• 드라이브 ㆍ 컨트롤
• /
• 제20권4호
• /
• pp.133-139
• /
• 2023

A weighing system calculates the bucket's excavation amount of an excavator. Usually, the excavation amount is computed by the excavator's motion equations with sensing data. But these motion equations have computing errors that are induced by assumptions to the linear systems and identification of the equation's parameters. To reduce computing errors, some commercial weighing system incorporates particular motion into the excavation process. This study introduces a linear regression model on an artificial neural network that has fewer predicted errors and doesn't need a particular pose during an excavation. Time serial data were gathered from a 30tons excavator's loading test. Then these data were preprocessed to be adjusted by MPL (Multi Layer Perceptron) or CNN (Convolutional Neural Network) based linear regression models. Each model was trained by changing hyperparameter such as layer or node numbers, drop-out rate, and kernel size. Finally ID-CNN-based linear regression model was selected.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• Korean Journal of Radiology
• /
• 제24권7호
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• Nuclear Engineering and Technology
• /
• 제55권12호
• /
• pp.4607-4616
• /
• 2023

We implement machine learning regression models to predict peak pressures of primary and secondary systems, a major safety concern in Loss Of Condenser Vacuum (LOCV) accident. We selected the Multi-dimensional Analysis of Reactor Safety-KINS standard (MARS-KS) code to analyze the LOCV accident, and the reference plant is the Korean Optimized Power Reactor 1000MWe (OPR1000). eXtreme Gradient Boosting (XGBoost) is selected as a machine learning tool. The MARS-KS code is used to generate LOCV accident data and the data is applied to train the machine learning model. Hyperparameter optimization is performed using a simulated annealing. The randomly generated combination of initial conditions within the operating range is put into the input of the XGBoost model to predict the peak pressure. These initial conditions that cause peak pressure with MARS-KS generate the results. After such a process, the error between the predicted value and the code output is calculated. Uncertainty about the machine learning model is also calculated to verify the model accuracy. The machine learning model presented in this paper successfully identifies a combination of initial conditions that produce a more conservative peak pressure than the values calculated with existing methodologies.

• 한국건설관리학회논문집
• /
• 제21권6호
• /
• pp.38-45
• /
• 2020

본 연구는 양방향 LSTM, Random Search, 데이터 조합, Dropout을 이용한 철근 가격 단기예측 딥러닝 모델을 개발하는 체계적인 절차를 제시한다. 일반적으로 사용자가 직관적으로 이러한 값을 결정하여 예측성능이 우수한 결과를 탐색하는데 시간이 많이 걸리고 반복적인 시도를 하게 되는데, 이러한 시도로 찾아낸 결과가 우수하다고 보장할 수 없다. 본 연구에서 제시하는 제안된 접근방식으로 단기 가격예측의 평균 정확도는 약 98.32%이다. 그리고 이 방식은 철근 이외의 건축재료를 비롯하여 통계기반의 시계열 데이터로 가격을 예측하는 연구에서 본 연구에서 제시한 내용이 우수한 예측결과를 도출하기 위한 기초적 자료로 활용될 수 있을 것이다.

• 한국공간구조학회논문집
• /
• 제20권2호
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1328-1336
• /
• 2019

안전하고 최적의 배터리 성능을 유지하기 위해 정확한 충전상태(SOC) 추정 기술이 필수적이다. 본 논문에서는 기존의 전류적산 방법이 가지고 있는 문제를 해결하기 위해 시간 종속성을 가지는 인공지능 기반의 LSTM을 이용한 SOC 추정 방법을 적용하였다. 훈련과 검증에 필요한 데이터는 전기적 실험을 통해 일정 크기로 방전된 전류, 전압, 온도를 수집하였고 학습을 위한 입력데이터의 질을 향상시키기 위해 데이터 전처리를 수행하였다. 또한, LSTM 모델의 구조 및 하이퍼파라미터 설정에 따른 학습 능력과 SOC 추정 성능을 비교하였다. 학습한 모델은 UDDS 프로파일을 통해 검증하였으며, RMSE 0.82%, MAX 2.54%의 추정 정확도를 달성하였다.

• 한국정보통신학회논문지
• /
• 제21권10호
• /
• pp.1909-1916
• /
• 2017

최근 딥 러닝 알고리듬이 다양한 분야에 적용되어 좋은 성능을 내고 있지만, 소나시스템에는 아직 활발히 적용되지 않고 있다. 본 논문에서는 기뢰와 같은 금속 물체와 바위로부터 반사된 능동소나 수신음 데이터를 딥 러닝 알고리듬의 하나인 컨볼루션 신경망으로 식별하는 실험을 수행하였다. 과적합 방지 및 성능 향상을 위해 데이터 확장을 하였고, 확장 및 하이퍼파라미터 값 변화에 따른 성능 변화를 분석하였다. 훈련데이터를 수신각도에 독립적인 경우와 의존적인 경우로 나누어 실험을 수행하였고, 그 결과 각각 88.9%, 94.9%의 성능을 보였다. 이는 이전 연구에서 인공신경망 및 Support Vector Machine 알고리듬을 적용하여 얻은 성능보다 최대 4.5% 포인트 향상되었다.

• 전기전자학회논문지
• /
• 제24권3호
• /
• pp.766-776
• /
• 2020

최근 기계학습에 대한 관심이 높아지고 연구가 활성화됨에 따라 다양한 기계학습 모델에서 최적의 하이퍼 파라미터 조합을 찾는 것이 중요해지고 있다. 본 논문에서는 다양한 하이퍼 파라미터 중에서 옵티마이저에 중점을 두고, 다양한 데이터에서 주요 옵티마이저들의 성능을 측정하고 비교하였다. 특히, 가장 기본이 되는 SGD부터 Momentum, NAG, AdaGrad, RMSProp, AdaDelta, Adam, AdaMax, Nadam까지 총 9개의 옵티마이저의 성능을 MNIST, CIFAR-10, IRIS, TITANIC, Boston Housing Price 데이터를 이용하여 비교하였다. 실험 결과, 전체적으로 Adam과 Nadam을 사용하였을 때 기계학습 모델의 손실 함숫값이 가장 빠르게 감소하는 것을 확인할 수 있었으며, F1 score 또한 높아짐을 확인할 수 있었다. 한편, AdaMax는 학습 중에 불안정한 모습을 많이 보여주었으며, AdaDelta는 다른 옵티마이저들에 비하여 수렴 속도가 느리며 성능이 낮은 것을 확인할 수 있었다.