• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1317-1328
• /
• 2021

This study analyzes the early satellite mission marine fog detection results from Geostationary Ocean Color Imager-II (GOCI-II). We investigate optical characteristics of the GOCI-II spectral bands for marine fog between October 2020 and March 2021 during the overlapping mission period of Geostationary Ocean Color Imager (GOCI) and GOCI-II. For Rayleigh-corrected reflection (R_rc) at 412 nm band available for the input of the GOCI-II marine fog algorithm, the inter-comparison between GOCI and GOCI-II data showed a small Root Mean Square Error (RMSE) value (0.01) with a high correlation coefficient (0.988). Another input variable, Normalized Localization Standard (NLSD), also shows a reasonable correlation (0.798) between the GOCI and GOCI-II data with a small RMSE value (0.007). We also found distinctive optical characteristics between marine fog and clouds by the GOCI-II observations, showing the narrower distribution of all bands' R_rc values centered at high values for cloud compared to marine fog. The GOCI-II marine fog detection distribution for actual cases is similar to the GOCI but more detailed due to the improved spatial resolution from 500 m to 250 m. The validation with the automated synoptic observing system (ASOS) visibility data confirms the initial reliability of the GOCI-II marine fog detection. Also, it is expected to improve the performance of the GOCI-II marine fog detection algorithm by adding sufficient samples to verify stable performance, improving the post-processing process by replacing real-time available cloud input data and reducing false alarm by adding aerosol information.

• Korean Journal of Ecology and Environment
• /
• v.54 no.3
• /
• pp.151-155
• /
• 2021

The application of environmental DNA in the domestic ecosystem is also accelerating, but the processing and analysis of the produced data is limited, and doubts are raised about the reliability of the analyzed and produced biological taxa identification data, and the sample medium (target sample, water, air, sediment, Gastric contents, feces, etc.) and quantification and improvement of analysis methods are also needed. Therefore, in order to secure the reliability and accuracy of biodiversity research using the environmental DNA of the domestic ecosystem, it is a process of actively using the database accumulated through ecological taxonomy and undergoing verification procedures, and experts verifying the resolution of the data increased by gene sequence analysis. This is absolutely necessary. Environmental DNA research cannot be solved only by applying molecular biology technology, and interdisciplinary research cooperation such as ecology-taxa identification-genetics-informatics is important to secure the reliability of the produced data, and researchers dealing with various media can approach it together. It is an area in desperate need of an information sharing platform that can do this, and the speed of development will proceed rapidly, and the accumulated data is expected to grow as big data within a few years.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.359-366
• /
• 2021

A number of construction companies in Korea invest considerable human and financial resources to construct a system for managing apartment defect data and for categorizing repair tasks. Thus, this study proposes machine learning models to automatically classify defect complaint text-data into one of the sub categories of 'finishing work' (i.e., one of the defect repair tasks). In the proposed models, we employed two word representation methods (Bag-of-words, Term Frequency-Inverse Document Frequency (TF-IDF)) and two machine learning classifiers (Support Vector Machine, Random Forest). In particular, we conducted both binary- and multi- classification tasks to classify 9 sub categories of finishing work: home appliance installation work, paperwork, painting work, plastering work, interior masonry work, plaster finishing work, indoor furniture installation work, kitchen facility installation work, and tiling work. The machine learning classifiers using the TF-IDF representation method and Random Forest classification achieved more than 90% accuracy, precision, recall, and F1 score. We shed light on the possibility of constructing automated defect classification systems based on the proposed machine learning models.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1709-1718
• /
• 2021

The waveform data of the Airborne Bathymetric LiDAR (ABL; LiDAR: Light Detection And Ranging) system provides data with improved accuracy, resolution, and reliability compared to the discrete-return data, and increases the user's control over data processing. Furthermore, we are able to extract additional information about the return signal. Waveform decomposition is a technique that separates each echo from the received waveform with a mixture of water surface and seabed reflections, waterbody backscattering, and various noises. In this study, a new waveform decomposition technique based on a Gaussian model was developed to improve the point extraction performance from the ABL waveform data. In the existing waveform decomposition techniques, the number of decomposed echoes and decomposition performance depend on the peak detection results because they use waveform peaks as initial values. However, in the study, we improved the approximation accuracy of the decomposition model by adding the estimated potential peak candidates to the initial peaks. As a result of an experiment using waveform data obtained from the East Coast from the Seahawk system, the precision of the decomposition model was improved by about 37% based on evaluating RMSE compared to the Gaussian decomposition method.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.199-204
• /
• 2021

Digital substation refers to a substation that digitizes functions and communication methods of power facilities such as monitoring, measuring, control, protection, and operation based on IEC 61850, an international standard for the purpose of intelligent power grids. Based on the intelligent operating system, efficient monitoring and control of power facilities is possible, and automatic recovery function and remote control are possible in the event of an accident, enabling rapid power failure recovery. With the development of digital technology and the expansion of the introduction of eco-friendly renewable energy and electric vehicles, the spread of direct current distribution systems is expected to expand. MVDC is a system that utilizes direct current lines with voltage levels and transmission capacities between HVDCs applied to conventional transmission systems and LVDCs from consumers. Converting existing lines in substations, where most power equipment is alternating current centric, to direct current lines will reduce transmission losses and ensure greater current capacity. The process bus of a digital substation is a communication network consisting of communication equipment such as Ethernet switches that connect installed devices between bay level and process level. For MVDC linkage to existing digital substations, the process level was divided into two buses: AC and DC, and a system that can be comprehensively managed in conjunction with diagnostic IEDs as well as surveillance and control was proposed.

• Journal of vocational education research
• /
• v.37 no.2
• /
• pp.77-99
• /
• 2018

The purpose of this study was to investigate the employment possibility of the humanities college graduates to science and engineering field occupations, and to identify the occupational characteristics related to employability perceived by workers. To do this, basic statistical analysis, correlation analysis, and hierarchical multiple regression analysis were conducted using the data surveyed on 2,600 workers in the science and engineering field in the 'Research on Korean Occupational Index for Career and Employment Service(2017)'. The main results are as follows. First, the employment possibility of the humanities college graduates to science and engineering field was low, except for some occupations in the information communication, manufacturing and processing fields. Second, the occupational characteristics affecting the employment possibilities of the humanities college graduates to science and engineering field are as follows: low importance of the final education, low importance of the major, low importance of qualification, high importance of vocational training, easy to return after the career break, high level of gender equality, high level of pleasant work environment, high employment retention, easy to self-employment or start-up, and increasing number of jobs. Based on the results of this study, to support employment of humanities college graduate from the occupational aspect, it is necessary to find out some detailed jobs or to develop convergence occupations. At this time, it is possible to utilize the occupational characteristics factors that increase the employment possibility of humanities college graduates to science and engineering occupations.

• Journal of agriculture & life science
• /
• v.51 no.6
• /
• pp.137-144
• /
• 2017

A diverse of recommendation has been made for the structure and management of dairy cows, despite demanding research, the relationship between lactation number and various factors is yet to be established. The present study was aimed to investigate the covariance among lactation number, growth performance, calving interval, and milk production was considered to increase an efficiency of selection schemes and to manage more efficiently Holstein dairy cows that have been raised on small-scale family farms in Republic of Korea. For that purpose, the data were observed from 850 Holstein dairy cows, which a total of 3929 milking, since April 2016 - January 2017. We measured the body weight, height, age, calving interval, and milk production of the each dairy cow. Also, information about the date of lactation, calving interval, and milk production was recorded using an automatic milking system(AMS) with identification numbers. Milk production was calculated per udder quarter in the AMS. Our study results showed the increased average body weight(p>0.05) in 1, 2, 3, and $4^{th}$ lactating dairy cows and afterwards, we noticed the tendency on the average body weight(p<0.05) per lactation progressed. There was no significant difference noticed on height measurement of dairy cows. From the processing data of 850 Holstein dairy cows, the lactation number 1 and 7 had a greater calving interval with significantly lowered milk production, and the lactation number 2, 3, 4, 5, and 6 had significantly lowered the calving interval(p<0.05) with a greater milk production. From our study results, we evidenced that there is a significant relationship between the lactation number, growth performance, calving interval, and milk yield, and the maximum production of milk occurring in the $3^{rd}$ and $4^{th}$ lactation dairy cows. The achieved results from this study can be used by the small-scale farmers to encourage the structure and management of growth performance, calving interval, and milk yield in Holstein dairy cows in Korea.

• Journal of Ginseng Culture
• /
• v.1
• /
• pp.57-66
• /
• 2019

Ginseng has been recognized as a lifespan extending medicine which has been regarded as one of the medicines classified as top medicines, as the Boncho (medical herbs) study which is influenced by the idea of guidance's costume and food concept mainly in China is gaining its bona fide form. As the demand for ginseng has been expanded to other levels, the demand for ginseng has been increasing. Ginseng from the nature reached its supply chain limit due to its extinction and difficulty of picking, so it translated into ginseng cultivation of economy rather than harvesting in nature. After the start of ginseng cultivation, the ginseng cultivation was further enhanced by the rapid development of processing methods such as white-ginseng and red-ginseng, and the surge of consumption due to the traditional belief in ginseng drug efficacy and support of scientific research. In the Joseon Dynasty, the name Gasam (cultivated ginseng) had been created as ginseng was cultivated on farmland after the stage of SanYang (wild cultivated ginseng), the purpose of the new name Gasam is to differentiate from natural ginseng, and natural ginseng lost its firm position as the genuine ginseng as the Gasam replaced the genuine ginseng, and the natural ginseng got a new name of SanSam (wild ginseng). Because the real ginseng substance concept dissipated, and as Gasam is being called ginseng, the name Gasam was also disappeared. As a result, it was possible to grow large quantities according to the arrival of the Gasam era, and it was possible to supply the demand for ginseng, and it could become one agricultural industry. In this ginseng cultivation, in Japan where ginseng did not grow naturally, it was difficult to obtain ginseng from Joseon and faced with a shortage of ginseng at all times. Therefore, the shogun cultivated the Gasam systematically at the national level by the inside of the shogunate. However, since the natural ginseng is native to China and Korea, there is a concern about the deterioration of the quality of natural ginseng due to the incorporation of cultivated ginseng (Gasam). To protect the interests, the cultivation of ginseng was subject to control. For this reason, the lack of historical information on Gasam cultivation, which had to be started secretly, would be a natural result. In this paper, althouh not sufficient enough, the historical informations were used to summarize the history of ginseng cultivation in China, Japan and Korea.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.12
• /
• pp.301-312
• /
• 2018

In industrial wireless sensor networks, the continuous object detection such as fire or toxic gas detection is one of major applications. A continuous object occurs at a specific point and then diffuses over a wide area. Therefore, many studies have focused on accurately detecting a continuous object and delivering data to a static sink with an energy-efficient way. Recently, some applications such as fire suppression require mobile sinks to provide real-time response. However, the sink mobility support in continuous object detection brings challenging issues. The existing approaches supporting sink mobility are designed for individual object detection, so they establish one-to-one communication between a source and a mobile sink for location update. But these approaches are not appropriate for a continuous object detection since a mobile sink should establish one-to-many communication with all sources. The one-to-many communication increases energy consumption and thus shortens the network lifetime. In this paper, we propose the origin-centric communication scheme to support sink mobility in a continuous object detection. Simulation results verify that the proposed scheme surpasses all the other work in terms of energy consumption.