• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.456-462
• /
• 2022

In this paper, we introduce a method of predicting time offset by applying LSTM, a deep learning model, to a precision time comparison technique based on measurement data extracted from code signals transmitted from GPS satellites to determine Universal Coordinated Time (UTC). First, we introduce a process of extracting time information from code signals received from a GPS satellite on a daily basis and constructing a daily time offset into one time series data. To apply the deep learning model to the constructed time offset time series data, LSTM, one of the recurrent neural networks, was applied to predict the time offset of a GPS satellite. Through this study, the possibility of time offset prediction by applying deep learning in the field of GNSS precise time transfer was confirmed.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.561-568
• /
• 2023

Various defects occur in concrete structures due to internal and external environments. If there is a defect, it is important to efficiently identify and maintain it because there is a problem with the structural safety of concrete. However, recent deep learning research has focused on cracks in concrete, and studies on exfoliation and contamination are lacking. In this study, focusing on exfoliation and contamination, which are difficult to label, four models were developed and their performance evaluated through unlabelling method, filtering method, the convergence of transfer learning based k-means clustering. As a result of the analysis, the convergence model classified the defects in the most detail and could increase the efficiency compared to direct labeling. It is hoped that the results of this study will contribute to the development of deep learning models for various types of defects that are difficult to label in the future.

• Journal of the Korean Home Economics Association
• /
• v.26 no.2
• /
• pp.69-79
• /
• 1988

This study was to increase the experimental learning effect of textile materials in middle and high school. To this study, three kinds of simply devised apparatus were used for warmth retaining test, air permeability test and static electricity test. Two classes were chosen in a girls' high school comparing learning effect and classified the theoretical learning group and the experimental learning group. In the experimental group, a teaching plan to teach the properties of textile materials was made to use these apparatuses. The results were. 1. In the interest on the unit either the theoretical learning group or the experimental learning group were not different significantly. 2. In the items facilitation of motivation, unsatisfied desires and prevention of failure, effect of transfer and development of inquiry power, both groups were significant. 3. For the purpose of comparing the learning effect, two groups were examined for determining the level of understanding after teaching properties of textile materials. The mean value of the experimental learning group was higher than that of the theoretical learning group. The experimental learning group had more higher markers(over the point of 90) than the theoretical learning group.

• English Language & Literature Teaching
• /
• no.6
• /
• pp.35-47
• /
• 2000

This study questions the validity of Crosslinguistic Influence (CLI) in EFL Learning. A ten-minute grammaticality judgement test involving resumptive pronouns in English relative clauses was given to 15 female subjects. The research results, which were analysed in terns of language transfer and universalist arguments, support the existence of a universal process that guides L2 learning, and some common developmental patterns between the two processes of L1 and L2 learning. Hence, the universalist view should be given at least equal Weight as the CLI approach.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.133-145
• /
• 2022

Compared to the continuously increasing dog population and industry size in Korea, systematic analysis of related data and research on breed classification methods are very insufficient. In this paper, an automatic breed classification method is proposed using deep learning technology for 14 major dog breeds domestically raised. To do this, dog images are collected for deep learning training and a dataset is built, and a breed classification algorithm is created by performing transfer learning based on VGG-16 and Resnet-34 as backbone networks. In order to check the transfer learning effect of the two models on dog images, we compared the use of pre-trained weights and the experiment of updating the weights. When fine tuning was performed based on VGG-16 backbone network, in the final model, the accuracy of Top 1 was about 89% and that of Top 3 was about 94%, respectively. The domestic dog breed classification method and data construction proposed in this paper have the potential to be used for various application purposes, such as classification of abandoned and lost dog breeds in animal protection centers or utilization in pet-feed industry.

• International Journal of High-Rise Buildings
• /
• v.9 no.4
• /
• pp.335-342
• /
• 2020

This article comes up with a new method which is based on the visual characteristic of the objects and machine learning technology to achieve semi-automated recognition of the personnel, machine & materials of the construction sites. Balancing the real-time performance and accuracy, using Faster RCNN (Faster Region-based Convolutional Neural Networks) with transfer learning method appears to be a rational choice. After fine-tuning an ImageNet pre-trained Faster RCNN and testing with it, the result shows that the precision ratio (mAP) has so far reached 67.62%, while the recall ratio (AR) has reached 56.23%. In other word, this recognizing method has achieved rational performance. Further inference with the video of the construction of Huoshenshan Hospital also indicates preliminary success.

• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.35-44
• /
• 2018

Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying icebergs from SAR images. The metrics for performance evaluation uses the log loss. The two-layer CNN model proposed in research of C.Bentes et al.[1] is used as a benchmark model and compared with the four-layer CNN model using data augmentation. Finally, the performance of the final CNN model using the VGG-16 pre-trained model is compared with the previous model. This paper shows how to improve the benchmark model and propose the final CNN model.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.10
• /
• pp.883-892
• /
• 2021

This paper provides a process for developing deep learning-based aerial object detection models that can run in realtime on onboard. To improve object detection performance, we pre-process and augment the training data in the training stage. In addition, we perform transfer learning and apply a weighted cross-entropy method to reduce the variations of detection performance for each class. To improve the inference speed, we have generated inference acceleration engines with quantization. Then, we analyze the real-time performance and detection performance on custom aerial image dataset to verify generalization.

• International Area Studies Review
• /
• v.12 no.3
• /
• pp.391-415
• /
• 2008

This paper adopts a present basis of research on the Chinese characteristic culture of enterprise, phenomenon of learning, learning attitude and transferring of learning attitude, and forms a research model and hypothesis. There are three different types of Chinese enterprises basined on the research of Chinese intellectuals: legalistic organization, the ethic organization culture and seeking development organization culture, from which the legalistic organization culture has positive influence on the people level learning and structure level learning by the test of hypothesis. Ethnic organizational cultural has positive influence on the organization level; however, it never has any contributions to the people leanings. Seeking development organization culture benefits a lot to the people leanings, but it never has any positive influence on the organizational cultures.