• Industrial Engineering and Management Systems
• /
• v.10 no.2
• /
• pp.97-103
• /
• 2011

This paper develops a technology level quantification (TLQ) model by utilizing a learning curve. Original learning curve shows the relationship between cumulative number of units and the required time for the unit. On the other hand, in our developed model, the technology level, such as speed of production and quality of the produced items, is expressed as a function of not cumulative number of units but time, for increasing generality. Furthermore, for expressing each learning that consists of conceptual learning and operational learning, S-curve is utilized in our developed model. By fitting the S-curve and/or decomposing into some activities, our TQL model can be applied to approximate organizational and complicated process. Some variations in time and levels, parameters of our developed model are shown. By using the parameters, the procedure to identify our developed model is proposed. Also, the influential factors for the parameters of our developed model are discussed with classifying the factors into technoware, infoware, humanware, and orgaware. The expected technology level is utilized for expecting the capacity of production system, and the expected capacity can be utilized in predicting various changes in the organization and deciding managerial decision about TT. A case study in manufacturing industry shows the effectiveness of the developed model.

• Journal of Biomedical Engineering Research
• /
• v.41 no.1
• /
• pp.48-54
• /
• 2020

In this paper, we deal with a liver fibrosis classification problem using ultrasound B-mode images. Commonly representative methods for classifying the stages of liver fibrosis include liver biopsy and diagnosis based on ultrasound images. The overall liver shape and the smoothness and roughness of speckle pattern represented in ultrasound images are used for determining the fibrosis stages. Although the ultrasound image based classification is used frequently as an alternative or complementary method of the invasive biopsy, it also has the limitations that liver fibrosis stage decision depends on the image quality and the doctor's experience. With the rapid development of deep learning algorithms, several studies using deep learning methods have been carried out for automated liver fibrosis classification and showed superior performance of high accuracy. The performance of those deep learning methods depends closely on the amount of datasets. We propose an enhanced U-net architecture to maximize the classification accuracy with limited small amount of image datasets. U-net is well known as a neural network for fast and precise segmentation of medical images. We design it newly for the purpose of classifying liver fibrosis stages. In order to assess the performance of the proposed architecture, numerical experiments are conducted on a total of 118 ultrasound B-mode images acquired from 78 patients with liver fibrosis symptoms of F0~F4 stages. The experimental results support that the performance of the proposed architecture is much better compared to the transfer learning using the pre-trained model of VGGNet.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.651-658
• /
• 2021

Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

• Journal of Multimedia Information System
• /
• v.4 no.3
• /
• pp.115-122
• /
• 2017

Over the years, there has been much research in blended learning. However, research regarding its use and evaluation is inconsistent, not following any specific evaluation method, and may not be applicable to local students. In this research, a case study was conducted to evaluate the environment based on three levels of Kirkpatrick's model. Methodological triangulation was the principle of data collection used in which multiple sources of evidence were triangulated to provide insights into this study. Instruments used include surveys, interviews, questionnaires and pre- and post-tests that are guided by Kirkpatrick's model. The results revealed that students were positive with the learning environment. Students enjoyed learning with multimedia and motivated to learn as well as engaged in the environment. The tests showed significant difference in their learning. Students also perceived that they have transferred their learning from face-to-face lecture into problem-based learning and learning outcome. This research contributes to the field by providing deeper insights into assessments in multimedia-based blended learning environment and empirical evidence on views, attitudes, learning and knowledge transfer of students in higher education.

• Asia Marketing Journal
• /
• v.19 no.3
• /
• pp.75-98
• /
• 2017

Our study is trying to investigate the perceived training effectiveness by applying the theory of planned behavior (TPB) and Technological Acceptance Model (TAM) and intend to examine the effects of individual differences on perceived training effectiveness and performance of individuals. The main purpose is to evaluate the perceived training effectiveness, and role of individual differences in terms of learning. The results of this study supported all the hypothesis that participants with higher level of creative self-efficacy, intrinsic motivation, creativity and emotional intelligence (EI) will have greater inclinations to learn. Results showed that perceive training effectiveness is positively related to training transfer and training transfer increase the performance of individuals. Study results significantly agree with the theory of planned behavior (TPB) which was applied to measure the perceived training effectiveness and suggest trainee's perception of usefulness, ease and benefits enhance learning dimensions of participants that make any program effective. The study has highlighted a number of issues that influence the perceived training effectiveness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1450-1463
• /
• 2019

The problem towards crowd behavior recognition in a serious clustered scene is extremely challenged on account of variable scales with non-uniformity. This paper aims to propose a crowed behavior classification framework based on a transferring hybrid network blending 3D res-net with inception-v3. First, the 3D res-inception network is presented so as to learn the augmented visual feature of UCF 101. Then the target dataset is applied to fine-tune the network parameters in an attempt to classify the behavior of densely crowded scenes. Finally, a transferred entropy function is used to calculate the probability of multiple labels in accordance with these features. Experimental results show that the proposed method could greatly improve the accuracy of crowd behavior recognition and enhance the accuracy of multiple label classification.

• The Korean Journal of Health Service Management
• /
• v.11 no.4
• /
• pp.17-28
• /
• 2017

Objectives : This study analyzed job performance in local area general hospitals to look for measurable effects from educational training and/or organizational communication. Methods : For the purposes of this study, a survey was conducted of general hospital employees from 29 hospitals in Gwangju and Jeonnam. The survey period was August 22 - September 30, 2016, and 1,004 responses were used in the final analysis. Results : This study revealed that certain aspects of communication (upward,downward,vertical,orinformal) had significant effects on job satisfaction, learning transfer, and general performance. Conclusions : To improve job performance in general hospitals, employers must improve overall satisfaction by improving upon job training and internal communication. Specifically, training should be better connected to learning transfer and organizational design must encourage active communication between employees.

• The KIPS Transactions:PartA
• /
• v.11A no.2
• /
• pp.207-212
• /
• 2004

In this paper, based on SCORM Sequencing Model, we propose the learning content structure which has structure informations of learning object and decision rules how to transfer learning object to learner. It is intended to provide the technical means for learning content objects to be easily shared and reused across multiple learning delivery environment. We develop the generation tool of learning object sequencing, for processing the learning with variable teaching methodologies. The teaming objects also are automatically packaged the PIE(Package Interchange File) to transmit with SCORM RTE(Run-Time Environment) and attached SCO(Sharable Content Object) function for tracking learner information.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.01a
• /
• pp.99-100
• /
• 2018

컴퓨팅 사고력이 강조됨에 따라 우리 나라를 비롯한 세계 여러 나라에서는 프로그래밍 교육 등 컴퓨팅 관련 교육을 실시하고 있다. 일반적으로 프로그래밍 교육에서 초보 학습자에게는 블록 기반 프로그래밍 언어를 학습한 후 텍스트 기반 프로그래밍 언어를 학습하게 된다. 블록 기반 언어와 텍스트 기반 언어는 동일한 프로그래밍 논리를 함양하게 되지만, 다른 모든 언어들과 마찬가지로 언어 특성, 사용법, 형태 등 다소 차이가 있다. 따라서 본 논문에서는 블록 기반 프로그래밍 언어에서 텍스트 기반 프로그래밍 언어의 학습 전이의 효과에 대해 이론적 고찰을 실시하였으며, 그 결과 대부분의 연구에서 긍정적 전이 효과를 입증하였음을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.873-876
• /
• 2020

매실의 병충해 이미지를 Tensorflow hub에서 제공하는 Resnet50모델에 Transfer Learning기법을 이용하여 학습시키고, 학습된 모델을 Flask를 이용하여 연동시킨다. 이렇게 완성된 웹앱은 사용자가 매실의 이미지를 업로드 하면, 어떤 병충해를 가지고 있는 지 알려주며, 사용자는 얻은 결과를 통해 육안으로 구분하기 어려운 병충해의 정보를 얻어 매실이 손상이 가는 것을 예방할 수 있다.