• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.

• Journal of Animal Environmental Science
• /
• v.18 no.3
• /
• pp.247-256
• /
• 2012

This study was carried out to investigate the effects of various regions of sorghum-sorghum hybrid (SSH) silage on nutritive values and qualities of SSH silage. SSH "SS405" was harvested at ripen stage and ensiled. Samples of SSH silage used in this study were collected in three regions (outside, middle and inside). The contents of crude protein (CP), neutral detergent fiber (NDF), acid detergent fiber (ADF), total digestible nutrients (TDN) and in vitro dry matter digestibility (IVDMD) in SSH silage were not influenced by SSH silage manufacture methods and lactic acid bacteria. The contents of CP in inside region of SSH silage were lower than those of outside and middle regions (p<0.05). However, the contents of NDF, ADF and TDN, and IVDMD were not different between the regions of SSH silage. The content of lactic acid in SSH round bale silage was significantly decreased (p<0.05), as compared to SSH square bale silage (SB), gunny bag silage (GB) and trench silage (TS). The contents of acetic acid and butyric acid in SSH silage were not influenced by SSH silage manufacture methods and lactic acid bacteria. The contents of lactic acid in inside region of SSH silage were lower than those of outside and middle regions (p<0.05). In addition, the contents of lactic acid, acetic acid and butyric acid were not different between the regions of SSH silage. Therefore we suggest that nutritive values and quality of SSH silage were not influenced by regions of sampling collected from these silages.

• Journal of Environmental Impact Assessment
• /
• v.32 no.3
• /
• pp.166-175
• /
• 2023

This study aims to identify the cause of the red-water occurrence (the phenomenon of water being red) that occurs at some points and sections of rivers in Yongin City. As a result of conducting a preliminary investigation, total three sites were selected as the investigation point as it was found that the red-water occurrence continued. As a result of the investigation, it is judged that the cause of the red-water in Yongin-city river is due to the soil color and iron content of the region. JPS, SBS, and JJS sites all showed that the color of soil is mainly consist of reddish brown and red-yellow. The average Fe concentration was 13.75 mg/L, 10.85 mg/L, and 1.31 mg/L, for each sites, and considering that the Fe concentration in general river water was less than 0.5 mg/L, it was confirmed that the concentration was quite high. At the JPS and JJS points, the red-water occurrence occurred mainly in stagnant places, which is believed to be strengthened by the reaction of organic and microorganisms. In the case of SBS, the wateris red, but as a result of observing the actual color, it is judged that the iron component deposited in the pipe causes an optical illusion with a deep red color. In addition, it is believed that the iron concentration can be reduced to the general river water concentration range by removing the particulate iron component through a decrease of more than 95% as a result of filtering with glass fiber filter with particulate iron. As a result of this study, it is necessary to manage the river to maintain the flow, and it is believed that the occurrence of red-water at the survey point can be alleviated through uptake action through planting and agglomeration precipitation and agglomeration filtration methods for particulate iron treatment.