• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.

• Journal of the Korean Society of Radiology
• /
• v.82 no.1
• /
• pp.12-28
• /
• 2021

Mammography is the primary imaging modality for breast cancer detection; however, a high level of expertise is needed for its interpretation. To overcome this difficulty, artificial intelligence (AI) algorithms for breast cancer detection have recently been investigated. In this review, we describe the characteristics of AI algorithms compared to conventional computer-aided diagnosis software and share our thoughts on the best methods to develop and validate the algorithms. Additionally, several AI algorithms have introduced for triaging screening mammograms, breast density assessment, and prediction of breast cancer risk have been introduced. Finally, we emphasize the need for interest and guidance from radiologists regarding AI research in mammography, considering the possibility that AI will be introduced shortly into clinical practice.

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.81-90
• /
• 2020

In the real world, new types of attacks or variants are constantly emerging, but attack traffic classification models developed through artificial neural networks and supervised learning do not properly detect new types of attacks that have not been trained. Most of the previous studies overlooked this problem and focused only on improving the structure of their artificial neural networks. As a result, a number of new attacks were frequently classified as normal traffic, and attack traffic classification performance was severly degraded. On the other hand, the softmax function, which outputs the probability that each class is correctly classified in the multi-class classification as a result, also has a significant impact on the classification performance because it fails to calculate the softmax score properly for a new type of attack traffic that has not been trained. In this paper, based on this characteristic of softmax function, we propose an efficient method to improve the classification performance against new types of attacks by classifying traffic with a probability below a certain level as attacks, and demonstrate the efficiency of our approach through experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.186-191
• /
• 2023

Data processing techniques play a critical role in decision-making, including handling missing and outlier data, prediction, and recommendation models. This requires a clear explanation of the validity, reliability, and accuracy of all processes and results. In addition, it is necessary to solve data problems through explainable models using decision trees, inference, etc., and proceed with model lightweight by considering various types of learning. The multi-layer mining classification method that applies the sixth principle is a method that discovers multidimensional relationships between variables and attributes that occur frequently in transactions after data preprocessing. This explains how to discover significant relationships using mining on transactions and model the data through regression analysis. It develops scalable models and logistic regression models and proposes mining techniques to generate class labels through data cleansing, relevance analysis, data transformation, and data augmentation to make explanatory decisions.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.495-497
• /
• 2022

COVID-19 상황이 지속됨에 따라 플라스틱 쓰레기 배출량은 해마다 기하급수적으로 증가하고 있는 반면 플라스틱 폐기물의 재활용률은 현저히 낮은 편에 속한다. 이러한 문제점들을 해결하기 위해 국가적으로 여러 플라스틱 폐기물 중 순환 가능한 PET를 분리하여 수거하고자 하는 노력을 하고 있다. 하지만, 현재 대량의 플라스틱 폐기물은 수거되는 시점부터 여러 폐기물과 혼합된 형태로 재활용 센터에 수거되어 추가 분류하는 인적자원이 요구되는 문제점이 존재한다. 따라서 본 논문에서는 이러한 한계점들을 해결하기 위해 AI 기술 중 하나인 Multi-Object Detection의 YOLOv7 모델을 적용하여 실시간으로 PET에 부착된 객체들을 탐지함으로써 순환 가능한 PET만을 분류하는 YOLOv7 기반 순환 가능한 PET 분류시스템을 설계 및 구현한다.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.712-714
• /
• 2022

프로젝트 테마는 'CNN 딥러닝 모델을 기반으로 한 AI 가상 옷장'이다. 딥러닝 기술을 웹페이지에 적용시켜 사용자의 옷장 속에 있는 옷들을 자동으로 저장해서 관리해준다. 의류 이미지를 수집하고 딥러닝 모델을 통해 이미지를 학습시키고 분류하여 저장함으로써 사람들이 옷을 쉽게 찾을 수 있는 방법을 고안한다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.41-47
• /
• 2024

When there were disparities in performance between models trained in the time and frequency domains, even after conducting an ensemble, we observed that the performance of the ensemble was compromised due to imbalances in the individual model performances. Therefore, this paper proposes a leakage detection technique to enhance the accuracy of pipeline leakage detection through a step-wise learning approach that extracts features from both the time and frequency domains and integrates them. This method involves a two-step learning process. In the Stage 1, independent model training is conducted in the time and frequency domains to effectively extract crucial features from the provided data in each domain. In Stage 2, the pre-trained models were utilized by removing their respective classifiers. Subsequently, the features from both domains were fused, and a new classifier was added for retraining. The proposed transfer learning-based feature fusion technique in this paper performs model training by integrating features extracted from the time and frequency domains. This integration exploits the complementary nature of features from both domains, allowing the model to leverage diverse information. As a result, it achieved a high accuracy of 99.88%, demonstrating outstanding performance in pipeline leakage detection.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.333-335
• /
• 2022

본 논문에서는 기존에 두 가지 모델이 필요했던 작업을 하나의 모델로 처리할 수 있는 자연어 처리 아키텍처를 제안한다. 단일 모델로 알츠하이머 환자의 언어패턴과 대화맥락을 분석하고 두 가지 결과인 환자분류와 챗봇의 대답을 도출한다. 일상생활에서 챗봇으로 환자의 언어특징을 파악한다면 의사는 조기진단을 위해 더 정밀한 진단과 치료를 계획할 수 있다. 제안된 모델은 전문가가 필요했던 질문지법을 대체하는 챗봇 개발에 활용된다. 모델이 수행하는 자연어 처리 작업은 두 가지이다. 첫 번째는 환자가 병을 가졌는지 여부를 확률로 표시하는 '자연어 분류'이고 두 번째는 환자의 대답에 대한 챗봇의 다음 '대답을 생성'하는 것이다. 전반부에서는 셀프어탠션 신경망을 통해 환자 발화 특징인 맥락벡터(context vector)를 추출한다. 이 맥락벡터와 챗봇(전문가, 진행자)의 질문을 함께 인코더에 입력해 질문자와 환자 사이 상호작용 특징을 담은 행렬을 얻는다. 벡터화된 행렬은 환자분류를 위한 확률값이 된다. 행렬을 챗봇(진행자)의 다음 대답과 함께 디코더에 입력해 다음 발화를 생성한다. 이 구조를 DementiaBank의 쿠키도둑묘사 말뭉치로 학습한 결과 인코더와 디코더의 손실함수 값이 유의미하게 줄어들며 수렴하는 양상을 확인할 수 있었다. 이는 알츠하이머병 환자의 발화 언어패턴을 포착하는 것이 향후 해당 병의 조기진단과 종단연구에 기여할 수 있음을 보여준다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.713-714
• /
• 2023

본 논문에서는 사전학습모델을 활용한 수학학습 도구 자동 생성 시스템을 제안한다. 본 시스템은 사전학습모델을 활용하여 수학학습 도구를 교과과정 및 단원, 유형별로 다각화하여 자동 생성하고 사전학습모델을 자체 구축한 Dataset을 이용해 Fine-tuning하여 학생들에게 적절한 학습 도구와 적절치 않은 학습 도구를 분류하여 학습 도구의 품질을 높이었다. 본 시스템을 활용하여 학생들에게 양질의 수학학습 도구를 많은 양으로 제공해 줄 수 있는 초석을 다지었으며, 추후 AI 교과서와의 융합연구의 가능성도 열게 되었다.