• Journal of the Korean Institute of Rural Architecture
• /
• v.21 no.2
• /
• pp.27-34
• /
• 2019

This study explores the emergence of a modern form of Cheongju-eup townscape in the late 1930s by re-examining the 1960s restoration model of Seongan-dong and Jungang-dong in Cheongju, one of the historic cities in South Korea. According to the acquired data from the restoration model, it is found that the construction of a new urban area during the late 1930 was resulted from the following events: the development of a railroad station located outside of the north gate of Cheongju-eup since 1921, the completion of Musimcheon embankment outside the south gate in 1932, and the construction of Chungcheongbuk provincial office outside the eastern gate in 1937. In this period of development, which the author named 'Cheongju-eup period', the streets in the old castle, consisting only of two-story financial buildings, had been expanded from the existing area at the Seongan-gil intersection to the outside the east gate of Cheongju-eup. In addition, public government buildings, which were mainly located in both Seongan-gil and Yulgok-ro in the east-west direction, were newly constructed during the late 1930s in Seokgyo-dong, a new area in which a large number of commercial buildings including department stores, clothing stores, shoes shops, and watch stores were also built along the streets. Moreover, the modern form of Cheongju-eup was to be formed by several construction projects in the area of Jungang-ro in the late 1930s. Until the 1920s, the townscape outside the northern gate of Cheongju-eup, were composed of primary, agricultural, and female schools built on a largest site of Gyoseo-ro and Daeseong-ro as well as a transportation warehouse and a railway office near the Cheongju station. Then, entering the 1930s, new school buildings and domestic industrial shops and factories were built around the area of Jungang-ro ranging from the railway outside the northern gate to Bangadari. As a result, the expansion of townscape with newly constructed buildings in the late 1930s marked the emergence of a modern form of Cheongju-eup.

• Journal of Animal Science and Technology
• /
• v.63 no.6
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• Smart Media Journal
• /
• v.11 no.7
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• Korean Journal of Agricultural Science
• /
• v.50 no.3
• /
• pp.357-364
• /
• 2023

In this study, we propose a ripe tomato bunch localization method based on convolutional neural networks, to be applied in robotic harvesting systems. Tomato images were obtained from a smart greenhouse at the Rural Development Administration (RDA). The sample images for training were extracted based on tomato maturity and resized to 128 × 128 pixels for use in the classification model. The model was constructed based on four-layer convolutional neural networks, and the classes were determined based on stage of maturity, using a Softmax classifier. The localization of the ripe tomato bunch region was indicated on a class activation map. The class activation map could show the approximate location of the tomato bunch but tends to present a local part or a large part of the ripe tomato bunch region, which could lead to poor performance. Therefore, we suggest a recursive method to improve the performance of the model. The classification results indicated that the accuracy, precision, recall, and F1-score were 0.98, 0.87, 0.98, and 0.92, respectively. The localization performance was 0.52, estimated by the Intersection over Union (IoU), and through input recursion, the IoU was improved by 13%. Based on the results, the proposed localization of the ripe tomato bunch area can be incorporated in robotic harvesting systems to establish the optimal harvesting paths.

• Journal of Korean Society of Transportation
• /
• v.33 no.6
• /
• pp.554-563
• /
• 2015

This study dealt with developing an accident model for rural signalized intersections with random parameter negative binomial method. The limitation of previous count models(especially, Poisson/Negative Binomial model) is not to explain the integrated variations in terms of time and the distinctive characters a specific point/segment has. This drawback of the traditional count models results in the underestimation of the standard error(t-value inflation) of the derived coefficient and finally affects the low-reliability of the whole model. To solve this problem, this study improves the limitation of traditional count models by suggesting the use of random parameter which takes account of heterogeneity of each point/segment. Through the analyses, it was found that the increase of traffic flow and pedestrian facilities on minor streets had positive effects on the increase of traffic accidents. Left turning lanes and median on major streets reduced the number of accidents. The analysis results show that the random parameter modeling is an effective method for investigating the influence on traffic accident from road geometries. However, this study could not analyze the effects of sequential changes of driving conditions including geometries and safety facilities.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.1 no.1
• /
• pp.58-69
• /
• 2002

Most of the traffic accidents are a rear-end collision and a clash generated in the signalized intersection on the local roads. So, it is demanded that the high-quality of signal control and dilemma zone control. According to the cases generated by foreign countries, we established the strategies which are composed of Volume-Density Control, strategy of the dilemma zone control using R-detector (microwave detector) In Japan and EC-DC Control. MOEs(Measure of effectiveness) are car numbers in the dilemma zone , max-out probability in the safe side and the average stopping delay in the progress side. We choose a signalized intersection in rural highway to analyze the effect of the strategies and practiced an on-the-spot survey. The result of the survey is applied to the basic data in the simulator. Consequently, strategy of the dilemma zone control using R-detector(microwave detector) in Japan is the best effective in the safe side and EC-DC control is the best in the progress side. Based on the result, we developed the effective strategy of the signal control . This strategy is composed of the strategy of Japan and the detector on the stopping line used in the EC-DC control. On the result of the analysis, new strategy is the best effective in two sides.

• Journal of Korean Society of Transportation
• /
• v.20 no.1
• /
• pp.131-139
• /
• 2002

This study introduces a developed artificial neural networks(ANN) model as a more efficient and reliable prediction model in operating speed Prediction with the 85th percentile horizontal curve of two-way rural highway in the aspect of evaluating highway design consistency. On the assumption that the speed is decided by highway geometry features, total 30 survey sites were selected. Data include currie radius, curve length, intersection angle, sight distance, lane width, and lane of those sites and were used as input layer data of the ANN. The optimized model structure was drawn by number of unit of hidden layer, learning coefficient, momentum coefficient, and change in learning frequency in multi-layer a ANN model. To verify learning Performance of ANN, 30 survey sites were selected while data in obtained from the 20 cites were used as learning data and those from the remaining 10 sites were used as predictive data. As a result of statistical verification, the model D of 4 types of ANN was evaluated as the most similar model to the actual operating speed value: R2 was 85% and %RMSE was 0.0204.

• The Korean Journal of Community Living Science
• /
• v.17 no.4
• /
• pp.97-112
• /
• 2006

For 387 married women in their 20s to 50s, we inquired about the differences in whether they intended on moving into a welfare facility, depending on their views on supporting the elderly and the burden of supporting elderly parents, and tried to find out factors that would affect their decision to move into a welfare facility. With those objectives in mind, we conducted a survey targeting married women in their 20s to 50s who live in Seoul, Daejun or a city or county in Choongnam-do, and carried out frequency analysis, intersection analysis, one-way ANOVA and judge analysis. Our findings from those analyses are summarized as follows. First, when considering married women's characteristics and examining their intention of moving into a welfare facility for the elderly, there was a meaningful difference in their intention depending on age, academic background, occupation, and area of residence. Second, our analysis of the differences in their intention of moving in, based on married women's view on supporting the elderly and the burden of supporting elderly parents, indicates that due to these responsibilities, the greatest number of married women expressed their intention of moving in if a convenient facility for the elderly and service were provided. However, the analysis for the intention of moving in depending on savings for old age, did not exhibit any meaningful difference. Third, from the examination of determining factors for married women's intention of moving into a welfare facility for the elderly, based on age, academic background, occupation, residential area, responsibility for supporting an elderly family member and savings for old age, it was found that the burden of support was the only meaningful effective factor.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.2
• /
• pp.100-109
• /
• 2008

Traffic accidents at night occur more than any other time because of improper road light facility and delineators. Therefore, cost-effective criteria of installing delineators are needed instead of expensive road light facility, especially, on rural road including light volume of traffic. This paper presents the criteria of installing 'Chevron Alignment Sign' considering driver's visual behavior characteristics and 'Raised Pavement Marker' considering critical encroachment angie of both straight section and curve one in order to reduce both the number of accidents on curve sections and the number of road encroachment accidents, respectively. The characteristics of visual behaviors can be expressed by visual angle involving curve radius and intersection angle. The estimated installing angles are $1^{\circ}{\sim}2.5^{\circ}$ by radii, which is based on changes in sensitivity across visual field by exogenous attention. Also, the raised pavement marker is installed every 2m, 3m, and 4m considering critical encroachment angles by radii.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.3
• /
• pp.77-84
• /
• 2015

The key objective of this research is to review the effectiveness of spatial regression to identify the influencing factors of spatial distribution patterns of floating population. To this end, global and local spatial autocorrelation test were performed using seoul floating population survey(2014) data. The result of Moran's I and Getis-Ord $Gi^*$ as used in the analysis derived spatial heterogeneity and spatial similarities of floating population patterns in a statistically significant range. Accordingly, Geographically Weighted Regression was applied to identify the relationship between land use attributes and population floating. Urbanization area, green tract of land of micro land cover data were aggregated in to $400m{\times}400m$ grid boundary of Seoul. Additionally public transportation variables such as intersection density transit accessibility, road density and pedestrian passage density were adopted as transit environmental factors. As a result, the GWR model derived more improved results than Ordinary Least Square(OLS) regression model. Furthermore, the spatial variation of applied local effect of independent variables for the floating population distributions.