• Journal of Korean Society on Water Environment
• /
• v.37 no.5
• /
• pp.335-343
• /
• 2021

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-ob servation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

• Journal of Information Management
• /
• v.27 no.2
• /
• pp.65-94
• /
• 1996

The article presents the method that medium enterprises could manage technical information effectively. There are some merits in using the next generation Web brower, HyperWave as technical information management system. First, it makes anyone else to manage the technical information easily. Second, if he could manages the technical in-formation by using HyperWave, he can input, modify, and delete information effectively. Third, HyperWave system can creat the link to connect the related documents or images. Fourth, it provides various retrieval techniques. Lastly, HyperWave system can organize technical information at a low cost.

• Journal of Korean Society of Forest Science
• /
• v.98 no.4
• /
• pp.504-511
• /
• 2009

This study to understand the production cost of cultivation in chestnut tree (Castanea spp.) as a result of a survey conducted of 227 farmers is as follows. In full-time farmer, average cultivation area was 5.5 hectares and average chestnut production was 1.6 tons per hectare. In chestnut sale type, more than 73% of total production was sold by Nong-hyup (7an agricultural cooperative association) and intermediaries, and also proportion of nut size grade was 18% in special-large nut, following 49% in large nut, 25% in middle nut and 8% in small nut. There was considerable difference among cultivated regions in gross income, whereas total average gross income was 2,103 thousand KRW per hectare and 66.4% of it was used in management expenses. Finally the chestnut cultivated farmers have a yearly income of 706 thousands KRW (net income rate 33.6%). As peculiarity of regional production cost, a low tree farm in height and a labor intensive growing helped the improved quality of the chestnut so, on average, 2,161 thousand KRW per hectare of the income of the Chungnam was raised. However caused by an old-age of chestnut trees, there was a little input to management expenses and it resulted in low productivity in the Jeonnam and the Gyeongnam.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.15 no.4
• /
• pp.369-380
• /
• 2017

In order to manage the uncertainty about the evaluation and analysis of the human intrusion scenario of the Gyeongju Low and Intermediate Level Radioactive Waste(LILW) disposal facility, the calculation result by the GENII code was assessed using the RESRAD code, which was developed to evaluate the radiation effects of contaminated soil. The post-drilling scenario was selected as a human intrusion scenario into the near-surface disposal facility to analyze the uncertainty of the modeling by identifying any limitations in the simulation of each code and comparing the evaluation results under the same input data conditions. The results revealed a difference in the migration of some nuclides between the codes, but confirmed that the dose trends at the end of the post-closure control period were similar for all exposure pathways. Based on the results of the dose evaluation predicted by RESRAD, sensitivity analysis on the input factors was performed and major input factors were derived. The uncertainty of the modeling results and the input factors were analyzed and the reliability of the safety evaluation results was confirmed. The results of this study can be applied to the implementation 'Safety Case Program' for the Gyeongju LILW disposal facility.

• Journal of Korean Society of Water and Wastewater
• /
• v.36 no.4
• /
• pp.239-248
• /
• 2022

The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.

• Industry Promotion Research
• /
• v.9 no.1
• /
• pp.259-273
• /
• 2024

In this study, 31 provincial-level administrative regions in China from 2011 to 2021 were taken as the research objects, and the super-SBM model was used to measure the regional eco-efficiency with capital, labor, land and resource input as input variables, GDP and green coverage as the desirable outputs, and wastewater, waste gas and solid waste emissions as the undesired outputs. Tobit regression was used to analyze the effects of external environmental factors on eco-efficiency. The results showed that the average level of eco-efficiency in China was low, and the eco-efficiency in the eastern region was higher than that in other regions, and there were great differences in the western, northeast and central regions.

• Journal of Biosystems Engineering
• /
• v.3 no.1
• /
• pp.64-76
• /
• 1978

A dimensional supply of petroleum fuels and increased competition for petroleum products has made the conservation of energy in grain drying an important cost and management factor. Research on solar grain drying is directed toward utilization of a renewable energy source as an alternative to petroleum fuels for drying. There are many technical and economic problems in accepting and adopting solor energy as a new energy source for grain drying. The purpose of this study are to assess the state of the art of solar grain drying and to find out the problems by reviewing literatures available. The results obtained may be summarized as follows; 1.It may be considered that the weather conditions in October of Korea was satisfactory for the forced natural air and solar heated air drying. 2. Solar energy is considered more applicable to low-temperature, In-storage drying systems than to high-temperature, high-speed drying systems. In-storage drying systems require low levels of heat input. The costs of collector systems to provide low temperature are considerably cheaper than for high-temperature systems. 3. Tubular type collector made of polyvinyle film seems to be the most practical at this stage of development and black-painted bare-plate collectors mounted on the outside of a typical, round, low-temperature drying bin can supply an appreciable amount of the energy efficiently needed for low-temperature grain drying at a lower cost. 4. All of the grains in solar drying tests was successfully dried up to safe storaged moisture levels without significant spoilage. Drying rates with solar system were faster than natural air drying systems, and usually a little slower than similar low-temperature electric drying systems. 5. Final grain moisture levels were lower in solar tests than in natural air tests, and generally higher than in tests with continuous heated air. 6. Savings of energy by use of solar collectors ranged from 23% to 55%, compared to the natural and electric ileated air drying systems. However, total drying cost effectiteness tvas not significant. Therefore, it is desirable that solar grain dry-ing sIFstems tvhich could be suitable for multiple heating purposes on farms shouldbe developed. 7. Supplemental heat with solar radiation did little to reduce air flow requirementsbut refuced drying time and increased the p\ulcornerobability of successful drying duringdrying poriod.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.16 no.6
• /
• pp.745-753
• /
• 2016

This paper presents a fully synthesizable low power interconnect bus for millimeter-scale wireless sensor nodes. A segmented ring bus topology minimizes the required chip real estate with low input/output pad count for ultra-small form factors. By avoiding the conventional open drain-based solution, the bus can be fully synthesizable. Low power is achieved by obviating a need for local oscillators in member nodes. Also, aggressive power gating allows low-power standby mode with only 53 gates powered on. An integrated wakeup scheme is compatible with a power management unit that has nW standby mode. A 3-module system including the bus is fabricated in a 180 nm process. The entire system consumes 8 nW in standby mode, and the bus achieves 17.5 pJ/bit/chip.

• Journal of IKEEE
• /
• v.13 no.4
• /
• pp.63-68
• /
• 2009

The power management integrated circuit(PMIC) for CCD image sensor is presented in this study. A CCD image sensor is very sensitive against temperature. The temperature, that is heat, is generally generated by the PMIC with low efficiency. Since the generated heat influences performance of CCD image sensor, it should be minimized by using a PMIC which has a high efficiency. In order to develop the PMIC with high efficiency, the input stage is designed with synchronous type step down DC-DC converter. The operating range of the converter is from 5V to 15V and the converter is controlled using PWM method. The PWM control circuit consists of a saw-tooth generator, a band-gap reference circuit, an error amplifier and a comparator circuit. The saw-tooth generator is designed with 1.2MHz oscillation frequency. The comparator is designed with the two stages OP Amp. And the error amplifier has 40dB DC gain and $77^{\circ}$ phase margin. The output of the step down converter is connected to input stage of the charge pump. The output of the charge pump is connected to input of the LDO which is the output stage of the PMIC. Finally, the PMIC, based on the PWM control circuit and the charge pump and the LDO, has output voltage of 15V, -7.5V, 3.3V and 5V. The PMIC is designed with a 0.35um process.

• Journal of Digital Convergence
• /
• v.12 no.12
• /
• pp.611-620
• /
• 2014

This research analyzed the operation efficiency and influence factors of housing facilities for the severely disabled in Jeolla region by using the DEA model. First, the analysis of efficiency for 2012 was carried out using the CCR model. As a result, 12 DMUs were proved to be efficient, and the average efficiency of CCR was 0.85, confirming that the efficiency of all DMUs were satisfactory. Second, regression analysis was carried out to analyze the factors affecting the efficiency of the DEA model by using the Tobit model. In this case, the inputs and calculated variables were set as independent variables whereas the efficiency as the dependent variable. As a result, the detailed variables had a low significance; the overall input variables showed a negative influence while the calculated variables tended to be a positive influence. In terms of operation efficiency, there was no meaningful result in input variables besides the number of workers. Instead of expanding the input variables, the following should be made for housing facilities of the severely disabled; more efforts should be put in to improve welfare service delivery system and operating environment and structure, and the program must be supplemented as well.