• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1794-1799
• /
• 2022

Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. therefore we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Also, we propose an integrated system for tracking the detected vehicles. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.118-118
• /
• 2022

지속적인 학문의 발전을 위해서는 선행연구에 대한 재현성이 무엇보다도 중요하다고 할 수 있다. 하지만 컴퓨터와 소프트웨어의 급속한 발달로 인한 컴퓨터 환경의 다양화, 분석 소프트웨어의 지속적 최신화로 인해서 최근 구축된 모델도 짧게는 몇 달, 길게는 1~2년후면 다양한 에러로 인하여 재현성이 불가능해지고 있다. 이러한 재현성의 극복을 위해서 온라인을 통한 데이터와 소스코드의 공유의 필요성이 제시되고 있으나, 실제로는 개인마다 컴퓨터 환경, 버전, 소프트웨어 설치에 필요한 라이브러리의 버전 또는 디렉토리 등이 달라 단순히 온라인을 통한 데이터와 소스코드의 공유만으로 재현성을 개선하기는 힘든 것이 현실이다. 따라서 이러한 컴퓨터 모델링 환경의 공유는 과거의 형태와 같이 데이터, 소스코드와 매뉴얼의 공유만으로 불가능하다고 할 수 있다. 따라서 본 연구에서는 수자원 모델링의 재현성 개선을 위해 1) 온라인 저장소, 2) 클라우드기반 JupyterHub 모델링 환경과 3) 모델 APIs 3개의 핵심 구성요소를 제시하고, 최근 미국에서 개발된SUMMA(Structure for Unifying Multiple Modeling Alternative) 수자원 모델에 적용하여 재현성 달성을 위한 3개의 핵심 구성요소의 필요성과 용이성을 검증하였다. 첫 번째, 데이터와 모델의 온라인 공유는 FAIR(Findable, Accessible, Interoperable, Reusable) 원칙으로 개발된 수자원분야의 대표적인 온라인 저장소인 HydroShare를 활용하여 모델입력자료를 메타데이터와 함께 공유하였다. 두 번째, HydroShare에서 Web App의 형태로 제공되는 클라우드기반 JupyterHub환경인 CUAHSI JupyterHub(CJH)와 일루노이대학에서 제공하는 CyberGIS-Jupyter for water JupyterHub(CJW)환경에 수자원모델링 환경을 컨테이너(Docker) 환경을 통해 구축·공유하였다. 마지막으로, 클라우드에서 수자원모델의 효율적 이용을 위해 Python기반의SUMMA모델 API인 pySUMMA를 개발·공유하였다. 이와같이 구축된 3개의 핵심 구성요소를 이용하여 2015년 Water Resources Research에 게재된 SUMMA 논문의 9개 Test Cases 중에서 5개를 누구나 쉽게 재현할 수 있음을 증명하였다. 재현성의 중요성에 대한 인식의 증가로 Open과 Transparent Hydrology에 대한 요구가 증대되고 있으며, 이를 위해서 클라우드 기반의 모델링 환경구축 및 제공이 확대되고 있다. 본 연구에서 제시한 HydroShare와 같은 온라인 저장소, CJH와 CJW와 같은 클라우드기반 모델링환경, 모델의 효율적 이용을 위한 모델 APIs는 급속도로 발달하고 있는 컴퓨터 및 소프트웨어 환경에서 핵심구성요소이며, 연구의 재현성 개선을 통해 수자원공학 발전에 기여할 것으로 기대된다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2207-2218
• /
• 2008

Various kind of business process exists within enterprise. These business processes achieve business purposes while operate and control using eAI solution. However legacy systems-ERP, PDM are able to many cooperations and interoperability. Generally real data is becoming interoperability using query based on store-procedure on legacy system for business process transaction. Also, It may occur some problems among schema conversion, matching, mapping and other heterogeneous between data interoperability in process. We propose business process interoperability framework based on XMDR Hub that can guarantee interoperability between legacy systems using process that is consisted of SQL query based on store-procedure. It is easy to process data interoperability between legacy systems when business process execute.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1759-1768
• /
• 2022

This paper proposes a model to detect depression-related emotions in a user's speech using wellness dialogue scripts provided by AI Hub, topic-specific daily conversation datasets, and chatbot datasets published on Github. There are 18 emotions, including depression and lethargy, in depression-related emotions, and emotion classification tasks are performed using KoBERT and KOELECTRA models that show high performance in language models. For model-specific performance comparisons, we build diverse datasets and compare classification results while adjusting batch sizes and learning rates for models that perform well. Furthermore, a person performs a multi-classification task by selecting all labels whose output values are higher than a specific threshold as the correct answer, in order to reflect feeling multiple emotions at the same time. The model with the best performance derived through this process is called the Depression model, and the model is then used to classify depression-related emotions for user utterances.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.562-565
• /
• 2022

Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. However, this irregular weight distribution is not possible to be recognized with the current weight measurement system for vehicles on roads. To address this limitation, we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles from the CCTV, black box, and hand-held camera point of view. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data. From the result, we believe that public big data can be utilized more efficiently and applied to the development of an object detection-based overloaded vehicle detection model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.402-403
• /
• 2023

본 연구의 목적은 LDA 토픽 모델링을 활용하여 한국어 SNS데이터에 분석을 통해 우리나라의 여가활동, 일과 직업, 주거와 생활의 동향을 살펴보는 것이다. AI Hub에서 제공하는 한국어 SNS데이터를 수집하고 형태소 분석, 전처리 과정을 거친 후 coherence score을 토대로 최적의 토픽 수를 결정하여 토픽을 추출하였다. 도출한 트렌드를 바탕으로 경영, 마케팅 분야에 미치는 영향을 예측할 수 있을 것으로 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.52-54
• /
• 2023

최근 인공지능 기술의 발전에 따라서 다양한 서비스에서 음성 인식을 활용한 서비스를 제공하면서 음성 인식에 대한 중요성이 증가하고 있다. 이 논문에서는 국내에서 많이 사용되고 있는 대표적인 인공지능 서비스 API 를 제공하는 구글, ETRI, 네이버에 대해서 감정 음성 관점에서 그 차이를 평가하였다. AI Hub 에서 제공하는 감성 대화 말뭉치 데이터 셋의 일부인 음성 테스트 데이터를 사용하여 평가한 결과 ETRI API 가 문자 오류율 (1.29%)과 단어 오류율(10.1%)의 성능 지표에 대해서 가장 우수한 음성 인식 성능을 보임을 확인하였다.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.155-161
• /
• 2021

Gesture recognition analytics through a camera in real time have been widely studied in recent years. Since a small number of features from human joints are extracted, low accuracy of classifying models is get in conventional gesture recognition studies. In this paper, CBAM (Convolutional Block Attention Module) with high accuracy for classifying images is proposed as a classification model and algorithm calculating the angle of joints depending on actions is presented to solve the issues. Employing five exercise gestures images from the fitness posture images provided by AI Hub, the images are applied to the classification model. Important 8-joint angles information for classifying the exercise gestures is extracted from the images by using MediaPipe, a graph-based framework provided by Google. Setting the features as input of the classification model, the classification model is learned. From the simulation results, it is confirmed that the exercise gestures are classified with high accuracy in the proposed model.