• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.195-202
• /
• 2006

The infiltration route analysis is a military application using geospatial information technology. The result of the analysis would present vulnerable routes for potential enemy infiltration. In order to find the susceptible routes, optimal path search algorithms (Dijkstra's and $A^*$) were used to minimize the cost function, summation of detection probability. The cost function was produced by capability of TOD (Thermal Observation Device), results of viewshed analysis using DEM (Digital Elevation Model) and two related geospatial information coverages (obstacle and vegetation) extracted from VITD (Vector product Interim Terrain Data). With respect to 50m by 50m cells, the individual cost was computed and recorded, and then the optimal infiltration routes was found while minimizing summation of the costs on the routes. The proposed algorithm was experimented in Daejeon region in South Korea. The test results show that Dijkstra's and $A^*$ algorithms do not present significant differences, but A* algorithm shows a better efficiency. This application can be used for both infiltration and surveillance. Using simulation of moving TOD, the most vulnerable routes can be detected for infiltration purpose. On the other hands, it can be inversely used for selection of the best locations of TOD. This is an example of powerful geospatial solution for military application.

• Korean Journal of Culture and Social Issue
• /
• v.14 no.4
• /
• pp.1-18
• /
• 2008

The present study examined the accuracy of polygraph tests through two types of statistical methods with unknown ground truth. One method evaluated the accuracy based on the rates of agreements between polygraph test results of crime suspects and prosecutors' indictment decisions for them. Those crime suspects were tested with polygraph by the Prosecutors' Office of the Republic of Korea between 2000 and 2004. The other method estimated the accuracy by using the latent class analysis based on the frequency distributions of the polygraph results and indictments during 2006. Excluding cases that were 'inconclusive' on the polygraph test, the study showed that the accuracy of the polygraph tests is .914 (SE=.004) for the 2000-2004 data, and .885 (SE=.021) for the 2006 data. With the inclusion of 'inconclusive' cases in the 2006 data, the results from the latent class analysis showed the accuracy in the range between .707 and .734 (SE=.027~.031), with false positives between .078 and .087 (SE=.019~.023), and false negatives between .029 and .078 (SE=.010~.023). The probability that the polygraph test correctly classifies subjects appeared to be in the range between .912 and .925 (SE=.013-.016) for those who lie, and in the range between .867 to .955 (SE=.011-.040) for those who tell the truth.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Food Science and Preservation
• /
• v.30 no.3
• /
• pp.459-471
• /
• 2023

The Bayesian network (BN) model was applied to analyze the characteristic variables that affect compliance with safety inspections of farmed eel during the production stage, using the data from 30,063 cases of eel aquafarm safety inspection in the Integrated Food Safety Information Network (IFSIN) from 2012 to 2021. The dataset for establishing the BN model included 77 non-conforming cases. Relevant HACCP data, geographic information about the aquafarms, and environmental data were collected and mapped to the IFSIN data to derive explanatory variables for nonconformity. Aquafarm HACCP certification, detection history of harmful substances during the last 5 y, history of nonconformity during the last 5 y, and the suitability of the aquatic environment as determined by the levels of total coliform bacteria and total organic carbon were selected as the explanatory variables. The highest achievable eel aquafarm noncompliance rate by manipulating the derived explanatory variables was 24.5%, which was 94 times higher than the overall farmed eel noncompliance rate reported in IFSIN between 2017 and 2021. The established BN model was validated using the IFSIN eel aquafarm inspection results conducted between January and August 2022. The noncompliance rate in the validation set was 0.22% (15 nonconformances out of 6,785 cases). The precision of BN model prediction was 0.1579, which was 71.4 times higher than the non-compliance rate of the validation set.

• Journal of the Korean Society of Radiology
• /
• v.81 no.3
• /
• pp.610-619
• /
• 2020

Purpose The study aimed to investigate the role of Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) in predicting incidental prostate cancer (PCa) or urothelial carcinoma (UCa) extension in urinary bladder (UB) cancer patients. Materials and Methods A total of 72 UB cancer patients who underwent radical cystoprostatectomy and 3 Tesla multiparametric MRI before surgery were enrolled. PI-RADS v2 ratings were assigned by two independent radiologists. All prostate specimens were examined by a single pathologist. We compared the multiparametric MRI findings rated using PI-RADS v2 with the pathologic data. Results Of the 72 UB cancer patients, 29 had incidental PCa (40.3%) and 20 showed UCa extension (27.8%), with an overlap for 3 patients. With a score of 4 as the cut-off value for predicting incidental PCa, the diagnostic accuracy was 65.3%, specificity was 90.7%, and positive predictive value (PPV) was 66.7%. The diagnostic accuracy for incidental UCa extension was 47.2%, specificity was 92.3%, and PPV was 83.3%. Conclusion Despite the low diagnostic accuracy, the PPV and specificity were relatively high. Therefore, PI-RADS v2 scores of 1, 2, or 3 may help exclude the probability of incidental PCa or UCa extension.

• Atmosphere
• /
• v.34 no.3
• /
• pp.305-317
• /
• 2024

The study examines the effects of parameters that define the characteristics of raindrops on the simulated precipitation during the summer season over Korea using the Weather Research and Forecasting (WRF) Double-Moment 6-class (WDM6) cloud microphysics scheme. Prescribed parameters, defining the characteristics of hydrometeors in the WDM6 scheme such as a_R, b_R, and f_R in the fall velocity (V_R) - diameter (D_R) relationship and shape parameter (𝜇_R) in the number concentration (N_R) - D_R relationship, presents different values compared to the observed data from Two-Dimensional Video Disdrometer (2DVD) at Boseong standard meteorological observatory during 2018~2019. Three experiments were designed for the heavy rainfall event on August 8, 2022 using WRF version 4.3. These include the control (CNTL) experiment with original parameters in the WDM6 scheme; the MUR experiment, adopting the 50th percentile observation value for 𝜇_R; and the MEDI experiment, which uses the same 𝜇_R as MUR, but also includes fitted values for a_R, b_R, and f_R from the 50th percentile of the observed V_R - D_R relationship. Both sensitivity experiments show improved precipitation simulation compared to the CNTL by reducing the bias and increasing the probability of detection and equitable threat scores. In these experiments, the raindrop mixing ratio increases and its number concentration decreases in the lower atmosphere. The microphysics budget analysis shows that the increase in the rain mixing ratio is due to enhanced source processes such as graupel melting, vapor condensation, and accretion between cloud water and rain. Our study also emphasizes that applying the solely observed 𝜇_R produces more positive impact in the precipitation simulation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.825-832
• /
• 2020

The detection of estrus is very important for the successful reproductive efficiency of cattle. This has prompted the development of electronic estrus detection techniques by using the characterization of estrus behavior. The objective of this study was to investigate the changes in physical activity, mounting behavior and vocalization during estrus in Hanwoo (Korean native cattle). Bio-telemetry devices were attached to 4 multiparous Hanwoo and physical activity was compared, namely mounting behavior and vocalization for 6 days (from 2 days before the day of estrus to 3 days after the day of estrus). Physical activity rapidly increased on the day of estrus (p<0.001) and was frequently observed at night time. Mounting behavior gradually increased, starting from 2 days before the day of estrus and reached its highest level on the day of estrus (p<0.01). The circadian rhythm showed irregularities during this entire period (p>0.05). There was no significant difference in vocalization during the experiment period (p>0.05). In conclusion, we assumed that mounting behavior is an early indicator to detect estrus in Hanwoo and if both mounting behavior and physical activity are considered together it would be possible to detect estrus with a higher probability. Further studies with more information from different sources regarding the measuring of estrus in Hanwoo are needed.

• Clinical and Experimental Pediatrics
• /
• v.51 no.7
• /
• pp.736-741
• /
• 2008

Purpose : The incidence of thromboembolic episodes in children with nephrotic syndrome (NS) is low; however, these episodes are often severe. Moreover, both pulmonary thromboembolism (PTE) and renal vein thrombosis (RVT) rarely show clinical symptoms. This study was performed to determine the benefits of routine screening in the detection of thrombosis in childhood NS. Methods : Among 62 children with nephrotic syndrome, a total of 54 children (43 males, 11 females) were included in this study. When the patients experienced their first NS episode, we performed renal Doppler ultrasonography in order to detect RVT. To rule out the possibility of PTE, a lung perfusion scan was performed. Computed tomographic (CT) pulmonary angiography was recommended to patients who showed possible signs of PTE. All patients were evaluated for clinical signs of thrombosis, biochemical indicators of renal disease, as well as clotting and thrombotic parameters. Results : RVT or related clinical symptoms were not observed in any children. Based on the findings of the lung perfusion scans, 15 patients (27.8%) were observed with as a high probability of PTE. We were able to perform a CT pulmonary angiography only on 12 patients, and 5 patients were diagnosed with PTE (prevalence 8.1%). The serum fibrinogen level in the group with PTE was significantly higher ($776.7{\pm}382.4mg/dL$, P<0.05) than that in the group without PTE, and other parameters were not significantly different between each group. Conclusion : Further studies are required for clarifying the role of renal Doppler ultrasonography for the detection of RVT in NS. Children with NS who developed non-specific respiratory symptoms should be evaluated for the diagnosis of PTE. In the management of NS, a lung perfusion scan should be performed at the time of the initial episode of NS regardless of the pulmonary symptoms, since patients having PTE are either often asymptomatic, or present with nonspecific symptoms.