• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.2
• /
• pp.48.1-48.1
• /
• 2018

We report on a series of science articles presented in the Children's magazine 고래가그랬어. The monthly articles (appearing since 2016) highlight current issues in Physics and Astronomy with particular emphasis on science being conducted in Korea. Reporting is performed by interviewing experts in their respective fields. In an effort to encourage children to envisage themselves as scientists, interviews are taken predominantly from Korean early-career researchers. Gender balance is obtained through a careful selection of interviewees ensuring that children are exposed to a broad cross-section of science researchers. This series has introduced children to the 1st detection of Gravitational Waves, the KMTnet telescope system, the Korean Very Long Baseline Interferometric Network, KGMT, IBS Axion experiments, and many other experiments and discoveries.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• Journal of Ocean Engineering and Technology
• /
• v.38 no.3
• /
• pp.115-123
• /
• 2024

USBL systems are essential for providing accurate positions of autonomous underwater vehicles (AUVs). On the other hand, the accuracy can be degraded by outliers because of the environmental conditions. A failure to address these outliers can significantly impact the reliability of underwater localization and navigation systems. This paper proposes a novel outlier rejection algorithm for AUV localization using Voronoi diagrams and query point calculation. The Voronoi diagram divides data space into Voronoi cells that center on ultra-short baseline (USBL) data, and the calculated query point determines if the corresponding USBL data is an inlier. This study conducted experiments acquiring GPS and USBL data simultaneously and optimized the algorithm empirically based on the acquired data. In addition, the proposed method was applied to a sensor fusion algorithm to verify its effectiveness, resulting in improved pose estimations. The proposed method can be applied to various sensor fusion algorithms as a preprocess and could be used for outlier rejection for other 2D-based location sensors.

• Journal of the Korean Society of Food Culture
• /
• v.15 no.4
• /
• pp.269-277
• /
• 2000

A survey was conducted to examine the knowledge and acceptance of food irradiation in order to provide baseline data required in the development of food irradiation education programs for college students. 150 students majoring in food and nutrition or food technology in the Chungnam National University were chosen for a survey. The results are as follows. First, college students' knowledge about food irradiation is scanty. Knowledge assessment showed that 56% of the participants had previously heard of food irradiation. 68% of the respondents thought that radioactivity remains in food after irradiation and 25.3% of them were not sure whether radioactivity remains in food after irradiation or not. Only half of the respondents thought that nutrient loss due to irradiation is equal to or lower than that due to cooking or freezing. Second, approximately 56% of the respondents showed that food irradiation is somewhat or strongly needed for meat or fish; whereas, over 60% of them showed that food irradiation is not needed for grain, vegetable and fruit. Almost 40% of the respondents were seriously concerned about irradiation of vegetables and fruits; whereas, they showed less concern about spice irradiation. More than half of the respondents were not willing to use irradiated food in all the six food groups. Third, the correlation analysis showed that the need of food irradiation is negatively correlated with concerning about the irradiated fish and fruits, but positively correlated with willingness to use irradiated food in all the five food groups, except in spices. Concern about the irradiated food is negatively correlated with willingness to use irradiated food from all the six food groups. Fourth, almost all the respondents (over 90%) agreed that the irradiated food labeling is required as well as the development of proper methods to identify irradiated foods.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.668-673
• /
• 2017

Deep neural networks have shown remarkable performance in various fields of pattern recognition such as voice recognition, image recognition and object detection. However, underlying mechanisms of the network have not been fully revealed. In this paper, we focused on empirical analysis of the network parameters. The Faster R-CNN(region-based convolutional neural network) was used as a baseline network of our work and three important parameters were analyzed: the dropout ratio which prevents the overfitting of the neural network, the size of the anchor boxes and the activation function. We also compared the performance of dropout and batch normalization. The network performed favorably when the dropout ratio was 0.3 and the size of the anchor box had not shown notable relation to the performance of the network. The result showed that batch normalization can't entirely substitute the dropout method. The used leaky ReLU(rectified linear unit) with a negative domain slope of 0.02 showed comparably good performance.

• Journal of the Korean Society for Railway
• /
• v.14 no.4
• /
• pp.320-326
• /
• 2011

This paper proposes a baseline-free SHM technique in which the time-reversal process of Lamb waves and the imaging method are used. The proposed SHM technique has three distinct features when compared with the authors' previously proposed one: (1) It use the reconstructed signal for damage diagnosis, without need to extract the damage signal as the difference between reconstructed signal and initial input signal; (2) It use the imaging method based on the time-offlight information from the reconstructed signal, instead of using a pattern comparison method; (3) In order to make the damage image more clear, the modified mathematical definition of damage image in a pixel is used. The proposed SHM technique is evaluated through the damage detection experiment for an aluminum plate with damage at different locations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1841-1857
• /
• 2023

CenterNet, a novel object detection algorithm without anchor based on key points, regards the object as a single center point for prediction and directly regresses the object's height and width. However, because the objects have different sizes, directly regressing their height and width will make the model difficult to converge and lose the intrinsic relationship between object's width and height, thereby reducing the stability of the model and the consistency of prediction accuracy. For this problem, we proposed an algorithm based on the regression of the diagonal half-length and the center angle, which significantly compresses the solution space of the regression components and enhances the intrinsic relationship between the decoded components. First, encode the object's width and height into the diagonal half-length and the center angle, where the center angle is the angle between the diagonal and the vertical centreline. Secondly, the predicted diagonal half-length and center angle are decoded into two length components. Finally, the position of the object bounding box can be accurately obtained by combining the corresponding center point coordinates. Experiments show that, when using CenterNet as the improved baseline and resnet50 as the Backbone, the improved model achieved 81.6% and 79.7% mAP on the VOC 2007 and 2012 test sets, respectively. When using Hourglass-104 as the Backbone, the improved model achieved 43.3% mAP on the COCO 2017 test sets. Compared with CenterNet, the improved model has a faster convergence rate and significantly improved the stability and prediction accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Korean Journal of Radiology
• /
• v.24 no.9
• /
• pp.890-902
• /
• 2023

Objective: The clinical impact of artificial intelligence-based computer-aided detection (AI-CAD) beyond diagnostic accuracy remains uncertain. We aimed to investigate the influence of the clinical implementation of AI-CAD for chest radiograph (CR) interpretation in daily practice on the rate of referral for chest computed tomography (CT). Materials and Methods: AI-CAD was implemented in clinical practice at the Seoul National University Hospital. CRs obtained from patients who visited the pulmonology outpatient clinics before (January-December 2019) and after (January-December 2020) implementation were included in this study. After implementation, the referring pulmonologist requested CRs with or without AI-CAD analysis. We conducted multivariable logistic regression analyses to evaluate the associations between using AI-CAD and the following study outcomes: the rate of chest CT referral, defined as request and actual acquisition of chest CT within 30 days after CR acquisition, and the CT referral rates separately for subsequent positive and negative CT results. Multivariable analyses included various covariates such as patient age and sex, time of CR acquisition (before versus after AI-CAD implementation), referring pulmonologist, nature of the CR examination (baseline versus follow-up examination), and radiology reports presence at the time of the pulmonology visit. Results: A total of 28546 CRs from 14565 patients (mean age: 67 years; 7130 males) and 25888 CRs from 12929 patients (mean age: 67 years; 6435 males) before and after AI-CAD implementation were included. The use of AI-CAD was independently associated with increased chest CT referrals (odds ratio [OR], 1.33; P = 0.008) and referrals with subsequent negative chest CT results (OR, 1.46; P = 0.005). Meanwhile, referrals with positive chest CT results were not significantly associated with AI-CAD use (OR, 1.08; P = 0.647). Conclusion: The use of AI-CAD for CR interpretation in pulmonology outpatients was independently associated with an increased frequency of overall referrals for chest CT scans and referrals with subsequent negative results.

• The Journal of the Korean Society for Microbiology
• /
• v.35 no.2
• /
• pp.181-190
• /
• 2000

To investigate resistance to lamivudine (3TC), we examined the incidence of M184V in 20 HIV-1 patients treated with 3TC for $13.1{\pm}9$ months. Fourteen of 20 patients had been exposed to zidovudine (ZDV) or didanosine (ddI) prior to 3TC therapy. Nested PCR targeting to reverse transcriptase (RT) and direct sequencing were performed for peripheral blood mononuclear cells sampled serially. There were resistance mutations to ZDV in at least 9 patients at baseline, although there was no resistance mutation to 3TC. We could detect M184V in 6 (30%) out of 20 patients. The incidence of M184V increased as the duration of therapy prolongs (13% in samples <12 months; 47% in samples ${\ge}12$ months). The frequency of mutation M184V was higher in patients with previous mutation to ZDV than in patients with wild type. Resistance mutation was not detected in 7 patients. This study shows that resistance to 3TC tends to develop rapidly in patients with baseline mutations or two drugs combination therapy than in those treated simultaneously with triple drugs. This report is the first on resistance to 3TC in Korean AIDS patients.