• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3359-3366
• /
• 2023

In this study, a spiking cortical model (SCM) based n-g discrimination method is proposed. The SCM-based algorithm is compared with three other methods, namely: (i) the pulse-coupled neural network (PCNN), (ii) the charge comparison, and (iii) the zero-crossing. The objective evaluation criteria used for the comparison are the FoM-value and the time consumption of discrimination. Experimental results demonstrated that our proposed method outperforms the other methods significantly with the highest FoM-value. Specifically, the proposed method exhibits a 34.81% improvement compared with the PCNN, a 50.29% improvement compared with the charge comparison, and a 110.02% improvement compared with the zero-crossing. Additionally, the proposed method features the second-fastest discrimination time, where it is 75.67% faster than the PCNN, 70.65% faster than the charge comparison and 38.4% slower than the zero-crossing. Our study also discusses the role and change pattern of each parameter of the SCM to guide the selection process. It concludes that the SCM's outstanding ability to recognize the dynamic information in the pulse signal, improved accuracy when compared to the PCNN, and better computational complexity enables the SCM to exhibit excellent n-γ discrimination performance while consuming less time.

• Molecules and Cells
• /
• 제38권2호
• /
• pp.145-150
• /
• 2015

Continuous intra- and extracellular stresses induce disorder of $Ca^{2+}$ homeostasis and accumulation of unfolded protein in the endoplasmic reticulum (ER), which results in ER stress. Severe long-term ER stress triggers apoptosis signaling pathways, resulting in cell death. Neural epidermal growth factor-like like protein 2 (NELL2) has been reported to be important in protection of cells from cell death-inducing environments. In this study, we investigated the cytoprotective effect of NELL2 in the context of ER stress induced by thapsigargin, a strong ER stress inducer, in Cos7 cells. Overexpression of NELL2 prevented ER stress-mediated apoptosis by decreasing expression of ER stress-induced C/EBP homologous protein (CHOP) and increasing ER chaperones. In this context, expression of anti-apoptotic Bcl-xL was increased by NELL2, whereas NELL2 decreased expression of pro-apoptotic proteins, such as cleaved caspases 3 and 7. This anti-apoptotic effect of NELL2 is likely mediated by extracellular signal-regulated kinase (ERK) signaling, because its inhibitor, U0126, inhibited effects of NELL2 on the expression of anti- and pro-apoptotic proteins and on the protection from ER stress-induced cell death.

• Journal of Radiation Protection and Research
• /
• 제47권3호
• /
• pp.111-133
• /
• 2022

The exciting advancement related to the "modeling of digital human" in terms of a computational phantom for radiation dose calculations has to do with the latest hype related to deep learning. The advent of deep learning or artificial intelligence (AI) technology involving convolutional neural networks has brought an unprecedented level of innovation to the field of organ segmentation. In addition, graphics processing units (GPUs) are utilized as boosters for both real-time Monte Carlo simulations and AI-based image segmentation applications. These advancements provide the feasibility of creating three-dimensional (3D) geometric details of the human anatomy from tomographic imaging and performing Monte Carlo radiation transport simulations using increasingly fast and inexpensive computers. This review first introduces the history of three types of computational human phantoms: stylized medical internal radiation dosimetry (MIRD) phantoms, voxelized tomographic phantoms, and boundary representation (BREP) deformable phantoms. Then, the development of a person-specific phantom is demonstrated by introducing AI-based organ autosegmentation technology. Next, a new development in GPU-based Monte Carlo radiation dose calculations is introduced. Examples of applying computational phantoms and a new Monte Carlo code named ARCHER (Accelerated Radiation-transport Computations in Heterogeneous EnviRonments) to problems in radiation protection, imaging, and radiotherapy are presented from research projects performed by students at the Rensselaer Polytechnic Institute (RPI) and University of Science and Technology of China (USTC). Finally, this review discusses challenges and future research opportunities. We found that, owing to the latest computer hardware and AI technology, computational human body models are moving closer to real human anatomy structures for accurate radiation dose calculations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.468-468
• /
• 2000

In our laboratory, the control aspects are investigated in the photovoltaic power generation systems (PV systems). The PV system is very good for earth environment, but if it connects to power network system, many problems are raised (protection, voltage, harmonics etc.). In this paper, we present the result of the basic studies for the building of the PV system that amplifies the electric energy obtained from the solar cell. We consider electronic circuits in order to protect the PV system from power surge induced by lightning and also design an electronic circuit in order to detect defaults in the power network system. We would like to integrate these circuits into the PV system by considering its control equipment build by 8-bit microcomputer using various control theory (fuzzy, neural network etc.).

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.81-86
• /
• 2023

Recently, there has been an increased demand for light-emitting diode (LED) due to the growing emphasis on environmental protection. However, the use of GaN-based sapphire in LED manufacturing leads to the generation of defects, such as dislocations caused by lattice mismatch, which ultimately reduces the luminous efficiency of LEDs. Moreover, most inspections for LED semiconductors focus on evaluating the luminous efficiency after packaging. To address these challenges, this paper aims to detect defects at the wafer stage, which could potentially improve the manufacturing process and reduce costs. To achieve this, image processing and deep learning-based defect detection techniques for Sapphire Epi-Wafer used in Green LED manufacturing were developed and compared. Through performance evaluation of each algorithm, it was found that the deep learning approach outperformed the image processing approach in terms of detection accuracy and efficiency.

• 한국수자원학회논문집
• /
• 제54권5호
• /
• pp.301-309
• /
• 2021

본 연구에서는 시계열 순서의 의미가 희석될 수 있는 기존의 U-net 기반 딥러닝 강우예측 모델의 성능을 개선하고자 하였다. 이를 위해서 데이터의 연속성을 고려한 ConvLSTM2D U-Net 신경망 구조를 갖는 모델을 적용하고, RainNet 모델 및 외삽 기반의 이류모델을 이용하여 예측정확도 개선 정도를 평가하였다. 또한 신경망 기반 모델 학습과정에서의 불확실성을 개선하기 위해 단일 모델뿐만 아니라 10개의 앙상블 모델로 학습을 수행하였다. 학습된 신경망 강우예측모델은 현재를 기준으로 과거 30분 전까지의 연속된 4개의 자료를 이용하여 10분 선행 예측자료를 생성하는데 최적화되었다. 최적화된 딥러닝 강우예측모델을 이용하여 강우예측을 수행한 결과, ConvLSTM2D U-Net을 사용하였을 때 예측 오차의 크기가 가장 작고, 강우 이동 위치를 상대적으로 정확히 구현하였다. 특히, 앙상블 ConvLSTM2D U-Net이 타 예측모델에 비해 높은 CSI와 낮은 MAE를 보이며, 상대적으로 정확하게 강우를 예측하였으며, 좁은 오차범위로 안정적인 예측성능을 보여주었다. 다만, 특정 지점만을 대상으로 한 예측성능은 전체 강우 영역에 대한 예측성능에 비해 낮게 나타나, 상세한 영역의 강우예측에 대한 딥러닝 강우예측모델의 한계도 확인하였다. 본 연구를 통해 시간의 변화를 고려하기 위한 ConvLSTM2D U-Net 신경망 구조가 예측정확도를 높일 수 있었으나, 여전히 강한 강우영역이나 상세한 강우예측에는 공간 평활로 인한 합성곱 신경망 모델의 한계가 있음을 확인하였다.

• 한국의학물리학회지:의학물리
• /
• 제20권3호
• /
• pp.132-138
• /
• 2009

호흡으로 인한 방사선 치료 표적의 움직임을 고려함으로써 치료 성적 향상과 동시에 주변 장기 보호를 지향하는 4차원 방사선 치료의 구현, 성능 개선의 연구가 활발히 진행되고 있다. 환자가 자연스럽게 호흡하도록 하는 장점이 있는 호흡 동기방식이나 종양추적방식을 사용하는 경우, 방사선조사 표적의 움직임을 예측, 방사선조사 시 이를 보정하여 줌으로써 방사선치료 효과를 극대화할 수 있다. 신경회로망은 통계 수식에 의존하지 않고 주어진 자료를 표현하는 일종의 규칙을 찾아내므로, 방사선 치료 표적의 실시간 움직임과 같은 비선형성을 가진 시계열(Time Series)을 표현하는 데에 유리하다. 본 연구에서는 신경회로망 예측 알고리즘의 4차원 방사선치료에 적용 가능성을 평가하였다. Multi-layer Perceptron으로 신경회로망을 구성하였고 Scaled Conjugate Gradient 알고리즘을 신경회로망 학습 알고리즘으로 사용하였다. RPM 시스템을 이용하여 획득한 실제 임상 현장의 환자에 대한 호흡 자료를 기반으로 학습한 신경회로망 예측 결과를 RPM 시스템의 측정치와 상호 비교하였다. 10명의 환자에의 적용 결과, 신경회로망 학습에 사용된 자료가 환자의 호흡 범위 전체를 포함하지 않는 경우를 제외하고는, 최대절대오차 3 mm 미만의 우수한 예측 성능을 보였다. 학습 영역 이외의 호흡 자료 예측 시 발생하는 상당한 오차는 신경회로망의 외삽에 대한 학습능력 부족을 보이는 것으로, 오차의 원인을 제거하기 위한 일환으로, 호흡자료를 측정할 때 최대 호흡을 하도록 하여 충분한 학습 자료를 확보하는 방안을 고려해 볼 수있겠다. 4차원 방사선치료 시스템 성능 개선에의 직접 활용을 위하여, 다양한 시스템 대기시간에 따른 예측 성능 평가와 방사선 조사 장치와 연동, 실용 타당성 검증의 추가 연구가 진행될 것이다.

• 유통과학연구
• /
• 제18권1호
• /
• pp.15-26
• /
• 2020

Purpose: This study is to analyze the image classification using Convolution Neural Network and Transfer Learning for Jeju Island and to suggest related implications. As the biggest tourist destination in Korea, Jeju Island encounters environmental issues frequently caused by marine debris along the seaside. The ever-increasing volume of plastic waste requires multidirectional management and protection. Research design, data and methodology: In this study, the deep learning CNN algorithm was used to train a number of images from Jeju clean and polluted beaches. In the process of validating and testing pre-processed images, we attempted to explore their applicability to coastal tourism applications through probabilities of classifying images and predicting clean shores. Results: We transformed and augmented 194 small image dataset into 3,880 image data. The results of the pre-trained test set were 85%, 70% and 86%, and then its accuracy has increased through the process. We finally obtained a rapid convergence of 97.73% and 100% (20/20) in the actual training and validation sets. Conclusions: The tested algorithms are expected to implement in applications for tourism service distribution aimed at reducing coastal waste or in CCTVs as a detector or indicator for residents and tourists to protect clean beaches on Jeju Island.

• 국제물리치료학회지
• /
• 제1권2호
• /
• pp.107-112
• /
• 2010

The majority of strokes are caused by ischemia and result in brain tissue damage, leading to problems of the central nervous system including hemiparesis, dysfunction of language and consciousness, and dysfunction of perception. The purpose of this study was to investigate the effects of Poly(ADP-ribose) polymerase(PARP) on necrosis in neuronal cells that have undergone needle electrode electrical stimulation(NEES) prior to induction of ischemia. Ischemia was induced in male SD rats(body weight 300g) by occlusion of the common carotid artery for 5 min, after which the blood was reperfused. After induction of brain ischemia, NEES was applied to Zusanli(ST 36), at 12, 24 and 48 hours. Protein expression was investigated using immuno-reactive cells, which react to PARP antibodies in cerebral nerve cells, and Western blotting. The results were as follows: In the cerebral cortex, the number of PARP reactive cells after 24 hours significantly decreased(p<.05) in the NEES group compared to the GI group. PARP expression after 24 hours significantly decreased(p<.05) in the NEES group compared to the GI group. As a result, NEES showed the greatest effect on necrosis-related PARP immuno-reactive cells 24 hours after ischemia, indicating necrosis inhibition, blocking of neural cell death, and protection of neural cells. Based on the results of this study, NEES can be an effective method of treating dysfunction and improving function of neuronal cells in brain damage caused by ischemia.

• 한국산학기술학회논문지
• /
• 제21권10호
• /
• pp.454-460
• /
• 2020

최근 들어, 동영상의 간편한 촬영 그리고 인터넷을 통한 동영상의 보급 및 시청이 기하급수적으로 늘어남에 따라서 개인 정보의 외부 노출로 인한 피해가 발생하고 있다. 본 논문에서는 연속적으로 들어오는 영상으로부터 사람의 개인 정보가 노출된 목표 객체 영역을 강인하게 추출한 다음, 추출된 객체를 위치 예측 알고리즘을 이용해 빠르게 추적하면서 영상 블러링 기법을 통해 동시에 블로킹하는 새로운 방법을 제안한다. 본 논문에서는 먼저 입력받은 컬러 영상으로부터 개인 정보 영역이 노출된 목표 객체 영역을 인공 신경망 기반의 학습 알고리즘을 이용하여 정확하게 추출한다. 그런 다음, 검출된 객체를 위치 예측 알고리즘을 이용하여 빠르게 추적하면서 영상 블러링을 적용하여 블로킹한다. 실험 결과에서는 제안된 방법이 받아들인 다양한 종류의 컬러 영상 데이터로부터 개인 정보가 노출된 목표 객체를 기존 방법에 비해 2.5% 보다 정확하게 추적하면서 동시에 블러링함으로써 개인 정보 영역을 효과적으로 차단한다는 것을 보여준다. 본 논문에서 제안된 물체 차단 방법은 개인 정보의 보호, 비디오 감시 및 보안, 객체 검출 및 추적 등과 같은 많은 실제적인 응용 분야에서 유용하게 활용될 수 있을 것으로 기대된다.