Performance Enhancement of Emergency Rescue System using Surface Correlation Technology

Shin, Beomju,Lee, Jung Ho,Shin, Donghyun,Yu, Changsu,Kyung, Hankyeol,Lee, Taikjin 항법시스템학회 2020 Journal of Positioning, Navigation, and Timing Vol.9 No.3

In emergency rescue situations, the localization accuracy of the rescue requestor is a very important factor in determining the success or failure of the rescue. Indoors where Global Navigation Satellite System (GNSS) is not operated, there is no choice but to use Wi-Fi or LTE signals. However, the performance of the current emergency rescue system utilizing those RF signals is exceedingly low. In this study, the effectiveness of the surface correlation technology using the accumulated signal pattern of RF signals was verified in relation to the emergency localization technology. To validate the proposed system, we configured and tested an emergency rescue scenario in multi-floors building. When the emergency rescue was requested, it was confirmed that the initial localization error was large owing to the short length of the accumulated signal pattern. However, the localization error decreased over time, which eventually led to the accurate location information being delivered to the rescuer.

Motion Recognition-Based 3D Pedestrian Navigation System Using Smartphone

Shin, Beomju,Kim, Chulki,Kim, Jaehun,Lee, Seok,Kee, Changdon,Kim, Hyoung Seok,Lee, Taikjin IEEE 2016 IEEE SENSORS JOURNAL Vol.16 No.18

<P>A motion recognition-based 3D pedestrian navigation system that employs a smartphone is presented. In existing inertial measurement unit ( IMU)-based pedestrian dead-reckoning ( PDR) systems, sensor axes are fixed regardless of user motion, because the IMU is mounted on the shoes or helmet. On the other hand, the sensor axes of a smartphone are changed according to the walking motion of the user, because the smartphone is usually carried by hand or kept in the pocket. Therefore, the conventional PDR method cannot apply to the smartphone-based PDR system. To overcome this limitation, the walking status is detected using a motion recognition algorithm with sensor measurements from the smartphone. Then, different PDR algorithms are applied according to the recognized pattern of the pedestrian motion. The height information of the pedestrian is also estimated using the on-board barometric pressure sensor of the smartphone. The 3D position, which consists of the 2D position calculated by the PDR and the height information, is provided to the pedestrian. The proposed system has several advantages in terms of cost and accessibility. It requires no additional peripheral devices except for the smartphone, because smartphones are equipped with all the necessary sensors, such as an accelerometer, magnetometer, gyroscope, and barometric pressure sensor. This paper implements the proposed system as an android-based application. The experimental results demonstrate the performance of the proposed system and reveal a high positioning accuracy.</P>

Indoor 3D Pedestrian Tracking Algorithm Based on PDR using Smarthphone

Beomju Shin,Jung Ho Lee,Hyunho Lee,Eungyeong Kim,Jeahun Kim,Seok Lee,Young-su Cho,Sangjoon Park,Taikjin Lee 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10

In this paper, we develop the indoor navigation system based on PDR (Pedestrian Dead Reckoning) using various sensors in smartphone. Usually PDR is consisted of step detection, step length estimation and heading estimation. The issue of PDR is step length estimation and to enhance the accuracy of step length, we apply the walking status recognition algorithm using ANN (Artificial Neuron Network). The features used in ANN are extracted through sensor signals of accelerometer and gyroscope. After recognizing the walking status, it is applied to estimate the step length. And when the status is recognized as stop, even if sensor signal is generated by redundant motion or movement of pedestrian, the moved distance is not calculated additionally and distance error is not increased. We use the barometric pressure sensor to extend the positioning area to whole building. To verify the proposed indoor navigation system, we implemented the application for android and conducted the experiment. Through the results, we demonstrated the accuracy of our system.

A Study on Altitude Estimation using Smartphone Pressure Sensor for Emergency Positioning

Shin, Donghyun,Lee, Jung Ho,Shin, Beomju,Yu, Changsu,Kyung, Hankyeol,Choi, Dongwook,Kim, Yeji,Lee, Taikjin 항법시스템학회 2020 Journal of Positioning, Navigation, and Timing Vol.9 No.3

This paper introduces a study to estimate the user altitude in need of rescue in an emergency. The altitude is estimated by using the barometric pressure sensor embedded in the smartphone. Compared to GPS, which is degraded in urban or indoor environments, it has the advantage of not having spatial restrictions. With the endless development of smartphone hardware, it is possible to estimate the absolute altitude using the measured value if only the bias of the embedded barometric pressure sensor is applied. The altitude information of the person in need of rescue in an emergency is a great help in reducing rescue time. Since time is tight, we propose online calibration that provides the barometric pressure sensor bias used for altitude estimation through database. Furthermore, experiments were conducted to understand the characteristics of the barometric pressure sensor, which is greatly affected by wind. At the end, the altitude estimation performance was confirmed through an actual field tests in various floors in the building.

WiFi와 PDR을 결합한 스마트폰 기반 실내항법기술

신범주(Beomju Shin),이정호(Jung Ho Lee),김현덕(Hyun Duk Kim),유보선(Boseon Yu),이택진(Taikjin Lee) 한국통신학회 2016 한국통신학회 학술대회논문집 Vol.2016 No.1

Smartphone based Indoor Localization Technology using 1D CNN -BLSTM

Changsoo Yu,Beomju Shin,Chung G. Kang,Jung Ho Lee,Hankyeol Kyung,Taehun Kim,Taikjin Lee 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

The study of indoor localization technology using smart phone has been continuously studied. Fingerprinting is a representative indoor positioning technology. This technology estimates the location by comparing Radio Signal Strength (RSS) information received in one-shot at a specific location with the previously constructed Radio Map. Since the RSS received in one-shot is used, the ability to discriminate signals according to space is low. To solve this problem, the use of RSS spatial patterns based on Pedestrian Dead Reckoning (PDR) improves signal discrimination according to space and increases accuracy. However, since PDR is used, there is a problem that it is difficult to use a spatial pattern if PDR distortion occurs due to a heading drift error and a change motion. We propose an indoor positioning technology using 1D Convolutional Neural Network (CNN) and Bi-directional Long Short Term Memory (BLSTM). We estimated the position by learning the 1D RSS pattern. In order to generate a large amount of data, we used the pre-built Radio Map. We use a model that combines 1D CNN and BLSTM. 1D CNN is used to extract RSS patterns, and BLSTM is used to learn the relationship of sequential data in both directions. Through this, it is possible to estimate the position using only the RSS. To verify the proposed technology, we compared it with the previous technology. As a result, the previous technology showed 2.19m error and the proposed technology showed 4.663m error. However, the calculation speed is 30 times faster than the proposed technology. It was confirmed that indoor positioning technology using deep learning technology can provide position information with only 1D RSS pattern.

Real-time and Precise Indoor Localization System in Multi-Floor Buildings for Pedestrian using Cloud Platform

Taehun Kim,Beomju Shin,Chung G. Kang,Jung Ho Lee,Changsoo Yu,Hankyeol Kyung,Donghyun Shin,Taikjin Lee 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

Pedestrians use their smartphones to determine their location. Accordingly, there is a growing demand for seamless localization that can estimate the location regardless of indoor and outdoor space. However, the Global Navigation Satellite System used for outdoor location estimation has poor reception in the indoor environment, making it difficult to use in indoor space. Therefore, we propose the indoor localization technology based on Surface Correlation (SC). This indoor localization technology can estimate the location of pedestrians on only one floor. In this study, floor detection was performed using only RF signal without using other sensors such as barometric pressure sensor in the multi-floor building. The most important thing in floor detection is the reliability of the current floor and floor change detection. We can estimate the coarse floor using the unique ID of the RF source installed on each floor. Then, the virtual trajectory is generated using only RF signal, and the degree of similarity with the floor is determined by identifying the fine floor of the coarse floor estimated by applying the existing SC-based localization. Once the fine floor of pedestrians is identified, the final absolute location of pedestrians in the multi-floor building can be estimated by calculating the indoor location of the estimated floor using conventional SC-based localization. To verify the performance of the proposed algorithm in real-time, the algorithm was implemented in Google Cloud Platform. Pedestrians can check the indoor location results through real-time connection with the smartphone. In the actual multi-floor building, the similarity between the floor estimated by the proposed algorithm and the floor estimated using the barometric pressure sensor is about 95.0%. And the RMSE of the indoor localization results of the proposed system is about 3.662m.

Real Time Adaptive Step Length Estimation for Smartphone User

Jung Ho Lee,Beomju Shin,Chulki Kim,Jaehun Kim,Seok Lee,Taikjin Lee 제어로봇시스템학회 2013 제어로봇시스템학회 국제학술대회 논문집 Vol.2013 No.10

An indoor positioning with a high accuracy is still a challenging research area. The error of pedestrian dead reckoning (PDR) is usually caused from both heading and step length error. In this paper, we focus on the reducing of step length estimation. We apply a linear combination consisted of 4 parameters obtained from an acceleration, an angular velocity, and a pedestrian average step length. For an in-flight calibration of step length estimation, we utilize map information and calculate constants for linear combination. We conduct a field test and its result suggests that the proposed algorithm is more accurate than the fixed step length method.

Surface Correlation 기법을 활용한 가스 플랜트 내 작업자 정밀 위치 인식 시스템

이정호(Jung Ho Lee),신범주(Beomju Shin),이서호(Seo Ho Lee),이택진(Taikjin Lee) 한국가스학회 2018 한국가스학회 학술대회논문집 Vol.2018 No.5

MLC 플래시 메모리에서의 셀간 간섭 제거 알고리즘

전명운(Myeongwoon Jeon),김경철(Kyungchl Kim),신범주(Beomju Shin),이정우(Jungwoo Lee) 大韓電子工學會 2010 電子工學會論文誌-SD (Semiconductor and devices) Vol.47 No.12

NAND Multi-level cell Flash memory는 한 셀에 여러 bit의 정보를 저장하는 방법으로, 용량 집적도를 더욱 높일수 있는 기술로 각광 받고 있다. 하지만 한 셀당 레벨 수를 올릴 경우, 셀간 간섭 등 여러 물리적 이유들로 인해 오류가 발생하며, 이주된 오류 방향은 unidirectional 함이 알려져 있다. 기존에는 오류 정정 부호(ECC)등을 이용하여 이를 해결하려 했지만, 우리는 셀간 간섭으로 인한 오류에 포커스를 맞추어, 이 영향을 예측하고 줄여서 오류를 보정하는 새로운 알고리즘들을 제안한다. 이 알고리즘은 기존 오류정정부호 기법들과 별도의 단계로 동시에 적용할 수 있기에 에러 정정능력 향상에 효과적이다. 제안된 알고리즘들을 시뮬레이션을 통하여 성능을 비교하고 효율적인 알고리즘이 무엇인지 알아본다. NAND multilevel cell (MLC) flash memory is widely issued because it can increase the capability of storage by storing two or more bits to a single cell. However if a number of levels in a cell increases, some physical features like cell to cell interference result cell voltage shift and it is known that a VT shift is unidirectional. To reduce errors by the effects, we can consider error correcting codes(ECC) or signal processing methods. We focus signal processing methods for the cell to cell interference voltage shift effects and propose the algorithms which reduce the effects of the voltage shift by estimating it and making level read voltages be adaptive. These new algorithms can be applied with ECC at the same time, therefore these algorithms are efficient for MLC error correcting ability. We show the bit error rate simulation results of the algorithms and compare the performance of the algorithms.