• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.18 no.4
• /
• pp.430-435
• /
• 2009

The cooling stage greatly affects the product quality in the injection molding process. The cooling system that minimizes temperature variance in the product surface will improve the quality and the productivity of products. The cooling circuit optimization problem that was once solved by a response surface method with 4 design variables. It took too much time for the optimization as an industrial design tool. It is desirable to reduce the optimization time. Therefore, we tried the back-propagation algorithm of artificial neural network(BPN) to find an optimum solution in the cooling circuit design in this research. We tried various ways to select training points for the BPN. The same optimum solution was obtained by applying the BPN with reduced number of training points by the fractional factorial design.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.05a
• /
• pp.357-360
• /
• 2009

The cooling stage greatly affects the product quality in the injection molding process. The cooling system that minimizes temperature variance in the product surface will improve the quality and the productivity of products. In this research, we tried the back-propagation algorithm of artificial neural network to find an optimum solution in the cooling system design of injection mold. The cooling system optimization problem that was once solved by a response surface method with 4 design variables was solved by applying the back-propagation algorithm, resulting in a solution with a sufficient accuracy. Furthermore the number of training points was much reduced by applying the fractional factorial design without losing solution accuracy.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.1
• /
• pp.184-189
• /
• 2004

In this paper, the warm forging process sequence has been determined to manufacture the warm forged product for the precision bevel gear used as the differential gear unit of a commercial automobile. The preform shape of bevel gear influences the dimensional accuracy and stiffness of final product. The aspect ratio and chamfer length are considered as design parameters to achieve adequate metal distribution in the finish forging operation. Then the optimal conditions of design parameters have been selected by artificial neural network (ANN). Finally, to verify the optimal preform shape, the experiments of the warm forging of the bevel gear have been executed. The proposed method can give more systematic and economically feasible means for designing the preform shape in metal forming process.

• IE interfaces
• /
• v.19 no.4
• /
• pp.333-341
• /
• 2006

RFID (Radio Frequency Identification) is a technology that can input identification information to microchip and make goods, animals, persons recognized, chased, and managed using radio frequency, and is founded on the core technology of ubiquitous environment of the future. In this paper, we propose a RFID integrated system designed to manage the lifecycle of an individual product efficiently. The proposed system can enable traceability and visibility of items through their entire life by integrating distribution and banking information on the basis of EPCglobal Network. It may provide the infra of Digital Manufacturing and RTE (Real Time Enterprise) and effective information sharing structure with existing legacy system (ERP, CRM, SCM) by real time.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.665-675
• /
• 2019

In this paper, we compare and analyze the classification performance of deep learning algorithm Convolutional Neural Network(CNN) ac cording to ensemble generation and combining techniques. We used several CNN models(VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, GoogLeNet) to create 10 ensemble generation combinations and applied 6 combine techniques(average, weighted average, maximum, minimum, median, product) to the optimal combination. Experimental results, DenseNet169-VGG16-GoogLeNet combination in ensemble generation, and the product rule in ensemble combination showed the best performance. Based on this, it was concluded that ensemble in different models of high benchmarking scores is another way to get good results.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.83-92
• /
• 2023

The majority of product users rely on the reviews that are posted on the appropriate website. Both users and the product's manufacturer could benefit from these reviews. Daily, thousands of reviews are submitted; how is it possible to read them all? Sentiment analysis has become a critical field of research as posting reviews become more and more common. Machine learning techniques that are supervised, unsupervised, and semi-supervised have worked very hard to harvest this data. The complicated and technological area of feature engineering falls within machine learning. Using deep learning, this tedious process may be completed automatically. Numerous studies have been conducted on deep learning models like LSTM, CNN, RNN, and GRU. Each model has employed a certain type of data, such as CNN for pictures and LSTM for language translation, etc. According to experimental results utilizing a publicly accessible dataset with reviews for all of the models, both positive and negative, and CNN, the best model for the dataset was identified in comparison to the other models, with an accuracy rate of 81%.

• The Journal of Information Systems
• /
• v.33 no.2
• /
• pp.143-168
• /
• 2024

Purpose This study highlights the crucial role of external APIs in driving dynamic evolution within a digital ecosystem. Drawing on the concept of evolutionary network biology perspective, this study hypothesizes that APIs' (non)network properties can significantly impact a digital ecosystem's product variety. Design/methodology/approach This study analyzes plug-in source code data from WordPress.org between January 2004 and December 2014, using survival analysis to test this hypothesis. Findings The empirical results demonstrate that external APIs have a more significant impact on promoting ecosystem evolution over time than those offered by a focal platform system. This research enhances our understanding of ecosystem dynamics and emphasizes the critical role of the generative nature of APIs in fostering ecosystem growth.

• International Journal of CAD/CAM
• /
• v.4 no.1
• /
• pp.1-10
• /
• 2004

Through reviewing and comparing the current virtual shopping malls web sites integrated VR into E-commerce, this paper analyzed both the advantages and disadvantages of two kinds of methods for product presentation: 2D image based and 3D model based presentation method. Using the virtual shopping mall (EasyMall) as a showcase, we presented the architecture of the system and the development technologies, especially those in the mixed presentation method. The presentation and customization methods in the two related modules, including the PhoneShow for mobile phone and EasyShow for textile products, were discussed. It indicated that the integration of E-commerce with VR could provide consumers with virtual experience and intelligent service for business activities. Furthermore, the product presentation methods can be made available for use in different cases.

• Journal of Information Technology Applications and Management
• /
• v.21 no.4_spc
• /
• pp.361-379
• /
• 2014

With the rapid increase of social network usage, there are emerging trends of adopting social information among online users in building recommendation system. This study aims to investigate whether the additional usage of social information can improve recommendation performance in recommendation system and how much the improvement can be different according to the product involvement level. As an experiment result, social information does not affect positively to the recommendation accuracy but affect significantly to the recommendation quality. Also social information contributed more sensitively to the improvement of recommendation quality in high product involvement domain.

• Proceedings of the Technology Innovation Conference
• /
• 2005.08a
• /
• pp.5-28
• /
• 2005

This paper estimates the effect of networks on innovative performance at the firm level , using Korean Innovation Survey (KIS) dataset Product innovation, product improvement , and process innovation are used as proxies for innovative activity. The explanatory variables such as firm size, market concentration ratio, lagged profitability, foreign ownership, export ratio, firm's age, formal R&D activity, and industrial R&D intensity are yet other considerations. With two year-long (2000 and 2001) data from 1,124 Korean manufacturing firms, we estimated the logistic regression model. The research finding indicates that the external networks have a strong positive effect on innovative output regardless of type of innovation. However, the network effects by partner (other firms or research institutions) vary across the type of innovation. Especially, we found that the user-supplier linkage plays an important role in product ion innovation, product improvement, and process innovation.