• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.647-654
• /
• 2023

Deep Learning is a useful method for classifying and recognizing complex data such as images and text, and the accuracy of the deep learning method is the basis for making artificial intelligence-based services on the Internet useful. However, the vast amount of user da vita used for training in deep learning has led to privacy violation problems, and it is worried that companies that have collected personal and sensitive data of users, such as photographs and voices, own the data indefinitely. Users cannot delete their data and cannot limit the purpose of use. For example, data owners such as medical institutions that want to apply deep learning technology to patients' medical records cannot share patient data because of privacy and confidentiality issues, making it difficult to benefit from deep learning technology. In this paper, we have designed a privacy preservation technique-applied deep learning technique that allows multiple workers to use a neural network model jointly, without sharing input datasets, in multi-party system. We proposed a method that can selectively share small subsets using an optimization algorithm based on modified stochastic gradient descent, confirming that it could facilitate training with increased learning accuracy while protecting private information.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.118-128
• /
• 2020

A semitransparent photovoltaic-thermal (PV/T) air collector can produce electricity and heat simultaneously. To maximize the thermal and overall efficiency of the semitransparent PV/T air collector, its availability should be maximum; this can be determined through a Markov analysis. In this paper, a Markov model is developed to select an optimized number of semitransparent PV modules in service with five states and two states by considering two parameters, namely failure rate (λ) and repair rate (μ). Three artificial neural network (ANN) models are developed to obtain the minimum cost, minimum temperature, and maximum thermal efficiency of the semitransparent PV/T air collector by setting its type appropriately and optimizing the number of photovoltaic modules and cost. An attempt is also made to achieve maximum thermal and overall efficiency for the semitransparent PV/T air collector by using ANN after obtaining its minimum temperature and available solar radiation.

• Computers and Concrete
• /
• v.22 no.4
• /
• pp.355-363
• /
• 2018

In the following paper, a socio-political heuristic search approach, named the imperialist competitive algorithm (ICA) has been used to improve the efficiency of the multi-layer perceptron artificial neural network (ANN) for predicting the compressive strength of concrete. 173 concrete samples have been investigated. For this purpose the values of slump flow, the weight of aggregate and cement, the maximum size of aggregate and the water-cement ratio have been used as the inputs. The compressive strength of concrete has been used as the output in the hybrid ICA-ANN model. Results have been compared with the multiple-linear regression model (MLR), the genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate the superiority and high accuracy of the hybrid ICA-ANN model in predicting the compressive strength of concrete when compared to the other methods.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.27-30
• /
• 2000

Many human inventions were inspired by nature. The artificial neural network is one example. Another example is Genetic Algorithms(GA). GAs search by simulating evolution, starting from an initial set of solutions or hypotheses, and generating successive "generations" of solutions. This particular branch of AI was inspired by the way living things evolved into more successful organisms in nature. To simulate the process of GA in a computer, we must simulate many times according to varying many GA parameters. This paper describes the implementation of Java Package for efficient applications on Genetic Algorithms, called "JavaGA". The JavaGA used as a application program as well as applet provides graphical user interface of assigning major GA parameters.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2004.06a
• /
• pp.254-254
• /
• 2004

Final disposal of radioactive waste generated from Nuclear Power Plant (NPP) requires the detailed information about the characteristics and the quantities of radionuclides in waste package. Most radionuclides are difficult to measure and expensive to assay. Thus it is suggested to the indirect method by which the concentration of the Difficult-to-Measure (DTM) nuclide is estimated using the correlations of concentration-it is called the scaling factor-between Easy-to-Measure (Key) nuclides and DTM nuclides with the measured concentration of the Key nuclide.(omitted)

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.5
• /
• pp.29-35
• /
• 2002

This study shows the process design and forming analysis of permalloy shielding can that support the automobile multi-display parts to indicate the accurate information of car. This study is particularly important, since the accuracy of permalloy shielding can is known to affect the magnetic properties such as coercivity and permeability quite sensitively. The objective functions are defects such as hemming wind, hemming length, hemming wrap and tightness in prehemming process. The pre-hemming angle is considered as design parameter. The commercial finite element program PAM-STAMP™ was used to simulate the pre-hemming and hemming process. The ANN (Artificial Neural Network) has been implemented for minimizing of objective function and for investigating effect of punch angle relevant to the pre-hemming process. The results of analysis to validate the proposed design method are presented.

• Journal of the Speleological Society of Korea
• /
• no.82
• /
• pp.5-7
• /
• 2007

In this paper, p-n junction formation using screen-printed metalization and co-firing is used to fabricate high-efficiency solar cells on single- crystalline silicon substrates. In order to form high-quality contacts, co-firing of a screen-printed Ag grid on the front and Al on the back surface field is implemented. These contacts require low contact resistance, high conductivity, and good adhesion to achieve high efficiency. Before co-firing, a statistically designed experiment is conducted. After the experiment, a neural network (NN) trained by the error back-propagation algorithm is employed to model the crucial relationships between several input factors and solar cell efficiency. The trained NN model is also used to optimize the beltline furnace process through genetic algorithms.

• Journal of the Korean Institute of Gas
• /
• v.10 no.2 s.31
• /
• pp.55-60
• /
• 2006

Detailed modeling of PEMFCs has been getting considerable interest for predicting the fuel cell performance and also for use in various systems engineering activities. While CFD-based equipment models provide detailed analyses of the performance, they are very time-consuming to develop and run. The computations become quite complex when such models have to be embedded into the flowsheet-level optimization of fuel cell systems. In this paper, we present results about building and using NN-based reduced order models for quickly and repetitively predicting the flow of reactants in a PEMFC manifold.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1901_1902
• /
• 2009

본 논문에서는 Interval Type-2 퍼지 집합을 이용한 퍼지집합 기반 퍼지뉴럴네트워크를 설계하고 최적화한다. Interval Type-2 퍼지뉴럴네트워크는 각 입력 변수에 따른 서로 분리된 입력 공간을 분할함으로서 네트워크 및 규칙을 구성한다. 규칙의 전반부는 퍼지 입력 공간을 개별적으로 분할하여 표현하고, 각 공간은 Interval Type-2 퍼지 집합으로 구성된다. 규칙의 후반부는 Interval 집합을 이용하여 다항식으로서 표현되며, 오류역전파 알고리즘을 이용하여 연결가중치인 후반부 다항식을 학습한다. 또한, 각 입력에 대한 전반부 멤버쉽함수의 정점과 불확실성 계수 그리고 학습률 및 모멘텀 계수를 유전자 알고리즘을 이용하여 최적 동조한다. 제안된 네트워크는 표준 모델로서 널리 사용되는 수치적인 예를 통하여 평가한다.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2093-2094
• /
• 2006

본 논문에서는 입출력 데이터의 특성을 이용하기 위하여 HCM 클러스터링에 의한 정보 입자를 이용한 퍼지 뉴럴 네트워크의 설계를 제안하고 최적화한다. 대상 시스템의 입출력 데이터를 취득하여 데이터들간의 거리를 중심으로 멤버쉽 함수를 정의하고 각 규칙에 속한 입출력 데이터를 추출하여 후반부 추론에 적용한다. 또한, 앞서 정의된 멤버쉽 파라미터는 유전자 알고리즘을 이용하여 최적으로 동정하여 퍼지 뉴럴 네트워크를 최적화한다. 제안된 퍼지 뉴럴 네트워크는 삼각형 멤버쉽 함수를 이용하며, 후반부 추론에는 간략, 선형, 변형된 2차식을 이용한다. 제안된 퍼지 뉴럴 네트워크는 표준 모델로서 널리 사용되는 수치적인 예를 통하여 평가한다.