Neural Network-Based Ranging with LTE Channel Impulse Response for Localization in Indoor Environments

Halim Lee,Ali A. Abdallah,Jongmin Park,Jiwon Seo,Zaher M. Kassas 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10

A neural network (NN)-based approach for indoor localization via cellular long-term evolution (LTE) signals is proposed. The approach estimates, from the channel impulse response (CIR), the range between an LTE eNodeB and a receiver. A software-defined radio (SDR) extracts the CIR, which is fed to a long short-term memory model (LSTM) recurrent neural network (RNN) to estimate the range. Experimental results are presented comparing the proposed approach against a baseline RNN without LSTM. The results show a receiver navigating for 100 m in an indoor environment, while receiving signals from one LTE eNodeB. The ranging root-mean squared error (RMSE) and ranging maximum error along the receiver’s trajectory were reduced from 13.11 m and 55.68 m, respectively, in the baseline RNN to 9.02 m and 27.40 m, respectively, with the proposed RNN-LSTM.

수중 자율이동체의 장시간 수중항법 성능 개선을 위한 표준 수력학 모델 기반 속도 추정필터 설계

이윤하(Yunha Lee),나원상(Won-Sang Ra),김광훈(Kwanghoon Kim),안명환(Myonghwan Ahn),이범직(Bum-Jik Lee) 대한전기학회 2016 전기학회논문지 Vol.65 No.11

This paper proposes a novel velocity estimator for long-term underwater navigation of autonomous underwater vehicles(AUVs). Provided that an external position fix is not given, a viable goal in designing a underwater navigation algorithm is to reduce the divergence rate of position error only using the sporadic velocity information obtained from Doppler velocity log(DVL). For such case, the performance of underwater navigation eventually depends on accuracy and reliability of external velocity information. This motivates us to devise a velocity estimator which can drastically enhance the navigation performance even when the DVL measurement is unavailable. Incorporating the Gertler-Hagen hydrodynamics model of an AUV with the measurement models of velocity and depth sensors, the velocity estimator design problem is resolved using the extended Kalman filter. Different from the existing methods in which an AUV simulator is regarded as a virtual sensor, our approach is less sensitive to the model uncertainty often encountered in practice. This is because our velocity filter estimates the simulator errors with sensor aids and furthermore compensates these errors based on the indirect feedforward manner. Through the simulations for typical AUV navigation scenarios, the effectiveness of the proposed scheme is demonstrated.

전자기장 네비게이션을 이용한 슬관절 전치환술의 8-10년 추시 결과

조재영(Jae Young Cho),정승현(Seung Hyeon Jeung),홍성민(Sung Min Hong),서정탁(Jeung Tak Suh),최윤영(Yoon Young Choi),이승준(Seung Joon Rhee) 대한정형외과학회 2018 대한정형외과학회지 Vol.53 No.3

목적: 전자기장 네비게이션 시스템을 이용한 슬관절 전치환술과 고식적 방식을 이용한 전치환술 후 8-10년간 추시 가능하였던 환자들에서 임상적 및 방사선적 결과를 비교 분석하고자 하였다. 대상 및 방법: 2004년 2월부터 2006년 12월까지 슬관절 전치환술을 시행 받은 후 8-10년 이상 추시가 가능하였던 환자 32명 40예 슬관절을 대상으로 각각 네비게이션군, 고식적 군으로 나누어 술 전 및 최종 추시 시의 관절 가동 각도, 슬관절 점수 및 기능 점수를 측정하였고 비교 대조하여 분석하였다. 또한 같은 시기의 대퇴골 치환물의 외반각(α), 굴곡각(γ) 및 경골 치환물의 내반각(β), 후방 경사각(δ)을 측정하여 삽입물의 정렬을 비교하였다. 결과: 네비게이션군에서 평균 운동 범위는 최종 추시 시 121.8°±16.3° (92°-140°)로 호전되었고, Western Ontario McMaster Universities osteoarthritis Index (WOMAC) score는 89.8±5.4점으로, Knee Society score (KSS)는 91.5±7.5점으로 각각 향상되었다. 고식적 군에서 평균 운동 범위는 최종 추시 시 112.6°±25.6° (60°-140°)로 측정되었다. WOMAC score는 84.2±10.6점, KSS는 81.1±14.3점으로 각각 향상되었다. 삽입물의 외반각(α), 내반각(β), 굴곡각(γ), 후방 경사각(δ)은 두 군 모두에서 수술 직후에 비하여 최종 추시 시까지 유의한 변화를 보이지 않았다. 두 군의 비교에 있어서는 평균 운동 범위(p=0.018)와 KSS (p=0.038)만이 네비게이션군에서 고식적 군에 비하여 통계적으로 유의하게 좋은 결과를 보였다. 결론: 네비게이션을 이용한 슬관절 전치환술을 시행한 군에서 8-10년 추시결과 관절 운동 범위와 KSS가 고식적 군에 비해 유의하게 높았다. 그러나 술 전 및 술 후 대비 최종 추시 시 지표들의 변화량은 KSS를 제외하고는 고식적 군과 유의 차한이를 보이지 않았다. Purpose: The purpose of this study was to compare the clinical and radiological results between patients who underwent total knee arthroplasty using the conventional method and the navigation-assisted method. Materials and Methods: A retrospective review of was performed on 32 patients (40 knees) who underwent total knee arthroplasty between February 2004 and December 2006 and were followed-up for 8 to 10 years. Mechanical axis deviation, range of motion, radiologic position of the implants, and subjective clinical scores were measured and compared between 20 navigation-assisted total knee arthroplasties and 20 conventional total knee arthoplasties. Change in the values (α, β, γ, and δ angles) from the immediate postoperative period to the last follow-up were also calculated and compared between the two groups. Results: The mean range of motion in the navigation group was improved to 121.8°±16.3° (92°–140°) at the last follow-up, and the Western Ontario McMaster Universities osteoarthritis Index (WOMAC) score was 89.8±5.4 and the Knee Society score (KSS) was 91.5±7.5. The mean range of motion in the conventional group was 112.6°±25.6° (60°–140°) at the last follow-up. The WOMAC score was 84.2±10.6, and the KSS was 81.1±14.3. The α, β, γ, and δ angles of the implants were not significantly changed until the last follow-up. In the comparison between the two groups, only the mean range of motion (p=0.018) and the KSS (p=0.038) showed statistically better results in the navigation group than the conventional group. Conclusion: Navigation-assisted total knee arthroplasty showed better KSS and range of motion compared with the conventional group in a cross-sectional study with 8 to 10 years of follow-up results. However, only the KSS showed a significant difference between the two groups by the amount of changes in the clinical and radiological results.

Novel Maritime Wireless Communication based on Mobile Technology for the Safety of Navigation: LTE-Maritime focusing on the Cell Planning and its Verification

Woo-Seong Shim,Bu-Young Kim,Chan-Yong Park,Byeong-Hyeok Lee 한국항해항만학회 2021 한국항해항만학회지 Vol.45 No.5

Enhancing the performance of maritime wireless communication has been highlighted by the issue of cell planning in the sea area because of lack of an appropriate Propagation Loss Model (PLM). To resolve the cell planning issue in vast sea areas, it was essential to develop the (PLM) matching the intended sea area. However, there were considerable gaps between the prediction of legacy PLMs and field measurement in propagation loss and there was a need to develop the adjusted PLM (A-PLM). Therefore, cell planning was performed on this adjusted model, including modification of the base station’s location, altitude, and antenna azimuth to meet the quality objectives. Furthermore, in order to verify the availability of the cell planning, Communication Service Quality Monitoring System (CS-QMS) was developed in the LTE-Maritime project to collect LTE signal quality information from the onboard equipment at regular intervals and to ensure that the service quality was high enough to satisfy the goals in each designated grid. As a result of verification, the success rate of RSRP was 95.7% for the intensive management zone (IMZ) and 96.4% for the interested zone (IZ), respectively.

LSTM을 이용한 항법시스템의 확장칼만필터 공분산 튜닝

양현정(Hyeon-Jung Yang),성상만(Sang Man Seong) 제어로봇시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.2

Noise covariances in the EKF (Extended Kalman Filter) act as tuning parameters due to modeling errors, such as the error generated in the process of linearizing the nonlinear system equation. Filter designers traditionally prefer the trial-and-error method. However, because the noise covariances require retuning in concert with changes in trajectories or changes in system equations, human tuning is very time consuming. Accordingly, this study proposes an automation method for real-time parameter tuning using an LSTM (Long Short-Term Memory) neural network. The proposed method consists of two stages: 1) generating residual and state error covariances from an EKF using fixed-noise covariances and 2) producing a state estimate from an EKF using tuned time-varying noise covariances obtained from an LSTM neural network. This scheme is applied to navigation systems to calculate accurate velocity, attitude, and IMU bias estimates under challenging maneuvering situations. Using simulation, we showed that the proposed method outperforms the conventional EKF of navigation systems in suppressing estimation error in different trajectory scenarios.

이내비게이션 서비스 시나리오 및 변조코딩방식(MCS)을 고려한 초고속해상무선통신망(LTE-Maritime)의 전송속도 성능 분석

김부영(Bu-Young Kim),심우성(Woo-Seong Shim) 한국항해항만학회 2021 한국항해항만학회지 Vol.45 No.6

한국형 이내비게이션 사업의 일환으로 구축된 초고속해상무선통신망(LTE-maritime)은 ‘21년 1월부터 해안으로 부터 최대 100㎞ 해역까지 품질목표를 만족하는 통신 서비스를 제공하고 있다. 실 사용자 관점에서 적절한 초고속해상무선통신망의 통신 서비스 제공을 위해서는 서비스 구현과 효율적 주파수 자원 활용을 고려한 추가적인 통신망 성능 분석이 필요하다. 본 논문은 해역별 어선의 입출항 및 조업 형태 등을 고려한 선박분포를 고려하여 이내비게이션 서비스 시나리오에 따른 요구 전송속도와 주파수 자원 할당에 따른 LTE 변조코딩방식(MCS) 기반 제공 가능한 통신 속도를 산출하고, 실해역 성능 품질 측정 결과와 교차 분석하였다. LTE-maritime, which was built as part of the Korean e-Navigation project, has been providing a service that meets the goal of establishing a network up to 100㎞ from the coast since January 31, 2021. To provide appropriate communication services for LTE-maritime from the perspective of real users, additional performance analysis of LTE-maritime is required considering service implementation, and efficient use of spectrum resources. This paper presents the requirement of transmission speed according to the e-Navigation service scenario, and available transmission speed based on LTE modulation coding scheme (MCS) according to sea-specific ship distribution scenario and frequency resource allocation, and is cross-analyzed with results of the sea test.

LSTM 기반 딥러닝을 활용한 강인 지형대조항법 설계

이정신(Jungshin Lee),오주현(Juhyun Oh),성창기(Chang-Ky Sung),한경준(Kyungjun Han),남성호(Seongho Nam),이상우(Sang-Woo Lee) 한국항공우주학회 2018 한국항공우주학회 학술발표회 논문집 Vol.2018 No.11

초고속해상무선통신망(LTE-M.) 실해역 통신환경 분석

김부영,심우성 해양환경안전학회 2020 해양환경안전학회 학술발표대회 논문집 Vol.2020 No.11

Wi-Fi RSSI Based Indoor Localization System Using Deep Learning LSTM Networks

Alwin Poulose,Dong Seog Han(한동석) 한국통신학회 2019 한국통신학회 학술대회논문집 Vol.2019 No.11