• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06d
• /
• pp.360-365
• /
• 2010

In this paper, we present a distributed algorithm for detecting dynamic event regions in wireless sensor network with the consideration on energy saving. Our model is that the sensing field is monitored by a large number of randomly distributed sensors with low-power battery and limited functionality, and that the event region is dynamic with motion or changing the shape. At any time that the event happens, we need some sensors awake to detect it and to wake up its k-hop neighbors to detect further events. Scheduling for the network to save the total power-cost or to maximize the monitoring time has been studied extensively. Our scheme is that some predetermined sensors, called critical sensors are awake all the time and when the event is detected by a critical sensor the sensor broadcasts to the neighbors to check their sensing area. Then the neighbors check their area and decide whether they wake up or remain in sleeping mode with certain criteria. Our algorithm uses only 2 bit of information in communication between sensors, thus the total communication cost is low, and the speed of detecting all event region is high. We adapt two kinds of measure for the wake-up decision. With suitable threshold values, our algorithm can be applied for many applications and for the trade-off between energy saving and the efficiency of event detection.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.176-184
• /
• 2023

Points of interest (POIs) are widely used in tourism recommendations and to provide information about areas of interest. Currently, situation judgement using POI and GPS data is mainly rule-based. However, this approach has the limitation that inferences can only be made using predefined POI information. In this study, we propose an algorithm that uses POI data, GPS data, and schedule information to calculate the current speed, location, schedule matching, movement trajectory, and POI coverage, and uses machine learning to determine whether to stay or go. Based on the input data, the clustered information is labelled by k-means algorithm as unsupervised learning. This result is trained as the input vector of the SVM model to calculate the probability of moving and staying. Therefore, in this study, we implemented an algorithm that can adjust the schedule using the travel schedule, POI data, and GPS information. The results show that the algorithm does not rely on predefined information, but can make judgements using GPS data and POI data in real time, which is more flexible and reliable than traditional rule-based approaches. Therefore, this study can optimize tourism scheduling. Therefore, the stay detection algorithm using GPS movement trajectories and POIs developed in this study provides important information for tourism schedule planning and is expected to provide much value for tourism services.

• Journal of the Korea Institute of Building Construction
• /
• v.12 no.1
• /
• pp.98-107
• /
• 2012

Reinforcing bars (rebar) comprise an integral part of a concrete structure, and play a major role in the safety and durability of the building. However, the actual placement or installation of rebar is not planned and controlled by the detailer. Recently, 4D simulations, using 3D model and scheduling software, have been used to improve the efficiency of the construction phrase. However, 4D simulators have not been introduced at the detailed level of work, such as rebar placement. Therefore, this paper suggests a BIM-based simulator for rebar placement to determine the sequence with which rebar is placed into the form. The system using Autodesk Revit API automatically generates rebar placement plans for a building structure, and labels the placement sequence of each individual bar or set of bars with ascending numbers. The placement sequence is then visualized using Autodesk Revit Structure 2012. This paper provides a short description of a field assessment and limits.

• 대한예방의학회:학술대회논문집
• /
• 2005.10a
• /
• pp.427-427
• /
• 2005

• Proceedings of the IEEK Conference
• /
• 2001.06a
• /
• pp.357-360
• /
• 2001

In this paper, we propose and evaluate a new interference cancellation method using low pass filtered data estimation method of the instantaneous decision sawnle obtained from each decision stage. With respect to the convergence to the optimal solution the superiority of the proposed method to parallel interference cancellation (PIC) referred as prevailing techniques is proved by its (asymptotic) spectral radius. Through the simulation under the various environment, we show the performance superiority of the IC scheme using proposed method to the PIC scheme. Furthermore, we show transcendence of the proposed method on the possibility of multirate transmission or multiple power scheduling and of performance in the various traffic environments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4C
• /
• pp.364-370
• /
• 2010

In this paper, we propose a cooperative channel sensing scheme in the presence of feedback errors. Accurate local sensing results may not directly be applied to cooperative sensing due to feedback errors. We consider the cooperative channel sensing that utilizes local sensing results in good feedback channel condition. Finally, simulation results show that the proposed scheme can maximize the detection probability while guaranteeing desired false alarm probability.

• Information Display
• /
• v.23 no.4
• /
• pp.35-44
• /
• 2022

AI기술의 유용성과 발전 가능성은 다양한 분야에서 확인되어 왔고, 디스플레이 산업에도 AI 기술들이 적극 도입되고 있다. 디스플레이 산업에 도입된 기존의 AI 기술들은 주로 engineer나 불량 검사자의 업무를 자동화하는 목적이었으나, 최근에는 engineer의 업무를 대체하는 고도의 지능화된 AI 기술들이 도입되고 있다. 본 논문에서는 이러한 지능화된 AI 기술 중에서 강화 학습, 자연어 처리, Pattern Matching 기술의 원리와 적용 사례들을 다루어 보았다. 첫번째로 강화 학습의 기본 개념을 설명하고, 설비 control (scheduling), 재료 탐색, 그리고 회로 설계에서의 적용 사례를 살펴보았다. 두번째로는 자연어 처리에서는 기술의 기본 원리 및 다양한 적용 방법론들에 대하여 다루었고, 제조 검사 리포트 분석, 지식재산권 분석, 연구문헌 분석 등에서의 활용 사례를 살펴보았다. 마지막으로 Pattern Matching에서는 기술 개요와 최근의 기술 동향을 기술하였고, Object Detection과 Object Tracking 기술 비교와 함께 패널 설계 도면으로부터 engineer 가 관심을 가져야 할 pattern 탐색에 대한 적용 사례를 살펴보았다.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.493-505
• /
• 2016

Among modern computer vision and video surveillance systems, the pedestrian counting system is a one of important systems in terms of security, scheduling and advertising. In the field of, pedestrian counting remains a variety of challenges such as changes in illumination, partial occlusion, overlap and people detection. During pedestrian counting process, the biggest problem is occlusion effect in crowded environment. Occlusion and overlap must be resolved for accurate people counting. In this paper, we propose a novel pedestrian counting system which improves existing pedestrian tracking method. Unlike existing pedestrian tracking method, proposed method shows that average filter tracking method can improve tracking performance. Also proposed method improves tracking performance through frame compensation and outlier removal. At the same time, we keep various information of tracking objects. The proposed method improves counting accuracy and reduces error rate about S6 dataset and S7 dataset. Also our system provides real time detection at the rate of 80 fps.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.2
• /
• pp.97-104
• /
• 2013

This paper introduces waiting time based periodic packet discard policy for frame based scheduler. This policy can be used with conventional packet discard policy or buffer management schemes, such as drop-tail or random early detection. Proposed discard policy discards packets, which are stayed in the buffer longer than threshold, at every period of scheduling. This decision of discard is based on waiting time of packet. In this paper, mathematical analysis is performed with situation of network congestion. Also, the simulation is performed to evaluate the performance of proposed discard policy. In the result, proposed discard policy can limit queuing delay by threshold. Also, if the packet discard is performed before scheduling and threshold is set with smaller value than frame length, it can limit the throughput of traffic.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.12
• /
• pp.630-640
• /
• 2007

As the range of sensor network's applicability is getting wider, it creates new application areas which is required real-time operation, such as military and detection of radioactivity. However, existing researches are focused on effective management for resources, existing sensor network operating system cannot support to real-time areas. In this paper, we propose the ${\mu}TMO$ model which is lightweight real-time distributed object model TMO. We design the real-time sensor network operation system ${\mu}TMO-NanoQ+$ which is based on ETRI's sensor network operation system Nano-Q+. We modify the Nano-Q+'s timer module to support high resolution and apply Context Switch Threshold, Power Aware scheduling techniques to realize lightweight scheduler which is based on EDF. We also implement channel based communication way ITC-Channel and periodic thread management module WTMT.