• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.1
• /
• pp.23-28
• /
• 2021

Data analysis research using deep learning has recently been studied in various field. In this paper, we conduct a GNSS (Global Navigation Satellite System)-based meteorological study applying deep learning by estimating the ZWD (Zenith tropospheric Wet Delay) through MLP (Multi-Layer Perceptron) and LSTM (Long Short-Term Memory) models. Deep learning models were trained with meteorological data and ZWD which is estimated using zenith tropospheric total delay and dry delay. We apply meteorological data not used for learning to the learned model to estimate ZWD with centimeter-level RMSE (Root Mean Square Error) in both models. It is necessary to analyze the GNSS data from coastal areas together and increase time resolution in order to estimate ZWD in various situations.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.668-673
• /
• 2021

As the fourth industrial revolution begins in earnest, related technologies are becoming a hot topic. Hardware development is accelerating to make the most of technologies such as high-speed wireless communication, and related companies are growing rapidly. Artificial intelligence often uses desktops in general for related research, but it is mainly used for the learning process of deep learning and often transplants the generated models into devices to be used by including them in programs, etc. However, it is difficult to produce results for devices that do not have sufficient power or performance due to excessive learning or lack of power due to the use of models built to the desktop's performance. In this paper, we analyze efficiency using boards with several Neural Process Units on sale before developing the performance of deep learning to match embedded boards, and deep learning accelerators that can increase deep learning performance with USB, and present a simple development direction possible using embedded boards.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.757-759
• /
• 2017

현대인들은 삶을 영위하기 위해 매우 바쁘게 생활한다. 아이러니하게도, 이로 인해 자신의 건강은 챙기기 쉽지 않다. 특히 치아 쪽은 건강검진에도 포함되어 있지 않아 더욱 그렇다. 이를 해결하기 위해 본 논문은 충치를 판단해주는 플랫폼을 제안한다. 실시간으로 사용자의 구강 안을 촬영한 영상에서 충치, 아말감, 골드 크라운 이렇게 세 가지 치아의 상태를 구분하여 검출한다. 치아의 종류를 판단하는 기술은 딥러닝을 이용하였다. 딥러닝 학습모델이 치아 판별기로써의 기능을 다하려면 충분하게 많은 각 종류의 치아 데이터가 필요하다. 따라서, 인터넷, 학술 자료 등을 활용하여 수집했다. 이 시스템을 혈압측정기, 신장계와 같이 공공장소에 설치함으로써 사용자 스스로 치아의 상태를 확인 할 수 있을 것으로 예상된다.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1156-1164
• /
• 2017

Existing studies on automatic bug triage were mostly used the method of designing the prediction system based on the machine learning algorithm. Therefore, it can be said that applying a high-performance machine learning model is the core of the performance of the automatic bug triage system. In the related research, machine learning models that have high performance are mainly used, such as SVM and Naïve Bayes. In this paper, we apply Deep Learning, which has recently shown good performance in the field of machine learning, to automatic bug triage and evaluate its performance. Experimental results show that the Deep Learning based Bug Triage system achieves 48% accuracy in active developer experiments, un improvement of up to 69% over than conventional machine learning techniques.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.306-309
• /
• 2019

The damage to farms due to wild animals such as wild boars and elks increases every year, but, in the current system, the catchers from government hunt animals by using guns at night as making an effort to detect wild animals personally by using flashlights. This is very time-inefficient and immediate follow-up action on being damaged is not possible. In this paper, we introduce a system which can detect and recognize the wild animals or the people with high accuracy using thermal imaging camera and infrared camera in company with deep learning technology, so that could kick out or catch the wild animals more quickly than current system.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.269-282
• /
• 2021

As the distribution of 3D content such as augmented reality and virtual reality increases, the importance of real-time computer animation technology is increasing. However, the computer animation process consists mostly of manual or marker-attaching motion capture, which requires a very long time for experienced professionals to obtain realistic images. To solve these problems, animation production systems and algorithms based on deep learning model and sensors have recently emerged. Thus, in this paper, we study four methods of implementing natural human movement in deep learning model and kinect camera-based animation production systems. Each method is chosen considering its environmental characteristics and accuracy. The first method uses a Kinect camera. The second method uses a Kinect camera and a calibration algorithm. The third method uses deep learning model. The fourth method uses deep learning model and kinect. Experiments with the proposed method showed that the fourth method of deep learning model and using the Kinect simultaneously showed the best results compared to other methods.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2017.11a
• /
• pp.327-328
• /
• 2017

본 논문에서는 사회재난 안전사고 중 수상 안전사고를 예방 및 사고 발생시 즉각 대응을 위한 센서 융복합 상황인지 기술을 개발하였다. 실제 현장에서의 위험상황을 전문가 컨설팅을 통하여 정의하였으며 이를 영상 분석을 이용한 객체의 검출 및 객체의 추적을 통한 위험상황 검출을 개발하였다. 기존 패턴인식 기술에 비하여 우수한 성능을 보이는 인공지능 기반 딥러닝 기술을 적용하였으며 딥러닝 기술을 적용하기 위하여는 많은 수의 데이터베이스 확보가 필수적이고 이를 위하여 기존 데이터베이스의 확보 및 현장에서의 실제 데이터베이스 구축을 위한 작업을 통하여 충분한 데이터베이스를 확보하였다. 객체 검출은 최적의 속도를 확보하기 위하여 SSD 구조를 이용하였으며 객체 추적을 위해서는 Re-identification 기법을 적용하여 Tied convolution 구조를 이용하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.297-298
• /
• 2019

본 논문에서는 드론용 오픈 소스 API를 이용하여 셀프 카메라 촬영이 가능한 드론용 앱을 설계한다. 특히, 딥러닝 기반의 YOLO 객체 탐지 기술을 적용하여 배경 속에서 사람을 탐지하여 개인 및 단체 사진 촬영이 가능하도록 설계한다. 개발하는 셀프 카메라 앱은 기체의 자동 회전 및 선회 기반 연속 촬영 기능을 포함하여 다양한 형태의 인물 사진 촬영이 가능하다. 개발된 앱 기술을 기반으로 선회 및 회전을 통한 경비 구역의 침입자 촬영을 위한 시스템 및 드론 제어 기술에 활용하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.552-554
• /
• 2021

We propose a fall recognition system using a deep learning algorithm using motion data acquired by a Doppler radar sensor. Among the deep learning algorithms, an RNN that has an advantage in time series data is used to recognize falls. The fall data of the Doppler radar sensor has a temporal characteristic as time series data, and the structure of the RNN is sequenced because the result only determines whether a fall or not It is designed in a structure that outputs a fixed size to the input.