• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.131-131
• /
• 2021

Deep learning models, especially those based on long short-term memory (LSTM), have presented their superiority in addressing time series data issues recently. This study aims to comprehensively evaluate the performance of deep learning models that belong to the supervised learning category in streamflow prediction. Therefore, six deep learning models-standard LSTM, standard gated recurrent unit (GRU), stacked LSTM, bidirectional LSTM (BiLSTM), feed-forward neural network (FFNN), and convolutional neural network (CNN) models-were of interest in this study. The Red River system, one of the largest river basins in Vietnam, was adopted as a case study. In addition, deep learning models were designed to forecast flowrate for one- and two-day ahead at Son Tay hydrological station on the Red River using a series of observed flowrate data at seven hydrological stations on three major river branches of the Red River system-Thao River, Da River, and Lo River-as the input data for training, validation, and testing. The comparison results have indicated that the four LSTM-based models exhibit significantly better performance and maintain stability than the FFNN and CNN models. Moreover, LSTM-based models may reach impressive predictions even in the presence of upstream reservoirs and dams. In the case of the stacked LSTM and BiLSTM models, the complexity of these models is not accompanied by performance improvement because their respective performance is not higher than the two standard models (LSTM and GRU). As a result, we realized that in the context of hydrological forecasting problems, simple architectural models such as LSTM and GRU (with one hidden layer) are sufficient to produce highly reliable forecasts while minimizing computation time because of the sequential data nature.

• 한국과학교육학회지
• /
• 제37권6호
• /
• pp.993-1003
• /
• 2017

교수자들은 팀기반 프로젝트 학습을 통해 학생들이 협업능력과 실생활 문제해결력을 기르기를 기대한다. 하지만 프로젝트 학습에서 학생들은 단순분업방식으로 문제를 해결하려 할 뿐 아니라 학습전이가 잘 일어나지 않는 경향이 있다. 학생들이 협업의 시너지를 내고 서로의 지식을 이용하여 학습전이를 일어나게 하기 위해서, 이 연구에서는 교류기억체계(TMS) 기반 협력학습 모형을 개발하여 적용하고 그 효과를 검증하고자 한다. 교류기억체계 기반 협력학습 모형은 과학개념을 학습하면서 동료의 전문성을 파악하는 교류기억체계 개발 단계, 간단한 협력적 문제해결을 통해 신뢰를 기르는 교류기억체계 정교화 단계, 마지막으로 조직화된 지식처리를 하는 교류기억체계 적용의 3단계로 이루어져 있다. 첫 번째 단계에서 동료교수법을 통해 과학개념을 학습함과 동시에 그룹 구성원이 서로 어떤 지식을 잘 알고 있는지 전문성을 파악한다. 두 번째 단계에서 잘 정의된 실험 문제를 협력적으로 해결하며 근전이를 경험한다. 세 번째 단계에서 근전이 경험을 바탕으로 프로젝트 수행을 위한 원전이를 통해 빈약하게 정의된 문제를 해결한다. 이 모형을 기반으로 기하광학과 음파에 관한 15주 교육 프로그램을 만들어 대학생들에게 적용하였다. 이 중 프로젝트 1개를 적용한 5주간의 자료를 수집하고 분석하였다. 적용결과, 일반 프로젝트 학습을 적용한 그룹의 TMS변화는 유의하지 않았음에 비해, 교류기억체계 기반 협력학습모형을 적용한 그룹의 TMS는 단계적으로 향상되었고, 첫째 주와 마지막 주의 차이는 통계적으로 유의하였다. 또한 실험집단은 비교집단에 비해 프로젝트 수행에서 학습전이가 더 잘 일어난 것을 확인할 수 있었다. 학생들이 협력을 통해 시너지를 얻는 방법을 익히고, 학습한 내용을 문제해결에 잘 적용하도록 하는데 교류기억체계기반 협력학습 모형이 사용될 수 있을 것이다.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.119-130
• /
• 2022

Crime is a common social problem that affects the quality of life. As the number of crimes increases, it is necessary to build a model to predict the number of crimes that may occur in a given period, identify the characteristics of a person who may commit a particular crime, and identify places where a particular crime may occur. Data privacy is the main challenge that organizations face when building this type of predictive models. Federated learning (FL) is a promising approach that overcomes data security and privacy challenges, as it enables organizations to build a machine learning model based on distributed datasets without sharing raw data or violating data privacy. In this paper, a federated long short- term memory (LSTM) model is proposed and compared with a traditional LSTM model. Proposed model is developed using TensorFlow Federated (TFF) and the Keras API to predict the number of crimes. The proposed model is applied on the Boston crime dataset. The proposed model's parameters are fine tuned to obtain minimum loss and maximum accuracy. The proposed federated LSTM model is compared with the traditional LSTM model and found that the federated LSTM model achieved lower loss, better accuracy, and higher training time than the traditional LSTM model.

• 대한전자공학회논문지SP
• /
• 제43권4호
• /
• pp.37-45
• /
• 2006

본 논문에서는 인지학에서 연구되고 있는 동질 연상 기억 현상과 장기 및 단기 기억 강화 조절 기능을 담당하는 해마의 두뇌 원리를 공학적으로 모델링한 MHLA(Modulatory Hippocampus Learning Algorithm)의 개발을 제안한다. 해마에서 중요시 하는 연관된 3단계 조직(DG, CA3, CAl)에 기반한 동질 연상 메모리를 구성하도록 하였으며, 장기 기억 학습에 모듈레이터(modulator)를 추가하여 학습 수렴 속도를 향상시켰다. 해마 구조에서 정보는 3단계 순서에 따라 치아 이랑 영역에서 통계적인 편차를 적용하여 호감도 조정에 따라서 반응 패턴으로 이진화 되고, CA3 영역에서 자기 연상 메모리를 하여 패턴이 재구성이 된다. CA3의 정보를 받는 CAI영역에서는 모듈레이터가 적용되는 신경망에 의해 장기기억 인식에 이용되는 연결n강도의 수렴이 빠르게 학습된다. MHLA의 성능을 측정하기 위하여 포즈 및 표정과 화질 상태에 따라 분류된 얼굴 영상에 PCA(Principal Component Analysis)를 적용하여 특정 벡터들을 계산하 MHLA로 학습한 후, 인식률을 확인 하였다. 실험 결과, 제안한 학습 방법을 다른 방법들과 비교하였을 때, 학습시간비용과 인식률에서 우수함을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.22.3-22
• /
• 2001

An attention task, in which context information should be extracted from the first presented pattern, and the recognition answer of the second presented pattern should be generated using the context information, is employed in this paper. An Elman-type recurrent neural network is utilized to extract and keep the context information. A reinforcement signal that indicates whether the answer is correct or not, is only a signal that the system can obtain for the learning. Only by this learning, necessary context information became to be extracted and kept, and the system became to generate the correct answers. Furthermore, the function of an associative memory is observed in the feedback loop in the Elman-type neural network.

• 전력전자학회논문지
• /
• 제27권1호
• /
• pp.48-55
• /
• 2022

This paper proposes a battery remaining useful life (RUL) prediction method using a deep learning-based EMD-CNN-LSTM hybrid method. The proposed method pre-processes capacity data by applying empirical mode decomposition (EMD) and predicts the remaining useful life using CNN-LSTM. CNN-LSTM is a hybrid method that combines convolution neural network (CNN), which analyzes spatial features, and long short term memory (LSTM), which is a deep learning technique that processes time series data analysis. The performance of the proposed remaining useful life prediction method is verified using the battery aging experiment data provided by the NASA Ames Prognostics Center of Excellence and shows higher accuracy than does the conventional method.

• Communications for Statistical Applications and Methods
• /
• 제31권2호
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• 대한본초학회지
• /
• 제28권2호
• /
• pp.25-31
• /
• 2013

Objectives : The purpose of this study was to characterize the effect of the Ethanolic extracts of Platycodon grandiflorum and its permented production the learning and memory impairments induced by scopolamine. Methods : The cognition-enhancing effect of Platycodon grandiflorum and its permented production were investigated using a passive avoidance test, the Morris water maze test and Y-maze test in mice. Drug-induced amnesia was induced by treating animals with scopolamine (1 mg/kg, i.p.). Results : The results showed that the Permented Platycodon grandiflorum extract-treated group (100 mg/kg, p.o.) and the tacrine-treated group (10 mg/kg, p.o.) significantly ameliorated scopolamine-induced amnesia based on the Passive avoidance Y-maze test and Water maze test. And these results are same manner in DPPH radical scavenger effect and Acetylcholineseterase inhibition effect. Conclusions : These results suggest that 80% Ethanol extract of fermented P.grandiflorum showed significant anti-amnestic and cognitive-enhancing activities related to the memory processes, and these activities were parallel to treatment duration and dependent of the learning models.

• 제어로봇시스템학회논문지
• /
• 제21권5호
• /
• pp.477-481
• /
• 2015

Implementation of memristor-based multilayer neural networks and their hardware-based learning architecture is investigated in this paper. Two major functions of neural networks which should be embedded in synapses are programmable memory and analog multiplication. "Memristor", which is a newly developed device, has two such major functions in it. In this paper, multilayer neural networks are implemented with memristors. A Random Weight Change algorithm is adopted and implemented in circuits for its learning. Its hardware-based learning on neural networks is two orders faster than its software counterpart.