• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.579-581
• /
• 2023

에너지바우처 사업은 해마다 지원 예산의 규모를 증액하고 대상 가구원 특성 기준을 추가하는 등 지속적인 노력에도 불구하고 현재 에너지바우처 사용률은 전국 평균 약 81.8%로 여전히 목표치에는 못 미치는 상황이다. 본 논문에서는 2015년 최초 시행 이후부터 누적된 에너지바우처의 데이터와 에너지연료비(유가 정보, 지역 난방비 등), 기상청의 개방된 기상자료(기상특보, 예보), 한전의 실시간 전력 소비데이터 등 타 정보를 결합하여 인공지능 기반 데이터 분석으로 에너지바우처 사용률을 높여 사용률 저조 원인을 분석하고 이를 기반으로 위험 가구에 대한 사전 탐지와 관리를 위한 시스템을 제안한다. 향후, 제안 시스템의 현실적인 운영을 위해서는 사용률과 연관된 다양한 변수에 대한 분석과 시스템 성능평가가 필요하다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.536-539
• /
• 2023

딥러닝 기술은 더 많은 분야와 과제에 적용되기 위해서 네트워크는 더 복잡하고 거대한 형태로 발전해왔다. YOLOv7-tiny과 같은 객체탐지 네트워크는 다양한 객체와 환경에서 활용하기 위해 COCO 데이터 세트를 대상으로 발전해왔다. 그러나 본 논문에서 적용할 모델은 임베디드 보드 환경에서 실시간으로 1개의 Class를 대상으로 객체를 탐지하는 네트워크 모델이 찾고자 프루닝을 적용하였다. 모델의 프루닝을 할 필터를 찾기 위해 본 논문에서는 클러스터링을 통한 필터 프루닝 방법을 제안한다. 본 논문의 제안 방법을 적용했을 때 기준 모델보다 정확도가 7.6% 감소하였으나, 파라미터가 1% 미만으로 남고, 속도는 2.1배 증가함을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.35-36
• /
• 2024

전신 마취 수술 중 저혈압의 발생은 다양한 합병증을 유발하며 이를 사전에 예측하여 대응하는 것은 매우 중요한 일이다. 따라서 본 연구에서는 SHAP 모델을 통해 변수 선택을 진행하고, Transformer 모델을 이용해 저혈압 발생 여부를 예측함으로써 임상적 의사결정을 지원한다. 또한 기존 연구들과는 달리, 수술실에서 수집되는 데이터를 기반으로 하여 높은 범용성을 가진다. 비침습적 혈압 예측에서 RMSE 9.46, MAPE 4.4%를 달성하였고, 저혈압 여부를 예측에서는 저혈압 기준 F1-Score 0.75로 우수한 결과를 얻었다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.11a
• /
• pp.97-98
• /
• 2023

Recently, the use of digital technology in architectural technology is gradually increasing with the development of various industrial technologies. There are artificial intelligence and drones in the field of architecture, and among them, deep learning technology has been introduced to conduct research in areas such as precise inspection of buildings, and it is expressed in a highly reliable way. When a building is deteriorated, various defects such as cracks in the surface and subsidence of the structure may occur. Since these cracks can represent serious structural damage in the future, the detection of cracks was conducted using artificial intelligence that can detect and identify surface defects by detecting cracks and aging of buildings.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.836-838
• /
• 2024

본 논문은 현대 사회에서 급증하는 VPN의 악용 가능성을 인지하고 VPN과 Non-VPN 트래픽 구별의 중요도를 강조한다. 전통적인 포트 기반 분류와 패킷 분석 접근법의 한계를 넘어서기 위해 트래픽 플로우 특징과 인공지능(AI) 기술을 결합하여 VPN과 Non-VPN 프로토콜을 구별하는 새로운 방법을 제안한다. 직접 수집한 패킷 데이터셋을 사용하여 트래픽 플로우 특징을 추출하고, 패킷의 페이로드와 결합해 이미지를 생성한다. 이를 CNN 모델에 적용함으로써 높은 정확도로 프로토콜을 구별한다. 실험 결과, 제안된 방법은 99.71%의 높은 정확도를 달성하여 트래픽 분류 및 네트워크 보안 강화에 기여할 수 있는 방법론임을 입증한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.29-43
• /
• 2023

Consumers should look at the ingredients of cosmetics or food for their health and purchase them after checking whether they contain allergy-causing ingredients. Therefore, this paper aimed to develop an artificial intelligence-based smartphone application for automatically recognizing the ingredients displayed on a curved container and delivering it to consumers in an easy-to-understand manner. The app needs to allow consumers to immediately comprehend the restricted ingredients by recognizing the ingredients' words in the cropped image. Two major issues should be solved during the development process: First, although there were flat containers for cosmetics or food, most were curved containers. Thus, it was necessary to recognize the ingredient table displayed on the curved containers. Second, since the ingredients' words were displayed on the curved surface, the transformed or line-changed words also needed to be recognized. The proposed new methods were enough to solve the above two problems. The application developed through various tests verified that there was no problem recognizing the ingredients' words contained in a cylindrical curved container.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.1037-1040
• /
• 2017

현재 머신러닝과 딥러닝의 기술이 빠른 속도로 발전하면서 수많은 인공지능 음성 비서가 출시되고 있지만, 발화자의 문장 내 존재하는 단어만 분석하여 결과를 반환할 뿐, 비언어적 요소는 인식할 수 없기 때문에 결과의 구조적인 한계가 존재한다. 따라서 본 연구에서는 인간의 의사소통 내 존재하는 비언어적 요소인 말의 빠르기, 성조의 변화 등을 수치 데이터로 변환한 후, "플루칙의 감정 쳇바퀴"를 기초로 지도학습 시키고, 이후 입력되는 음성 데이터를 사전 기계학습 된 데이터를 기초로 kNN 알고리즘을 이용하여 분석한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1248-1254
• /
• 2022

Efforts are being made to prevent traffic accidents in the school zone in advance. However, traffic accidents in school zones continue to occur. If the driver can know the situation information in the child protection area in advance, accidents can be reduced. In this paper, we design a camera that eliminates blind spots in school zones and a number recognition camera system that can collect pre-traffic information. It is designed by improving the LIDAR system that recognizes vehicle speed and pedestrians. It collects and processes pedestrian and vehicle image information recognized by cameras and LIDAR, and applies artificial intelligence time series analysis and artificial intelligence algorithms. The artificial intelligence traffic accident prevention system learned by deep learning proposed in this paper provides a forced push service that delivers school zone information to the driver to the mobile device in the vehicle before entering the school zone. In addition, school zone traffic information is provided as an alarm on the LED signboard.

• Journal of the Korean Society for information Management
• /
• v.41 no.1
• /
• pp.261-282
• /
• 2024

This study proposed and evaluated electroencephalography (EEG)-based and eye-tracking-based methods to determine relevance by utilizing users' implicit relevance feedback while navigating content in a digital library. For this, EEG/eye-tracking experiments were conducted on 32 participants using video, image, and text data. To assess the usefulness of the proposed methods, deep learning-based artificial intelligence (AI) techniques were used as a competitive benchmark. The evaluation results showed that EEG component-based methods (av_P600 and f_P3b components) demonstrated high classification accuracy in selecting relevant videos and images (faces/emotions). In contrast, AI-based methods, specifically object recognition and natural language processing, showed high classification accuracy for selecting images (objects) and texts (newspaper articles). Finally, guidelines for implementing a digital library interface based on EEG, eye-tracking, and artificial intelligence technologies have been proposed. Specifically, a system model based on implicit relevance feedback has been presented. Moreover, to enhance classification accuracy, methods suitable for each media type have been suggested, including EEG-based, eye-tracking-based, and AI-based approaches.