• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.501-516
• /
• 2023

Dynamic irregularity and acceleration of bridges subjected to high-speed trains provide crucial information for comprehensive evaluation of the health state of under-track structures. This paper proposes a novel approach for real-time estimation of vertical track dynamic irregularity and bridge acceleration using deep generative adversarial network (GAN) and vibration data from in-service train. The vehicle-body and bogie acceleration responses are correlated with the two target variables by modeling train-bridge interaction (TBI) through least squares generative adversarial network (LSGAN). To realize supervised learning required in the present task, the conventional LSGAN is modified by implementing new loss function and linear activation function. The proposed approach can offer pointwise and accurate estimates of track dynamic irregularity and bridge acceleration, allowing frequent inspection of high-speed railway (HSR) bridges in an economical way. Thanks to its applicability in scenarios of high noise level and critical resonance condition, the proposed approach has a promising prospect in engineering applications.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.113-117
• /
• 2020

Images were taken under various weather such as rain, haze, snow often show low visibility, which can dramatically decrease accuracy of some tasks in computer vision: object detection, segmentation. Besides, previous work to enhance image usually downsample the image to receive consistency features but have not yet good upsample algorithm to recover original size. So, in this research, we jointly implement removal streak in heavy rain image and super resolution using a deep network. We put forth a 2-stage network: a multi-model network followed by a refinement network. The first stage using rain formula in the single image and two operation layers (addition, multiplication) removes rain streak and noise to get clean image in low resolution. The second stage uses refinement network to recover damaged background information as well as upsample, and receive high resolution image. Our method improves visual quality image, gains accuracy in human action recognition task in datasets. Extensive experiments show that our network outperforms the state of the art (SoTA) methods.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.395-398
• /
• 2021

최근 방대한 양의 텍스트 정보가 인터넷에 유통되면서 정보의 핵심 내용을 파악하기가 더욱 어려워졌으며, 이로 인해 자동으로 텍스트를 요약하려는 연구가 활발하게 이루어지고 있다. 텍스트 자동 요약을 위한 다양한 기법 중 특히 트랜스포머(Transformer) 기반의 모델은 추상 요약(Abstractive Summarization) 과제에서 매우 우수한 성능을 보이며, 해당 분야의 SOTA(State of the Art)를 달성하고 있다. 하지만 트랜스포머 모델은 매우 많은 수의 매개변수들(Parameters)로 구성되어 있어서, 충분한 양의 데이터가 확보되지 않으면 이들 매개변수에 대한 충분한 학습이 이루어지지 않아서 양질의 요약문을 생성하기 어렵다는 한계를 갖는다. 이러한 한계를 극복하기 위해 본 연구는 소량의 데이터가 주어진 환경에서도 양질의 요약문을 생성할 수 있는 문서 요약 방법론을 제안한다. 구체적으로 제안 방법론은 한국어 사전학습 언어 모델인 KoBERT의 임베딩 행렬을 트랜스포머 모델에 적용하는 방식으로 문서 요약을 수행하며, 제안 방법론의 우수성은 Dacon 한국어 문서 생성 요약 데이터셋에 대한 실험을 통해 ROUGE 지표를 기준으로 평가하였다.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.355-369
• /
• 2023

Since the widespread adoption of deep-learning and related distributed representation, there have been substantial advancements in part-of-speech (POS) tagging for many languages. When training word representations, morphology and shape are typically ignored, as these representations rely primarily on collecting syntactic and semantic aspects of words. However, for tasks like POS tagging, notably in morphologically rich and resource-limited language environments, the intra-word information is essential. In this study, we introduce a deep neural network (DNN) for POS tagging that learns character-level word representations and combines them with general word representations. Using the proposed approach and omitting hand-crafted features, we achieve 90.47%, 80.16%, and 79.32% accuracy on our own dataset for three morphologically rich languages: Uyghur, Uzbek, and Kyrgyz. The experimental results reveal that the presented character-based strategy greatly improves POS tagging performance for several morphologically rich languages (MRL) where character information is significant. Furthermore, when compared to the previously reported state-of-the-art POS tagging results for Turkish on the METU Turkish Treebank dataset, the proposed approach improved on the prior work slightly. As a result, the experimental results indicate that character-based representations outperform word-level representations for MRL performance. Our technique is also robust towards the-out-of-vocabulary issues and performs better on manually edited text.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.647-649
• /
• 2023

Sentiment analysis as part of natural language processing (NLP) has received much attention following the demand to understand people's opinions. Aspect-based sentiment analysis (ABSA) is a fine-grained subtask from sentiment analysis that aims to classify sentiment at the aspect level. Throughout the years, researchers have formulated ABSA into various tasks for different scenarios. Unlike the early works, the current ABSA utilizes many elements to improve performance and provide more details to produce informative results. These ABSA formulations have provided greater challenges for researchers. However, it is difficult to explore ABSA's works due to the many different formulations, terms, and results. In this paper, we conduct a comparative analysis of recent studies on ABSA. We mention some key elements, problem formulations, and datasets currently utilized by most ABSA communities. Also, we conduct a short review of the latest papers to find the current state-of-the-art model. From our observations, we found that span-level representation is an important feature in solving the ABSA problem, while multi-task learning and generative approach look promising. Finally, we review some open challenges and further directions for ABSA research in the future.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.687-688
• /
• 2023

Bone age assessment is a crucial task in pediatric radiology for assessing growth and development in children. In this paper, we explore the potential of Vision Transformer, a state-of-the-art deep learning model, for bone age assessment using X-ray images. We generate heatmap outputs using a pre-trained Vision Transformer model on a publicly available dataset of hand X-ray images and show that the model tends to focus on the overall hand and only the bone part of the image, indicating its potential for accurately identifying the regions of interest for bone age assessment without the need for pre-processing to remove background noise. We also suggest two methods for extracting the region of interest from the heatmap output. Our study suggests that Vision Transformer holds great potential for bone age assessment using X-ray images, as it can provide accurate and interpretable output that may assist radiologists in identifying potential abnormalities or areas of interest in the X-ray image.

• Educational Technology International
• /
• v.17 no.1
• /
• pp.87-116
• /
• 2016

In this research, we designed a teacher professional development (PD) program where a small group of mathematics teachers could share, reflect on, and discuss their pedagogical knowledge and practices of ICT-integrated lessons, using a video annotation tool called DIVER. The main purposes of this paper are both micro and macro: to examine how the teachers were engaged in the meaning-making process in a video-based PD (micro); and to derive implications about how to design effective video-based teacher PD programs toward a teacher community of practices (macro). To examine teachers' meaning-making in the PD sessions, discourse data from a series of 10 meetings was segmented into idea units and coded to identify discourse patterns, focusing on (a) participation levels, (b) conversation topics, and (c) conversation depth. Regarding the affordance of DIVER, discourse patterns of two meetings, before and after individual annotation with DIVER were compared through qualitative vignette analysis. Overall, we found that the teacher discourse shifted the focus from surface features to deeper pedagogical issues as the PD sessions progressed. In particular, the annotation function in DIVER afforded the teachers to exercise descriptive analyses of video clips in a flexible manner, thereby helping them cognitively prepared to take interpretative and evaluative stances in face-to-face discussions with colleagues. In conclusion, deriving from our research experiences, we discuss the possibilities and challenges of designing video-based teacher PD in a school context.

• SUVANNABHUMI
• /
• v.6 no.2
• /
• pp.65-84
• /
• 2014

Asia-Pacific Confucian Capitalism is comparable to Atlantic Protestant Capitalism in terms of economic success, as most economies influenced by Confucian culture in East Asia and Southeast Asia are economically well-off in the past 50 years, save for Vietnam. This paper seeks to determine whether Vietnam can follow the path of development of the other Confucian economies, especially in the context of globalization and upcoming regional integration. In the paper, I will use an analytic framework derived from Weber and Huntington to examine the cultural dimension of Vietnam's economic development. In the domestic field, I argue that the core values of Confucianism continue to contribute to the development in Vietnam in many ways; yet one critical element needs to be tapped: the political culture of strong leadership and efficient bureaucracy. Confucian values for development may be compromised by pushing for democratization too early in Vietnam. On a positive note, Confucianism for Vietnam is instrumental in its regional integration into Southeast Asia since it is integrative rather than exclusive. Vietnam's cultural similarity with China may however lead to too much passive learning and conflicts. In conclusion, Confucianism is a valuable asset for Vietnam's economic development, but challenges have to be addressed in order for Vietnam to become the next tiger.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2483-2504
• /
• 2023

Most existing low-light enhancement algorithms either use a large number of training parameters or lack generalization to real-world scenarios. This paper presents a novel lightweight and robust pixel-wise polynomial approximation-based deep network for low-light image enhancement. For mapping the low-light image to the enhanced image, pixel-wise higher-order polynomials are employed. A deep convolution network is used to estimate the coefficients of these higher-order polynomials. The proposed network uses multiple branches to estimate pixel values based on different receptive fields. With a smaller receptive field, the first branch enhanced local features, the second and third branches focused on medium-level features, and the last branch enhanced global features. The low-light image is downsampled by the factor of 2b-1 (b is the branch number) and fed as input to each branch. After combining the outputs of each branch, the final enhanced image is obtained. A comprehensive evaluation of our proposed network on six publicly available no-reference test datasets shows that it outperforms state-of-the-art methods on both quantitative and qualitative measures.

• Journal of Practical Engineering Education
• /
• v.15 no.3
• /
• pp.589-595
• /
• 2023

Artificial intelligence(AI) is spurring advancements in EdTech, the merger of technology and education. This includes the creation of effective learning materials and personalized student experiences. Our study focuses on developing a programming education software that employs state-of-the-art generative AI. Our software also includes prompts optimized for programming code analysis, which are based on the well-known ChatGPT API. Furthermore, the necessary functions for acquiring programming skills were created with a user interface and developed as a question-and-answer template function based on an AI chatbot. The objective of this study is to guide the development of educational programmes that make use of generative AI.