• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.594-596
• /
• 2019

본 논문에서는 핑거프린트를 기반으로 실내에 있는 물류의 위치와 재고를 파악하는 실내 물류 위치추적 시스템을 제안한다. 또한 이를 통해 실제 물류 센터 환경 인프라를 구축하고 물류 관리 시스템을 설계 및 구현하였다. 제안하는 시스템은 위치 단말기를 통해 신호 세기를 수집하고 신호지도를 제작하여 물품의 위치를 파악한다. 위치 단말기는 UHF RFID 리더기와 무선 랜카드로 이루어져 있으며 주변 RFID 신호와 무선 AP의 신호를 읽어 웹 서버로 전송한다. 이를 통해 사용자는 스마트폰 앱을 통해 서버와 통신하면서 주변 물품의 정보와 위치를 파악할 수 있다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 추계학술발표대회
• /
• pp.168-171
• /
• 2016

In recent years, indoor localization in Wi-Fi environment has been researched for its location determining capability. The fingerprint and RF propagation models has been the main approach in determining indoor positioning. With the use of fingerprint, a low-cost, versatile localization system can be achieved without the use of external hardware. However, only a few research have been made on virtual access points (VAPs) among indoor localization models. In this paper, the idea of indoor localization system using fingerprint with the addition of VAP in Wi-Fi environment is discussed. The idea is to virtually add APs in the existing indoor Wi-Fi system, this would mean additional virtually APs in the network. The experiments of the proposed algorithm shows the positive results when 2VAPs are used compared with only APs. A combination of 3APs and 2VAPs had the lowest average error in all 4 scenarios with 3.99 meters.

• Journal of Positioning, Navigation, and Timing
• /
• 제10권1호
• /
• pp.49-54
• /
• 2021

Indoor positioning system becomes of increasing interests due to the demands for accurate indoor location information where Global Navigation Satellite System signal does not approach. Wi-Fi access points (APs) built in many construction in advance helps developing a Wi-Fi Received Signal Strength Indicator (RSSI) based indoor localization. This localization method first collects pairs of position and RSSI measurement set, which is called fingerprint database, and then estimates a user's position when given a query measurement set by comparing the fingerprint database. The challenge arises from nonlinearity and noise on Wi-Fi RSSI measurements and complexity of handling a large amount of the fingerprint data. In this paper, machine learning techniques have been applied to implement Wi-Fi based localization. However, most of existing indoor localizations focus on single position estimation. The main contribution of this paper is to develop multi-target localization by using deep neural, which is beneficial when a massive crowd requests positioning service. This paper evaluates the proposed multilocalization based on deep learning from a multi-story building, and analyses its learning effect as increasing number of target positions.

• 제어로봇시스템학회논문지
• /
• 제12권9호
• /
• pp.905-911
• /
• 2006

Smart homes are expected to offer various intelligent services by recognizing the residents' life pattern, health, and feeling. One of the key issues for realizing the smart home is how to detect the locations of residents. Currently, the research effort is focused on two approaches: terminal-based and non-terminal-based method. The terminal-based method employs a type of device that should be carried by the resident while the non-terminal-based method has no such device. This paper presents a novel non-terminal-based approach using an array of pyroelectric infrared sensors (PIRs) that can detect residents. The feasibility of the system is evaluated experimentally on a test bed.

• Journal of Advanced Marine Engineering and Technology
• /
• 제39권2호
• /
• pp.187-194
• /
• 2015

Accurate relative location estimation is a key requirement in indoor localization systems based on wireless sensor networks (WSNs). However, although these systems have applied not only various optimization algorithms but also fusion with sensors to achieve high accuracy in position determination, they are difficult to provide accurate relative azimuth and locations to users because of cumulative errors in inertial sensors with time and the influence of external magnetic fields. This paper based on ultra-wideband positioning system, which is relatively suitable for indoor localization compared to other wireless communications, presents an indoor localization system for estimating relative azimuth and location of location-unaware nodes, referred to as target nodes without applying any algorithms with complex variable and constraints to achieve high accuracy. In the proposed method, the target nodes comprising three mobile nodes estimate the relative distance and azimuth from two reference nodes that can be installed by users. In addition, in the process of estimating the relative localization information acquired from the reference nodes, positioning errors are minimized through a novel modified rounding estimation technique in which Kalman filter is applied without any time consumption algorithms. Experimental results show the feasibility and validity of the proposed system.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.364-367
• /
• 2007

실내위치인식을 위한 플랫폼으로서 RSSI(Received Signal Strength Indicator)기반으로 Zigbee/IEEE802.15.4표준을 따르는 CC2431(Chipcon, Norway)과 베이스스테이션노드를 결합하여 실내위치인식 시스템을 구현하였다. CC2431은 지정된 위치에서 자신의 현재위치를 전송해주는 레퍼런스노드와 인접해있는 레퍼런스노드들의 현재위치(X, Y좌표)와 RSSI값을 수신받아 내장된 Location Engine에서 자신의 현재위치를 계산하여 베이스스테이션노드로 전송해주는 블라인드노드로 구성이 되어있다. 베이스스테이션노드는 블라인드노드의 현재위치를 전송받아서 PC로 데이터를 넘겨주기 위한 게이트웨이로 사용하였으며 서버측의 원격지뿐만 아니라 외부에서도 블라인드노드의 현재위치를 실시간으로 확인할 수가 있다.

• 한국인터넷방송통신학회논문지
• /
• 제22권3호
• /
• pp.117-123
• /
• 2022

인공위성 기반의 실외 측위 시스템과는 달리 실내 측위 시스템은 BLE, Wi-Fi, UWB 등 다양한 무선 기술을 활용한다. BLE 기반 비컨 기술은 일정 주기로 사전에 정의된 장치 ID와 위치 정보를 제공하고 이를 수신한 장치에서 RSSI를 활용하여 실내에서 사용자의 위치를 측정할 수 있다. 기존의 BLE 기반 실내 측위 시스템 연구들은 단일 지점에서 사용자의 실제 위치와 계산된 위치의 오차를 비교하는 연구가 많았다. 본 논문에서는 엔트로피 분석 모델을 적용하여 이동 경로나 구역에 따른 측위 정확도를 평가하는 기법을 제안하였다. 또한 시뮬레이션을 통해 서로 다른 경로에 대한 엔트로피 결과값을 추출하고 이를 비교하여 어느 경로가 더 정확한지에 대해 평가할 수 있음을 검증하였다.

• 설비공학논문집
• /
• 제17권5호
• /
• pp.397-403
• /
• 2005

The thermal comfort of occupants is directly related to several environmental factors such as velocity of air flow, turbulence intensity and temperature distribution of indoor air. The purpose of this study is to evaluate the indoor air flow and temperature distribution in office area using under-floor air-conditioning system (UFAC System) based on the results from physical measurements and to perform a Computer Fluid Dynamics (CFD) under the same condition of inlet and outlet as field measurement. The results from the CFD simulation are similar to those from the field measurement. The results show that UFAC system is provide proper indoor condition for occupants.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 추계학술대회 논문집
• /
• pp.11-12
• /
• 2006

• 공학교육연구
• /
• 제13권5호
• /
• pp.76-80
• /
• 2010

In this paper, the Location Compensation Mechanism using equivalent distance rate ($LCM_{edr}$) for localization system based on SDS-TWR (Symmetric Double-Sided Two-Way Ranging) in wireless sensor network is proposed. The performance of the mechanism is experimented in terms of two types of the localization tracking scenarios of indoor and outdoor environments in university campus. From the experimentations, the compensation ratio in the $LCM_{edr}$ is better than that in SDS-TWR about 90% in indoor/outdoor environments in scenario 1 but also is better than that of SDS-TWR about 91.7% in indoor environment and about 100% in outdoor environment in scenario 2 respectively.