• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.

• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.152-162
• /
• 2022

This study developed simulation model for predicting the greenhouse interior environment using artificial intelligence machine learning techniques. Various methods have been studied to predict the internal environment of the greenhouse system. But the traditional simulation analysis method has a problem of low precision due to extraneous variables. In order to solve this problem, we developed a model for predicting the temperature inside the greenhouse using machine learning. Machine learning models are developed through data collection, characteristic analysis, and learning, and the accuracy of the model varies greatly depending on parameters and learning methods. Therefore, an optimal model derivation method according to data characteristics is required. As a result of the model development, the model accuracy increased as the parameters of the hidden unit increased. Optimal model was derived from the GRU algorithm and hidden unit 6 (r² = 0.9848 and RMSE = 0.5857℃). Through this study, it was confirmed that it is possible to develop a predictive model for the temperature inside the greenhouse using data outside the greenhouse. In addition, it was confirmed that application and comparative analysis were necessary for various greenhouse data. It is necessary that research for development environmental control system by improving the developed model to the forecasting stage.

• Journal of Advanced Marine Engineering and Technology
• /
• v.41 no.3
• /
• pp.258-268
• /
• 2017

In this study, we aim to converge a technology for analyzing the hydraulic circuit of a loading arm with an- other one for analyzing multi-body dynamics by utilizing analysis software SimulationX. Further, this study intends to overcome the limitations of the existing technology for analyzing a hydraulic circuit with a variation at the rotation center of the moving mass and the difficulty of incorporating the behavior in a gravity field. First, the specifications of the hydraulic circuit components were reflected in an analysis model to secure reliability. Hydraulic circuit modeling was then performed using a single analysis model with a verified reliability. Subsequently, the multi-body system (MBS) model of the loading arm was formed. Finally, the analysis model of the hydraulic circuit and the MBS model were converged to check if the circuit analysis result was exactly reflected in the MBS model. The convergence analysis model has development cost-saving effect because it is capable of predicting the dynamic behavior of an object without the prototype.

• Journal of Biomedical Engineering Research
• /
• v.22 no.1
• /
• pp.69-80
• /
• 2001

본 연구에서는 환자의 골다공증 유무에 따른 내고정 장치 시술 직후 및 융합 후의 안정성을 평가하기 위해 다양한 하중 모드에서 C5-C6 운동분절의 생체역학적 거동을 분석하였다. 이러한 목적으로 먼저, C5-C6 경추부의 유한요소 모델을 구현하여 검증하였다. 모델의 결과는 기존 실험치와 유사하여 신뢰성이 부여되었다. 검증된 모델은 Smith-Robinson 방식으로 골이식물을 삽입한 후 전방 내고정 장치를 적용한 시술 상황을 재현하기 위해 수정되었다. 수정된 모델은 두 종류로 구현되었다. (1) 첫 번째 모델에서는, 시술 직후의 상황을 재현하기 위해 골이식물과 종판의 경계면에 접촉요소를 사용하였다. (2)두 번째 모델에서는 완전히 융합된 상황을 나타내기 위해 골이식물을 종판에 고정하였다. 골다공증의 효과를 예측하기 위하여 두 모델의 해면골에 대한 탄성계수를 변화시켰다(정상: 100MPa, 골다공증: 40MPa). 각 모델의 C5 주체의 상위면에 73.6N의 압축 하중을 가한 후에 108Nm의 굴곡/신전, 굽힘, 비틀림 하중을 가하였으며, C6 추체의 하단면은 모든 방향에 대하여 구속하였다. 전체적인 결과에 있어서 상대적 회전운동, 미끄럼운동, 골이식물 내에서의 von Mises 응력의 경우 정상 모델에 비해 골다공증 모델에서 증가함을 보였으며, 특히 시술 직후의 모델에서 비틀림 하중이 가해진 경우, 상대적 회전운동 및 미끄럼 운동이 가장 높게 예측되었다. 이는 골다공증환자에게 전방 내고정 장치를 시술한 경우 골이식물의 파단 및 유합의 실패가 비틀림 하중에서 발생할 수 있음을 나타낸다. 해면골의 von Mises 응력은 시술 직후에 골다공증 모델의 모든 하중 모드에서, 유합 후에는 굽힘 하중 외의 모든 하중에서 ultimate strength를 초과하는 것으로 나타나 골다공증 환자에게 screw의 해리가 발생할 가능성이 높은 것으로 예측되었다. 따라서 골다공증 환자에게 과도한 운동이 발생하지 않도록 하기 위해서 시술 후 세심한 주의와 halo 같은 견고한 정형술이 필요할 것으로 사료된다.

• The Journal of Society for e-Business Studies
• /
• v.16 no.4
• /
• pp.335-357
• /
• 2011

In this paper, we report the empirical study results theorizing IPTV user's loyalty formation process. Considering the convergent characteristics ofinnovative media and telecommunication, we employed innovation adoption and diffusion as our theoretical framework for research model development. As the purpose of this research includes verification of detail attributes of IPTV service, we formulated structural model which treats relative advantage as the second order factor, of which incorporates the seven detail attributes as the first order factors. Then, using the data collected from 250 Korean IPTV subscribers, the model is validated and relevant attributes are identified through PLS analysis. The results provide insights for future research on the adoption and diffusion of new digital convergent high-tech services.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.161-168
• /
• 2021

Cracks affect the robustness of infrastructures such as buildings, bridge, pavement, and pipelines. This paper presents an automated crack detection system which detect cracks in diverse surfaces. We first constructed the combined crack dataset, consists of multiple crack datasets in diverse domains presented in prior studies. Then, state-of-the-art deep learning models in computer vision tasks including VGG, ResNet, WideResNet, ResNeXt, DenseNet, and EfficientNet, were used to validate the performance of crack detection. We divided the combined dataset into train (80%) and test set (20%) to evaluate the employed models. DenseNet121 showed the highest accuracy at 96.20% with relatively low number of parameters compared to other models. Based on the validation procedures of the advanced deep learning models in crack detection task, we shed light on the cost-effective automated crack detection system which can be applied to different surfaces and structures with low computing resources.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1065-1074
• /
• 2007

Among various methods to compare reference signatures with an input signature, the segment-to-segment matching method has more advantages than global and point-to-point methods. However, the segment-to-segment matching method has the problem of having lower recognition rate according to the variation of partitioning points. To resolve this drawback, this paper proposes a signature verification method by considering linear discriminant analysis as well as segment-to-segment matching method. For the final decision step, we adopt statistical based Bayesian classifier technique to effectively combine two individual systems. Under the various experiments, the proposed method shows better performance than segment-to-segment based matching method.

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.297-302
• /
• 2015

The increase in applying IT to vehicles has given birth to smart cars or connected cars. As smarts cars become connected with external network systems, threats to communication security are on the rise. With simulation test results supporting such threats to Convergence security in vehicular communication, concerns are raised over relevant vulnerabilities, while an increasing number of studies on secure vehicular communication are published. Hacking attacks against vehicles are more dangerous than other types of hacking attempts because such attacks may threaten drivers' lives and cause social instability. This paper designed a Convergence security protocol for inter-vehicle and intra-vehicle communication using a hash function, nonce, public keys, time stamps and passwords. The proposed protocol was tested with a formal verification tool, Casper/FDR, and found secure and safe against external attacks.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.734-747
• /
• 2015

The aging population and the advancement of science and technology are transforming the healthcare industry to focus on health management for the prevention of diseases. The U-health and remote healthcare services have not yet achieved the social agreement in the nation; however, these have been extensively used in the global scale. The innovation of user experience through cognitive computing are expected to increase the health effects of consumers, by converging with healthcare information services. This study suggests the conceptual model of healthcare information service converged with cognitive computing. Then, the acceptance factors for consumers have been investigated. For this purpose, reliability and validity analysis have been conducted using an online survey. The path analysis was performed to verify the hypotheses and moderating effect based upon the gender, by using structural equation modeling.

• Review of KIISC
• /
• v.29 no.3
• /
• pp.29-36
• /
• 2019

폭발적으로 성장하는 소셜 미디어 서비스로 인해 개인간의 연결이 강화된 환경에서는 URL로써 전파되는 피싱 공격의 위험성이 크게 강조된다. 최근 텍스트 분류 및 모델링 분야에서 그 성능을 입증받은 딥러닝 알고리즘은 피싱 URL의 구문적, 의미적 특징을 각각 모델링하기에 적절하지만, 기존에 사용하는 규칙 기반 앙상블 방법으로는 문자와 단어로부터 추출되는 특징간의 비선형적인 관계를 효과적으로 융합하는데 한계가 있다. 본 논문에서는 피싱 URL의 구문적, 의미적 특징을 체계적으로 융합하기 위한 컨볼루션 신경망 기반의 퓨전 신경망을 제안하고 기계학습 방법 중 최고의 분류정확도 (0.9804)를 달성하였다. 학습 및 테스트 데이터셋으로 45,000건의 정상 URL과 15,000건의 피싱 URL을 수집하였고, 정량적 검증으로 10겹 교차검증과 ROC커브, 정성적 검증으로 오분류 케이스와 딥러닝 내부 파라미터를 시각화하여 분석하였다.