• 한국수자원학회논문집
• /
• 제56권11호
• /
• pp.801-813
• /
• 2023

최근 인공신경망(Artificial Neural Network, ANN)의 연구가 활발하게 진행되면서 ANN을 이용하여 하천의 수질을 예측하는 연구가 진행되고 있다. 그러나 ANN은 Black-box의 형태이기 때문에 ANN 내부의 연산과정을 분석하는데 어려움이 있다. ANN의 연산과정을 분석하기 위해 설명가능한 인공지능(eXplainable Artificial Intelligence, XAI) 기술이 사용되고 있으나, 수자원 분야에서 XAI 기술을 활용한 연구는 미비한 실정이다. 본 연구는 XAI 기술 중 Layer-wise Relevance Propagation (LRP)을 사용하여 낙동강의 다산 수질관측소의 수온, 용존산소량, 수소이온농도 및 엽록소-a를 예측하기 위한 Multi Layer Perceptron (MLP)을 분석하였다. LRP를 기반으로 수질을 학습한 MLP를 분석하여 수질을 예측하기 위한 최적의 입력자료를 선정하고, 최적의 입력자료를 이용하여 학습한 MLP의 예측결과에 대한 분석을 실시하였다. LRP를 이용하여 최적의 입력자료를 선정한 결과를 보면, 수온, 용존산소량, 수소이온농도 및 엽록소-a 모두 주변지역의 일 강수량을 제외한 입력자료를 학습한 MLP의 예측정확도가 가장 높았다. MLP의 용존산소량 예측결과에 대한 분석결과를 보면, 최고점에서 수소이온농도 및 용존산소량의 영향이 크고 최저점에서는 수온의 영향이 큰 것으로 분석되었다.

• 한국수자원학회논문집
• /
• 제49권10호
• /
• pp.877-885
• /
• 2016

본 연구에서는 기상학적 가뭄지수인 표준강수지수(Standardized Precipitation Index, SPI)를 이용하여 우리나라 전역에 대한 가뭄예측의 시공간적인 평가를 수행하였다. 또한 다층 퍼셉트론 인공신경망(Multi Layer Perceptron-Artificial Neural Network, MLP-ANN) 예측 기법을 이용하여 SPI(3), (6)에 대한 선행예보시간별 가뭄 예측을 실시하였다. 입력 자료는 기상청 산하의 59개 관측소에서 관측된 기상자료를 활용하였고, 관측자료 기간은 1976~2015년이다. 예측 모델의 성능평가는 기준점(Threshold)에 따른 가뭄 발생유무와 같은 이진분류 혼동행렬을 구성하여 Receiver Operating Characteristics (ROC) score와 조건부 확률에 따른 F score를 산정하여 예측 성능평가를 수행하였다. 예측성능에 대한 ROC 분석결과 다층 퍼셉트론 인공신경망(MLP-ANN) 모형을 적용한 가뭄예측성능이 매우 우수한 것으로 나타났으며, SPI (3)은 2개월, SPI (6)는 5개월 정도의 선행예측이 충분히 가능한 것으로 나타났다.

• Computers and Concrete
• /
• 제34권2호
• /
• pp.151-168
• /
• 2024

This research aimed to appraise the effectiveness of four optimization approaches - cuckoo optimization algorithm (COA), multi-verse optimization (MVO), particle swarm optimization (PSO), and teaching-learning-based optimization (TLBO) - that were enhanced with an artificial neural network (ANN) in predicting the bearing capacity of shallow foundations located on cohesionless soils. The study utilized a database of 97 laboratory experiments, with 68 experiments for training data sets and 29 for testing data sets. The ANN algorithms were optimized by adjusting various variables, such as population size and number of neurons in each hidden layer, through trial-and-error techniques. Input parameters used for analysis included width, depth, geometry, unit weight, and angle of shearing resistance. After performing sensitivity analysis, it was determined that the optimized architecture for the ANN structure was 5×5×1. The study found that all four models demonstrated exceptional prediction performance: COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP. It is worth noting that the MVO-MLP model exhibited superior accuracy in generating network outputs for predicting measured values compared to the other models. The training data sets showed R² and RMSE values of (0.07184 and 0.9819), (0.04536 and 0.9928), (0.09194 and 0.9702), and (0.04714 and 0.9923) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively. Similarly, the testing data sets produced R² and RMSE values of (0.08126 and 0.07218), (0.07218 and 0.9814), (0.10827 and 0.95764), and (0.09886 and 0.96481) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.135-135
• /
• 2021

In water resources management, rainfall prediction with high accuracy is still one of controversial issues particularly in countries facing heavy rainfall during wet seasons in the monsoon climate. The aim of this study is to develop an artificial neural network (ANN) for predicting future six months of rainfall data (from April to September 2020) from daily meteorological data (from 1971 to 2019) such as rainfall, temperature, wind speed, and humidity at Seoul, Korea. After normalizing these data, they were trained by using a multilayer perceptron (MLP) as a class of the feedforward ANN with 15,000 neurons. The results show that the proposed method can analyze the relation between meteorological datasets properly and predict rainfall data for future six months in 2020, with an overall accuracy over almost 70% and a root mean square error of 0.0098. This study demonstrates the possibility and potential of MLP's applications to predict future daily rainfall patterns, essential for managing flood risks and protecting water resources.

• 한국항해항만학회지
• /
• 제35권1호
• /
• pp.83-91
• /
• 2011

예측의 정확성은 비용의 감소나 고객서비스의 제고를 위해 필수적으로 선행되어야 하기에 현재까지도 많은 연구자들에 의해 연구되고 있는 분야이다. 본 연구에서는 국내 항만의 컨테이너 물동량 예측에 있어 대표적인 비선형예측모형인 인공신경망모형과 ARIMA모형에 대한 비교연구를 수행하는데 목적을 두었고, 컨테이너 물동량 예측력 제고를 위해 ARIMA모형과 인공신경망(ANN)모형을 결합한 하이브리드모형을 사용해 다른 모형들과 예측성과를 비교하고자 한다. 특히 인공신경망모형의 네트워크 구조 설계에 부분에 있어 방대하며 복잡한 탐색공간에서도 전역해 찾기에 효과적인 기법으로 알려져 있는 유전알고리즘을 사용함과 동시에 인공신경망의 대표적인 모형으로 알려진 다층 퍼셉트론(MLP)뿐만 아니라 시간지연네트워크(TDNN)를 사용해 예측성과를 비교하였다. 그 결과 ANN모형과 하이브리드모형이 ARIMA모형보다 더 뛰어난 예측성과를 보이는 것으로 나왔다.

• Steel and Composite Structures
• /
• 제51권4호
• /
• pp.417-440
• /
• 2024

Artificial neural networks (ANN) have been the focus of several studies when it comes to evaluating the pile's bearing capacity. Nonetheless, the principal drawbacks of employing this method are the sluggish rate of convergence and the constraints of ANN in locating global minima. The current work aimed to build four ANN-based prediction models enhanced with methods from the black hole algorithm (BHA), league championship algorithm (LCA), shuffled complex evolution (SCE), and symbiotic organisms search (SOS) to estimate the carrying capacity of piles in cold climates. To provide the crucial dataset required to build the model, fifty-eight concrete pile experiments were conducted. The pile geometrical properties, internal friction angle 𝛗 shaft, internal friction angle 𝛗 tip, pile length, pile area, and vertical effective stress were established as the network inputs, and the BHA, LCA, SCE, and SOS-based ANN models were set up to provide the pile bearing capacity as the output. Following a sensitivity analysis to determine the optimal BHA, LCA, SCE, and SOS parameters and a train and test procedure to determine the optimal network architecture or the number of hidden nodes, the best prediction approach was selected. The outcomes show a good agreement between the measured bearing capabilities and the pile bearing capacities forecasted by SCE-MLP. The testing dataset's respective mean square error and coefficient of determination, which are 0.91846 and 391.1539, indicate that using the SCE-MLP approach as a practical, efficient, and highly reliable technique to forecast the pile's bearing capacity is advantageous.

• 센서학회지
• /
• 제29권1호
• /
• pp.19-26
• /
• 2020

Electrocardiogram (ECG) classification has become an essential task of modern day wearable devices, and can be used to detect cardiovascular diseases. State-of-the-art Artificial Intelligence (AI)-based ECG classifiers have been designed using various artificial neural networks (ANNs). Despite their high accuracy, ANNs require significant computational resources and power. Herein, three different ANNs have been compared: multilayer perceptron (MLP), convolutional neural network (CNN), and spiking neural network (SNN) only for the ECG classification. The ANN model has been developed in Python and Theano, trained on a central processing unit (CPU) platform, and deployed on a PYNQ-Z2 FPGA board to validate the model using a Jupyter notebook. Meanwhile, the hardware accelerator is designed with Overlay, which is a hardware library on PYNQ. For classification, the MIT-BIH dataset obtained from the Physionet library is used. The resulting ANN system can accurately classify four ECG types: normal, atrial premature contraction, left bundle branch block, and premature ventricular contraction. The performance of the ECG classifier models is evaluated based on accuracy and power. Among the three AI algorithms, the SNN requires the lowest power consumption of 0.226 W on-chip, followed by MLP (1.677 W), and CNN (2.266 W). However, the highest accuracy is achieved by the CNN (95%), followed by MLP (76%) and SNN (90%).

• 전기전자학회논문지
• /
• 제22권1호
• /
• pp.197-200
• /
• 2018

본 논문에서는 하드웨어레벨로 구현이 어렵고 속도가 느린 sigmoid 함수를 PLAN을 이용하여 근사치로 출력하였다. 이를 MLP 구조의 활성화 함수로 사용하여 자원소모를 줄이고 속도를 개선하고자 하였다. 본 논문에서 제안하는 방법은 $5{\times}5$크기의 숫자 인식에 약 95%의 정확도를 유지하면서 GPGPU보다 약 1.83배의 빠른 속도를 보였다. 또한 MLPA가속기와 비슷한 자원을 사용함에도 더 많은 뉴런을 사용하여 높은 정확도에 빠른 속도로 수렴하는 것을 확인하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 하계학술대회 논문집 D
• /
• pp.2091-2093
• /
• 2003

Generally, the correlation between the responses of various sensors can be exploited to detect a possible malfunctioning sensor during operation. The sensor fault detection is implemented by using the regression ability of artificial neural networks(ANN). In this work, sensor fault detection scheme based on ANN is proposed. To verify its applicability, simulation study on the water data gathered from Saemangeum measurement stations is executed.

• Computers and Concrete
• /
• 제32권2호
• /
• pp.217-232
• /
• 2023

Numerous studies have been performed on the behavior of pile foundations in cold regions. This study first attempted to employ artificial neural networks (ANN) to predict pile-bearing capacity focusing on pile data recorded primarily on cold regions. As the ANN technique has disadvantages such as finding global minima or slower convergence rates, this study in the second phase deals with the development of an ANN-based predictive model improved with an Elephant herding optimizer (EHO), Dragonfly Algorithm (DA), Genetic Algorithm (GA), and Evolution Strategy (ES) methods for predicting the piles' bearing capacity. The network inputs included the pile geometrical features, pile area (m²), pile length (m), internal friction angle along the pile body and pile tip (Ø°), and effective vertical stress. The MLP model pile's output was the ultimate bearing capacity. A sensitivity analysis was performed to determine the optimum parameters to select the best predictive model. A trial-and-error technique was also used to find the optimum network architecture and the number of hidden nodes. According to the results, there is a good consistency between the pile-bearing DA-MLP-predicted capacities and the measured bearing capacities. Based on the R2 and determination coefficient as 0.90364 and 0.8643 for testing and training datasets, respectively, it is suggested that the DA-MLP model can be effectively implemented with higher reliability, efficiency, and practicability to predict the bearing capacity of piles.