• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.801-803
• /
• 1998

가압경수형 원전에서 증기발생기의 수위제어가 저출력하에서 유체거동이 부정확하고 비정상적이어서 기존의 PI제어기 만으로는 파라메타 설정이 곤란하여 효과적인 제어가 어렵다. 이러한 문제점을 개선하고자 인공지능기법의 일종인 신경회로망을 이용한 수위제어 알고리즘의 적용을 연구하였다. 저출력시에는 증기발생기내에서의 물리적인 현상이 상당히 복잡하여 정확한 수학적 모델링이 어렵기 때문에 기존의 PI제어기와는 별도로 입출력신호패턴에 근거한 수위변동의 경향인식으로 요구되는 수위레벨을 과도현상없이 안정적으로 제어 할 수 있었다. 이 연구결과에 기초하여 저출력시에 한하여 신경회로망을 적용한 컴퓨터로써 병렬운전을 수행한다면 효과적인 현장적용성을 높일 수가 있다.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.159-159
• /
• 2017

스마트 시설환경은 대표적으로 원예, 축산 분야 등 여러 형태의 농업현장에 정보 통신 및 데이터 분석 기술을 도입하고 있는 시설화된 생산 환경이라 할 수 있다. 근래에 하드웨어적으로 급증한 스마트 시설환경에서 생산되는 방대한 생육/환경 데이터를 올바르고 적합하게 사용하기 위해서는 일반 산업 현장과는 차별화 된 분석기법이 요구된다고 할 수 있다. 소프트웨어 공학 분야에서 연구된 빅데이터 처리 기술을 기계적으로 농업 분야의 빅데이터에 적용하기에는 한계가 있을 수 있다. 시설환경 내/외부의 다양한 환경 변수는 시계열 데이터의 난해성, 비가역성, 불특정성, 비정형 패턴 등에 기인하여 예측 모델 연구가 매우 난해한 대상이기 때문이라 할 수 있다. 본 연구에서는 근래에 관심이 급증하고 있는 인공신경망 연구 소프트웨어인 Tensorflow (www.tensorflow.org)와 대표적인 Open source인 OpenNN (www.openn.net)을 스마트 시설환경 환경변수 상호간 상관성 분석에 응용하였다. 해당 소프트웨어 라이브러리의 운영환경을 살펴보면 Tensorflow 는 Linux(Ubuntu 16.04.4), Max OS X(EL capitan 10.11), Windows (x86 compatible)에서 활용가능하고, OpenNN은 별도의 운영환경에 대한 바이너리를 제공하지 않고 소스코드 전체를 제공하므로, 해당 운영환경에서 바이너리 컴파일 후 활용이 가능하다. 소프트웨어 개발 언어의 경우 Tensorflow는 python이 기본 언어이며 python(v2.7 or v3.N) 가상 환경 내에서 개발이 수행이 된다. 주의 깊게 살펴볼 부분은 이러한 개발 환경의 제약으로 인하여 Tensorflow의 주요한 장점 중에 하나인 고속 연산 기능 수행이 일부 운영 환경에 국한이 되어 제공이 된다는 점이다. GPU(Graphics Processing Unit)의 제공하는 하드웨어 가속기능은 Linux 운영체제에서 활용이 가능하다. 가상 개발 환경에 운영되는 한계로 인하여 실시간 정보 처리에는 한계가 따르므로 이에 대한 고려가 필요하다. 한편 근래(2017.03)에 공개된 Tensorflow API r1.0의 경우 python, C++, Java언어와 함께 Go라는 언어를 새로 지원하여 개발자의 활용 범위를 매우 높였다. OpenNN의 경우 C++ 언어를 기본으로 제공하며 C++ 컴파일러를 지원하는 임의의 개발 환경에서 모두 활용이 가능하다. 특징은 클러스터링 플랫폼과 연동을 통해 하드웨어 가속 기능의 부재를 일부 극복했다는 점이다. 상기 두 가지 패키지를 이용하여 2016년 2월부터 5월 까지 충북 음성군 소재 딸기 온실 내부에서 취득한 온도, 습도, 조도, CO2에 대하여 Large-scale linear model을 실험적(시간단위, 일단위, 주단위 분할)으로 적용하고, 인접한 세그먼트의 환경변수 예측 모델링을 수행하였다. 동일한 조건의 학습을 수행함에 있어, Tensorflow가 개발 소요 시간과 학습 실행 속도 측면에서 매우 우세하였다. OpenNN을 이용하여 대등한 성능을 보이기 위해선 병렬 클러스터링 기술을 활용해야 할 것이다. 오프라인 일괄(Offline batch)처리 방식의 한계가 있는 인공신경망 모델링 기법과 현장 보급이 불가능한 고성능 하드웨어 연산 장치에 대한 대안 마련을 위한 연구가 필요하다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.271-282
• /
• 2022

In this paper, we propose a digital human content creation system. The digital human content creation system works with 3D AI modeling through whole-body scanning, and is produced with 3D modeling post-processing, texturing, rigging. By combining this with virtual reality(VR) content information, natural motion of the virtual model can be achieved in virtual reality, and digital human content can be efficiently created in one system. Therefore, there is an effect of enabling the creation of virtual reality-based digital human content that minimizes resources. In addition, it is intended to provide an automated pre-processing process that does not require a pre-processing process for 3D modeling and texturing by humans, and to provide a technology for efficiently managing various digital human contents. In particular, since the pre-processing process such as 3D modeling and texturing to construct a virtual model are automatically performed by artificial intelligence, so it has the advantage that rapid and efficient virtual model configuration can be achieved. In addition, it has the advantage of being able to easily organize and manage digital human contents through signature motion.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.2
• /
• pp.39-57
• /
• 2018

The purpose of this study was to construct an artificial intelligence model that learns and estimates the relationship between vehicle queue length and link travel time in urban areas. The vehicle queue length estimation model is modeled by three models. First of all, classify whether vehicle queue is a link overflow and estimate the vehicle queue length in the link overflow and non-overflow situations. Deep learning model is implemented as Tensorflow. All models are based DNN structure, and network structure which shows minimum error after learning and testing is selected by diversifying hidden layer and node number. The accuracy of the vehicle queue link overflow classification model was 98%, and the error of the vehicle queue estimation model in case of non-overflow and overflow situation was less than 15% and less than 5%, respectively. The average error per link was about 12%. Compared with the detecting data-based method, the error was reduced by about 39%.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.53-59
• /
• 2021

In this paper, we propose a BERGPT-chatbot, a domestic AI chatbot that can alleviate negative emotions based on text input such as 'Replika'. We made BERGPT-chatbot into a chatbot capable of mitigating negative emotions by pipelined two models, KR-BERT and KoGPT2-chatbot. We applied a creative method of giving emotions to unrefined everyday datasets through KR-BERT, and learning additional datasets through KoGPT2-chatbot. The development background of BERGPT-chatbot is as follows. Currently, the number of people with depression is increasing all over the world. This phenomenon is emerging as a more serious problem due to COVID-19, which causes people to increase long-term indoor living or limit interpersonal relationships. Overseas artificial intelligence chatbots aimed at relieving negative emotions or taking care of mental health care, have increased in use due to the pandemic. In Korea, Psychological diagnosis chatbots similar to those of overseas cases are being operated. However, as the domestic chatbot is a system that outputs a button-based answer rather than a text input-based answer, when compared to overseas chatbots, domestic chatbots remain at a low level of diagnosing human psychology. Therefore, we proposed a chatbot that helps mitigating negative emotions through BERGPT-chatbot. Finally, we compared BERGPT-chatbot and KoGPT2-chatbot through 'Perplexity', an internal evaluation metric for evaluating language models, and showed the superity of BERGPT-chatbot.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.35-44
• /
• 2022

In this paper, we propose an intra-picture prediction method by a quadratic surface modeling method for depth video coding. The pixels of depth video are transformed to 3D coordinates using distance information. A quadratic surface with the smallest error is found by least square method for reference pixels. The reference pixel can be either the upper pixels or the left pixels. In the intra prediction using the quadratic surface, two predcition values are computed for one pixel. Two errors are computed as the square sums of differences between each prediction values and the pixel values of the reference pixels. The pixel sof the block are predicted by the reference pixels and prediction method that they have the lowest error. Comparing with the-state-of-art video coding method, simulation results show that the distortion and the bit rate are improved by up to 5.16% and 5.12%, respectively.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.905-912
• /
• 2022

Virtual reality, one of the core technologies of the 4th industrial revolution, is entering a new phase with the spread of low-cost wearable devices represented by Oculus. In the case of disaster evacuation drills, where practical training is almost impossible due to the risk of accidents, virtual reality is becoming a new alternative that enables effective training. In this paper, we propose a smoke modeling method that can be applied to fire evacuation drills implemented with virtual reality technology. In the event of a fire, smoke spreads along the aisle, and the density of the smoke changes over time. The proposed method models the smoke by applying a procedural function that can reflect the density of smoke calculated through simulation to the model in real-time. Implementation results in the background of the factory show that the proposed method produces models that can express the smoke according to the user's movement.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1031-1042
• /
• 2023

In this study, a deep learning model was developed to predict the yield of cabbage and radish, one of the five major supply and demand management vegetables, using satellite images of Landsat 8. To predict the yield of cabbage and radish in Gangwon-do from 2015 to 2020, satellite images from June to September, the growing period of cabbage and radish, were used. Normalized difference vegetation index, enhanced vegetation index, lead area index, and land surface temperature were employed in this study as input data for the yield model. Crop yields can be effectively predicted using satellite images because satellites collect continuous spatiotemporal data on the global environment. Based on the model developed previous study, a model designed for input data was proposed in this study. Using time series satellite images, convolutional neural network, a deep learning model, was used to predict crop yield. Landsat 8 provides images every 16 days, but it is difficult to acquire images especially in summer due to the influence of weather such as clouds. As a result, yield prediction was conducted by splitting June to July into one part and August to September into two. Yield prediction was performed using a machine learning approach and reference models , and modeling performance was compared. The model's performance and early predictability were assessed using year-by-year cross-validation and early prediction. The findings of this study could be applied as basic studies to predict the yield of field crops in Korea.

• Journal of the Korean Society for information Management
• /
• v.32 no.1
• /
• pp.135-152
• /
• 2015

The goal of this paper is to explore the field of Computer and Information Science with the aid of text mining techniques by mining Computer and Information Science related conference data available in DBLP (Digital Bibliography & Library Project). Although studies based on bibliometric analysis are most prevalent in investigating dynamics of a research field, we attempt to understand dynamics of the field by utilizing Latent Dirichlet Allocation (LDA)-based multinomial topic modeling. For this study, we collect 236,170 documents from 353 conferences related to Computer and Information Science in DBLP. We aim to include conferences in the field of Computer and Information Science as broad as possible. We analyze topic modeling results along with datasets collected over the period of 2000 to 2011 including top authors per topic and top conferences per topic. We identify the following four different patterns in topic trends in the field of computer and information science during this period: growing (network related topics), shrinking (AI and data mining related topics), continuing (web, text mining information retrieval and database related topics), and fluctuating pattern (HCI, information system and multimedia system related topics).