처럼 개발된 식은 이차원 수리해석 모형인 HDM-2D에 적용되었다. HDM-2D는 수심 적분된 2차원 운동량 방정식을 지배방정식으로 사용하는 수리해석모형으로서, 이차류의 영향을 반영하기 위하여 개발한 황방향 유속의 연직분포식을 분산 응력항에 대입하여 이차류에 의한 전단 효과를 구현하였다. HDM-2D 흐름 모의 수행 결과와 하천실험센터 실험결과와 비교하여 이차류 효과가 주 흐름 유속의 분포에 미치는 영향을 확인하였다. 분석 결과, 모의 결과는 실험에서 발생하는 유속의 주 흐름 분포가 바깥쪽으로 편중되는 현상을 적절하게 재현함을 알 수 있었다. 모의 결과를 통해 HDM-2D 모형이 이러한 이차류 영향을 구현할 수 있음을 확인하였으며, 사행수로에서 주 흐름분포의 재분배는 하천 환경에서 유사 이동 및 오염물 이동에 큰 영향을 미칠 것으로 판단된다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.173-182
• /
• 2022

In this paper, we propose a machine learning model that can prevent fraudulent transactions in advance and interpret them using the XAI approach. For the experiment, we collected a real data set of 12,258 mobile phone sales posts from Joonggonara, a major domestic online C2C resale trading platform. Characteristics of the text corresponding to the post body were extracted using Doc2vec, dimensionality was reduced through PCA, and various derived variables were created based on previous research. To mitigate the data imbalance problem in the preprocessing stage, a complex sampling method that combines oversampling and undersampling was applied. Then, various machine learning models were built to detect fraudulent postings. As a result of the analysis, LightGBM showed the best performance compared to other machine learning models. And as a result of SHAP, if the price is unreasonably low compared to the market price and if there is no indication of the transaction area, there was a high probability that it was a fraudulent post. Also, high price, no safe transaction, the more the courier transaction, and the higher the ratio of 0 in the price also led to fraud.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.75-86
• /
• 2022

This study aims to solve the problem of class imbalance in numerical data by using a deep learning-based Variational AutoEncoder and to improve the performance of the learning model by augmenting the learning data. We propose 'D-VAE' to artificially increase the number of records for a given table data. The main features of the proposed technique go through discretization and feature selection in the preprocessing process to optimize the data. In the discretization process, K-means are applied and grouped, and then converted into one-hot vectors by one-hot encoding technique. Subsequently, for memory efficiency, sample data are generated with Variational AutoEncoder using only features that help predict with RFECV among feature selection techniques. To verify the performance of the proposed model, we demonstrate its validity by conducting experiments by data augmentation ratio.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.641-648
• /
• 2022

This paper is a study to find out the factors affecting the defects that occur during the use of Electron Beam Melting (EBM), one of the 3D printer output methods, through data analysis. By referring to factors identified as major causes of defects in previous studies, log files occurring between processes were analyzed and related variables were extracted. In addition, focusing on the fact that the data is time series data, the concept of a window was introduced to compose variables including data from all three layers. The dependent variable is a binary classification problem with the presence or absence of defects, and due to the problem that the proportion of defect layers is low (about 4%), balanced training data were created through the SMOTE technique. For the analysis, I use XGBoost using Gridsearch CV, and evaluate the classification performance based on the confusion matrix. I conclude results of the stuy by analyzing the importance of variables through SHAP values.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.365-370
• /
• 2023

This paper aims to compare the performance of speech data classification into two groups, adult and elderly, based on the acoustic and linguistic characteristics that change due to aging, such as changes in respiratory patterns, phonation, pitch, frequency, and language expression ability. For acoustic features we used attributes related to the frequency, amplitude, and spectrum of speech voices. As for linguistic features, we extracted hidden state vector representations containing contextual information from the transcription of speech utterances using KoBERT, a Korean pre-trained language model that has shown excellent performance in natural language processing tasks. The classification performance of each model trained based on acoustic and linguistic features was evaluated, and the F1 scores of each model for the two classes, adult and elderly, were examined after address the class imbalance problem by down-sampling. The experimental results showed that using linguistic features provided better performance for classifying adult and elderly than using acoustic features, and even when the class proportions were equal, the classification performance for adult was higher than that for elderly.

• Journal of the Korean Regional Science Association
• /
• v.39 no.2
• /
• pp.63-76
• /
• 2023

Recently, due to the location of residential complexes in commercial areas of large cities, the urban function is shifting from commercial to residential.In order to improve the use volume system in the commercial area of Daejeon Metropolitan City, the system of special and metropolitan cities was compared and analyzed, and problems were derived by analyzing 8 cases. First, use classification of mixed-residential buildings, Second, unbalance of urban planning for functional loss of commercial area, Thrid, damage on urban environment due to difference of development density. Accordingly, improvement measures include First, securing the ratio of residential function and mixed use at least 10%, Second, securing urban competitiveness by inducing facilities that combine various uses and functions. The overall floor area ratio of housing is applied, Third, the development density is presented through the establishment of the district unit plan and consultation.