• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.

• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.125-132
• /
• 2020

The objective of this study was to analyze the axle load of a rice transplanter when planting rice seedlings at different working load conditions to select a suitable gear stage and a constant planting depth for rice seedlings. In this study, there are four levels of planting distances (26, 35, 43, and 80 cm) and three planting depths (low, medium, and high) with two gear stages (1.3 and 1.7 m/s). Axle loads and required planting pressures were analyzed statistically. It was observed that axle torques were increased with increasing planting depths for both gear stages, meaning that axle torques were directly proportional to planting depths for both gear stages. It was also observed that required planting pressures had a significant difference between planting distances. Planting pressures also showed significant difference according to gear stage and planting depth. These results indicate that planting pressures were directly proportional to both gear stage and planting depth. Results revealed that the automatic depth control system of a rice transplanter could not guarantee a constant planting depth as supplied pressures were variable. This indicates that a control algorithm is needed to ensure a constant planting depth. In the future, a control algorithm will be developed for an automatic depth control system of a rice transplanter to improve its comprehensive performance and efficiency.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.515-521
• /
• 2020

Recently, data traffic has exploded due to development of various industries, which causes problems about losing of efficiency and overloaded existing networks. To solve these problems, network slicing, which uses a virtualization technology and provides a network optimized for various services, has received a lot of attention. In this paper, we propose a resource allocation method using credit value. In the method using the clustering technology, an operation for selecting a cluster is performed whenever an allocation request for various services occurs. On the other hand, in the proposed method, the credit value is set by using the residual capacity and balancing so that the slice request can be processed without performing the operation required for cluster selection. To prove proposed method, we perform processing time and balancing simulation. As a result, the processing time and the error factor of the proposed method are reduced by about 13.72% and about 7.96% compared with the clustering method.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.117-133
• /
• 2021

This study aimed to identify its research trends using social network analysis(SNA). The results of the analysis showed that, for degree centrality, Busan Port(0.223) was the keyword that had the highest centrality, followed by DEA(0.060), AHP(0.056), and container terminal and port competitiveness(0.049). Busan Port(0.245) also had the highest betweenness centrality, followed by DEA(0.048), container terminal(0.044), AHP(0.039), and Busan New Port(0.032). The trend analysis inferred that efficiency analysis(DEA), strategy selection, and competition analysis(AHP) were the keywords with a high centrality for Busan Port to gain a competitive edge with global ports. However, research on the Fourth Industrial Revolution, which is emerging as a key issue, was insufficient. In the future, research using social data, such as mass media and social networks, is necessary.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.37-42
• /
• 2021

NOMA (Non-orthogonal multiple Access) system has been focused on the next generation cellular system for higher spectral efficiency. However, this requires user scheduling as the NOMA system is a multi-user system which accesses simultaneously. There are two representative scheduling schemes, proportionate scheduling (FP) and cumulative distribution function (CFD) scheduling. The PF scheduling is applied, the cell edge user is hard to obtain a transmit opportunity. Recently, CDF scheduling is obviously noted that it offers the same possibility of transmission for a user regardless of the location in a cell. We consider an uplink NOMA system with CDF scheduling, and obtain the channel access probabilities, the outage probabilities of the system with different number of users and different kinds of weights through simulation. The results indicate that the likelihood of each user accessing the channel is the same and the probability of failure decreases as the number of users increases. We found that the effect of the probability of failure is negligible as the weight of the cell edge user increases.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.24 no.6
• /
• pp.67-87
• /
• 2021

Provisioning service, which is one of the ecosystem service functions, means goods and services such as food and fuel that people get from ecosystem. Provisioning functions are closely related to the primary industry, a sector of economy. Excessive demand and use of human society can cause trade-offs among regulation, cultural, and supporting services. Therefore, it is important to perform evaluation ecosystem services periodically and to monitor the time series fluctuations to identify the impact of provisioning services on other ecosystem services (trade-off) and to maintain sustainable provisioning service. When it comes to the precise assessment of provisioning service, it is necessary to get the statistical data and standardize indicators and methods. In this study, indicators and methods, which are applicable to the spatial level of national-local-protected areas, were derived through literature analysis and expert survey. The result of this study implies that provisioning services measurement by spatial level improve the efficiency of the establishment of environmental conservation plans by whose purpose.

• Journal of Korea Port Economic Association
• /
• v.37 no.3
• /
• pp.75-91
• /
• 2021

Due to increased competition in supply side to reduce operational costs, port professionals have experienced extreme pressure, which demanded academicians to develop the model for efficient port operations from the industry perspective. Among many ports in the world, U.S. ports are our primary interest to analyze in our study for its high volume of cargoes transacted in the U.S. ports. We primarily employed DEA (Data Envelopment Analysis) technique to research the productivity of U.S. ports and applied the algorithm of double bootstrapped DEA proposed by Simar & Wilson (2007) to further investigate the driving forces of the performance of U.S. port operations. The external variables employed in our study comprise onDock Rail, Channel Depth, Location, Area, Acres, ForeignCargoRatio, and TEUChange, out of which onDock Rail, Acres, ForeignCargoRatio, and TEUChange were significant. In order to evaluate the effects of methodology selection, we conducted the same analysis applying the Censored model (Tobit) and contrasted the outcomes drawn from the two different techniques. Based on the findings from this work we proposed managerial implications and concluded.

• Journal of Biomedical Engineering Research
• /
• v.44 no.1
• /
• pp.11-18
• /
• 2023

Currently, studies to predict the risk of rectal cancer surgery select MRI image slices based on the clinical experience of surgeons. The purpose of this study is to semi-automatically select and classify 2D MRI image slides to predict the risk of rectal cancer surgery using biomarkers. The data used were retrospectively collected MRI imaging data of 50 patients who underwent laparoscopic surgery for rectal cancer at Gachon University Gil Medical Center. Expert-selected MRI image slices and non-selected slices were screened and radiomics was used to extract a total of 102 features. A total of 16 approaches were used, combining 4 classifiers and 4 feature selection methods. The combination of Random Forest and Ridge performed with a sensitivity of 0.83, a specificity of 0.88, an accuracy of 0.85, and an AUC of 0.89±0.09. Differences between expert-selected MRI image slices and non-selected slices were analyzed by extracting the top five significant features. Selected quantitative features help expedite decision making and improve efficiency in studies to predict risk of rectal cancer surgery.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.32 no.4
• /
• pp.359-370
• /
• 2022

Objective: This study is intended to design a commercially available passive sampler and conduct performance test on its use as a media for evaluating a working environment. Methods: This study was conducted to select adsorbents, design models, and evaluate storage stability and sampling rates for the development of new types of passive samplers. Results: The impurity detection, adsorbent capacity and breakthrough volume of five types of activated carbon were tested for selection of an adsorbent. One product was selected in consideration of the efficiency of purchase. A number of passive samplers were designed in a radial style and a badge style using plastic as a material. The final two prototypes were made using molds or 3D printing. For the storage stability evaluation, samples were stored at different temperature for 1~21 days and then analyzed. Most of the chemicals had excellent storage stability when refrigerated. However, some chemicals such as dichloromethane and methyl ethyl ketone need to be analyzed as soon as possible after sampling. Conclusion: In this study, new types of passive samplers for 66 chemical compounds were developed. The evaluation of storage stability and sampling rates showed different results depending on the properties of the chemical substance. For some chemicals such as methyl ethyl ketone and dimethylformamide, activated carbon is inappropriate as an absorbent. In future studies, additional experiments are required on chemicals that are difficult to collect with activated carbon.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.6
• /
• pp.843-852
• /
• 2022

Despite continuous safety management, the death rate of construction workers is not decreasing every year. Accordingly, various studies are in progress to prevent construction site accidents. In this paper, we developed an AI-based priority inspection target selection model that preferentially selects sites are expected to cause construction accidents among construction sites with construction costs of less than 5 billion won (KRW). In particular, Random Forest (90.48 % of accident prediction AUC-ROC) showed the best performance among applied AI algorithms (Classification analysis). The main factors causing construction accidents were construction costs, total number of construction days and the number of construction performance evaluations. In this study an ROI (return of investment) of about 917.7 % can be predicted over 8 years as a result of better efficiency of manual inspections human resource and a preemptive response to construction accidents.