• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.456-457
• /
• 2021

Recently, in order to more accurately provide indoor location-based services, technologies using Wi-Fi fingerprints and deep learning are being studied. Among the deep learning models, an RNN model that can store information from the past can store continuous movements in indoor positioning, thereby reducing positioning errors. When using an RNN model for indoor positioning, the collected training data must be continuous sequential data. However, the Wi-Fi fingerprint data collected to determine specific location information cannot be used as training data for an RNN model because only RSSI for a specific location is recorded. This paper proposes a region clustering technique for sequential input data generation of RNN models based on Wi-Fi fingerprint data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.5
• /
• pp.451-458
• /
• 2016

Urban railway can be divided into ground and underground sections. In particular, the center of the metropolitan has been built mostly underground stations and tunnels. Underground section is difficult to measure the position because GPS signal is unavailable, so it is necessary to apply the indoor positioning technology. For this purpose, we analyzed the positioning technologies which are based on Wi-Fi and mobile base stations. The positing technology for smart phone which uses mobile base station' information is developed in the underground area of urban railway where the core technique is to implement base station ID into the positing technology by considering hand-off point.

• The KIPS Transactions:PartC
• /
• v.17C no.3
• /
• pp.251-258
• /
• 2010

In an indoor localization method taking the lateration-based approach, the location of a target is estimated with the location of anchor points (APs) and the approximated distances between the target and APs using received signal strength (RSS) measurements. The accuracy of distance estimation affects the localization accuracy of a lateration-based method. Since a radio propagation environment varies randomly in time and space, the highest RSSs do not necessarily give the best estimation of the distances between a target and APs. Thus, all APs hearing a target have been used for localization. However, the accuracy of a lateration-based method degrades if more APs beyond a certain threshold are used because the area of polygon with the APs increases. In this paper, we focus on reducing the size of the polygon to further increase the localization accuracy. We use the centroid of the polygon as a reference point to estimate the relative location of a target in the polygon. Once the relative location is estimated, only the APs which are closest to the target are used for localization to reduce the area of the polygon with the APs. We validate the proposed method by implementing an indoor localization system and evaluating the accuracy of the proposed method in the various experimental environments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1003-1004
• /
• 2017

본 연구에서는 실내 환경에서 드론의 측위를 위한 마커 인식 및 검출 기술을 소개한다. 기존 실내 측위를 위한 기술인 Global Positioning System이나 Wi-Fi를 이용한 삼각측량 기법은 실내 환경에서 각각의 성질로 인하여 사용하기 어려운 점이 있다. 본 논문에서는 2차원 바코드와 마커 등의 객체를 드론의 카메라를 이용한 실시간 영상 전송을 통하여 검출하여 위치 정보를 획득하는 기술을 소개한다. 실험에서는 드론의 카메라를 통하여 실시간 전송된 영상에서 OpenCV V2.4.10을 통하여 객체를 검출하였고, 카메라와 객체 사이의 거리와 바코드 크기에 따른 2차원 바코드의 검출 여부를 보였으며 15*15cm의 2차원 바코드는 비교적 잘 인식하였으나 비교적 작은 11*11cm의 2차원 바코드는 거리가 멀어질 수록 인식이 힘들어지는 결과를 보였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.340-342
• /
• 2013

The suitcase can follow its owner all on its own via the Bluetooth connectivity in your phone. A robotic vacuum cleaner than can understand voice commands and even follow homeowner. Robots are used in a variety of applications such as a robot wheelchair. In this paper, I focus the problem of automatic return to the base in the process of developing the moving robot for loading things.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.991-994
• /
• 2018

최근 사용자의 위치 정보를 기반으로 응용서비스를 제공하는 위치 기반 서비스가 각광 받고 있다. 그 중 실내 위치 정보 수집을 위한 방법 중 하나로 비콘을 사용하고 있다. 비콘을 이용하여 실내공간에서 사용자의 위치를 계산하는 방법은 비콘과 단말기와의 거리를 측정하고, 측위 알고리즘을 적용하여 단말기의 위치를 계산하는 것이다. 하지만 비콘이 단말기와의 거리를 측정하는데 사용하는 RSSI는 주변 환경에 영향을 많이 받아 측정 시 오차가 발생한다. 따라서 정확한 실내 측위를 위해서는 불안정한 RSSI를 보정할 필요가 있다. 본 논문에서는 RSSI의 오차 범위를 평균필터와 칼만필터, 그리고 신호의 정확도 개선 과정을 통해 보정하고 그 결과를 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.526-528
• /
• 2013

최근 실내 측위 기술을 이용한 다양한 서비스 제공을 위해 많은 위치 인식 기법이 연구되고 있다. 기존의 실내 위치 인식 기법은 사전에 획득한 맵 정보나 미리 구축한 기반 시설이 필요하거나, 추가 장비를 착용 및 부착해야 하는 단점이 있었다. 이에 본 논문에서는 스마트폰 내부센서를 이용하여 실내에서 사용자의 위치를 측정하는 시스템을 제안하였다. 제안한 시스템은 가속도 센서를 이용하여 이동여부를 파악하고, 사용자의 평균적인 이동속도와 방향센서를 이용하여 획득한 이동방향을 이용하여 위치를 추정한다. 제안한 시스템을 안드로이드 스마트폰에 구현하여 실험한 결과 약 ${\pm}75cm$ 이내의 오차에서 위치 인식이 가능함을 확인하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.4
• /
• pp.76-86
• /
• 2013

As the basic Kalman filter is limited to be used for indoor navigation, and particle filters incur serious computational overhead, especially in mobile devices, we propose an adaptive hybrid filter for WiFi-based indoor positioning systems. The hybrid filter utilizes the same prediction framework of the basic Kalman filter, and it adopts the notion of particle filters only using a small number of particles. Restricting the predicts of a moving object to a small number of particles on a way network and substituting a dynamic weighting scheme for Kalman gain are the key features of the filter. The adaptive hybrid filter showed significantly better accuracy than the basic Kalman filter did, and it showed greatly improved performance in processing time and slightly better accuracy compared with a particle filter.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.8
• /
• pp.1643-1654
• /
• 2015

With standardization of IEEE 802.11n, APs with the 2.4GHz and 5GHz dual-band capability have widely been deployed over a metropolitan area by individuals and internet service providers. Moreover, due to the increasing attentions on indoor-localization technique using Wi-Fi, the need for LOS and NLOS determination scheme is increasing to enhance accuracy of the localization. In this paper, we propose a novel LOS/NLOS determination technique by using different radio attenuation characteristics in different frequency bands and different mediums. Based on this technique, we designed a LOS/NLOS-aware indoor localization scheme. The proposed LOS/NLOS determination algorithm can be used when the distance between an user device and an AP is unknown, and the proposed localization scheme provides very accurate room-level position information. We validated the proposed scheme by implementing it on Android smart phones.

• Journal of Digital Contents Society
• /
• v.15 no.1
• /
• pp.129-136
• /
• 2014

Wi-Fi fingerprinting system is a very popular positioning method used in indoor spaces. The system depends on Wi-Fi Received Signal Strength (RSS) from Access Points (APs). However, the Wi-Fi RSS is changeable by multipath fading effect and interference due to walls, obstacles and people. Therefore, the Wi-Fi fingerprinting system produces low position accuracy. Also, Wi-Fi signals pass through walls. For this reason, the existing system cannot distinguish users' floor. To solve these problems, this paper proposes a LED fingerprinting system for accurate indoor positioning. The proposed system uses a received optical power from LEDs and LED-Identification (LED-ID) instead of the Wi-Fi RSS. In training phase, we record LED fingerprints in database at each place. In serving phase, we adopt a K-Nearest Neighbor (K-NN) algorithm for comparing existing data and new received data of users. We show that our technique performs in terms of CDF by computer simulation results. From simulation results, the proposed system shows that a positioning accuracy is improved by 8.6 % on average.