• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4395-4412
• /
• 2020

The multisource image fusion has become an active topic in the last few years owing to its higher segmentation rate. To enhance the accuracy of multimodal pig-body feature segmentation, a multisource image fusion method was employed. Nevertheless, the conventional multisource image fusion methods can not extract superior contrast and abundant details of fused image. To superior segment shape feature and detect temperature feature, a new multisource image fusion method was presented and entitled as NSST-GF-IPCNN. Firstly, the multisource images were resolved into a range of multiscale and multidirectional subbands by Nonsubsampled Shearlet Transform (NSST). Then, to superior describe fine-scale texture and edge information, even-symmetrical Gabor filter and Improved Pulse Coupled Neural Network (IPCNN) were used to fuse low and high-frequency subbands, respectively. Next, the fused coefficients were reconstructed into a fusion image using inverse NSST. Finally, the shape feature was extracted using automatic threshold algorithm and optimized using morphological operation. Nevertheless, the highest temperature of pig-body was gained in view of segmentation results. Experiments revealed that the presented fusion algorithm was able to realize 2.102-4.066% higher average accuracy rate than the traditional algorithms and also enhanced efficiency.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.99-110
• /
• 2021

This study presents the estimation of crack depth by analyzing temperatures extracted from thermal images and environmental parameters such as air temperature, air humidity, illumination. The statistics of all acquired features and the correlation coefficient among thermal images and environmental parameters are presented. The concrete crack depths were predicted by four different machine learning models: Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), and AdaBoost (AB). The machine learning algorithms are validated by the coefficient of determination, accuracy, and Mean Absolute Percentage Error (MAPE). The AB model had a great performance among the four models due to the non-linearity of features and weak learner aggregation with weights on misclassified data. The maximum depth 11 of the base estimator in the AB model is efficient with high performance with 97.6% of accuracy and 0.07% of MAPE. Feature importances, permutation importance, and partial dependence are analyzed in the AB model. The results show that the marginal effect of air humidity, crack depth, and crack temperature in order is higher than that of the others.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.11-17
• /
• 2019

In recent years, damage and loss of life and property have been occurred frequently due to swelling waves in the East Sea. Swelling waves are not easy to predict because they are caused by various factors. In this research, we build a model for predicting the swelling waves occurrence in the East Coast of Korea using machine learning technique. We collect historical data of unloading interruption in the Pohang Port, and collect air pressure, wind speed, direction, water temperature data of the offshore Pohang Port. We select important variables for prediction, and test various machine learning prediction algorithms. As a result, tide level, water temperature, and air pressure were selected, and Random Forest model produced best performance. We confirm that Random Forest model shows best performance and it produces 88.86% of accuracy

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.238-245
• /
• 2021

In this study, we carried out case study to predict dissolved oxygen (DO) concentration of Nakdong river estuary with LSTM model. we aimed to figure out a optimal model condition and appropriate predictor for prediction in dissolved oxygen concentration with model parameter and predictor as cases. Model parameter case study results showed that Epoch = 300 and Sequence length = 1 showed higher accuracy than other conditions. In predictor case study, it was highest accuracy where DO and Temperature were used as a predictor, it was caused by high correlation between DO concentration and Temperature. From above results, we figured out an appropriate model condition and predictor for prediction in DO concentration of Nakdong river estuary.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.577-578
• /
• 2021

Recently, artificial intelligence systems are being used in various fields. The accuracy of the decision algorithm of artificial intelligence is greatly affected by the amount of learning and the accuracy of the learning data. In the case of the amount of learning, a large amount of data is required because it has a decisive effect on the performance of AI. In this paper, we propose a data collection system for constructing a system that analyzes future conditions and changes in infants' conditions based on the body temperature data of infants and toddlers. The proposed system is a system that collects and transmits data, and it is believed that it can minimize the resource consumption of the server system in existing big data analysis and training data construction.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.34 no.1
• /
• pp.67-76
• /
• 2024

Objectives: Direct reading instruments (DRIs) are widely used by industrial hygienists and other experts for preliminary survey and identifying source locations in many industrial fields. Photoionization detectors (PIDs), which are a form of hand-held portable DRIs, have been used for a variety of airborne vaporized chemicals, especially evaporated hydrocarbon solvents. The benefits of PIDs are high sensitivity between each chemical, competitive price, and portability. With the goal of increasing the accuracy of logged PID concentrations, previous studies have performed tests for the assessment of single chemical compounds, not mixtures. The purpose of this preliminary study was to measure mixtures with a PID and charcoal tube at the same time and compare the accuracy between them. Methods: A chamber test was implemented with different mixtures of hydrocarbon chemicals (acetone, isopropyl alcohol, toluene, m-xylene) and levels in the range of 14 to 864 ppm. Three PIDs and charcoal tubes were connected to the chamber and measured the chemical mixtures simultaneously. A comparison of accuracy and the PID group of concentrations with manufacture correction factor (M_CF) and field correction factor (F_CF) applied was performed. Results: The accuracy of the PID concentrations data-logged from the PID did not meet the accuracy criteria except for the mixture level B and C logged from PID No. 2, which was 18% of all tests for meeting accuracy criteria. The mean and standard deviation (SD) of concentration (ppm) of the charcoal tube followed by each mixtures' level were 10.37±0.26, 155.33±5.28, 300.80±11.65, and 774.93±22.65, respectively. When applying F_CF into the PID concentrations, the accuracy increased by nearly 82%. However, in the case of M_CF, none met the accuracy criterion. Between the PID there were differences of logged concentrations. Conclusions: In this preliminary study, the concentration of a logged PID with F_CF applied was a better way to increase accuracy compared to applying M_CF. We suggest that additional research is necessary to consider environmental factors such as temperature and humidity.

• Korean Journal of Agricultural Science
• /
• v.41 no.4
• /
• pp.481-485
• /
• 2014

According to statistical data the past ten years, cultivation area and yield of radish are steadily decreasing. This phenomenon cause instability of radish's supply due to meteorological chage, even if radish's yield per unit area is increasing by cultivation technological development. These problems raise radish's price. So, we conducted study on meteorological factors for accuracy improvement of radish yield estimation. Panel analysis was used with two-way effect model considering group effect and time effect. As the result, we show that mixed effects model (fixed effect: group, random effects: time) was statistical significance. According to the model, a rise of one degree in the average air temperature on August will decrease radish's yield per unit area by $428kg{\cdot}10a^{-1}$ and that in the average air temperature on October will increase radish's yield per unit area by $438kg{\cdot}10a^{-1}$. The reason is that radish's growth will be easily influenced by meteorological condition of a high temperature on August and by meteorological condition of a low temperature on Octoboer.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.4
• /
• pp.387-394
• /
• 2015

We analyze heat generation as well as temperature distribution induced by accelerated electron impact on a target in a closed x-ray tube. For the sake of accuracy, we use Monte carlo analysis. This method gives accurate energy deposit in a medium with additional information such as secondary and backscattered electron as well as their paths. A Tungsten coated layer is divided by small rectangular cell which accumulate energy loss of primary electron beam. The cells and their accumulated energy datum are used for the input of finite element analysis. The Maximum temperature rising and temperature distribution were analyzed by transient heat analysis. Some temperature parameters such as target size and coating thickness were varied to investigate temperature sensitivity. Temperatures were compared each other to find primary variable that affect temperature rising on the x-ray target. The results will be helpful in development highresolution x-ray tube and related industries.

• The KSFM Journal of Fluid Machinery
• /
• v.3 no.4 s.9
• /
• pp.22-29
• /
• 2000

Numerical analysis using three dimensional finite volume method for the discretization, adaptive grid method for the numerical accuracy, multiple rotating frame method for the rotating body and the standard $k-{\epsilon}$ model for the turbulent flow was performed to understand the heat transfer phenomena and to improve the efficiency of the scroll compressor. The temperature measurement was carried out under ARI condition. It was found that the fluid temperature in the compressor was predicted accurately while the temperature of the motor coil showed large discrepancy between the calculation and experiment due to the large anisotropy of the conductivity and non homogeneity. We found that the efficiency of the compressor depends on the inlet temperature of the compressing part and the flow pattern around the inlet region of the compressing part influences the inlet temperature due to high surface temperature of the main frame. The efficiency of the compressor using Coanda effect is higher than the previous one because the smooth suction at the inlet region of the compressing part leads to low heat transfer to the refrigerant of the compressor.

• Journal of Power System Engineering
• /
• v.14 no.2
• /
• pp.34-39
• /
• 2010

Recently, technical trend for machine tools is focused on enhancement of speed and accuracy. High speedy processing causes thermal and structural deformation of objects from the machine tools. Water cooler has to be applied to machine tools to reduce the thermal negative influence with accurate temperature controlling system. Existing On-Off control type can't control temperature accurately because compressor is operated and stopped repeatedly and causes increment of power consumption and decrement of the expected life of compressor. The goal of this study is to minimize temperature error in steady state. In addition, control period of an electronic expansion valve were considered to increment of lifetime of the machine tools and quality of product with a water cooler. PI controller is designed using type of hot-gas bypass for precise control of temperature. Gain of PI is decided easily by method of critical oscillation response, excellent performance of control is shown with 4.24% overshoot and ${\pm}0.2^{\circ}C$error of steady state. Also, error range of temperature is controlled within $0.2^{\circ}C$although disturbance occurs.