• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.613-618
• /
• 2022

효과적인 자연어 처리를 위해 제안된 Transformer 구조의 등장 이후, 이를 활용한 대규모 언어 모델이자 사전학습 모델인 BERT, GPT, OPT 등이 공개되었고, 이들을 한국어에 보다 특화한 KoBERT, KoGPT 등의 사전학습 모델이 공개되었다. 자연어 처리 모델의 확보를 위한 학습 자원이 늘어나고 있지만, 사전학습 모델을 각종 응용작업에 적용하기 위해서는 데이터 준비, 코드 작성, 파인 튜닝 및 저장과 같은 복잡한 절차를 수행해야 하며, 이는 다수의 응용 사용자에게 여전히 도전적인 과정으로, 올바른 결과를 도출하는 것은 쉽지 않다. 이러한 어려움을 완화시키고, 다양한 기계 학습 모델을 사용자 데이터에 보다 쉽게 적용할 수 있도록 AutoML으로 통칭되는 자동 하이퍼파라미터 탐색, 모델 구조 탐색 등의 기법이 고안되고 있다. 본 연구에서는 한국어 사전학습 모델과 한국어 텍스트 데이터를 사용한 자연어 처리 모델 산출 과정을 정형화 및 절차화하여, 궁극적으로 목표로 하는 예측 모델을 자동으로 산출하는 시스템의 설계를 소개한다.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.25-33
• /
• 2023

The purpose of this study is to evaluate the impact of intermediate features on FER performance. To achieve this objective, intermediate features were extracted from the input images at specific layers (FM1~FM4) of the pre-trained network (Resnet-18). These extracted intermediate features and original images were used as inputs to the vision transformer (ViT), and the FER performance was compared. As a result, when using a single image as input, using intermediate features extracted from FM2 yielded the best performance (training accuracy: 94.35%, testing accuracy: 75.51%). When using the original image as input, the training accuracy was 91.32% and the testing accuracy was 74.68%. However, when combining the original image with intermediate features as input, the best FER performance was achieved by combining the original image with FM2, FM3, and FM4 (training accuracy: 97.88%, testing accuracy: 79.21%). These results imply that incorporating intermediate features alongside the original image can lead to superior performance. The findings can be referenced and utilized when designing the preprocessing stages of a deep learning model in FER. By considering the effectiveness of using intermediate features, practitioners can make informed decisions to enhance the performance of FER systems.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.167-177
• /
• 2024

With advancements in satellite technology, interest in target detection and identification is increasing quantitatively and qualitatively. Synthetic Aperture Radar(SAR) images, which can be acquired regardless of weather conditions, have been applied to various areas combined with machine learning based detection algorithms. However, conventional studies primarily focused on the detection of stationary targets. In this study, we proposed a method to identify moving targets using an algorithm that integrates sub-aperture SAR images and cosine similarity calculations. Utilizing a transformer-based deep learning target detection model, we extracted the bounding box of each target, designated the area as a region of interest (ROI), estimated the similarity between sub-aperture SAR images, and determined movement based on a predefined similarity threshold. Through the proposed algorithm, the quantitative evaluation of target identification capability enhanced its accuracy compared to when training with the targets with two different classes. It signified the effectiveness of our approach in maintaining accuracy while reliably discerning whether a target is in motion.

• Korean Journal of Radiology
• /
• v.24 no.10
• /
• pp.952-959
• /
• 2023

Large language models (LLMs) such as ChatGPT have garnered considerable interest for their potential to aid non-native English-speaking researchers. These models can function as personal, round-the-clock English tutors, akin to how Prometheus in Greek mythology bestowed fire upon humans for their advancement. LLMs can be particularly helpful for non-native researchers in writing the Introduction and Discussion sections of manuscripts, where they often encounter challenges. However, using LLMs to generate text for research manuscripts entails concerns such as hallucination, plagiarism, and privacy issues; to mitigate these risks, authors should verify the accuracy of generated content, employ text similarity detectors, and avoid inputting sensitive information into their prompts. Consequently, it may be more prudent to utilize LLMs for editing and refining text rather than generating large portions of text. Journal policies concerning the use of LLMs vary, but transparency in disclosing artificial intelligence tool usage is emphasized. This paper aims to summarize how LLMs can lower the barrier to academic writing in English, enabling researchers to concentrate on domain-specific research, provided they are used responsibly and cautiously.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.335-347
• /
• 2024

Open-vocabulary 3D point cloud instance segmentation (OV-3DIS) is a challenging visual task to segment a 3D scene point cloud into object instances of both base and novel classes. In this paper, we propose a novel model Open3DME for OV-3DIS to address important design issues and overcome limitations of the existing approaches. First, in order to improve the quality of class-agnostic 3D masks, our model makes use of T3DIS, an advanced Transformer-based 3D point cloud instance segmentation model, as mask proposal module. Second, in order to obtain semantically text-aligned visual features of each point cloud segment, our model extracts both 2D and 3D features from the point cloud and the corresponding multi-view RGB images by using pretrained CLIP and OpenSeg encoders respectively. Last, to effectively make use of both 2D and 3D visual features of each point cloud segment during label assignment, our model adopts a unique feature ensemble method. To validate our model, we conducted both quantitative and qualitative experiments on ScanNet-V2 benchmark dataset, demonstrating significant performance gains.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.15 no.3
• /
• pp.257-262
• /
• 2009

The unified power flow controller(UPFC) is one of the most effective devices in the FACTS family. This paper concerns about a filtering technique for reducing the computer calculation to determine the optimal location of UPFC in a power system. The sensitivities of the power generation cost for UPFC control parameters are evaluated. This technique requires that only one optimal power flow is run to get UPFC sensitivities for all possible transmission lines. To find out a optimal locating of a single UPFC in power system, an ideal transformer model which consists of a complex turns ratio and a variable shunt admittance was used. In this model, the UPFC control variables do not depend on UPFC input and output currents and voltages. The sensitivity method was tested on a 5-bus system derived from the IEEE 14-bus system and IEEE 14-bus system to establish its effectiveness.

• Geomechanics and Engineering
• /
• v.21 no.2
• /
• pp.95-102
• /
• 2020

Population concentration in urban areas has led traffic management a central issue. To mitigate traffic congestions, the government has planned to construct large-cross-section tunnels deep underground. This study focuses on estimating the damage caused to frame structures owing to tunnel excavation. When constructing a tunnel network deep underground, it is necessary to divide the main tunnel and connect the divergence tunnel to the ground surface. Ground settlement is caused by excavation of the adjacent divergence tunnel. Therefore, predicting ground settlement using diverse variables is necessary before performing damage estimation. We used the volume loss and cover-tunnel diameter ratio as the variables in this study. Applying the ground settlement values to the settlement induction device, we measured the extent of damage to frame structures due to displacement at specific points. The vertical and horizontal displacements that occur at these points were measured using preattached LVDT (Linear variable differential transformer), and the lateral strain and angular distortion were calculated using these displacements. The lateral strain and angular distortion are key parameters for structural damage estimation. A damage assessment chart comprises the "Negligible", "Very Slight Damage", "Slight Damage", "Moderate to Severe Damage", and "Severe to Very Severe Damage" categories was developed. This table was applied to steel frame and concrete frame structures for comparison.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.29 no.7
• /
• pp.373-384
• /
• 2017

The objective of this study was to determine the effect of refrigerant heat exchanger on the performance of type II absorption heat pump performance using numerical analysis. Two heat exchange installation methods were used: solution to refrigerant and waste hot water to refrigerant. These methods were compared to the standard model of hot water flow without using refrigerant heat exchanger. When waste hot waters were bypassed to refrigerant heat exchanger, COP was not affected. However, steam mass generation rates were increased compared to those of the standard model. When solutions were bypassed to the refrigerant heat exchanger, results were different depending on the place where the solution rejoined. COP and steam mass generation rates were lower compared to those when waste heat water was passed to refrigerant heat exchanger. Thus, it is possible to obtain higher steam mass generation rates by using waste water and installing refrigerant heat exchanger.

• Journal of the Korea Convergence Society
• /
• v.11 no.5
• /
• pp.1-8
• /
• 2020

Machine translation refers to a system where a computer translates a source sentence into a target sentence. There are various subfields of machine translation. APE (Automatic Post Editing) is a subfield of machine translation that produces better translations by editing the output of machine translation systems. In other words, it means the process of correcting errors included in the translations generated by the machine translation system to make proofreading. Rather than changing the machine translation model, this is a research field to improve the translation quality by correcting the result sentence of the machine translation system. Since 2015, APE has been selected for the WMT Shaed Task. and the performance evaluation uses TER (Translation Error Rate). Due to this, various studies on the APE model have been published recently, and this paper deals with the latest research trends in the field of APE.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.6
• /
• pp.1139-1150
• /
• 2022

With the rapid development of SW Industry, softwares are everywhere in our daily life. The number of vulnerabilities are also increasing with a large amount of newly developed code. Vulnerabilities can be exploited by hackers, resulting the disclosure of privacy and threats to the safety of property and life. In particular, since the large numbers of increasing code, manually analyzed by expert is not enough anymore. Machine learning has shown high performance in object identification or classification task. Vulnerability detection is also suitable for machine learning, as a reuslt, many studies tried to use RNN-based model to detect vulnerability. However, the RNN model is also has limitation that as the code is longer, the earlier can not be learned well. In this paper, we proposed a novel method which applied BERT to detect vulnerability. The accuracy was 97.5%, which increased by 1.5%, and the efficiency also increased by 69% than Vuldeepecker.