• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.54 no.5
• /
• pp.808-813
• /
• 2021

The diet composition of Spanish mackerel Scomberomorus niphonius, was investigated using 853 specimens collected using two-boat trawl, stow net, gill net and set net from January to December 2019 from the South Sea of Korea. The size of the specimens ranged from 25.2 to 114.8 cm in fork length. S. niphonius fed mostly on fishes. Its diets also included small quantities of shrimps, cephalopods, crabs, stomatopods, etc. Among them, Engraulis japonicus was the dominant species. The dietary composition of S. niphonius exhibited significant differences based on their size. The proportion of Trichiurus japonicus increased as body size of S. niphonius increased, whereas the proportion of E. japonicus decreased gradually. As the body size of S. niphonius increased, the mean weight of prey per the stomach (mW/ST) tended to increase significantly (one-way ANOVA, P<0.05).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.890-895
• /
• 2021

Recently, the "Act of Serious Disasters, etc" was enacted and institutional and social interest in safety accidents is increasing. In this paper, we analyze statistical data published by government agency on safety accidents that occur in manufacturing sites, and compare various object detection models based on deep learning to build a model to determine dangerous situations to reduce the occurrence of safety accidents. The data-set was directly constructed by collecting images from CCTVs at the manufacturing site, and the YOLO-v4, SSD, CenterNet models were used as training data and evaluation data for learning. As a result, the YOLO-v4 model obtained a value of 81% of mAP. It is meaningful to select a class in an industrial field and directly build a dataset to learn a model, and it is thought that it can be used as an initial research data for a system that determines a risk situation and infers it.

• Journal of Information Technology Services
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

Suncheon City Regeneration Project is known as the concept of cultural residents. Through the previous projects, the residents' capabilities have been improved, and the projects have been carried out according to their strategies. For this reason, participants in urban regeneration projects are important. The purpose of this study is to actually identify the 'rescue center' and 'direct relationship' with the analysis utilizing the characteristics of social networks NetMiner solution of the participants, who led the project, Suncheon. Surveys and interviews were conducted for participants, and the characteristics of social networks were analyzed in time series to quantify and visualize the results. As a result of the analysis, social networks were changed among the participants before and after the urban regeneration project. Initially, loose networks were denser over time, and initially networks formed only around participants were expanded over time. Network analysis has revealed that the system is strengthening with urban regeneration projects in the form of public and public-private cooperation. This highlights the need for a city-centered urban regeneration strategy centered on people and shows that a dense network of participants can be a success factor.

• Journal of the Korean Wood Science and Technology
• /
• v.49 no.5
• /
• pp.491-503
• /
• 2021

Wood identification is regularly performed by observing the wood anatomy, such as colour, texture, fibre direction, and other characteristics. The manual process, however, could be time consuming, especially when identification work is required at high quantity. Considering this condition, a convolutional neural networks (CNN)-based program is applied to improve the image classification results. The research focuses on the algorithm accuracy and efficiency in dealing with the dataset limitations. For this, it is proposed to do the sample selection process or only take a small portion of the existing image. Still, it can be expected to represent the overall picture to maintain and improve the generalisation capabilities of the CNN method in the classification stages. The experiments yielded an incredible F1 score average up to 93.4% for medium sample area sizes (200 × 200 pixels) on each CNN architecture (VGG16, ResNet50, MobileNet, DenseNet121, and Xception based). Whereas DenseNet121-based architecture was found to be the best architecture in maintaining the generalisation of its model for each sample area size (100, 200, and 300 pixels). The experimental results showed that the proposed algorithm can be an accurate and reliable solution.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.219-225
• /
• 2022

In this study, we propose training a support vector machine (SVM) model on top of deep networks for detecting Covid-19 from chest X-ray images. We started by gathering a real chest X-ray image dataset, including positive Covid-19, normal cases, and other lung diseases not caused by Covid-19. Instead of training deep networks from scratch, we fine-tuned recent pre-trained deep network models, such as DenseNet121, MobileNet v2, Inception v3, Xception, ResNet50, VGG16, and VGG19, to classify chest X-ray images into one of three classes (Covid-19, normal, and other lung). We propose training an SVM model on top of deep networks to perform a nonlinear combination of deep network outputs, improving classification over any single deep network. The empirical test results on the real chest X-ray image dataset show that deep network models, with an exception of ResNet50 with 82.44%, provide an accuracy of at least 92% on the test set. The proposed SVM on top of the deep network achieved the highest accuracy of 96.16%.

• Journal of Fisheries and Marine Sciences Education
• /
• v.25 no.3
• /
• pp.724-732
• /
• 2013

The purpose of this study is to obtain a basic data on layout of the trawlers' bridge equipment. The task activities of bridge workers involved in the navigation and fishing operation were analyzed by link analysis methods. The results are as follows. It was found that the movement pattern and frequency of bridge workers are different accordance with the bridge work (navigation, casting net, towing net and hauling net). The central workstation of movement of the bridge workers was a radar workstation, a steering workstation and a trawl winch workstation in the bridge work. But the radar did not show up as the center of movement during the hauling net. Workstations related deeply to the central workstations of the movement on the bridge were as below. Radar workstation was related to a GPS plotter, a microphone location for external communication with VHF and MF/HF equipment and a steering in the case of the navigation, the steering, the GPS plotter and the net monitor in the case of the fishing operation. Steering workstation was related deeply to the GPS plotter, the radar in the case of the navigation, a speed controller, the GPS plotter, a fish finder, the net monitor and the microphone location in the case of the fishing operation. Trawl winch workstation showed deep relation with the GPS plotter and the speed control during the fishing operation. Through this study, it was found that Workstations related deeply to the central workstation of the movement of the bridge workers in accordance with the bridge work. The results of this study might be utilized as the basic data on the bridge layout to minimize the fatigue degree due to a physical movement of the bridge workers.

• Journal of Engineering Education Research
• /
• v.14 no.4
• /
• pp.29-38
• /
• 2011

The objective of this study is the analysis of the effects of educational contents authoring in a PBL using NetLogo Pre-service teachers' creativity. With utilization of the analysis, we attempted to draw implications on the factors considered in instructional design. To compare their creativity before and after class, we have done pre-service teachers test for each Pre- and Post- TTCT and LCT. Based on the analysis, as a result, there has been a significant improvement in their creativity, most especially in the 'fluency' subcategory.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.26 no.4
• /
• pp.37-51
• /
• 1984

The purpose of this study is to find out the determination method of designed duty of water in the rice fields through the comparison of the net unit duty of water at the late reduction division to heading stage with that at the planting stage. The data used for analysing this problem are the data of precipitation and gauge evaporation observed by Cheong-ju Meterological Center, the coefficient of evapotranspiration by College of Agriculture, Chung Buk University and the data of transplanting progressing in Boun area. The results obtained from this analysis are summarized as follows. 1.The occurring year of 1/10 probability value for available precipitation, gauge evaporation and mean maximum daily evapotranspiration during growing season is the year of 1977. 2.The 1/10 probability values of mean maximum evapotranspiration per day under the production rate of 1, 400kg/l0a and 1, 500kg/10a based on the weight of dry matters are 9. 2mm/day and 9. 6mm/day, respectively. 3.The net unit duty of water required in the fields that the maximum planting rate exists is more than the one in the fields that the planting rate is uniform in the planting stage. 4.The determination of net unit duty of water in the late reduction division to heading stage or the planting stage depends upon the daily evapotranspiration and percolation rate in the late reduction division to heading stage or the water depth required for planting and daily consumptive use of water after planting at the planting stage. Therefore the use of figure 5-(1) to figure 5-(6) can easily make the determination of the designed net unit duty of water out of above two kinds of net unit duty of water.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.68-71
• /
• 2008

Our goal is to obtain a better scientific understanding how to define the nature and role of remotely sensed land surface parameters and energy fluxes in the heat island phenomena, and local and regional weather and climate. By using the MODIS visible and thermal imagery data and analyzing the surface energy flux images associated with the change of the landcover and landuse in study area, we will estimate and present how significant is the magnitude of the heat island heat effect and its relation with the surface parameters and the energy fluxes in Taiwan. To achieve our objective, we used the energy budget components such as net radiation, soil heat flux, sensible heat flux, and latent heat flux in the study area of interest derived form remotely sensed data to understand the island heat effect. The result shows that the water is the most important component to decrease the temperature, and the more the consumed net radiation to latent heat, the lower urban surface temperature.