• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.125-133
• /
• 2011

For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. 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 neighbors k and positions of reference points(RPs). So intuitive fuzzy c-means(IFCM) clustering algorithm is applied to improve KNN, which is the KNN/IFCM hybrid algorithm presented in this paper. In the proposed algorithm, through KNN, k RPs are firstly chosen as the data samples of IFCM based on signal to noise ratio(SNR). Then, the k RPs are classified into different clusters through IFCM based on SNR. Experimental results indicate that the proposed KNN/IFCM hybrid algorithm generally outperforms KNN, KNN/FCM, KNN/PFCM algorithm when the locations error is less than 2m.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.109-115
• /
• 2011

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 neighbors k and positions of reference points(RPs). So artificial neural network(ANN) clustering algorithm is applied to improve KNN, which is the KNN/ANN hybrid algorithm presented in this paper. For any pattern matching based algorithm in WLAN environment, the characteristics of signal to noise ratio(SNR) to multiple access points(APs) are utilized to establish database in the training phase, and in the estimation phase, the actual two dimensional coordinates of mobile unit(MU) are estimated based on the comparison between the new recorded SNR and fingerprints stored in database. In the proposed algorithm, through KNN, k RPs are firstly chosen as the data samples of ANN based on SNR. Then, the k RPs are classified into different clusters through ANN based on SNR. Experimental results indicate that the proposed KNN/ANN hybrid algorithm generally outperforms KNN algorithm when the locations error is less than 2m.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.521-534
• /
• 2021

Purpose: In this paper, we propose an indoor positioning scheme based on pedestrian dead reckoning using inertial measurement unit. By minimizing the effects of the orientation error of smart-phone, the more accurate estimation for the direction, the step count, and the stride can be achieved. Method: The effectiveness and the performance of the proposed scheme is evaluated by experiments, and it is compared with the conventional scheme in the same conditions. Result: The results showed that the positioning error of the proposed scheme was 0.76m, while that of the conventional scheme was 1.84m. Conclusion: Sine most people carry his/her own smart-phone, the proposed scheme can be helpful to recognize where he/she was and was heading when the fast evacuation is needed in indoors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2022

Accurately measuring location is necessary to provide a variety of services. The data for indoor positioning measures the RSSI values from the WiFi device through an application of a smartphone. The measured data becomes the raw data of machine learning. The feature data is the measured RSSI value, and the label is the name of the space for the measured position. For this purpose, the machine learning technique is to study a technique that predicts the exact location only with the WiFi signal by applying an efficient technique to classification. Ensemble is a technique for obtaining more accurate predictions through various models than one model, including backing and boosting. Among them, Boosting is a technique for adjusting the weight of a model through a modeling result based on sampled data, and there are various algorithms. This study uses Xgboost among the above techniques and evaluates performance with other ensemble techniques.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.6C
• /
• pp.611-618
• /
• 2009

Recently, an indoor location-aware technology has been focused on as a key technology for context awareness in ubiquitous computing environments. The conventional Cricket system was designed with a non-centralized architecture, which has advantages in terms of user privacy, deployment, scalability, decentralized administration, network heterogeneity, and low cost. In this paper, an indoor location system based on TDOA between RF and ultrasound signals is designed, which improves the Cricket system. A 2.4GHz frequency is employed for transmitting RF messages, which is in an ISM band. The beaconing frequency is doubled to enhance the channel utilization rate. The ultrasonic pulse duration is optimized to increase the coverage of ultrasonic signals. The function of calculating location coordinates is embedded in a listener. The location-update rate and location accuracy are also improved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.1C
• /
• pp.130-137
• /
• 2010

An uplink indoor positioning system is proposed in the present work, where the acoustic signals are solely used for positioning. The underlying acoustic signals include whistle, finger snap, and hands-clapping. In the proposed method, positioning is achieved by finding the time-difference-of-arrivals using several self-generating sounds. To evaluate the feasibility of the signals and their positioning accuracies, the database of 100 persons about self-generating acoustic signals is built up. The results show that the hands-clapping sound is the most suitable for acoustic-based indoor positioning.

• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.307-308
• /
• 2021

2020년 7월 정부는 포스트 코로나 시대를 선언하며, 한국판 뉴딜 정책을 발표하였다. 한국판 뉴딜은 디지털인프라 구축, 비대면 산업육성, SOC 디지털화를 기본방향으로 내세웠으며 빅데이터, 인공지능(AI), 사물인터넷(IoT) 등 4차산업 핵심기술의 육성방안을 제시하였다. 최근 인천공항은 한국판 뉴딜 정부정책에 부응하기 위해 인천공항 K-뉴딜 프로젝트를 추진 중이며, 세부 전략과제로 자산관리의 디지털전환을 위한 IoT기반 스마트 자산관리시스템을 구축 중이다. IoT기반 스마트자산관리시스템은 인천공항에 위치한 실내외 이동형 자산에 대해 끊김없는 위치정보를 제공하는 시스템으로 기존 시스템(RFID) 대비 약 4억 원의 인적, 물적 자원을 절감하는 효과를 나타낼 것으로 예상된다. 본 논문에서는 IoT기반 스마트 자산관리시스템의 핵심기술인 실내외 연속측위 스마트 트래커와 네트워크의 구성, 저전력 위치정보 제공방법을 제시한다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.123-124
• /
• 2023

Despite the acuuracy, stability, and economic feasibility of geomagnetic field-based indoor positioning, its applicability in construction sites needs to be thoroughly discussed due to the issue of distortion of geomagnetic fields around ferromagnetic objects such as rebars. In this study, the possibility of applying the geomagnetic field-based indoor positioning in construction sites was reviewed through the Student's t-test after measuring the changes in geomagnetic field values depending on the presence or absence of rebars. The statistical analysis revealed that there is a high probability (over 80%) of significant changes in geomagnetic field values when measuring points are located within 60cm from the rebars. On the other hand, the probability of minimal changes in geomagnetic field values is over 90% when measuring points are located more than 60cm from the rebars. This suggests the application of geomagnetic-based indoor positioning in construction sites would be possible if the issue of distortion in geomagnetic field values near rebars within 60cm is resolved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.1
• /
• pp.124-131
• /
• 2015

In this paper, we proposed indoor positioning system using RSS(Received Signal Strength) positioning method and TSS(Transmission Signal Strength). The main point in the paper is to improve reliability of accuracy positioning with the area recognition algorithm and probabilistic algorithm, which can be effectively used indoor. In the test in 1-dimensional or 2-dimensional spaces, also we checked effective positioning system considered environment of propagation that is changed by reflection, refraction and multipath in according to space form. It is necessary to find place where urgent situation happen and quickly to respond the situation for patients or the weak. Therefore, we expect the positioning system proposed can apply to the field of traffic IT.