• The Mathematical Education
• /
• v.63 no.2
• /
• pp.187-207
• /
• 2024

In this study, we explored the feasibility of automatically scoring descriptive assessment items using GPT-4 based ChatGPT by comparing and analyzing the scoring results between teachers and GPT-4 based ChatGPT. For this purpose, three descriptive items from the permutation and combination unit for first-year high school students were selected from the KICE (Korea Institute for Curriculum and Evaluation) website. Items 1 and 2 had only one problem-solving strategy, while Item 3 had more than two strategies. Two teachers, each with over eight years of educational experience, graded answers from 204 students and compared these with the results from GPT-4 based ChatGPT. Various techniques such as Few-Shot-CoT, SC, structured, and Iteratively prompts were utilized to construct prompts for scoring, which were then inputted into GPT-4 based ChatGPT for scoring. The scoring results for Items 1 and 2 showed a strong correlation between the teachers' and GPT-4's scoring. For Item 3, which involved multiple problem-solving strategies, the student answers were first classified according to their strategies using prompts inputted into GPT-4 based ChatGPT. Following this classification, scoring prompts tailored to each type were applied and inputted into GPT-4 based ChatGPT for scoring, and these results also showed a strong correlation with the teachers' scoring. Through this, the potential for GPT-4 models utilizing prompt engineering to assist in teachers' scoring was confirmed, and the limitations of this study and directions for future research were presented.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.45-52
• /
• 2004

According tothe development of digital media technologies various algorithms for video sequence matching have been proposed to match the video sequences efficiently. A large number of video sequence matching methods have focused on frame-wise query, whereas a relatively few algorithms have been presented for video sequence matching or video shot matching. In this paper, we propose an efficientalgorithm to index the video sequences and to retrieve the sequences for video sequence query. To improve the accuracy and performance of video sequence matching, we employ the Cauchy function as a similarity measure between histograms of consecutive frames, which yields a high performance compared with conventional measures. The key frames extracted from segmented video shots can be used not only for video shot clustering but also for video sequence matching or browsing, where the key frame is defined by the frame that is significantly different from the previous fames. Several key frame extraction algorithms have been proposed, in which similar methods used for shot boundary detection were employed with proper similarity measures. In this paper, we propose the efficient algorithm to extract key frames using the cumulative Cauchy function measure and. compare its performance with that of conventional algorithms. Video sequence matching can be performed by evaluating the similarity between data sets of key frames. To improve the matching efficiency with the set of extracted key frames we employ the Cauchy function and the modified Hausdorff distance. Experimental results with several color video sequences show that the proposed method yields the high matching performance and accuracy with a low computational load compared with conventional algorithms.

• Publications of The Korean Astronomical Society
• /
• v.27 no.4
• /
• pp.363-365
• /
• 2012

We report a search for fluctuations of the sky brightness toward the North Ecliptic Pole with AKARI, at 2.4, 3.2, and $4.1{\mu}m$. The stacked images with a diameter of 10 arcminutes of the AKARI-Monitor Field show a spatial structure on the scale of a few hundred arcseconds. A power spectrum analysis shows that there is a significant excess fluctuation at angular scales larger than 100 arcseconds that cannot be explained by zodiacal light, diffuse Galactic light, shot noise of faint galaxies, or clustering of low-redshift galaxies. These findings indicate that the detected fluctuation could be attributed to the first stars of the universe, i.e., Population III stars.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.775-792
• /
• 2015

Person re-identification is an important and challenging task in computer vision with numerous real world applications. Despite significant progress has been made in the past few years, person re-identification remains an unsolved problem. This paper presents a novel appearance-based approach to person re-identification. The approach exploits region covariance matrix and color histograms to capture the statistical properties and chromatic information of each object. Robustness against low resolution, viewpoint changes and pose variations is achieved by a novel signature, that is, the combination of Log Covariance Matrix feature and HSV histogram (LCMH). In order to further improve re-identification performance, third-party image sets are utilized as a common reference to sufficiently represent any image set with the same type. Distinctive and reliable features for a given image set are extracted through decision boundary between the specific set and a third-party image set supervised by max-margin criteria. This method enables the usage of an existing dataset to represent new image data without time-consuming data collection and annotation. Comparisons with state-of-the-art methods carried out on benchmark datasets demonstrate promising performance of our method.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.79-87
• /
• 2021

In recent years research on automatic font generation with machine learning mainly focus on using transformation-based methods, in comparison, generative model-based methods of font generation have received less attention. Transformation-based methods learn a mapping of the transformations from an existing input to a target. This makes them ambiguous because in some cases a single input reference may correspond to multiple possible outputs. In this work, we focus on font generation using the generative model-based methods which learn the buildup of the characters from noise-to-image. We propose a novel way to train a conditional generative deep neural model so that we can achieve font style control on the generated font images. Our research demonstrates how to generate new font images conditioned on both character class labels and character style labels when using the generative model-based methods. We achieve this by introducing a modified generator network which is given inputs noise, character class, and style, which help us to calculate losses separately for the character class labels and character style labels. We show that adding the character style vector on top of the character class vector separately gives the model rich information about the font and enables us to explicitly specify not only the character class but also the character style that we want the model to generate.

• The Journal of Korea Robotics Society
• /
• v.16 no.4
• /
• pp.299-305
• /
• 2021

In this study, the task of robotic tidy-up is to clean the current environment up exactly like a target image. To perform a tidy-up task using a robot, it is necessary to estimate the pose of various objects and to classify the objects. Pose estimation requires the CAD model of an object, but these models of most objects in daily life are not available. Therefore, this study proposes an algorithm that uses point cloud and PCA to estimate the pose of objects without the help of CAD models in cluttered environments. In addition, objects are usually detected using a deep learning-based object detection. However, this method has a limitation in that only the learned objects can be recognized, and it may take a long time to learn. This study proposes an image matching based on few-shot learning and Siamese network. It was shown from experiments that the proposed method can be effectively applied to the robotic tidy-up system, which showed a success rate of 85% in the tidy-up task.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.108-111
• /
• 2022

Applying deep learning to machine vision systems for defect detection of products requires vast amounts of training data about various defect cases. However, since data imbalance occurs according to the type of defect in the actual manufacturing industry, it takes a lot of time to collect product images enough to generalize defect cases. In this paper, we apply a Siamese neural network that can be learned with even a small amount of data to product defect detection, and modify the image pairing method and contrastive loss function by properties the situation of product defect image data. We indirectly evaluated the embedding performance of Siamese neural networks using AUC-ROC, and it showed good performance when the images only paired among same products, not paired among defective products, and learned with exponential contrastive loss.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.499-504
• /
• 2023

본 연구에서는 민감한 개인정보의 유출과 남용 위험이 높아지고 있는 상황에서 정확한 개인정보 탐지 및 비식별화의 효율을 높이기 위해 개인정보 항목에 특화된 개체명 체계를 개발하였다. 개인정보 태그셋이 주석된 대화 데이터 4,981세트를 구축하고, 생성 AI 모델을 활용하여 개인정보 개체명 탐지 실험을 수행하였다. 실험을 위해 최적의 프롬프트를 설계하여 퓨샷러닝(few-shot learning)을 통해 탐지 결과를 평가하였다. 구축한 데이터셋과 영어 기반의 개인정보 주석 데이터셋을 비교 분석한 결과 고유식별번호 항목에 대해 본 연구에서 구축한 데이터셋에서 더 높은 탐지 성능이 나타났으며, 이를 통해 데이터셋의 필요성과 우수성을 입증하였다.

• The Journal of Korean Medicine
• /
• v.45 no.1
• /
• pp.203-214
• /
• 2024

Objectives: In the context of competency-based education emphasized in Korean Medicine, this study aimed to develop a pilot version of a CPX (Clinical Performance Examination) Practicing Chatbot utilizing large language models with prompt engineering. Methods: A standardized patient scenario was acquired from the National Institute of Korean Medicine and transformed into text format. Prompt engineering was then conducted using role prompting and few-shot prompting techniques. The GPT-4 API was employed, and a web application was created using the gradio package. An internal evaluation criterion was established for the quantitative assessment of the chatbot's performance. Results: The chatbot was implemented and evaluated based on the internal evaluation criterion. It demonstrated relatively high correctness and compliance. However, there is a need for improvement in confidentiality and naturalness. Conclusions: This study successfully piloted the CPX Practicing Chatbot, revealing the potential for developing educational models using AI technology in the field of Korean Medicine. Additionally, it identified limitations and provided insights for future developmental directions.

• Progress in Medical Physics
• /
• v.16 no.1
• /
• pp.24-31
• /
• 2005

The stereotactic radiosurgery (SRS) describes a method of delivering a high dose of radiation to a small tar-get volume in the brain, generally in a single fraction, while the dose delivered to the surrounding normal tissue should be minimized. To perform automatic plan of the SRS, a new method of multi-isocenter/shot linear accelerator (linac) and gamma knife (GK) radiosurgery treatment plan was developed, based on a physical lattice structure in target. The optimal radiosurgical plan had been constructed by many beam parameters in a linear accelerator or gamma knife-based radiation therapy. In this work, an isocenter/shot was modeled as a sphere, which is equal to the circular collimator/helmet hole size because the dimension of the 50% isodose level in the dose profile is similar to its size. In a computer-aided system, it accomplished first an automatic arrangement of multi-isocenter/shot considering two parameters such as positions and collimator/helmet sizes for each isocenter/shot. Simultaneously, an irregularly shaped target was approximated by cubic structures through computation of voxel units. The treatment planning method by the technique was evaluated as a dose distribution by dose volume histograms, dose conformity, and dose homogeneity to targets. For irregularly shaped targets, the new method performed optimal multi-isocenter packing, and it only took a few seconds in a computer-aided system. The targets were included in a more than 50% isodose curve. The dose conformity was ordinarily acceptable levels and the dose homogeneity was always less than 2.0, satisfying for various targets referred to Radiation Therapy Oncology Group (RTOG) SRS criteria. In conclusion, this approach by physical lattice structure could be a useful radiosurgical plan without restrictions in the various tumor shapes and the different modality techniques such as linac and GK for SRS.