• Child Health Nursing Research
• /
• v.19 no.1
• /
• pp.1-11
• /
• 2013

Purpose: This study was done to develop a scenario and evaluate student performance in simulation learning of care for children with respiratory distress syndrome in neonatal intensive care units. Methods: To test the application effect, a one group pre-test design was applied. The scenario based on actual patients and textbook material was developed through several meetings of experts. The scenario was used with 17 groups of 55 senior nursing students who participated voluntarily. Results: Contents were organized focusing on the nursing process for simulation learning. In the application of knowledge and skills, nursing students had high scores in the contents of observation of oxygen saturation, and care to relieve dyspnea. Participants' ability, especially in suction and oxygen supply in the evaluation of objective structured clinical examination was not adequate. There was a significant positive correlation between problem-solving ability and satisfaction in learning. Conclusion: The respiratory distress syndrome simulation scenario developed in this study was an effective tool to give students experience in problem solving and critical thinking ability under conditions similar to reality. The development of various scenarios for child nursing care is needed.

• Korean Chemical Engineering Research
• /
• v.50 no.2
• /
• pp.223-228
• /
• 2012

The low-temperature pyrolysis of ABS, polyethylene (PE) and an ABS-polyethylene (ABS-PE) mixture was conducted in a batch reactor at $450^{\circ}C$. The conversion and the product yield were measured as a function of the reaction time with a variation of the mixture composition. The oil products formed during pyrolysis were classified into gas, gasoline, kerosene, gas oil and heavy oil according to the petroleum product quality standard of the Ministry of Knowledge Economy. The pyrolysis conversion increases with an increase in the content of PE. The yield of the pyrolytic products was ranked as heavy oil>gas>gasoline>gas oil>kerosene as the content of PE in the mixture increases.

• Journal of Korea Multimedia Society
• /
• v.25 no.7
• /
• pp.895-902
• /
• 2022

Building segmentation using satellite imagery such as EO (Electro-Optical) and SAR (Synthetic-Aperture Radar) images are widely used due to their various uses. EO images have the advantage of having color information, and they are noise-free. In contrast, SAR images can identify the physical characteristics and geometrical information that the EO image cannot capture. This paper proposes a learning framework for efficient building segmentation that consists of a teacher-student-based privileged knowledge distillation and deformable convolution block. The teacher network utilizes EO and SAR images simultaneously to produce richer features and provide them to the student network, while the student network only uses EO images. To do this, we present objective functions that consist of Kullback-Leibler divergence loss and knowledge distillation loss. Furthermore, we introduce deformable convolution to avoid pixel-level noise and efficiently capture hard samples such as small and thin buildings at the global level. Experimental result shows that our method outperforms other methods and efficiently captures complex samples such as a small or narrow building. Moreover, Since our method can be applied to various methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1598-1605
• /
• 2021

Recently, convolutional neural networks (CNNs) have been widely used with excellent performance in various computer vision fields, including super-resolution (SR). However, CNN is computationally intensive and requires a lot of memory, making it difficult to apply to limited hardware resources such as mobile or Internet of Things devices. To solve these limitations, network lightening studies have been actively conducted to reduce the depth or size of pre-trained deep CNN models while maintaining their performance as much as possible. This paper aims to lighten the SR CNN model, SRGAN, using the knowledge distillation among network lightening technologies; thus, it proposes four techniques with different methods of transferring the knowledge of the teacher network to the student network and presents experiments to compare and analyze the performance of each technique. In our experimental results, it was confirmed through quantitative and qualitative evaluation indicators that student networks with knowledge transfer performed better than those without knowledge transfer, and among the four knowledge transfer techniques, the technique of conducting adversarial learning after transferring knowledge from the teacher generator to the student generator showed the best performance.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.313-315
• /
• 2021

Timely and accurate diagnosis of lung diseases using Chest X-ray images has been gained much attention from the computer vision and medical imaging communities. Although previous studies have presented the capability of deep convolutional neural networks by achieving competitive binary classification results, their models were seemingly unreliable to effectively distinguish multiple disease groups using a large number of x-ray images. In this paper, we aim to build an advanced approach, so-called Ensemble Knowledge Distillation (EKD), to significantly boost the classification accuracies, compared to traditional KD methods by distilling knowledge from a cumbersome teacher model into an ensemble of lightweight student models with parallel branches trained with ground truth labels. Therefore, learning features at different branches of the student models could enable the network to learn diverse patterns and improve the qualify of final predictions through an ensemble learning solution. Although we observed that experiments on the well-established ChestX-ray14 dataset showed the classification improvements of traditional KD compared to the base transfer learning approach, the EKD performance would be expected to potentially enhance classification accuracy and model generalization, especially in situations of the imbalanced dataset and the interdependency of 14 weakly annotated thorax diseases.

• The Journal of Korean Academy of Prosthodontics
• /
• v.49 no.1
• /
• pp.57-64
• /
• 2011

Purpose: The purpose of this study was to compare the cleansing performance of a distilled water, a diluted solution of sodium hypochlorite as a household bleaching cleanser and three alkaline peroxide cleansers in vivo plaque deposits by using scanning electron microscope. Materials and methods: Five individuals were selected from department of the prosthodontics in Pusan National University Hospital, and each of them was inserted with specimens for plaque accumulation in their temporary dentures for 48 hours. The specimens were removed and cleaned by each cleansing agents for 8 hours. Scanning electron micrographs were made from the specimens at a magnification of ${\times}2,000$. A panel of ten persons with a dental or paradental background, but not directly involved in the study, was selected to analyze the photomicrographs to determine which denture cleanser was more effective in removing plaque. Results: Diluted solution of sodium hypochlorite was the most effective at removing plaque following $Polident^{(R)}$, $Cleadent^{(R)}e$, $Bonyplus^{(R)}$ and distilled water in order. But there was no significant difference of cleansing efficacy between diluted solution of sodium hypochlorite and $Polident^{(R)}$, $Polident^{(R)}$ and $Cleadent^{(R)}e$, $Cleadent^{(R)}e$ and $Bonyplus^{(R)}$, respectively (P > .05). Alkaline peroxide cleansers by themselves cannot adequately remove accumulated plaque deposits, especially if the deposits are heavy. Corrosion could be seen on the surface of non-precious alloy specimens immersed in diluted solution of sodium hypochlorite. Conclusion: It is recommended to use of alkaline peroxide type cleansers with brushing whenever possible, since denture cleanliness is often poor due to the relative inefficiency of these cleansers.

• Korean Chemical Engineering Research
• /
• v.49 no.4
• /
• pp.417-422
• /
• 2011

The low temperature pyrolysis of ABS resin has been carried out in a batch reactor under the atmospheric pressure. The effect of the reaction temperature on the yield of pyrolytic oils has been determined in the present study. The oil products formed during pyrolysis were classified into gas, gasoline, kerosene, gas oil and heavy oil according to the petroleum product quality standard of Ministry of Knowledge Economy. The conversion reaches 80% after 60 min at $500^{\circ}C$ in the pyrolysis of ABS resin. The amount of the final product was ranked as gas heavy oil > gasoline > gas oil > kerosen based on the yield. The yields of heavy oil and gas oil increase with an increase in the reaction time and temperature.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• Clean Technology
• /
• v.16 no.1
• /
• pp.26-32
• /
• 2010

The low temperature pyrolysis of polypropylene (PP), polystyrene (PS) and polypropylene-polystyrene (PP-PS) mixture in a batch reactor at the atmospheric pressure and $450^{\circ}C$ was conducted to investigate the synergy effect of PP-PS mixture on the yield of pyrolytic oil. The pyrolysis time was varied from 20 to 80 mins. The products formed during pyrolysis were classified into gas, gasoline, kerosene, gas oil and heavy oil according to the petroleum product quality standard of Ministry of Knowledge Economy. The analysis of the product oils by GC/MS(Gas chromatography/Mass spectrometry) showed that new components were not detected by mixing of PP and PS. There was no synergy effect according to the mixing of PP and PS. Conversions and yields of PP-PS mixtures were linearly dependent on the mixing ratio of samples except for heavy oil yields. Heavy oil yields showed almost constant regardless of the mixing ratio.