• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.473-478
• /
• 2005

The gastric cancer takes the great part of the cancer occurrence and the mortality from cancer in Korea, and the early detection of gastric cancer is very important in the treatment and convalescence. This paper. for the early detection of gastric cancer, Proposes the analysis system of endoscopic image of the stomach that detects the abnormal region by using the change of color in the image and provides the surface tissue information to the detector. While the advanced inflammation and the cancer may be easily detected, the early inflammation and the cancer have a difficulty in detection and require the more attention lot detection. This paper, at first, converts the endoscopic image to the Image of IHb(Index of Hemoglobin) model and removes noises incurred by illumination, and next, automatically detects the regions suspected as cancer and provides the related information to the detector, or provides the surface tissue information for the regions appointed by the detector. This paper does not intend to provide the final diagnosis of the detected abnormal regions as gastric cancer, but provides the supplementary mean that reduces the load and mistaken diagnosis of the detector by automatically detecting the abnormal regions being not easily detected by human eyes and providing the additional information for the diagnosis. The experiments using practical endoscopic images for performance evaluation showed that the proposed system is effective in the analysis of endoscopic image of the stomach.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.49-59
• /
• 2023

There are various items in the safety and health standards of the manufacturing industry, but they can be divided into work-related diseases and musculoskeletal diseases according to the standards for sickness and accident victims. Musculoskeletal diseases occur frequently in manufacturing and can lead to a decrease in labor productivity and a weakening of competitiveness in manufacturing. In this paper, to detect the musculoskeletal harmful factors of manufacturing workers, we defined the musculoskeletal load work factor analysis, harmful load working postures, and key points matching, and constructed data for Artificial Intelligence(AI) learning. To check the effectiveness of the suggested dataset, AI algorithms such as YOLO, Lite-HRNet, and EfficientNet were used to train and verify. Our experimental results the human detection accuracy is 99%, the key points matching accuracy of the detected person is @AP0.5 88%, and the accuracy of working postures evaluation by integrating the inferred matching positions is LEGS 72.2%, NECT 85.7%, TRUNK 81.9%, UPPERARM 79.8%, and LOWERARM 92.7%, and considered the necessity for research that can prevent deep learning-based musculoskeletal diseases.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.

• The Journal of Korean Society of Virology
• /
• v.26 no.2
• /
• pp.259-267
• /
• 1996

In order to evaluate the effect of viral load on the prognosis of human immunodeficiency virus-1 (HIV-1)-infected individuals, immune complex dissociated (ICD) serum p24 antigen (p24) by acid treatment was retrospectively measured for 50 HIV-infected patients for 60 months. Among them, 27 patients were p24 positive (p24+) above 25pg/ml for $40.4{\pm}12$ months and 23 patients were negative (p24-). Follow-up periods from HIV diagnosis were $63.0{\pm}19$ months (range; 40-112) for the p24+ and $68.4{\pm}19$ months (range; 38-106) for the p24-, respectively (P>0.05)Mean CD4+T cell counts in the p24+ group decreased from $473{\pm}$277/ul (median;373) to $157{\pm}150/ul$ (median; 111) for $60{\pm}16$ months (5.3/month P280/ul (median; 476) to $432{\pm}285/ul$ (median;382) for $63{\pm}19$ months (2.5/month, P<0.01). From CD4+T cell count >200/ul, the patient who progressed to AIDS of <200/ul were 13 of 23 (56%) in the p24+ and 4 of 22 (18%) in p24-, respectively (p<0.01). And the number of death in two groups were 6 (22%) and 1 (4%), respectively (p<0.01). Presumed survival in two groups were about 12 and 24.5 years. These data suggest that viral load itself be very important for the prognosis of HIV-infected patients.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.5
• /
• pp.365-372
• /
• 1998

The method of measuring the nonlinear effect of ultrasonic waves is suggested as a new approach for the effective evaluation of material degradation. In sonic wave propagation, the existence of nonlinear effect can be demonstrated by the generation of higher order harmonic waves. So, at first, the mechanism of generating higher order harmonic components due to nonlinear effect was explained by using nonlinear elasticity. Next, we attempted to measure how much of the higher order harmonic component was generated in the degraded material. For this purpose, a measurement system mainly based on a high-powered nonlinear ultrasonic signal analysis system was constructed, and SS41 and SS45 specimen intentionally degraded by tensile load and fatigue load were tested. From the results, we confirmed that the measurement of nonlinear acoustic effect may be useful for the evaluation of material degradation.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.2
• /
• pp.169-176
• /
• 2013

To generate the walking path of a humanoid robot in an unknown environment, the shapes of obstacles around the robot should be detected accurately. However, doing so incurs a very large computational cost. Therefore this study proposes a method to classify the obstacle shape into three types: a shape small enough for the robot to go over, a shape planar enough for the robot foot to make contact with, and an uncertain shape that must be avoided by the robot. To classify the obstacle shape, first, the range and the number of the obstacles is detected. If an obstacle can make contact with the robot foot, the shape of an obstacle is accurately derived. If an obstacle has uncertain shape or small size, the shape of an obstacle is not detected to minimize the computational load. Experimental results show that the proposed algorithm efficiently classifies the shapes of obstacles around the robot in real time with low computational load.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2002.05a
• /
• pp.134-139
• /
• 2002

Fracture behaviors of pipes with local wall thinning are very important for the integrity of nuclear power plant. However, effects of local wall thinning on strength and fracture behaviors of piping system were not well studied. Acoustic emission(AE) has been widely used in various fields because of its extreme sensitivity, dynamic detection ability and location of growing defects. In this study, we investigated failure modes of locally wall thinned pipes and AE signals by bending test. From test results, we could be divided four types of failure modes of ovalization, crack initiation after ovalization, local buckling and crack initiation after local buckling. And fracture behaviors such as elastic region, yielding range, plastic deformation range and crack progress could be evaluated by AE counts, accumulative counts and time-frequency analysis during bending test. It is expected to be basic data that can protect a risk according to local wall thinning of pipes, as a real time test of AE.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.2
• /
• pp.133-138
• /
• 2016

Force control and collision detection for a robot are usually conducted using a 6-axis force/torque sensor mounted at the end-effector. However, this scheme suffers from high-cost and the inability to detect collisions at the robot body. As an alternative, joint torque sensors embedded in each joint were used, which also suffered from various errors in torque measurement. To resolve this problem, a robot joint module with an improved joint torque sensor is proposed in this study. In the proposed torque sensor, a cross-roller bearing and disk-type coupling are added to prevent the moment load from adversely affecting the measurement of the joint torque under consideration. This joint design also aims to reduce the stress induced during the assembly process of the sensor. The performance of the proposed joint torque sensor was verified through various experiments.

• Journal of the Korean Society of Safety
• /
• v.12 no.3
• /
• pp.166-172
• /
• 1997

The BEF on the radial distribution line refers to a class of ground faults in which the load-side power line only is grounded, with the distribution line broken into two parts, the source-side and the load-side. Because its mechanism is remarkably different from that of other earth faults, the fault current is very low, and then difficult to detect the BEF. Thus, it is necessary to analyze its properties and to find an appropriate method that can economically protect the BEF of nonautomation area in the substation. As a result of analyzing the BEF data obtained by the RTDS, EMTP simulation, and the field test data of ETSA, we believe that it is the dominant factor in distinguishing the BEF from normal conditions by a criterion value that is appropriately handled from the zero-sequence current. Thus, with this criterion value, a BEF detecting algorithm is constructed which measures the variations of the zero-sequence current and processes then properly so as to make the fault decision. To prove the accuracy of this algorithm, it is compared with the field test data of ETSA under various conditions. The results show that the proposed algorithm is accurate.

• Journal of the Korean Ceramic Society
• /
• v.39 no.8
• /
• pp.735-741
• /
• 2002

This paper investigates circularity of fly ashes using the digital image processing. Fly ashes directly collect from electrostatic precipitator when the load of conditions of boiler are changed at a coal-fired power plant. Circularity measurement can be accomplished in five steps: ① image acquisition, ② grey image processing, ③ detection the component to measure ④ binary image processing ⑤ feature measurement. The mean circularity of fly ashes is in the range of 0.78 to 0.83. fly ashes collected from the same hopper has similar circularity regardless of the load of boiler and circularity increases as going from the 1st hopper to 3rd one, namely as particle size become finer.