• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.355-357
• /
• 2022

In this paper, as a positioning technology for predicting the movement path of a moving object using a recurrent neural network (RNN) model, which is a deep learning network, in an indoor environment, continuous location information is used to predict the path of a moving vehicle within a local path. We propose a movement path generation technique that can reduce decision errors. In the case of an indoor environment where GPS information is not available, the data set must be continuous and sequential in order to apply the RNN model. However, Wi-Fi radio fingerprint data cannot be used as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, we propose a movement path generation technique for a vehicle moving a local path in an indoor environment by giving the necessary sequential location continuity to the RNN model.

• Journal of Satellite, Information and Communications
• /
• v.8 no.4
• /
• pp.64-69
• /
• 2013

Recently, users who are interested in the service at indoor spaces is increasing. An indoor positioning system can minimize a range of positioning error using a variety of wireless communication infrastructure. Also, the system improves an indoor positioning accuracy by combining a mobile communication network. However, flexible positioning technologies regardless of an environment are insufficient. Therefore, this is time for a systematic study on an indoor positioning system business model. This paper classify differences between an indoor positioning system technology and outdoor positioning system technology. And we research a construction and application of the indoor positioning system that is adapted a wireless communication system (Wi-Fi, Bluetooth, RFID, UWE, Fingerprint, etc.) in domestic and foreign. We present a successful model of indoor positioning system and the development for future systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.86-88
• /
• 2017

The digital door lock is an electronic door lock that uses a password system and has the function of automatically locking the door when the door is closed, thus eliminating the worry about the door lock. As the technology has gradually developed, various authentication technologies such as semiconductor key system, RFID, and fingerprint recognition have been introduced. However, there is a danger of copying the door lock key, and there are password stealing and infringement. In this paper, we develop a remote control system that can unlock or open a smartphone to supplement the user's risk. The system you are going to develop can use WiFi to check if the door is locked or open on your smartphone, and you can lock or unlock the door remotely.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.47-49
• /
• 2022

IPS is an indoor positioning system that replaces GPS, which is less accurate due to walls and roofs inside buildings. Radio signals such as Wi-Fi are used instead of satellite signals, and complex methods are being used to increase accuracy. In this paper, we present a more efficient positioning method than before by applying high-level signals to high-accuracy fingerprint techniques. A radio map is configured with high-level signals collected by utilizing Wi-Fi APs, which are more than in the past. The suitability of use was confirmed by analyzing the pattern represented by the configured radio map for each location.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.490-491
• /
• 2021

Recently, technologies using Wi-Fi fingerprints and deep learning are being studied to provide accurate location-based services in an indoor environment. At this time, the composition of learning data is very important, and it is essential to collect sufficient data necessary for learning. However, the number of specific points for the collection of radio signal data within the area requiring positioning is infinite, and it is impossible to collect all of these data. Therefore, there is a need for a way to make up for insufficient learning data. This study proposes a method of constructing a sufficient number of location data necessary for learning based on insufficiently collected location data.

• Korean Management Science Review
• /
• v.29 no.2
• /
• pp.79-90
• /
• 2012

Focusing on the rapid market penetration of smart phones, the importance of LBS (Location Based Service) is drastically increased. However, traditional GPS method has critical weakness caused by limited availability, such as indoor environment. WPS is newly attractive method as a widely applicable positioning method. In WPS, RSSI (Received Signal Strength Indication) data of all Wi-Fi APs (Access Point) are measured and stored into a huge database. The stored RSSI data in database make single radio fingerprint map. By the radio fingerprint map, we can estimate the actual position of target point. The essential factor of radio fingerprint database is data integrity of RSSI. Because of millions of APs in urban area, RSSI measurement data are seriously contaminated. Therefore, we present the unified filtering method for RSSI measurement data. As the results of filtering, we can show the effectiveness of suggested method in practical positioning system of mobile operator.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.11
• /
• pp.2411-2418
• /
• 2011

The most typically utilized positioning method in the existing indoor WPS that is a positioning method utilizing distributed wireless network is the finger print. Its positioning is carried out by calculating the difference between the AP information map and WiFi AP signal collected. However, there are problems like low accuracy and high cost when the existing method and the radio map formation are applied to outdoors. In this paper, the characteristics of the existing WPS are surveyed and their problems are examined. In addition, we propose a new WPS using weak signal and a method to construct radio map in order to solve the above problems. And then, the results of experimental test will be analyzed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.657-659
• /
• 2018

In real life, We are using IoT technology directly. IoT technology has been applied in many fields and has developed continuously. Internet of Things is a technology or environment that attaches sensors to objects and sends and receives data through internet in real time. In this paper, if a password is wrong more than three times, the existing password is initialized and randomly changed. Changed password data seeks to realize that push alarms are sent via the app to the user or administrator. We have studied an Indono-based IoT system that can send real-time data to smart phones through WiFi. smart door locks are intended to implement them using Aduino, fingerprint sensor, camera sensor, Wi-Fi shield, Android Studio, and door lock components.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.2068-2079
• /
• 2015

Recently, interesting in flexible working has been increased, and some central government and large companies are conducting flexible working. With the conducting of flexible working, workers are able to get a convenience but the cost of managing is increased. In this paper, we suggest a method of reducing the cost and managing efficiently. Our study determines the position of the workers using indoor localization techniques through the Wi-Fi fingerprint and smartphone, and records the office hours. The previous time and attendance systems have to install attendance recording device(e.g. Fingerprint Attendance System, RFID Card Attendance System) and are needed to manipulate manually. Our system doesn't need to install extra devices, and also doesn't need to manipulate manually. Our system automatically records the office hours. Also most of previous time and attendance systems have another weakness. They only record data when workers start and stop work. But our system exactly records office hours for each workplaces. In this paper, We introduce an effective time and attendance system in variety flexible working. Our experiments shows that our system workers' detected office hours accurately. The accuracy of our time and attendance system was 98.7%.

• Proceedings of the Safety Management and Science Conference
• /
• 2012.04a
• /
• pp.175-180
• /
• 2012

최근 GPS와 Wi-Fi가 내장된 스마트폰의 보급으로 이를 이용한 위치기반 서비스(Location-based Service)가 발전하고 있다. 하지만 위치기반 서비스들의 오차 범위는 3~4m 내외로 크기 때문에 사용자들은 더 정확한 위치를 제공하기를 바라고 있다. 본 논문에서 위치기반 서비스의 핵심기능을 담당하는 측위기술 중 흔히 사용되고 있는 삼각측량법을 활용하여 핑거프린트 방법의 측위오차를 줄일 수 있는 방안을 연구하였고 프로그램으로 구현한 후 테스트를 실시하였다. 프로그램은 Labview2010으로 구현하였고, 각각의 알고리즘을 모듈화하여 필터링 적용 전 후 및 개선효과를 비교하기 쉽도록 구성하였다. 실내 테스트는 인하대학교의 강의실에서 실시하였고 실외 테스트는 인하대학교 운동장에서 실시하였다. 테스트 결과 실내의 경우 본 논문에서 제시하는 필터링 방법을 적용하기 전의 오차가 1.02미터에서 0.83미터로 감소하였고 실외에서는 0.74미터에서 0.54미터로 오차가 감소하였다.