• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.47-52
• /
• 2023

With the growing data size and the increased computing load in machine learning, energy-efficient resource planning in IoT systems is becoming increasingly important. In this paper, we suggest a new resource planning policy for real-time workloads that can be fluctuated over time in IoT systems. To handle such situations, we categorize real-time tasks into fixed tasks and variable tasks, and optimize the resource planning for various workload conditions. Based on this, we initiate the IoT system with the configuration for the fixed tasks, and when variable tasks are activated, we update the resource planning promptly for the situation. Simulation experiments show that the proposed policy saves the processor and memory energy significantly.

• Journal of Advanced Navigation Technology
• /
• v.18 no.2
• /
• pp.151-157
• /
• 2014

Recently UAV(unmanned aerial vehicle) is frequently used not only for military purpose but also for civil purpose. UAV automatically navigates following the coordinates input in advance using GPS information. However it is impossible when GPS cannot be received because of jamming or external interference. In order to solve this problem, we propose a real-time segmentation and classification algorithm for the specific regions from UAV image in this paper. We use the super-pixels algorithm using graph-based image segmentation as a pre-processing stage for the feature extraction. We choose the most ideal model by analyzing various color models and mixture color models. Also, we use support vector machine for classification, which is one of the machine learning algorithms and can use small quantity of training data. 18 color and texture feature vectors are extracted from the UAV image, then 3 classes of regions; river, vinyl house, rice filed are classified in real-time through training and prediction processes.

• Journal of Advanced Navigation Technology
• /
• v.22 no.6
• /
• pp.602-609
• /
• 2018

Differential GPS (DGPS) is known as a positioning method using pseudo range correction (PRC) which is communicating between a refence receiver and moving receivers. In real world, a moving receiver loses communication with the reference receiver, resulting in loss of PRC real-time communication. In this paper, we assume that the transmission of the pseudo range correction isinterrupted in the middle of real-time positioning situations, in which calibration information is received in the DGPS method. Under the disconnected communication, we propose 'predict DGPS' that real-time virtual PRC model which is modeled by a machine learning algorithm with previously acquired PRC data from a reference receiver. To verify predict DGPS method, we compared and analyzed positioning solutions acquired from real PRC and the virtual PRC. In addition, we show that positioning using the DGPS prediction method on a real road can provide an improved positioning solution assuming a scenario in which PRC communication was cut off.

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.302-313
• /
• 2000

In English-Korean machine translation, transitive verb-objective collocation is utilized for accurate translation of an English verbal phrase into Korean. This paper presents an algorithm for correct verb translation based on the k-nearest neighbor learning. The semantic distance is defined on the WordNet for the k-nearest neighbor learning. And we also present algorithms for automatic collocation dictionary optimization. The algorithms extract transitive verb-objective pairs as training examples from large corpora and minimize the examples, considering the tradeoff between translation accuracy and example size. Experiments show that these algorithms optimized collocation dictionary keeping about 90% accuracy for a verb 'build'.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.281-286
• /
• 2021

뉴스 헤드라인에 제3자의 발언을 직접 인용해 전언하는 이른바 '따옴표 저널리즘'이 언론 보도의 객관주의 원칙을 해치는지는 언론학 및 뉴스 구독자에게 중요한 문제이다. 이 연구는 온라인 포털사이트를 통해 실시간 유통되는 한국어 기사의 정확성을 판별하기 위한 기계학습(Machine Learning) 모델을 제안한다. 이 연구에서 제안하는 모델은 Edit Distance와 FastText 기법을 활용해 기사 제목과 본문 내 인용구의 유사성을 측정하고, XGBoost 모델을 활용해 최종 분류한다. 아울러 이 모델을 통해 229만 건의 뉴스 헤드라인에 대해 직접 인용구가 포함된 기사가 취재원의 발언을 주관적인 윤색없이 독자들에게 전하고 있는지를 판별했다. 이뿐만 아니라 딥러닝 기반의 KoELECTRA 모델을 활용해 기사의 제목 내 인용구에 대한 감성 분석을 진행했다. 분석 결과, 윤색이 가미되지 않은 직접 인용형 기사의 비율이 지난 20년 동안 10% 이상 증가했으며, 기사 제목의 인용구에 나타나는 감정은 부정 감성이 긍정 감성의 2.8배 정도로 우세했다. 이러한 시도는 앞으로 계산사회과학 방법론과 빅데이터에 기반한 언론 보도의 평가 및 개선에 도움을 주리라 기대한다.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.209-219
• /
• 2016

SVM is a machine learning method used for image processing. It is well known for its high classification performance. We have to perform multiple MAC operations in order to use SVM for image classification. However, if the resolution of the target image or the number of classification cases increases, the execution time of SVM also increases, which makes it difficult to be performed in real-time applications. In this paper, we propose an hardware architecture which enables real-time applications using SVM classification. We used parallel architecture to simultaneously calculate MAC operations, and also designed the system for several feature extractors for compatibility. RBF kernel was used for hardware implemenation, and the exponent calculation formular included in the kernel was modified to enable fixed point modelling. Experimental results for the system, when implemented in Xilinx ZC-706 evaluation board, show that it can process 60.46 fps for $1360{\times}800$ resolution at 100MHz clock frequency.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1005-1012
• /
• 2021

Recently, the use of various location-based services-based location information systems using maps on the web has been expanding, and there is a need for a monitoring system that can check power demand in real time as an alternative to energy saving. In this study, we developed a deep learning real-time virtual power demand prediction web system using open source-based mapping service to analyze and predict the characteristics of power demand data using deep learning. In particular, the proposed system uses the LSTM(Long Short-Term Memory) deep learning model to enable power demand and predictive analysis locally, and provides visualization of analyzed information. Future proposed systems will not only be utilized to identify and analyze the supply and demand and forecast status of energy by region, but also apply to other industrial energies.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.4
• /
• pp.231-241
• /
• 2006

Creating controllable, responsive avatars is an important problem in computer games and virtual environments. Recently, large collections of motion capture data have been exploited for increased realism in avatar animation and control. Large motion sets have the advantage of accommodating a broad variety of natural human motion. However, when a motion set is large, the time required to identify an appropriate sequence of motions is the bottleneck for achieving interactive avatar control. In this paper, we present a novel method for training avatar behaviors from unlabelled motion data in order to animate and control avatars at minimal runtime cost. Based on machine learning technique, called Q-teaming, our training method allows the avatar to learn how to act in any given situation through trial-and-error interactions with a dynamic environment. We demonstrate the effectiveness of our approach through examples that include avatars interacting with each other and with the user.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.58-62
• /
• 2008

인터넷 상에서 상품을 구입할 때 고려하는 부분 중의 하나가 상품평이다. 하지만 이러한 상품평들을 개인이 일일이 확인 하는데에는 상당한 시간이 소요된다. 이러한 문제점을 줄이기 위해서 본 논문에서는 인터넷 상의 상품평에 대한 의견을 긍정, 부정, 일반으로 나누는 시스템을 제안한다. 제안 시스템은 CRFs 기계학습모델을 기반으로 하며, 연결어미, 형태소 유니그램, 슬라이딩 윈도우 기법의 형태소 바이그램을 자질로 사용한다. 실험을 위해서 가격비교 사이트의 모니터 카테고리에서 561개의 상품평을 수집하였다. 이 중 465개의 상품평을 학습 문서로 사용하였고 96개의 상품평을 실험 문서로 사용하였다. 제안 시스템은 실험결과 79% 정도의 정확도를 보였다. 추가 실험으로 제안 시스템이 사람들과 얼마나 비슷한 성능을 보이는지 알아보기 위해서 카파 테스트를 실시하였다. 카파 테스트를 실시한 결과, 사람간의 카파 계수는 0.6415였으며, 제안 시스템과 사람 간의 카파 계수는 평균 0.5976이였다. 결론적으로 제안 시스템이 사람보다는 떨어지지만 유사한 정도의 성능을 보임을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.405-407
• /
• 2016

최근, ICT/loT 기술과의 융합은 다양한 산업분야에 적용되고 있으며, 안정적인 전력공급 및 지능형전력망 구축에 대해 다양한 연구가 이루어지고 있다. 특히, 수요라인과 직접적으로 연관된 배전계통의 효율적인 운영 및 배전설비의 유지/관리 기술에 대한 연구에 많은 연구를 수행하고 있다. 본 논문에서는 다양한 배전설비에 대한 환경정보를 loT 센서를 통해 수집함으로써 실시간으로 정전상황을 불러올 수 있는 기자재의 고장감지 및 예측을 위한 시스템 모델을 제안한다. 제안하는 시스템 모델은 실시간으로 수집되는 정보들에 대해 시계열 기반의 필터링 및 이상점 판단을 위한 성분 분석을 실시하고, 고장진단 및 예측을 위해 기계학습 기반의 데이터 분석실시하여 기자재들의 고장감지 및 고장 발생 여부를 예측한다.