• 대한조선학회논문집
• /
• 제35권3호
• /
• pp.79-87
• /
• 1998

본 연구는 선박의 개념 설계 단계에서 설계 변수-주요 치수 및 선형 요소 등-들을 효율적으로 도출할 수 있는 선박 설계용 뉴로 퍼지 시스템 개발을 내용으로 한다. 선박 설계용 뉴로 퍼지 시스템(NeFHull)은 주어진 입출력 데이터에 대한 정보를 퍼지 이론으로 처리하여, 이를 신경회로망에 적용하는 것으로, 무차원화한 입출력 데이터로부터 소속 함수로 입력 패턴을 재 정의한 후, 신경 회로망으로 그 정보를 처리한다. 신경 회로망 학습에는 혼합 학습 방법을 사용하였으며, 수학적 공학적 예를 통해 본 방법을 유용성을 검토하였다.

• 한국지능시스템학회논문지
• /
• 제9권5호
• /
• pp.490-495
• /
• 1999

본 논문에서는 보로노이 다이아그램을 이용하여 오류 역전파 신경망의 초기값을 결정할수 있는 VoD_EBP를 제안하였다. VoD_EBP는 초기 연결 가중치와 임계값을 공학적 계산방법으로 결정함으로써 기존의 EBP에서 자주 발생하는 학습 마비 현상을 피할수 있고 초기부터 빠른 속도로 학습이 진행되므로 학습횟수를 단축시킬수 있다, 또한 VoD_EBP는 은닉층의 노드 수를 보로노이 다각형으로 구분된 클러스터들의 개수로 정할 수있어 신경망 설계에 신뢰성을 향상시켰다. 제시된 VoD_EBP의 효율성을 입증하기 위해 간단한 실험으로 2차원 입력벡터를 갖는 XOR 문제와 3차원 패리티 코드 검출 문제에 대하여 적용하여 보았다. 그 결과 임의의 초기값으로 설정하였던 EBP보다 훨씬 빠르게 학습이 종료되었고, 지역 최소치에 빠져 학습이 진행되지 못하는 현상이 발생하지 않았다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2006년도 춘계종합학술대회
• /
• pp.335-339
• /
• 2006

자궁 경부 세포진 영상의 핵 영역 분할은 자궁 경부암 자동화 검색 시스템의 가장 어렵고도 중요한 분야로 알려져 있다. 자궁 경부 세포진 영상은 배경과 세포의 영역이 확실히 구분되지 않는 경우가 많기 때문에 이들을 확실히 구분하는 것이 매우 중요하다. 본 논문에서는 이러한 문제점을 해결하기 위해 자궁 경부 세포진 영상에서 Region growing 기법을 적용하여 세포 영상을 분할한다. Region growing 기법은 화소간의 유사도를 측정하여 영역을 확장하여 분할하는 방법이다. 세포와 배경이 분할된 영상을 일정 임계값을 이용하여 영상을 이진화 한 후, 8방향 윤곽선 추적 알고리즘을 이용해 세포 영역을 추출한다. 추출된 세포 영역을 원 영상인 RGB 컬러로 변환한 후에 K-means 알고리즘을 적용하여 각 세포 영역의 RGB 화소를 R, G, B 채널로 각각 분리하여 클러스터링한다. 클러스터링된 각각의 R, G, B 채널의 클러스터 값을 이용하여 HSI 모델로 변환시킨 후에 세포핵 영역의 Hue 정보를 추출한다. 추출된 세포핵의 특징을 오류 역전파 알고리즘을 적용하여 정상 세포와 비정상 세포를 분류하고 인식한다.

• 산업기술연구
• /
• 제41권1호
• /
• pp.1-6
• /
• 2021

Fly ash and silica fume belong to industry by-products that can be used to produce concrete. This study shows the model of a neural network to evaluate the strength development of blended concrete containing fly ash and silica fume. The neural network model has four input parameters, such as fly ash replacement content, silica fume replacement content, water/binder ratio, and ages. Strength is the output variable of neural network. Based on the backpropagation algorithm, the values of elements in the hidden layer of neural network are determined. The number of neurons in the hidden layer is confirmed based on trial calculations. We find (1) neural network can give a reasonable evaluation of the strength development of composite concrete. Neural network can reflect the improvement of strength due to silica fume additions and can consider the reductions of strength as water/binder increases. (2) When the number of neurons in the hidden layer is five, the prediction results show more accuracy than four neurons in the hidden layer. Moreover, five neurons in the hidden layer can reproduce the strength crossover between fly ash concrete and plain concrete. Summarily, the neural network-based model is valuable for design sustainable composite concrete containing silica fume and fly ash.

• Journal of Biosystems Engineering
• /
• 제43권4호
• /
• pp.352-361
• /
• 2018

Purpose: The objective of this study was to develop a multilayer perceptron (MLP) model to estimate solar radiation using a solar module. Methods: Data for the short-circuit current of a solar module and other environmental parameters were collected for a year. For MLP learning, 14,400 combinations of input variables, learning rates, activation functions, numbers of layers, and numbers of neurons were trained. The best MLP model employed the batch backpropagation algorithm with all input variables and two hidden layers. Results: The root-mean-squared error (RMSE) of each learning cycle and its average over three repetitions were calculated. The average RMSE of the best artificial neural network model was $48.13W{\cdot}m^{-2}$. This result was better than that obtained for the regression model, for which the RMSE was $66.67W{\cdot}m^{-2}$. Conclusions: It is possible to utilize a solar module as a power source and a sensor to measure solar radiation for an agricultural sensor node.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2414-2433
• /
• 2021

This article focuses on providing remedial solutions for COVID disease through the data collection process. Recently, In India, sudden human losses are happening due to the spread of infectious viruses. All people are not able to differentiate the number of affected people and their locations. Therefore, the proposed method integrates robotic technology for monitoring the health condition of different people. If any individual is affected by infectious disease, then data will be collected and within a short span of time, it will be reported to the control center. Once, the information is collected, then all individuals can access the same using an application platform. The application platform will be developed based on certain parametric values, where the location of each individual will be retained. For precise application development, the parametric values related to the identification process such as sub-interval points and intensity of detection should be established. Therefore, to check the effectiveness of the proposed robotic technology, an online monitoring system is employed where the output is realized using MATLAB. From simulated values, it is observed that the proposed method outperforms the existing method in terms of data quality with an observed percentage of 82.

• Steel and Composite Structures
• /
• 제44권1호
• /
• pp.119-139
• /
• 2022

This paper aims to use the artificial intelligence approach to develop a new model for predicting the ultimate axial strength of the circular concrete-filled steel tubular (CFST) stub columns. For this, the results of 314 experimentally tested circular CFST stub columns were employed in the generation of the design model. Since the influence of the column diameter, steel tube thickness, concrete compressive strength, steel tube yield strength, and column length on the ultimate axial strengths of columns were investigated in these experimental studies, here, in the development of the design model, these variables were taken into account as input parameters. The model was developed using the backpropagation algorithm named Bayesian Regularization. The accuracy, reliability, and consistency of the developed model were evaluated statistically, and also the design formulae given in the codes (EC4, ACI, AS, AIJ, and AISC) and the previous empirical formulations proposed by other researchers were used for the validation and comparison purposes. Based on this evaluation, it can be expressed that the developed design model has a strong and reliable prediction performance with a considerably high coefficient of determination (R-squared) value of 0.9994 and a low average percent error of 4.61. Besides, the sensitivity of the developed model was also monitored in terms of dimensional properties of columns and mechanical characteristics of materials. As a consequence, it can be stated that for the design of the ultimate axial capacity of the circular CFST stub columns, a novel artificial intelligence-based design model with a good and robust prediction performance was proposed herein.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 춘계학술발표대회
• /
• pp.334-337
• /
• 2010

디지털 선박 운행시 예기치 못한 상황에 의한 선박 내 화재나 충돌 등 긴급 상황 발생 시에 대형의 해난 사고가 발생할 수 있다. 이에 본 논문에서는 선박 상태를 자체 진단하여 모니터링하고 위험 분석을 통해 관리할 수 있는 시스템을 구현하고자 한다. 해양 디지털선박의 환경, 상황을 수집할 수 있는 무선 센서를 이용하여 수집된 환경 정보를 분석하는 시스템을 제안하였으며, 센싱된 데이터를 분석하기 위하여 역전파 신경망을 설계하였다. 300개의 데이터 집합을 사용하여 역전파 신경망을 실험한 결과 약 96%의 정확도를 가졌다. 제안된 시스템은 하드웨어 (UStar-2400 ISP, UStar-2400, Wireless sensors) 부분과 소프트웨어 부분(User Interface module)으로 구성되며 소프트웨어 부분은 HOST PC에 삽입된다. 그리고 시스템의 정확도를 개선하기 위하여 전방향 에러 정정 시스템(LDPC)을 구현하였고 진단된 결과는 CDMA 방식으로 전송하여 해양디지털선박 감지 모니터링 시스템을 구현했다.

• Geomechanics and Engineering
• /
• 재33권6호
• /
• pp.611-624
• /
• 2023

Soil properties make it attractive as a building material due to its mechanical strength, aesthetically appearance, plasticity, and low cost. However, it is frequently necessary to improve and stabilize the soil mechanical properties with binders. Soil-cement is applied for purposes ranging from housing to dams, roads and foundations. Unconfined compression strength (UCS) and split tensile strength (CD) are essential mechanical parameters for ascertaining the aptitude of soil-cement for a given application. However, quantifying these parameters requires specimen preparation, testing, and several weeks. Methodologies that allowed accurate estimation of mechanical parameters in shorter time would represent an important advance in order to ensure shorter deliverable timeline and reduce the amount of laboratory work. In this work, an extensive campaign of UCS and CD tests was carried out in a sandy soil from the Leiria region (Portugal). Then, using the machine learning tool Neural Pattern Recognition of the MATLAB software, a prediction of these two parameters based on six input parameters was made. The results, especially those obtained with resource to a Bayesian regularization-backpropagation algorithm, are frankly positive, with a forecast success percentage over 90% and very low root mean square error (RMSE).