PURPOSES : This study aims to develop and evaluate computer vision-based algorithms that classify the road roughness index (IRI) of road specimens with known IRIs. The presented study develops and compares classifier-based and deep learning-based models that can effectively determine pavement roughness grades. METHODS : A set road specimen was developed for various IRIs by generating road profiles with matching standard deviations. In addition, five distinct features from road images, including mean, peak-to-peak, standard variation, and mean absolute deviation, were extracted to develop a classifier-based model. From parametric studies, a support vector machine (SVM) was selected. To further demonstrate that the model is more applicable to real-world problems, with a non-integer road grade, a deep-learning model was developed. The algorithm was proposed by modifying the MNIST database, and the model input parameters were determined to achieve higher precision. RESULTS : The results of the proposed algorithms indicated the potential of using computer vision-based models for classifying road surface roughness. When SVM was adopted, near 100% precision was achieved for the training data, and 98% for the test data. Although the model indicated accurate results, the model was classified based on integer IRIs, which is less practical. Alternatively, a deep-learning model, which can be applied to a non-integer road grade, indicated an accuracy of over 85%. CONCLUSIONS : In this study, both the classifier-based, and deep-learning-based models indicated high precision for estimating road surface roughness grades. However, because the proposed algorithm has only been verified against the road model with fixed integers, optimization and verification of the proposed algorithm need to be performed for a real road condition.

In this study, we analyzed on-site monitoring data for 15 tributaries in Geumho watersheds for 3 years (2011-2013) in order to sort out priorities on water quality characteristics and improvement. As a result of estimating contribution to contamination of the tributary rivers, Dalseocheon showed the highest load densities, despite the smallest watershed area, with 22.7% BOD5, 30.7% CODMn, 31.3% TOC and 47.6% TP. After conducting PCA (principal component analysis) and FA (factor analysis) to analyze water quality characteristics of the tributary rivers, the first factor was classified as CODMn, TOC, EC, TP and BOD5, the second factor as pH, Chl-a and DO, the third factor as water temperature and TN, and the fourth factor as SS and surface flow. In addition, arithmetical sum of each factor’s scores based on grading criteria revealed that Dalseocheon and Namcheon were classified into Group A for their highest scores - 96 and 93, respectively -, and selected as rivers that require water environmental management measures the most. Also, water environmental contamination inspection showed that Palgeocheon had the most number of aquatic factors to be controlled: BOD5, CODMn, SS, TOC, T-P, Chl-a, etc.

This research The main focus of this research is to provide basic data for concrete recreation planning of future site by selecting Gwangmyeong-Siheung housing district, large residential development district focused on rural areas, by evaluation of recreation value and detailed biotope type classification. The main results of analysis are as follows. As a result of basic survey of the research area, total 79 family and 307 taxonomic groups are identified and also naturalization index and urbanization index were estimated 16.6 % and 17.6% respectively. Also, as a result of biotope type classification, it is divide into 12 biotope type gorups including forest biotope type group and its subordinate 53 biotop types. As a result of first value evaluation, there are total 13 biotope types such as vegetation-full artificial rivers in I grade. In addition it is analyzed as 9 types of II grade, 5 types of III grade, 8 types of IV grade, 18 types of V grade. Lastly, as a result of second evauation, it is analyzed that there are 21 special meaningful areas for recreation and natural experience(1a, 1b), and 50 meaningful areas for recreation and natural experience(2a, 2b, 2c). It is regarded that the results of biotope types classification and recreation value from this research play roles of analyzing the Suitable site for recreation area before development in terms of large residential development district, and then these results provide important basic data to secure recreational and natural experience area in development planning.

종전에는 Brassica napus에서 성분이 개량되지 않은 유채의 일반 품종들의 Winter type만을 대상으로 춘파성 정도를 분류하고 추태로서 분류기준을 삼았으나 본 시험에서는 같은 B. napus인 Summer type까지를 포함하고 성분이 개량된 양질유ㆍ양박 품종을 공시하여 임실여부로서 분류기준을 삼는 새로운 분류를 시도하여 춘파성 정도를 조사하였던 바 그 결과를 요약하면 다음과 같다. 1. 현재 목포지장에서 보유하고 있는 양질유ㆍ양박 유채(Brassica napus) 품종 및 육성계통들은 8단계 group으로 춘파성 정도를 분류할 수 있었고 춘파성 정도 제Ⅶ group는 Summer type의 계통들이 이에 속하였으며 이들 계통은 Oro, Midas 등의 Summer type의 품종과 교배하여 선발된 계통들이었다. 2. 춘파 파종기에 따른 성숙기변화는 춘파시기가 늦을수록 성숙기는 지연되는 경향이었고 춘파성 정도가 높음에 따라 생육일수와 적산온도가 줄어드는 경향이었다. 3. 춘파성 정도와 내한성 관계는 춘파성 정도가 높을수록 내한성이 낮았으며 춘파성 정도와 초성간에는 춘파성이 높을수록 초성에서 I형에 가깝고 주경의 신장이 분지보다 빈약한 바 이들 모든 상호관계는 고도의 부상관으로 나타났다. 4. 월동에 안전한 추파재배용계통은 춘파성 정도가 낮은 0, I, II group로서 공시품종중 59 품종이 이에 속하였다.