• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.9-21
• /
• 2020

The aim of this paper is to predict the Borsa Istanbul (BIST) 30 index movements to determine the most accurate buy and sell decisions using the methods of Artificial Neural Networks (ANN) and Genetic Algorithm (GA). We combined these two methods to obtain a hybrid intelligence method, which we apply. In the financial markets, over 100 technical indicators can be used. However, several of them are preferred by analysts. In this study, we employed nine of these technical indicators. They are moving average convergence divergence (MACD), relative strength index (RSI), commodity channel index (CCI), momentum, directional movement index (DMI), stochastic oscillator, on-balance volume (OBV), average directional movement index (ADX), and simple moving averages (3-day moving average, 5-day moving average, 10-day moving average, 14-day moving average, 20-day moving average, 22-day moving average, 50-day moving average, 100-day moving average, 200-day moving average). In this regard, we combined these two techniques and obtained a hybrid intelligence method. By applying this hybrid model to each of these indicators, we forecast the movements of the Borsa Istanbul (BIST) 30 index. The experimental result indicates that our best proposed hybrid model has a successful forecast rate of 75%, which is higher than the single ANN or GA forecasting models.

• 조명전기설비학회논문지
• /
• 제12권1호
• /
• pp.103-110
• /
• 1998

부하특성의 모델링은 부하의 비선형특성 때문에 어려운 문제이다. 이 연구는 부하특성을 표현하기 위하여 비선형 문제를 근사화 할 수 있는 신경회로망을 이용하였다. 대표적인 개별부하를 선정하고 전압과 주파수 변화에 대한 유효, 무효전력의 응답을 실험을 통해 얻었다. 그리고 개별부하특성을 식별하기 위하여 실험자료를 근거로 신경회로망을 구축하고 학습하였다. 학습된 신결회로망은 또다른 전압, 주파수 변화에 대한 개별부하의 특성을 식별하였다. 아울러 제안된 방법의 타당성을 입증하기 위하여 식별된 결과를 제시하였다.

• Advances in concrete construction
• /
• 제14권2호
• /
• pp.115-130
• /
• 2022

This paper presents an application of the maturation effect on the strength of high-strength concrete which is produced with different origin aggregates. While investigating the maturation effect on HSC 384 specimens were prepared with 22 different origin aggregates. These prepared specimens were subjected to the standard compressive tests which were applied after curing for 2, 7, 28, and 56 days under appropriate conditions. The test results revealed that bright surface-low adherence behavior is valid in normal strength concretes, but is not as effective as expected in high-strength concretes. The application of artificial neural networks (ANNs) to predict 2, 7, 28, and 56 day compressive strength of HSC is also investigated in this paper. An ANN model is built, trained, and tested using the available test data gathered from experimental studies. The ANN model is found to predict 2, 7, 28, and 56 days of compressive strength of high-strength concrete well within the ranges of the input parameters considered. These comparisons show that ANNs have strong potential as a feasible tool for predicting the compressive strength of high-strength concrete within the range of the input parameters considered.

• 수산해양기술연구
• /
• 제48권1호
• /
• pp.72-81
• /
• 2012

Using artificial neural network (ANN) technique, auction prices for common mackerel were forecasted with the daily total sale and auction price data at the Busan Cooperative Fish Market before introducing Total Allowable Catch (TAC) system, when catch data had no limit in Korea. Virtual input data produced from actual data were used to improve the accuracy of prediction and the suitable neural network was induced for the prediction. We tested 35 networks to be retained 10, and found good performance network with regression ratio of 0.904 and determination coefficient of 0.695. There were significant variations between training and verification errors in this network. Ideally, it should require more training cases to avoid over-learning, which leads to improve performance and makes the results more reliable. And the precision of prediction was improved when environmental factors including physical and biological variables were added. This network for prediction of price and catch was considered to be applicable for other fishes.

• 한국지반공학회논문집
• /
• 제24권11호
• /
• pp.17-24
• /
• 2008

하천 교각에서 유발되는 국부세굴은 교량의 붕괴를 유발하는 요인들 가운데 하나로 알려져 있다. 그러나, 교각주위 하천 흐름은 매우 복잡하기 때문에 국부세굴을 정확하게 산정하는 경험식을 도출하기가 쉽지 않다. 따라서, 기존의 경험식들은 특정 세굴 자료에는 좋은 상관 관계를 보이지만 다양한 현장 세굴자료들에 대해 신뢰성 있는 예측 정도를 갖기는 어렵다. 본 연구에서는 많은 현장 계측자료를 바탕으로 국부세굴심을 산정할 수 있는 인공신경망 모델을 제안하고자 하였다. 제안된 산정식은 교각 형상, 교각 폭, 교각 길이, 흐름 입사각, 흐름 속도, 수심 및 $D_{50}$의 총 7개의 변수의 함수로 구성되었다. 인공신경망 모델의 학습과 검증에 총 426개의 현장 계측자료들이 사용되었으며, 인공신경망 모델이 기존 경험 식들에 비하여 개선된 예측정도를 보임을 확인하였다.

• ETRI Journal
• /
• 제34권5호
• /
• pp.696-705
• /
• 2012

Accurate synthesis models based on artificial neural networks (ANNs) are proposed to directly obtain the physical dimensions of an asymmetric coplanar waveguide with conductor backing and substrate overlaying (ACPWCBSO). First, the ACPWCBSO is analyzed with the conformal mapping technique (CMT) to obtain the training data. Then, a modified genetic-algorithm-Levenberg-Marquardt (GA-LM) algorithm is adopted to train ANNs. In the algorithm, the maximal relative error (MRE) is used as the fitness function of the chromosomes to guarantee that the MRE is small, while the mean square error is used as the error function in LM training to ensure that the average relative error is small. The MRE of ANNs trained with the modified GA-LM algorithm is less than 8.1%, which is smaller than those trained with the existing GA-LM algorithm and the LM algorithm (greater than 15%). Lastly, the ANN synthesis models are validated by the CMT analysis, electromagnetic simulation, and measurements.

• Wind and Structures
• /
• 제39권2호
• /
• pp.101-110
• /
• 2024

Tall buildings are distinguished by their slenderness, making them sensitive to wind loads. A huge amount of resources is typically dedicated to controlling loads and vibrations caused by wind. Enhancing tall buildings' aerodynamic performance can save a large portion of these expenses. This enhancement can be achieved through aerodynamic optimization that can be tackled either by altering the outer shape of the building locally through modifying the corners (e.g., corner chamfering) or globally through changing the whole form of the building (e.g., twisting). In this paper, a newly developed aerodynamic optimization procedure (AOP) is adopted to enhance tall buildings' aerodynamic performance. This procedure is a combination of computational fluid dynamics (CFD), Artificial Neural Networks (ANN) and Genetic algorithm (GA). An ANN-based surrogate model is used to evaluate the aerodynamic parameters through the optimization procedure to reach a reliable aerodynamic shape. Helical twisting and corner modifications of the buildings are used to reduce the along-wind base moment.

• 한국ITS학회 논문지
• /
• 제18권5호
• /
• pp.126-141
• /
• 2019

차세대첨단교통시스템(C-ITS)의 우선 도입 서비스 항목 중 하나로 차량 추돌방지 지원 서비스가 고려되고 있다. 이에 인공신경망을 적용한 V2I2V 통신 기반의 후미추돌사고 예방 방법들이 몇몇 제시되었지만, 낮은 C-ITS 단말기 보급률 및 대용량 교통정보로 인한 지연 현상 등 한계로 인해 그 효과가 미미하다. 따라서 본 연구는 실시간 구간교통 정보를 활용한 인공신경망 기반 추돌 경고 서비스(ACWS, Artificial Neural Network-based Collision Warning Service)를 제안한다. 제안 서비스는 실시간 구간 교통정보를 반영해 인공신경망의 가중치를 갱신하고 구간 진입 차량에게 제공한다. 본 연구는 C-ITS 단말 보급률과 지연시간에 따른 제안 서비스의 성능 평가를 수행한다. 분석결과 C-ITS 단말 보급률이 높고 지연시간이 낮을수록 제안 서비스가 더 나은 성능을 나타내고, 같은 조건일 경우 고도화된 인공신경망을 적용한 서비스 성능이 더 뛰어난 것으로 확인된다.

• 소성∙가공
• /
• 제29권2호
• /
• pp.89-96
• /
• 2020

The finite element method has been widely applied in the sheet metal forming process. However, the finite element method is computationally expensive and time consuming. In order to tackle this problem, surrogate modeling methods have been proposed. An artificial neural network (ANN) is one such surrogate model and has been well studied over the past decades. However, when it comes to ANN with two or more layers, so called deep neural networks (DNN), there is distinct a lack of research. We chose to use DNNs our surrogate model to predict the behavior of sheet metal in the deep drawing process. Thickness variation is selected as an output of the DNN in order to evaluate workpiece feasibility. Input variables of the DNN are radius of die, die corner and blank holder force. Finite element analysis was conducted to obtain data for surrogate model construction and testing. Sampling points were determined by full factorial, latin hyper cube and monte carlo methods. We investigated the performance of the DNN according to its structure, number of nodes and number of layers, then it was compared with a radial basis function surrogate model using various sampling methods and numbers. The results show that our DNN could be used as an efficient surrogate model for the deep drawing process.

• 한국전산구조공학회논문집
• /
• 제20권3호
• /
• pp.229-237
• /
• 2007

본 논문에서는 보 구조물의 실시간 손상위치 경보를 위해 가속도 신호를 이용한 인공신경망기반 손상검색기법을 제안하였다. 이를 위해 먼저, 실시간 손상검색을 위해 가속도 응답신호만을 이용하는 새로운 인공신경망 알고리즘을 설계하였다. 구조물의 손상상태를 나타내는 특징으로 서로 다른 두 위치에서 측정된 가속도 신호의 교차공분산 값을 이용하였다. 다음으로 실제 하중조건을 모르는 상황을 고려하여 다양한 하중패턴에 따른 복수 신경망을 구성하였으며, 각각의 신경망 학습을 위한 손상시나리오를 선정하였다. 마지막으로 양단 자유보 모형실험을 통해 제안된 기법의 유용성과 적용성을 평가하였다.