• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1031-1041
• /
• 2020

Cloud computing technology plays an important role in the deep learning industry as deep learning services are deployed frequently on top of cloud infrastructures. In such cloud environment, virtualization technology provides logically independent and isolated computing space for each tenant. However, recent studies demonstrate that by leveraging vulnerabilities of virtualization techniques and shared processor architectures in the cloud system, various side-channels can be established between cloud tenants. In this paper, we propose a novel attack scenario that can steal internal information of deep learning models by exploiting the Meltdown vulnerability in a multi-tenant system environment. On the basis of our experiment, the proposed attack method could extract internal information of a TensorFlow deep-learning service with 92.875% accuracy and 1.325kB/s extraction speed.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.18 no.2
• /
• pp.57-81
• /
• 1993

This paper is concerned with analyzing the bankruptcy prediction power of three methods : Multivariate Discriminant Analysis (MDA), Inductive Learning, Neural Network, MDA has been famous for its effectiveness for predicting bankrupcy in accounting fields. However, it requires rigorous statistical assumptions, so that violating one of the assumptions may result in biased outputs. In this respect, we alternatively propose the use of two AI models for bankrupcy prediction-inductive learning and neural network. To compare the performance of those two AI models with that of MDA, we have performed massive experiments with a number of Korean bankrupt-cases. Experimental results show that AI models proposed in this study can yield more robust and generalizing bankrupcy prediction than the conventional MDA can do.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2017.11a
• /
• pp.499-510
• /
• 2017

기술혁신에는 본질적인 어려움이 따르는데, 이는 상당부분 기술이 지닌 불확실성에 기인한다. 따라서 혁신 추구의 어려움을 경감에는 혁신 예측 방법론이 큰 도움이 될 수 있다. 한편 최근 빅데이터와 인공지능에 큰 관심이 이어지며 특히 알파고의 알고리즘 중 하나인 딥 러닝이 뛰어난성능을 보이고 있다. 이에 본 연구는 혁신성과 예측에 있어 딥 러닝을 이용한 방법론을 접목하여 연구를 진행하였다.. 모델 구축 및 학습에 있어 KIS 2016 데이터를 이용하였으며, 투입 요인으로는 정보 원천의 사용도와 혁신 목적을 사용하였고 산출 요인으로는 혁신 성과 지표를 구성하여 사용하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.977-984
• /
• 2022

Recently, with the economic development of Southeast Asia, the use of information devices is widely spreading, and the demand for application services using intelligent character recognition is increasing. This paper discusses deep learning-based feature extraction and recognition of Myanmar, one of the Southeast Asian countries. Myanmar alphabet (33 letters) and Myanmar numerals (10 numbers) are used for feature extraction. In this paper, the number of nine features are extracted and more than three new features are proposed. Extracted features of each characters and numbers are expressed with successful results. In the recognition part, convolutional neural networks are used to assess its execution on character distinction. Its algorithm is implemented on captured image data-sets and its implementation is evaluated. The precision of models on the input data set is 96 % and uses a real-time input image.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2001.10a
• /
• pp.165-196
• /
• 2001

DNA chip 또는 microarray는 다수의 유전자 또는 유전자 조각을 (보통 수천내지 수만 개)칩상에 고정시켜 놓고 DNA hybridization 반응을 이용하여 유전자들의 발현 양상을 분석할 수 있는 기술이다. 이러한 high-throughput기술은 예전에는 생각하지 못했던 여러가지 분자생물학의 문제에 대한 해답을 제시해 줄 수 있을 뿐 만 아니라, 분자수준에서의 질병 진단, 신약 개발, 환경 오염 문제의 해결 등 그 응용 가능성이 무한하다. 이 기술의 실용적인 적용을 위해서는 DNA chip을 제작하기 위한 하드웨어/웻웨어 기술 외에도 이러한 데이터로부터 최대한 유용하고 새로운 지식을 창출하기 위한 bioinformatics 기술이 핵심이라고 할 수 있다. 유전자 발현 패턴을 데이터마이닝하는 문제는 크게 clustering, classification, dependency analysis로 구분할 수 있으며 이러한 기술은 통계학과인공지능 기계학습에 기반을 두고 있다. 주로 사용된 기법으로는 principal component analysis, hierarchical clustering, k-means, self-organizing maps, decision trees, multilayer perceptron neural networks, association rules 등이다. 본 세미나에서는 이러한 기본적인 기계학습 기술 외에 최근에 연구되고 있는 새로운 학습 기술로서 probabilistic graphical model (PGM)을 소개하고 이를 DNA chip 데이터 분석에 응용하는 연구를 살펴본다. PGM은 인공신경망, 그래프 이론, 확률 이론이 결합되어 형성된 기계학습 모델로서 인간 두뇌의 기억과 학습 기작에 기반을 두고 있으며 다른 기계학습 모델과의 큰 차이점 중의 하나는 generative model이라는 것이다. 즉 일단 모델이 만들어지면 이것으로부터 새로운 데이터를 생성할 수 있는 능력이 있어서, 만들어진 모델을 검증하고 이로부터 새로운 사실을 추론해 낼 수 있어 biological data mining 문제에서와 같이 새로운 지식을 발견하는 exploratory analysis에 적합하다. 또한probabilistic graphical model은 기존의 신경망 모델과는 달리 deterministic한의사결정이 아니라 확률에 기반한 soft inference를 하고 학습된 모델로부터 관련된 요인들간의 인과관계(causal relationship) 또는 상호의존관계(dependency)를 분석하기에 적합한 장점이 있다. 군체적인 PGM 모델의 예로서, Bayesian network, nonnegative matrix factorization (NMF), generative topographic mapping (GTM)의 구조와 학습 및 추론알고리즘을소개하고 이를 DNA칩 데이터 분석 평가 대회인 CAMDA-2000과 CAMDA-2001에서 사용된cancer diagnosis 문제와 gene-drug dependency analysis 문제에 적용한 결과를 살펴본다.

• Journal of Digital Policy
• /
• v.2 no.4
• /
• pp.25-32
• /
• 2023

This paper is a study to develop a deep neural network (DNN) blood glucose prediction model based on heart rate (HR) and heart rate variability (HRV) data measured by PPG-based sensors. MLP deep learning consists of an input layer, a hidden layer, and an output layer with 11 independent variables. The learning results of the blood glucose prediction model are MAE=0.3781, MSE=0.8518, and RMSE=0.9229, and the coefficient of determination (R²) is 0.9994. The study was able to verify the feasibility of glycemic control using non-blood vital signs using PPG-based digital devices. In conclusion, a standardized method of acquiring and interpreting PPG-based vital signs, a large data set for deep learning, and a study to demonstrate the accuracy of the method may provide convenience and an alternative method for blood glucose management in dogs.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.2
• /
• pp.1-8
• /
• 1998

In this paper, a method which cna detect tracking caused by the insulation deterioration of conduct wiring, is proposed. To investigate it, we analyzed the harmonics of each load current waveform and those of tracking current waveform with FFT. The computer which take experiment data is learned by neural network algorithm, which has recently been used for the load recognition. The proposed metod in our study can be applied to the development of several measuring equipments such as hotline insulation tester, cna earch tester for the detection of tracking under hot-line state, Furthermore, it can substitutes molded case circuit breaker, fuse, and so on.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.231-240
• /
• 2001

Conventional expert systems has been criticized due to its lack of capability to adapt to the changing decision-making environments. In literature, many methods have been proposed to make expert systems more environment-adaptive by incorporating fuzzy logic and neural networks. The objective of this paper is to propose a new approach to building a self-evolving expert system inference mechanism by integrating fuzzy neural network and fuzzy rule extraction technique. The main recipe of our proposed approach is to fuzzify the training data, train them by a fuzzy neural network, extract a set of fuzzy rules from the trained network, organize a knowledge base, and refine the fuzzy rules by applying a pruning algorithm when the decision-making environments are detected to be changed significantly. To prove the validity, we tested our proposed self-evolving expert systems inference mechanism by using the bankruptcy data, and compared its results with the conventional neural network. Non-parametric statistical analysis of the experimental results showed that our proposed approach is valid significantly.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.36-42
• /
• 1996

In this paper, we proposed a PID controller, which could control unknown plants using Artificial Neural Network(ANN) for auto-tuning of the PID parameters. In the proposed algorithm, the parameters of the controller were adjusted to reduce the error of the controlled plant. In this process, the sensitivity between input and output of the unknown plant was needed. So, in order to obtain this sensitivity, the ANN's learnig ability was used. Computer simualtions were performed for the regulation problems, and the results were compared with those of Ziegler-Nichols PID controller. As a result, it was shown that the proposed algorithm outperformed Ziegler-Nichols controller in rise time, overshoot, undershoot, and setting time.

• Journal of Intelligence and Information Systems
• /
• v.1 no.2
• /
• pp.103-121
• /
• 1995

This study proposes a artificial neural network method to predict the time to buy and sell the stocks listed on the Korea Composite Stock Price Index(KOSPI). Four types (NN1, NN2, NN3, NN4) of independent networks were developed to predict KOSPIs up/down direction after four weeks. These networks have a difference only in the length of learning period. NN5 - arithmetic average of four networks outputs - shows an higher accuracy than other network types and Multiple Linear Regression (MLR), and buying and selling simulation using systems outputs produces higher reture than buy-and-hold strategy.