• The Transactions of the Korean Institute of Power Electronics
• /
• v.26 no.3
• /
• pp.183-191
• /
• 2021

A battery management system (BMS) provides some functions for ensuring safety and reliability that includes algorithms estimating battery states. Given the changes caused by various operating conditions, the state-of-health (SOH), which represents a figure of merit of the battery's ability to store and deliver energy, becomes challenging to estimate. Machine learning methods can be applied to perform accurate SOH estimation. In this study, we propose a Long-Term Recurrent Convolutional Network (LRCN) that combines the Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) to extract aging characteristics and learn temporal mechanisms. The dataset collected by the battery aging experiments of NASA PCoE is used to train models. The input dataset used part of the charging profile. The accuracy of the proposed model is compared with the CNN and LSTM models using the k-fold cross-validation technique. The proposed model achieves a low RMSE of 2.21%, which shows higher accuracy than others in SOH estimation.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• 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.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.48 no.1
• /
• pp.108-119
• /
• 2024

In this study, we aimed to propose enhancements to the dimensions and design of walking aids tailored for elderly women. Specifically, we focused on wheeled walking assistance devices and aligned each structural component with the appropriate human body dimensions to suggest appropriate product dimensions organized by size clusters, aiming to maximize the practicality of the results. We extracted essential factors required for product design, including human body size elements. The dimension extraction method was clustered to establish connections between key human body parameters-such as height, weight, and age groups-and product dimensions. We conducted a comparative analysis of walking aid product dimensions according to the design elements and sizes of models currently available in the market. The outcomes of this study offer objective, data-driven insights into areas where existing models on the market could benefit from improvement and we anticipate that the findings of this study will provide a solid, quantitative foundation for individuals when selecting the most suitable model for their needs.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.368-376
• /
• 2021

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

• Korean Journal of Cognitive Science
• /
• v.17 no.1
• /
• pp.53-74
• /
• 2006

Similarity has been considered as one of basic concepts of cognitive psychology which is useful for explaining cognitive structure and process. MDS models(Shepard, 1964; Nosofsky, 1991) and Contrast model(Tversky, 1977) were proposed as early models of similarity comparison process. But, there have been a lot of theoretical doubts about the conceptual validity of similarity as a result of empirical findings which could not be explained by early models. Goldstone(1994) assumed that similarity could be defined by alignment processes, and suggested structural alignment as a prospective alternative for solving conceptual controversies so far. In this study, basic assumption and algorithms of MDS models(Shepard, 1944; Nosofsky, 1991) and Contrast model(Tversky, 1977) were described shortly and some theoretical limitations such as arbitrariness of selective attention and correlated structures were discussed as well. The conceptual characteristics and algorithms of SIAM(Goldstone, 1994) were described and how it has been applied to cognitive psychology areas such as categorization, conceptual combination, and analogical reasoning were reviewed. Finally, some theoretical limitations related with data-driven processing and alternative processing and possible directions for structural alignment were discussed.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.6 no.3
• /
• pp.205-215
• /
• 1994

A 3-dimensional numerical model of wind-induced flows has been established. and comparative evaluation of determination methods of vertical eddy viscosity has been performed. The model uses turbulence models to calculate vertical eddy viscosity. The examined methods arp 0-equation model of functional form, 1-equation model of turbulence kinetic energy, and two 2-equation models ($textsc{k}$-$\varepsilon$ and $textsc{k}$-ι models). The evaluation includes the verification tests against experimental data for wind-driven current On a closed one-dimensional channel and a recirculating one-dimensional channel. Comparative study of turbulence models has shown that the proper distribution of turbulence scale is parabolic and the eddy viscosity is depending strongly on mixing depth due to wind.

• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.148-163
• /
• 2021

Timely fault identification is important for safe and reliable operation of the electric valve system. Many research works have utilized different data-driven approach for fault diagnosis in complex systems. However, they do not consider specific characteristics of critical control components such as electric valves. This work presents an integrated shallow-deep fault diagnostic model, developed based on signals extracted from DN50 electric valve. First, the local optimal issue of particle swarm optimization algorithm is solved by optimizing the weight search capability, the particle speed, and position update strategy. Then, to develop a shallow diagnostic model, the modified particle swarm algorithm is combined with support vector machine to form a hybrid improved particle swarm-support vector machine (IPs-SVM). To decouple the influence of the background noise, the wavelet packet transform method is used to reconstruct the vibration signal. Thereafter, the IPs-SVM is used to classify phase imbalance and damaged valve faults, and the performance was evaluated against other models developed using the conventional SVM and particle swarm optimized SVM. Secondly, three different deep belief network (DBN) models are developed, using different acoustic signal structures: raw signal, wavelet transformed signal and time-series (sequential) signal. The models are developed to estimate internal leakage sizes in the electric valve. The predictive performance of the DBN and the evaluation results of the proposed IPs-SVM are also presented in this paper.

• Korean Management Science Review
• /
• v.32 no.4
• /
• pp.175-192
• /
• 2015

Due to the emergence of open innovation driven by development of network service technologies and convergence in ICT service industry, It is necessary for ICT service firms to examine their capabilities for open innovation. The purpose of this paper is to empirically examine determinants affecting open innovation in Korean ICT service industry. In order to analyze, this paper uses logistic and multiple regression models based on survey data of Korean ICT service firms. Estimation results show that external network for collaboration is positive on the technological innovation activity regardless of the innovation type. Specifically, user networks are significant in all types of technology innovation, revealing that it is important to innovation activities of the ICT service firms.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.2
• /
• pp.68-74
• /
• 1998

In this work, we have been concerned with developing an intelligent mold design system for plastic injection molding on the AutoCAD. We have concentrated on building a viable environment, including a mold parts database and a menu-driven user interface. This provides a more interactive and interface for selection of optimal mold-base and mold parts in mold design system. This work presents a method which allows the designer to select the mold parts and mold-base directly within an AutoCAD environment. It can also automatically generate detailed 3D drawings of the mold parts and mold-base. The system shows its potential capability for future enhancement. Since the system is independent of the data, it could easily be extended to other mold-bases and mold parts. In addition, it can be linked to the molding analysis system by creating subtracted 3-D models.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.2
• /
• pp.423-428
• /
• 2010

In the initial design phase of superscalar microprocessors, a performance model is necessary. A theoretic performance model is very useful since performance for various architecture parameters can be obtained by simply computing equations, without repeating simulations, Previous studies established theoretic performance models using the relation between the instruction window size and the issue width, with the penalties due to branch mispredictions and cache misses. However, the study was intended for unlimited number of functional units, which is insufficient for the real case application. This paper proposes a superscalar microprocessor theoretical performance model which also works for the limited functional units. To enhance the accuracy of our limited functional unit model, instruction dependency rates are employed. By using trace-driven data of SPEC 2000 integer programs as input, this paper shows that the theoretically computed performance of superscalar microprocessor with limited number of functional units is quite similar to the measured performance.