• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.83-88
• /
• 2006

Many applications in the area of location-based services and personal navigation require nowadays the location determination of a user not only in outdoor environment but also indoor. To locate a person or object in a building, systems that use either infrared, ultrasonic or radio signals, and visible light for optical tracking have been developed. The use of WiFi for location determination has the advantage that no transmitters or receivers have to be installed in the building like in the case of infrared and ultrasonic based location systems. WiFi positioning technology adopts IEEE802.11x standard, by observing the radio signals from access points installed inside a building. These access points can be found nowadays in our daily environment, e.g. in many office buildings, public spaces and in urban areas. The principle of operation of location determination using WiFi signals is based on the measurement of the signal strengths to the surrounding available access points at a mobile terminal (e.g. PDA, notebook PC). An estimate of the location of the terminal is then obtained on the basis of these measurements and a signal propagation model inside the building. The signal propagation model can be obtained using simulations or with prior calibration measurements at known locations in an offline phase. The most common location determination approach is based on signal propagation patterns, namely WiFi fingerprinting. In this paper the underlying technology is briefly reviewed followed by an investigation of two WiFi positioning systems. Testing of the system is performed in two localization test beds, one at the Vienna University of Technology and the second at the Hong Kong Polytechnic University. First test showed that the trajectory of a moving user could be obtained with a standard deviation of about ${\pm}$ 3 m.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1200-1215
• /
• 2023

With the development of IoT and artificial intelligence, location-based services are getting more and more attention. For solving the current problem that indoor positioning error is large and generalization is poor, this paper proposes a Model Stacking Algorithm for Indoor Positioning System using WiFi fingerprinting. Firstly, we adopt a model stacking method based on Bayesian optimization to predict the location of indoor targets to improve indoor localization accuracy and model generalization. Secondly, Taking the predicted position based on model stacking as the observation value of particle filter, collaborative particle filter localization based on model stacking algorithm is realized. The experimental results show that the algorithm can control the position error within 2m, which is superior to KNN, GBDT, Xgboost, LightGBM, RF. The location accuracy of the fusion particle filter algorithm is improved by 31%, and the predicted trajectory is close to the real trajectory. The algorithm can also adapt to the application scenarios with fewer wireless access points.

• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• pp.583-591
• /
• 2018

With the development of ICT(Information and Communication Technology), the number of smart devices is rapidly increasing. LBS(Location Based Service) applications that provide user's location based service are used in various fields. There is also a growing demand for indoor precision positioning technology to provide seamless services. In this paper, we propose an indoor positioning system that estimates the location of a smartphone user. The proposed algorithm determines whether the received signal is LOS(Line-of-Sight) or NLOS(Non-Line of-Sight) in order to decrease multipath effect by the indoor environment. The proposed positioning algorithm is very simple and requires only the AP(Access Point) coordinates. In addition, it requires only two APs for estimating the location of a smartphone user. The proposed algorithm is a practically applicable technology without any additional hardware and kernel modification in the smartphone. In the experiment results, the reliability of the positioning system was found to be within 0.83 m.

• Journal of Industrial Technology
• /
• v.28 no.A
• /
• pp.97-104
• /
• 2008

Recently, interests on positioning system for location-based services have been significantly increased. Many indoor environment systems using fingerprint scheme have been designed to take more accuracy of positioning, but they are inefficient in adapting to change of environments. In this paper, we focus on a client-based positioning system over WLAN for decreasing installation cost and adapting to change of environments. In the proposed system, APs with stable RSSI are selected as base APs independently for each reference point. Experimental results show that proposed system expands service area approximately 20% much than traditional systems using K-NN algorithm and needs only 20% modification process to fingerprint data compare with traditional systems whenever environment conditions are changed.

• Korean Institute of Interior Design Journal
• /
• v.22 no.5
• /
• pp.207-215
• /
• 2013

Due to an increase in the number of large-scale and high rise buildings, the importance of indoor location information has been highlighted. As a result, seamless three-dimensional space information, linked to various indoor and outdoor services is required. The purpose of this study is to develop a system which can edit and operate indoor space information using the IndoorGML(Geography Markup Language). It provides functions such as converting and editing authoring indoor space using the IndoorGML. Based on defined schema which is the IndoorGML international standardization work, we develop the "Editor" and "Viewer" for the IndoorGML. When indoor space is modeled in an authoring tool, a variety of topologies can be created automatically. These are available to be edited and modified. Moreover, the file of model can be saved as IndoorGML, SBM and KML file. These files are viewed by the "Viewer". Indoor LBS(Location Based Service)is served with these principles.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.25-30
• /
• 2024

Smart City, a key application area of the AIoT (Artificial Intelligence of Things), provides various services in safety, security, and healthcare sectors through location tracking and location-based services. an IPS (Indoor Positioning System) is required to implement location-based services, and wireless communication technologies such as WiFi, UWB (Ultra-wideband), and BLE (Bluetooth Low Energy) are being applied. BLE, which enables data transmission and reception with low power consumption, can be applied to various IoT devices such as sensors and beacons at a low cost, making it one of the most suitable wireless communication technologies for indoor positioning. BLE utilizes the RSSI (Received Signal Strength Indicator) to estimate the distance, but due to the influence of multipath fading, which causes variations in signal strength, it results in an error of several meters. In this paper, we conducted research on a path loss model that can be applied to BLE IPS for proximity services, and confirmed that optimizing the free space propagation loss coefficient can reduce the distance error between the Tx and Rx devices.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.458-459
• /
• 2021

Recently, researches using deep learning technology based on Wi-Fi fingerprints have been conducted for accurate services in indoor location-based services. 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. At this time, continuous sequential data is required as training data. However, since Wi-Fi fingerprint data is generally managed only with signals for a specific location, it is inappropriate to use it as training data for an RNN model. This paper proposes a path generation method through prediction of a moving path based on Wi-Fi fingerprint data extended to region data through clustering to generate sequential input data of the RNN model.

• Journal of Information Technology Applications and Management
• /
• v.13 no.4
• /
• pp.57-70
• /
• 2006

Location Based Service (LBS) provides high-value added service to users and various works about IBS have been actively performed. The core technology or LBS is positioning of the users. In the field of positioning, outdoor positioning and indoor positioning are developed separately. We are proposing a design of an outdoor-indoor positioning system, implementing a prototype of the system, and verifying the usefulness of the system through experiments. Our experimental results shows that the average error of our system is 4.8 m in the case of out-door positioning and it is 3.3 m in the case of in-door positioning.

• Spatial Information Research
• /
• v.20 no.4
• /
• pp.93-101
• /
• 2012

Due to complexity of indoor space, the demand of Location Based Services (LBS) in indoor space is increasing as well as outdoor. However, it includes privacy problems of exposing personal location. Location K-anonymity technology is a method to solve the privacy problems with cloaking their locations by Anonymized Spatial Region(ASR). It guarantees K users within a region containing the location of a given user. However previous researches have dealt the problems based on Euclidean distance in outdoor space, and cannot be applied in indoor space where there are constraints of movement such as walls. For this reason, we propose in this paper a K-anonymity for cloaking indoor location in consideration of structures and representation of indoor space. The basic concept of our approach is to introduce a hierarchical structure as ASR for including K-1 users for cloaking their locations. We also proposed a cost model by K and attributes of hierarchical structure to analyze the performance of the method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.279-281
• /
• 2015

Location awareness is an important capability for mobile-based indoor services. Those indoor services have motivated the implementation of methods that need high computational load cost and complex mechanisms for positioning prediction. These mechanisms, such as opportunistic sensing and machine learning, require more energy consumption to achieve accuracy. In this paper, we propose the Bluetooth Low Energy indoor zone detection (BLEIZOD) technique. This method exploits the concept of proximity zone to reduce the load cost and complexity. Our proposed method implements the received signal strength indicator (RSSI) function more effectively to gain accuracy and reduce energy consumption.