• 한국농공학회논문집
• /
• 제59권5호
• /
• pp.93-99
• /
• 2017

A model was developed using Artificial Neural Networks (ANNs) based on Principal Component Analysis (PCA), to accurately predict the air humidity inside an experimental greenhouse located in Daegu (latitude $35.53^{\circ}N$, longitude $128.36^{\circ}E$, and altitude 48 m), South Korea. The weather parameters, air temperature, relative humidity, solar radiation, and carbon dioxide inside and outside the greenhouse were monitored and measured by mounted sensors. Through the PCA of the data samples, three main components were used as the input data, and the measured inside humidity was used as the output data for the ALYUDA forecaster software of the ANN model. The Nash-Sutcliff Model Efficiency Coefficient (NSE) was used to analyze the difference between the experimental and the simulated results, in order to determine the predictive power of the ANN software. The results obtained revealed the variables that affect the inside air humidity through a sensitivity analysis graph. The measured humidity agreed well with the predicted humidity, which signifies that the model has a very high accuracy and can be used for predictions based on the computed $R^2$ and NSE values for the training and validation samples.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.438-441
• /
• 2007

Recently, due to molecular biology and engineering technology, DNA microarray makes people watch thousands of genes and the state of variation from the tissue samples of living body. With DNA Microarray, it is possible to construct a genetic group that has similar expression patterns and grasp the progress and variation of gene. This paper practices Cluster Analysis which purposes the discovery of biological subgroup or class by using gene expression information. Hence, the purpose of this paper is to predict a new class which is unknown, open leukaemia data are used for the experiment, and MCL (Markov CLustering) algorithm is applied as an analysis method. The MCL algorithm is based on probability and graph flow theory. MCL simulates random walks on a graph using Markov matrices to determine the transition probabilities among nodes of the graph. If you look at closely to the method, first, MCL algorithm should be applied after getting the distance by using Euclidean distance, then inflation and diagonal factors which are tuning modulus should be tuned, and finally the threshold using the average of each column should be gotten to distinguish one class from another class. Our method has improved the accuracy through using the threshold, namely the average of each column. Our experimental result shows about 70% of accuracy in average compared to the class that is known before. Also, for the comparison evaluation to other algorithm, the proposed method compared to and analyzed SOM (Self-Organizing Map) clustering algorithm which is divided into neural network and hierarchical clustering. The method shows the better result when compared to hierarchical clustering. In further study, it should be studied whether there will be a similar result when the parameter of inflation gotten from our experiment is applied to other gene expression data. We are also trying to make a systematic method to improve the accuracy by regulating the factors mentioned above.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.34-36
• /
• 2022

기존 텍스트 감성 분석 모델에서는 일반적으로 전체 텍스트를 직접 모델링하고, 텍스트 내용 간의 계층적 관계를 덜 고려한다. 그러나 감정분석의 구현에서는 많은 텍스트가 여러 감정으로 뒤섞여 있다. 전체의 의미론적 모델링을 직접 수행하면 감성분석 모델의 판단 난도가 높아져 혼합 감정 문장의 분류에 적용하기 어려울 수 있다. 따라서 본 논문에서는 텍스트 계층을 고려한 감성 분석 모델 BHGCN을 제안한다. 이 모델에서는 BERT의 각 레이어의 숨겨진 상태의 출력이 노드로 사용되며, 상위 레이어와 하위 레이어 사이에 직접 연결이 이루어져 의미 계층이 있는 그래프 네트워크를 구축한다. BHGCN 모델은 계층별 의미론에 주의를 기울일 뿐만 아니라 계층적 관계에도 주의를 기울이기 때문에 혼합 감성 분류 작업을 처리하는 데 적합하다. 본 논문에서는 비교 실험을 통해 제안하는 BHGCN 모델이 명백한 경쟁 우위를 보인다는 것을 입증하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 춘계학술대회 논문집
• /
• pp.457-462
• /
• 1995

This paper describes diagnosis strategy of the Flexible Multiple Fault Diagnosis Module for forecasting faults in system and deciding current machine state form sensor information. Most studydeal with diagnosis control stategy about single fault in a system, this studies deal with multiple fault diagnosis. This strategy is consist of diagnosis control module such as backward tracking expert system shell, various neural network, numerical model to predict machine state and communication module for information exchange and cooperate between each model. This models are used to describe structure, function and behavior of subsystem, complex component and total system. Hierarchical structure is very efficient to represent structural, functional and behavioral knowledge. FT(Fault Tree). ST(Symptom Tree), FCD(Fault Consequence Diagrapy), SGM(State Graph Model) and FFM(Functional Flow Model) are used to represent hierachical structure. In this study, IA(Intelligent Agent) concept is introduced to match FT component and event symbol in diagnosed system and to transfer message between each event process. Proposed diagnosis control module is made of IPC(Inter Process Communication) method under UNIX operating system.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.563-566
• /
• 2020

지식 그래프 기반의 질문 응답 문제는 자연어 질문에 대한 이해뿐만 아니라, 기반이 되는 지식 그래프상에서 올바른 답변을 찾기 위한 효과적인 추론 능력을 요구한다. 본 논문에서는 다중 홉 추론을 요구하는 복잡한 자연어 질문에 대해 연관 지식 그래프 위에서 답변 추론을 효과적으로 수행할 수 있는 심층 신경망 모델을 제안한다. 제안 모델에서는 지식 그래프상의 추론 과정에서 추른 경로를 명확히 하기 위한 노드의 양방향 특정 전파와 이웃 노드들 간의 맥락 정보까지 각 노드의 특정값에 반영할 수 있는, 표현력이 풍부한 쌍 선형 그래프 신경망 (BGNN)을 이용한다. 본 논문에서는 오픈 도메인의 지식 베이스 Freebase와 자연어 질문 응답 데이터 집합 WebQuestionsSP를 이용한 실험들을 통해, 제안 모델의 효과와 우수성을 확인하였다.

• 한국ITS학회 논문지
• /
• 제17권4호
• /
• pp.138-149
• /
• 2018

본 논문은 전력선 통신의 성능을 하락시키는 임펄스 잡음을 효과적으로 완화하는 시스템 모델을 제안한다. 최근 딥 러닝이 다양한 분야에 적용되어 효과적인 성능개선을 보이고 있다. 효과적인 임펄스 잡음 완화를 위해 딥 러닝 알고리즘 중 하나인 컨볼루션 뉴럴 네트워크를 기존의 시스템에 적용한다. 또한 다수의 사용자가 존재할 경우를 고려하여 연속적 간섭 제거 기법을 사용하여 다수의 사용자로부터 발생하는 임펄스 잡음을 완화시킨다. 제안한 시스템 모델을 전력선 통신에 적용하여 시뮬레이션을 하였고 비트 오류 확률 대 SNR 그래프를 통해 제안한 시스템 모델의 성능을 확인한다. 또한, 연속적 간섭 제거 기법 중 ZF와 MMSE 연속적 간섭 제거 기법, 최적의 순서를 가지는 연속적 간섭 제거 기법과 최적의 순서를 가지지 않는 연속적 간섭 제거 기법을 각각 비교하여 어떠한 기법이 더 우수한 성능을 가지는지를 확인한다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.290-293
• /
• 2021

본 논문에서는 공부하는 사용자의 상황을 감지하여, 학습의욕을 고취시키고 집중력 향상을 도와주기 위한 학습능률 확인 시스템을 구현하고자 한다. 이를 위해 실시간 카메라를 통해 사용자의 얼굴이나 몸의 움직임을 추출하여 학습 태도, 집중력에 대한 데이터를 측정한다. 실시간 임베디드 시스템 구현을 위해 Jetson 보드를 사용하였으며, 영상인식을 위한 CNN(Convolution Neural Network)를 구현하였다. CNN 을 이용해 대상의 특징 부분을 검출한 후 움직임 검파를 수행한다. 캡처한 영상을 PYQT5 로 작성된 GUI 에서 영상을 보여주며, 각각 방해되는 행동을 했을 때 푸시메시지를 보내며 데이터를 수집한다. 또한 GUI 로 만든 메인 화면에서 각각의 기능들을 실행 가능하며, 수집한 데이터를 산출해주는 통계그래프와 작업관리 목록, 화이트 노이즈 등의 기능을 수행한다. 구축된 학습능률 확인 시스템을 통해 대상의 데이터를 수집 및 분석을 비롯한 다양한 기능을 사용자에게 제공하였다.

• 동의생리병리학회지
• /
• 제38권1호
• /
• pp.1-9
• /
• 2024

Cognitive reserve (CR) is a concept that can explain the discrepancies between the pathologic burden of the disease and clinical manifestations. It refers to the individual susceptibility to age-related brain changes and pathologies related to Alzheimer's disease, thus recognized as a factor affecting the trajectories of the disease. The purpose of this study was to explore the current states of clinical studies on neural substrates of CR in Alzheimer's disease using functional magnetic resonance imaging. We searched for clinical studies on CR using fMRI in the Pubmed, Cochrane library, RISS, KISS and ScienceON on August 14, 2023. Once the online search was finished, studies were selected manually by the inclusion criteria. Finally, we analyzed the characteristics of selected articles and reviewed the neural substrates of CR. Total thirty-four studies were included in this study. As surrogate markers of CR, not only education and occupational complexity, but also composite score and questionnaire-based method, which cover various areas of life, were mainly used. The most utilized methods in resting-state fMRI were independent component analysis, seed-based analysis, and graph theory analysis. Through the analysis, we demonstrated that neuroimaging techniques could capture the neural substrates associated with cognitive reserve. Moreover, functional connectivity of brain regions centered on prefrontal and parietal cortex and network areas such as default mode network showed a significant correlation with CR, which indicated a significant association with cognitive performance. CR may induce differential effects according to the disease status. We hope that this perspective on cognitive reserve would be helpful when conducting clinical researches on the mechanisms of traditional Korean medicine for Alzheimer's disease in the future.

• 한국IT서비스학회지
• /
• 제16권4호
• /
• pp.137-148
• /
• 2017

Researches on the Artificial Intelligence has been explosively activated in various fields since the advent of AlphaGo. Particularly, researchers on the application of multi-layer neural network such as deep learning, and various machine learning algorithms are being focused actively. In this paper, we described a development of an artificial intelligence Janggi game based on reinforcement learning algorithm and MCTS (Monte Carlo Tree Search) algorithm with accumulated game data. The previous artificial intelligence games are mostly developed based on mini-max algorithm, which depends only on the results of the tree search algorithms. They cannot use of the real data from the games experts, nor cannot enhance the performance by learning. In this paper, we suggest our approach to overcome those limitations as follows. First, we collects Janggi expert's game data, which can reflect abundant real game results. Second, we create a graph structure by using the game data, which can remove redundant movement. And third, we apply the reinforcement learning algorithm and MCTS algorithm to select the best next move. In addition, the learned graph is stored by object serialization method to provide continuity of the game. The experiment of this study is done with two different types as follows. First, our system is confronted with other AI based system that is currently being served on the internet. Second, our system confronted with some Janggi experts who have winning records of more than 50%. Experimental results show that the rate of our system is significantly higher.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.965-976
• /
• 2020

We present in this work a segmentation method of E. coli bacterial images generated via phase contrast microscopy using a deep learning based hybrid feature generation. Unlike conventional machine learning methods that use the hand-crafted features, we adopt the denoising autoencoder in order to generate a precise and accurate representation of the pixels. We first construct a hybrid vector that combines original image, difference of Gaussians and image gradients. The created hybrid features are then given to a deep autoencoder that learns the pixels' internal dependencies and the cells' shape and boundary information. The latent representations learned by the autoencoder are used as the inputs of a softmax classification layer and the direct outputs from the classifier represent the coarse segmentation mask. Finally, the classifier's outputs are used as prior information for a graph partitioning based fine segmentation. We demonstrate that the proposed hybrid vector representation manages to preserve the global shape and boundary information of the cells, allowing to retrieve the majority of the cellular patterns without the need of any post-processing.