• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.345-347
• /
• 2016

Recently location based services is being expanded into the indoor service that can not access to the outdoor location informations, such as GPS. Thus, the research and development of an indoor positioning system with BLE(Bluetooth Low Energy) iBeacon technology has expanded. However, RSSI (Received Signal Strength Indicator) that is used as the distance information between the terminal and for positioning iBeacon signal has a problem in that distortion occurs, information such as the signal attenuation and the delay due to the characteristics of radio waves. In this paper, we propose a reliable method of verifying iBeacon signal with the signal distortion problems for reliable indoor positioning systems.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.1
• /
• pp.9-15
• /
• 2005

Most of location systems use RF signal. Because multipath is too severe at indoor environment, RF signal are usually used in outdoor positioning such as GPS. To overcome the difficulty at indoor positioning, m positioning is recently developed and is being vigorously studied. Some standardizations on UWB are in progress at IEEE 802.15 committee. In developing UWB positioning system, we should consider the synchronization of sensor network, positioning algorithm, sensor allocation, and so on. This paper presents a comparison of TDOA positioning algorithms that are widely used in location systems. Two algorithms are compared; one is derived by linearization, and the other is by analytic solution(CH algorithm). Simulation results show that the CH algorithm is superior to the linearized least square at indoor environment in that CH algorithm shows consistent positioning performance regardless of the visibility and geometry of basestations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1094-1097
• /
• 2019

디지털화된 현실 환경을 증강현실속에서 투영시키기 위해선 증강현실 디바이스의 측위가 필수적이다. 하지만 대부분의 측위 방식이 측위 대상 디바이스에 대해 별도의 하드웨어나 센서를 요구하는데 이를 스마트폰 환경에서 충족시키기란 매우 힘든 일이다. 이에 본 논문은 스마트폰 환경에서 별도의 하드웨어를 요구하지 않는 딥러닝 영상기반 실내 측위 시스템을 제안한다. 제안하는 시스템은 측위를 위하여 설계된 피라미드형의 비콘을 활용하며 실시간에 가까운 피드백을 구현하기 위해 딥러닝 기법을 활용한 탐지를 진행한다. 본 논문에서는 상기한 두 개의 요소를 포함한 제안 시스템의 구성요소들을 설명하고 학습 방법과 비콘의 자세 측정 방법, 최종 측위 프로세스 등 전반적인 측위 프로세스를 설명한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.641-642
• /
• 2018

Currently, the performance of positioning technology based on radio wave fingerprint is greatly influenced by the selection of data comparison algorithm. In this case, the accuracy of the indoor positioning can be greatly improved by the data expansion technique necessary for the learning structure. In this paper, we discuss the importance of learning structure that can be applied to actual positioning through classification and extension of learning data to construct learning structure based on Wi-Fi radio fingerprint.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.436-439
• /
• 2008

위치기반 서비스(LBS : Local Based Service)는 단연 GPS가 그 중심이라 할 수 있다. 그러나 실외가 아닌 실내에서의 측위는 GPS신호가 도달할 수 없고, 또한 기존에 연구 중인 실내측위 기술들은 여러 가지 문제점을 갖고 있다. 따라서 다양한 서비스가 구현 가능한 ZigBee 기반의 USN내에서 기존의 다양한 센서들이 구동되면서 ZigBee 노드 간의 신호의 세기인 RSSI(Received Signal Strength Indicator)를 활용한 위치측위시스템을 구현한다. 또한 기존의 RSSI를 활용한 실내측위의 문제점들을 보완하기 위하여 신경회로망을 이용한 위측측위 알고리즘을 제안하여 보다 정확하고 안정적인 위치정보 시스템을 구현한다. 따라서 실내위치측위가 필요한 다양한 공공장소에 적합한 위치기반 서비스가 도입될 수 있는 가능성을 제시한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06d
• /
• pp.222-225
• /
• 2010

최근 무선 인터넷 기술의 발달과 보급으로 인해 실생활에서도 쉽게 무선 네트워크를 이용한 통신을 할 수 있게 되었다. 무선 네트워크를 이용한 통신을 위해선 통신 망을 유지해 주는 AP(Access Point)가 필수적이다. 이러한 AP를 활용한 AP의 신호 세기를 이용하는 실내 위치 측위 기술은 위치 기반 서비스의 발달과 함께 주목 받고 있다. 본 논문에서는 실내 위치 측위에 많이 사용되는 삼각측량법을 개선하기 위해 다수의 무선 네트워크 인터페이스를 사용한다. 최근에는 하나의 디바이스에 여러 개의 무선 인터페이스가 장착되는 것이 보편화 되었는데 이러한 여러 개의 인터페이스를 활용하여 실내 위치 측위 값을 보정하였다. 실험 결과, 2개의 모듈을 사용할 때의 결과가 1개의 모듈을 사용했을 때 보다 평균 4.9% 좋은 성능을 보였다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.373-378
• /
• 2016

Recently, IPS(Indoor Positioning System) Technology has been progressing study and research, It has been studied in the fingerprinting and trilateration continuously. however because Fingerprinting and Trilateration Technology use AP(Access Point) for Positioning Calculation, Fingerprinting and Trilateration are not never had a credit positioning accuracy by using unstable RSSI in large scale. in this paper, to improve the problem about precise positioning in wide area, we introduced a concept of Sector including Cell. Sectors are not involved in each other and only fingerprinting calculation is proceed in a sector. we suggest this fingerprinting system considering efficiency and accuracy and compared to conventional fingerprinting, we demonstrated our system efficiency by mathematical techniques.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.146-153
• /
• 2010

For the indoor location, wireless fingerprinting is most favorable because fingerprinting is most accurate among the technique for wireless network based indoor location which does not require any special equipments dedicated for positioning. As fingerprinting method,k-nearest neighbor(KNN) has been widely applied for indoor location in wireless location area networks(WLAN), but its performance is sensitive to number of neighborsk and positions of reference points(RPs). So possibilistic fuzzy c-means(PFCM) clustering algorithm is applied to improve KNN, which is the KNN/PFCM hybrid algorithm presented in this paper. In the proposed algorithm, through KNN,k RPs are firstly chosen as the data samples of PFCM based on signal to noise ratio(SNR). Then, thek RPs are classified into different clusters through PFCM based on SNR. Experimental results indicate that the proposed KNN/PFCM hybrid algorithm generally outperforms KNN and KNN/FCM algorithm when the locations error is less than 2m.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.2
• /
• pp.71-77
• /
• 2019

With 5G standards proceeding in earnest and increasing demand for services of indoor localization, research on indoor location recognition is being studied in various industrial fields, and research based on fingerprint recognition technology using Wireless Local Area Network (WLAN) is representative. In this paper, we propose an indoor positioning system based on fingerprinting technique that uses Cloud Radio Access Network (C-RAN) architecture and Channel State Information (CSI). In order to improve the performance in indoor positioning, we combined existing fingerprinting method and K nearest neighbor (KNN) technology which is one of the machine running technique. The performance improvements of the proposed indoor positioning system was verified by comparative experiments with the existing localization technique in a indoor localizztion testbed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.302-313
• /
• 2018

As the demand for indoor location recognition system has been rapidly increased in accordance with the increasing use of smart devices and the increasing use of augmented reality, indoor positioning systems(IPS) using BLE (Bluetooth Lower Energy) beacons and UWB (Ultra Wide Band) have been developed. In this paper, a positioning plate is generated by using trilateration technique based on BLE Beacon and using RSSI (Received Signal Strength Indicator). The resultant value is used to calculate the PDR-based coordinates using the positioning element of the Inertial Measurement Unit sensor, We propose a precise indoor positioning algorithm that combines RSSI and PDR technique. Based on the plate algorithm proposed in this paper, the experiment have done at large scale indoor sports arena and airport, and the results were successfully verified by 65% accuracy improvement with average 2.2m error.