• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.399-403
• /
• 1998

In this paper, we proposed a new fuzzy supervised learning algorithm. We construct, and train, a new type fuzzy neural net to model the linear activation function. Properties of our fuzzy neural net include : (1) a proposed linear activation function ; and (2) a modified delta rule for learning algorithm. We applied this proposed learning algorithm to exclusive OR,3 bit parity using benchmark in neural network and pattern recognition problems, a kind of image recognition.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.376-376
• /
• 2012

본 연구는 Poly-Si에 이온 주입된 Boron의 Activation 거동을 연구하고자 SLS (Sequential Lateral Solidification) Poly-Si과 ELA (Excimer Laser Annealing) Poly-Si의 활성화 거동을 비교 분석하였다. SLS 및 ELA 결정화 방법으로 제조된 Poly-Si을 모재로 비 질량 분리 방식의 ISD (Ion Shower Doping) System을 사용하여 2.5~7.0 kV까지 이온주입 하였다. 이온주입 후 두 가지의 열처리 방법, 즉, FA 열처리(Furnace Annealing)와 RTA 열처리(Rapid Thermal Annealing)를 사용하여 도펀트 활성화 열처리를 수행하고 이온주입 조건 및 활성화 열처리 방법에 따른 결함 회복 및 도펀트 활성화 거동의 변화를 관찰하였다. TRIM-code Simulation 결과 가속 이온 에너지와 조사량이 증가 할수록 이온주입 시 발생하는 결함의 양이 증가하는 것을 정량적으로 계산하였다. 실험 결과 결함의 양이 증가 할수록 Activation이 잘되는 것을 관찰할 수 있었다. SLS Poly-Si에 비하여 ELA Poly-Si의 경우 도펀트 활성화 열처리 후 활성화 효율이 높게 나타났다. 본 결과는 Grain Boundary의 역할과 밀접한 관계가 있으며 간단한 정성적인 Model을 제시하였다. 활성화 효율의 경우 RTA 열처리 시편이 FA 시편에 비하여 높은 것이 관찰되었다. 본 결과는 열처리 온도 및 시간에 따라 변화하는 Boron의 특이한 활성화 거동인 Reverse Annealing 효과에 기인하는 것으로 규명되었다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.3
• /
• pp.268-274
• /
• 2007

In general, rocket or satellite circuit designers focus on reducing temperature of electronic devices in order to enhance electronic unit's reliability. This paper describes the quantitative analysis result of activation energy as well as device temperature effects to the system reliabilities. The quantitative analysis result shows that activation energy of device has more effects on system reliability than temperature does. And this paper suggests a strategy for enhancement of reliability during devices placement on PCB with simulation results.

• Journal of KIBIM
• /
• v.12 no.2
• /
• pp.40-48
• /
• 2022

It is very important to accurately predict construction costs in the early stages of the construction project. However, it is difficult to accurately predict construction costs with limited information from the initial stage. In recent years, with the development of machine learning technology, it has become possible to predict construction costs more accurately than before only with schematic construction characteristics. Based on machine learning technology, this study aims to analyze plans to more accurately predict construction costs by using only the factors influencing construction costs. To the end of this study, the effect of the error rate according to the activation function and the node configuration of the hidden layer was analyzed.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.78-79
• /
• 2021

It is necessary to calculate Apparent Activation Energy(Ea) in order to apply the equivalent age formula to predict compressive strength using the maturity method. For carbon reduction, it is necessary to consider the change of Ea by condition of GGBFS concrete, which is widely used today. In this study, as a basic study for the design of the compressive strength model of GGBFS concrete, the apparent activation energy of the GGBFS mixed paste was calculated through a calorimeter. The experiment was carried out at a hydration temperature of 10 to 30℃ with a paste test specimen having a GGBFS content of 0 to 80%. As a result, the GGBFS replacement rate of the paste increased, and Ea tended to increase as the temperature decreased.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2020.08a
• /
• pp.87-87
• /
• 2020

In this study, we investigated the immune-enhancing activity of water extracts from Hydrangea macrophylla subsp. serrata (WE-HML). WE-HML increased cell viability and production of immunomodulators, which contributed to activating phagocytic activity in RAW264.7 cells. Inhibition of JNK and NF-κB reduced the production of immunomodulators by WE-HML. ROS inhibition suppressed the production of immunomodulators, and the activation of JNK and NF-κB signaling by WE-HML. TLR4 inhibition attenuated the production of immunomodulators, and activation of JNK and NF-κB signaling by WE-HML. In the immunosuppressed mouse model, WE-HML increased the spleen index, the levels of the cytokines, the numbers of white blood cells, lymphocytes, and neutrophils. However, WE-HML inhibited LPS-mediated overproduction of pro-inflammatory mediators in RAW264.7 cells, which indicated that WE-HML may have anti-inflammatory activity under excessive inflammatory conditions. Taken together, WE-HML may be considered to have immune-enhancing activity and expected to be used as a potential immune-enhancing agent.

• Smart Structures and Systems
• /
• v.33 no.2
• /
• pp.133-143
• /
• 2024

Piezoelectric (PZT) actuators have been widely used in precision positioning fields for their excellent displacement resolution. However, due to the inherent characteristics of piezoelectric actuators, hysteresis has been proven to greatly reduce positioning performance. In this paper, five mathematical hysteretic models based on activation function are proposed to characterize the nonlinear hysteresis characteristics of piezoelectric actuators. Then the performance of the proposed models is verified by particle swarm optimization (PSO) algorithm and the experiment data. Thirdly, the fitting performance of the proposed models is compared with the classical Bouc-Wen model. Finally, the performance of the five proposed models in modelling hysteresis nonlinearity of piezoelectric drivers is compared, in terms of RMSE, MAPE, SAPE and operation efficiency, and relevant suggestions are given.

• The Korean Journal of Food And Nutrition
• /
• v.9 no.3
• /
• pp.281-288
• /
• 1996

The purpose of this study was to develop the curriculum for the Department of Food Service Business in Junior College. The purpose of the curriculum development is to train professionals combined theory and practice for medium or small restaurant managers. We have developed a model curriculum, which was based on Job analyses for related business, analyses of the curricula of departments related with food service, and survey on the questionnaire. The subjects of the model curriculum are as follows. 1) Subjects related with Food and Food Sanitation, 2) Subjects related nth Cuisine, 3) Subjects related with Restaurant Management and Service, 4) Subjects related nth training In practical business, and 5) Subjects related with a foreign language. The effects on opening the Department of Food Service are as follows. 1) To train professionals (or food service business, 2) Activation of the study on Food Service Industry, 3) Establishment of the traditional food culture, 4) Activation of the Tourist Industry, and 5) To improve the Quality of restaurant employees.

• Preventive Nutrition and Food Science
• /
• v.22 no.1
• /
• pp.62-66
• /
• 2017

This study was conducted to determine the rheological properties of gochujang and chogochujang at different temperatures (25, 35, and $45^{\circ}C$). Rheological properties of the samples were determined using a rotational rheometer at a shear range of 1 to $40s^{-1}$. Gochujang and chogochujang were found to be non-Newtonian fluids according to the Herschel-Bulkley model. Yield stress and consistency coefficient of gochujang at different temperatures were higher than those of chogochujang, whereas the opposite was observed for flow behavior index. Moreover, all rheological properties of gochujang and chogochujang decreased with increasing temperature. The consistency coefficient was related to temperature using an Arrhenius-type relationship. Gochujang (14.48 kJ/mol) had slightly higher activation energy than chogochujang (14.03 kJ/mol).