• Information Systems Review
• /
• v.26 no.2
• /
• pp.137-153
• /
• 2024

This study aimed to propose early diagnosis and management of dementia, which is increasing in aging societies, and suggest commercial utilization strategies by leveraging digital healthcare technologies, particularly lifelog data collected from wearable devices. By introducing new approaches to dementia prevention and management, this study sought to contribute to the field of dementia prediction and prevention. The research utilized 12,184 pieces of lifelog information (sleep and activity data) and dementia diagnosis data collected from 174 individuals aged between 60 and 80, based on medical pathological diagnoses. During the research process, a multidimensional dataset including sleep and activity data was standardized, and various machine learning algorithms were analyzed, with the random forest model showing the highest ROC-AUC score, indicating superior performance. Furthermore, an ablation test was conducted to evaluate the impact of excluding variables related to sleep and activity on the model's predictive power, confirming that regular sleep and activity have a significant influence on dementia prevention. Lastly, by exploring the potential for commercial utilization strategies of the developed model, the study proposed new directions for the commercial spread of dementia prevention systems.

• Journal of Korean Society of Forest Science
• /
• v.113 no.3
• /
• pp.349-360
• /
• 2024

This study aimed to analyze the main forest environmental factors affecting the discernment of slow-moving landslide-prone areas in the Republic of Korea, based on data from a detailed landslide survey conducted from 2019 to 2021. Field survey data from 256 sites were collected covering 29 forest environmental factors in seven categories, including geology, soil, and topography. The analysis was conducted using the Random Forest model (AUC = 0.910) and XGBoost model (Accuracy = 0.808, Kappa = 0.594, F1 - measure = 0.494), which were evaluated as having high classification accuracy during the machine learning model development process. Consequently, factors with a high mean decrease Gini (MDG), representing classification importance, were identified as the presence of cracks (average MDG of both models: 22.1), peak elevation (14.8), and the presence of steps (7.0), indicating that these were significant factors in determining slow-moving landslide-prone areas. The presence of cracks and steps aligned well with the characteristics of slow-moving landslides, suggesting that their importance should be emphasized in future detailed landslide surveys. However, the influence of the peak elevation was considered somewhat overestimated due to the characteristics of the input data used in the analysis. These findings are expected to further improve the accuracy and efficiency of final judgments in detailed landslide surveys.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.395-403
• /
• 2024

Recently, with the advancement of technology, the automotive industry has seen an increase in network connectivity. CAN (Controller Area Network) bus technology enables fast and efficient data communication between various electronic devices and systems within a vehicle, providing a platform that integrates and manages a wide range of functions, from core systems to auxiliary features. However, this increased connectivity raises concerns about network security, as external attackers could potentially gain access to the automotive network, taking control of the vehicle or stealing personal information. This paper analyzed abnormal messages occurring in CAN and confirmed that message occurrence periodicity, frequency, and data changes are important factors in the detection of abnormal messages. Through DBC decoding, the specific meanings of CAN messages were interpreted. Based on this, a model for classifying abnormalities was proposed using the GRU model to analyze the periodicity and trend of message occurrences by measuring the difference (residual) between the predicted and actual messages occurring within a certain period as an abnormality metric. Additionally, for multi-class classification of attack techniques on abnormal messages, a Random Forest model was introduced as a multi-classifier using message occurrence frequency, periodicity, and residuals, achieving improved performance. This model achieved a high accuracy of over 99% in detecting abnormal messages and demonstrated superior performance compared to other existing models.

• Korean Journal of Mineralogy and Petrology
• /
• v.37 no.2
• /
• pp.23-34
• /
• 2024

It is essential to know the mineral composition of core samples to assess the possibility of gas hydrate (GH) in sediments. During the exploration of gas hydrates (GH), mineral composition values were obtained from each core sample collected in the Ulleung Basin using X-ray diffraction (XRD). Based on this data, machine learning was performed with 3100 input values representing XRD peak intensities and 12 output values representing mineral compositions. The 488 data points were divided into 307 training samples, 132 validation samples, and 49 test samples. The random forest (RF) algorithm was utilized to obtain results. The machine learning results, compared with expert-predicted mineral compositions, revealed a Mean Absolute Error (MAE) of 1.35%. To enhance the performance of the developed model, principal component analysis (PCA) was employed to extract the key features of XRD peaks, reducing the dimensionality of input data. Subsequent machine learning with the refined data resulted in a decreased MAE, reaching a maximum of 1.23%. Additionally, the efficiency of the learning process improved over time, as confirmed from a temporal perspective.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1101-1118
• /
• 2017

Temperatures in urban areas are steadily rising due to rapid urbanization and on-going climate change. Since the spatial distribution of heat in a city varies by region, it is crucial to investigate detailed thermal characteristics of urban areas. Recently, many studies have been conducted to identify thermal characteristics of urban areas using satellite data. However,satellite data are not sufficient for precise analysis due to the trade-off of temporal and spatial resolutions.In this study, in order to examine the thermal characteristics of Daegu Metropolitan City during the summers between 2012 and 2016, Moderate Resolution Imaging Spectroradiometer (MODIS) daytime and nighttime land surface temperature (LST) data at 1 km spatial resolution were downscaled to a spatial resolution of 250 m using a machine learning method called random forest. Compared to the original 1 km LST, the downscaled 250 m LST showed a higher correlation between the proportion of impervious areas and mean land surface temperatures in Daegu by the administrative neighborhood unit. Hot spot analysis was then conducted using downscaled daytime and nighttime 250 m LST. The clustered hot spot areas for daytime and nighttime were compared and examined based on the land cover data provided by the Ministry of Environment. The high-value hot spots were relatively more clustered in industrial and commercial areas during the daytime and in residential areas at night. The thermal characterization of urban areas using the method proposed in this study is expected to contribute to the establishment of city and national security policies.

• The Journal of Korean Academy of Prosthodontics
• /
• v.48 no.4
• /
• pp.280-286
• /
• 2010

Purpose: This study evaluated the detorque values of screws in a multiple implant-supported superstructure using stone casts made with 2 different impression techniques. Material and methods: A fully edentulous mandibular master model and a metal framework directly connected to four implants (Br${\aa}$nemark $System^{(R)}$; Nobel Biocare AB) with a passive fit to each other were fabricated. Six experimental stone casts (Group 1) were made with 6 non-splinted impressions on a master cast and another 6 experimental casts (Group 2) were made with 6 acrylic resin splinted impressions. The detorque values of screws ($TorqTite^{(R)}$ GoldAdapt Abutment Screw; Nobel Biocare AB) were measured twice after the metal framework was fastened onto each experimental stone cast with 20 Ncm torque. Detorque values were analyzed using the mixed model with the fixed effect of screw and reading and the random effect of model for the repeated measured data at a .05 level of ignificance. Results: The mean detorque values were 7.9 Ncm (Group 1) and 8.1 Ncm (Group 2), and the mean of minimum detorque values were 6.1 Ncm (Group 1) and 6.5 Ncm (Group 2). No statistically significant differences between 2 groups were found and no statistically significant differences among 4 screws were found for detorque values. No statistically significant differences between 2 groups were also found for minimum detorque values. Conclusion: In a multiple external hexagon implant-supported prosthesis, no significant differences between 2 groups were found for detorque values and for minimum detorque values. There seems to be no significant differences in screw joint stability between 2 stone cast groups made with 2 different impression techniques.

• Journal of radiological science and technology
• /
• v.31 no.3
• /
• pp.223-228
• /
• 2008

The most critical point in the medical use of radiation is to minimize the patient's entrance dose while maintaining the diagnostic function. Low-energy photons (long wave X-ray) among diagnostic X-rays are unnecessary because they are mostly absorbed and contribute the increase of patient's entrance dose. The most effective method to eliminate the low-energy photons is to use the filtering plate. The experiments were performed by observing the image quality. The skin entrance dose was 0.3 mmCu (copper) filter. A total of 80 images were prepared as two sets of 40 cuts. In the first set (of 40 cuts), 20 cuts were prepared for the non-filter set and another 20 cuts for the Cu filter of signal + noise image set. In the second set of 40 cuts, 20 cuts were prepared for the non-filter set and another 20 cuts for the Cu filter of non-signal image (noisy image) with random location of diameter 4 mm and 3 mm thickness of acryl disc for ROC signal at the chest phantom. P(S/s) and P(S/n) were calculated and the ROC curve was described in terms of sensitivity and specificity. Accuracy were evaluated after reading by five radiologists. The number of optically observable lesions was counted through ANSI chest phantom and contrast-detail phantom by recommendation of AAPM when non-filter or Cu filter was used, and the skin entrance dose was also measured for both conditions. As the result of the study, when the Cu filter was applied, favorable outcomes were observed on, the ROC Curve was located on the upper left area, sensitivity, accuracy and the number of CD phantom lesions were reasonable. Furthermore, if skin entrance dose was reduced, the use of additional filtration may be required to be considered in many other cases.

• Journal of Environmental Impact Assessment
• /
• v.26 no.6
• /
• pp.538-552
• /
• 2017

In this study, total mercury (THg) of Black-tailed Gull (Larus crassirostris) eggs laid on Baengnyeongdo, West Sea of Korea was analyzed in order to compare the THg concentrations of eggs depending on egg-laying order. The first-laid eggs ($mean{\pm}standard$ error, $234.4{\pm}11.2ng/g\;wet$, n=18, t=8.4, p<0.01) significantly had higher THg concentrations than the second-laid eggs ($182.8{\pm}9.1ng/g\;wet$, n=18). Also, the first-laid eggs had higher values in biometrics (length $63.10{\pm}0.49mm$, t=2.4, p<0.05; width $44.51{\pm}0.19mm$, t=4.3, p<0.01; weight $65.53{\pm}0.87g$, t=4.2, p<0.01) than the second-laid eggs (length $62.37{\pm}0.40mm$, width $43.55{\pm}0.17mm$, and weight $62.48{\pm}0.72g$). These differences might be attributed to the amount of food eaten by females relating to males' courtship feeding pattern (males increase courtship feeding rate before the first eggs are laid, and decrease the rate following the laying of the first eggs). Moreover, the lower food intake of females could diminish the quantities of egg albumen that contains a protein binds to most of methylmercury during the period of egg production. Therefore, it is necessary to consistently apply one of egg selection methods (targeted selection (the first-laid egg or the second-laid egg), random selection, and etc.) in one nest for ensuring comparability of mercury concentrations among monitoring sites and monitoring years.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.337-357
• /
• 2021

Because the growth of paddy rice is affected by meteorological factors, the selection of appropriate meteorological variables is essential to build a rice yield prediction model. This paper examines the suitability of multiple meteorological datasets for the rice yield modeling in South Korea, 1996-2019, and a hindcast experiment for rice yield using a machine learning method by considering the nonlinear relationships between meteorological variables and the rice yield. In addition to the ASOS in-situ observations, we used CRU-JRA ver. 2.1 and ERA5 reanalysis. From the multiple meteorological datasets, we extracted the four common variables (air temperature, relative humidity, solar radiation, and precipitation) and analyzed the characteristics of each data and the associations with rice yields. CRU-JRA ver. 2.1 showed an overall agreement with the other datasets. While relative humidity had a rare relationship with rice yields, solar radiation showed a somewhat high correlation with rice yields. Using the air temperature, solar radiation, and precipitation of July, August, and September, we built a random forest model for the hindcast experiments of rice yields. The model with CRU-JRA ver. 2.1 showed the best performance with a correlation coefficient of 0.772. The solar radiation in the prediction model had the most significant importance among the variables, which is in accordance with the generic agricultural knowledge. This paper has an implication for selecting from multiple meteorological datasets for rice yield modeling.

• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.686-697
• /
• 2018

Due to the advance in remote sensing technology, it has become easier to more frequently obtain high resolution imagery to detect delicate changes in an extensive area, particularly including forest which is not readily sub-classified. Time-series analysis on high resolution images requires to collect extensive amount of ground truth data. In this study, the potential of land coverage mapas ground truth data was tested in classifying high-resolution imagery. The study site was Wonju-si at Gangwon-do, South Korea, having a mix of urban and natural areas. KOMPSAT-3A imagery taken on March 2015 and land coverage map published in 2017 were used as source data. Two pixel-based classification algorithms, Support Vector Machine (SVM) and Random Forest (RF), were selected for the analysis. Forest only classification was compared with that of the whole study area except wetland. Confusion matrixes from the classification presented that overall accuracies for both the targets were higher in RF algorithm than in SVM. While the overall accuracy in the forest only analysis by RF algorithm was higher by 18.3% than SVM, in the case of the whole region analysis, the difference was relatively smaller by 5.5%. For the SVM algorithm, adding the Majority analysis process indicated a marginal improvement of about 1% than the normal SVM analysis. It was found that the RF algorithm was more effective to identify the broad-leaved forest within the forest, but for the other classes the SVM algorithm was more effective. As the two pixel-based classification algorithms were tested here, it is expected that future classification will improve the overall accuracy and the reliability by introducing a time-series analysis and an object-based algorithm. It is considered that this approach will contribute to improving a large-scale land planning by providing an effective land classification method on higher spatial and temporal scales.