http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
UWB 시스템에서의 Channel Impulse Response 기반 First Path Estimation 기법
최세환(Sehwan Choi),임채훈(Chaehun Im),이충용(Chungyong Lee) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.11
FPE(First Path Estimation) performance could depend on pulse shaping difference in the UWB system. We observed FPE error by pulse shape and find out optimal pulse shape in high dynamic range performance receiver. While there is no mandatory specification regarding pulse shape in standard. Thereby we investigated in case of receiving an unknown pulse shape and have proposed a technique to improve FPE error.
무선 주파수 신호와 단말 내장 센서를 이용한 심층 신경망 기반 융합 측위 기법
이현욱(Hyunwook Lee),임채훈(Chaehun Im),장수환(Suhwan Jang),이충용(Chungyong Lee) 대한전자공학회 2021 대한전자공학회 학술대회 Vol.2021 No.6
We propose an enhanced pedestrian localization based on a deep neural network. The input of DNN comprises estimated positioning parameters from built in sensors of mobile devices and radio frequency signal, such as step information, heading, and distances between device and access points (APs). By adopting DNN, the limitations of existing probability-based method, computation complexity and noise variance knowledge requirement, can be releaved. Moreover, simulation results show that the proposed localization method is more precise than the comparative method.
실내 측위 정확도 향상을 위한 딥러닝 기반의 출발 각도 추정 기법
이성호(Seongho Lee),정성훈(Sunghoon Jung),임채훈(Chaehun Im),이충용(Chungyong Lee) 대한전자공학회 2019 대한전자공학회 학술대회 Vol.2019 No.11
As services using the Internet of Things (IoT) are diversified, it is very important to estimate the location of the device. Though network based localization using radio frequency (RF) signals is widely used in indoor environments. The proposed method utilizes neural network to improve the error of the existing localization method in indoor environment. Experimental results show that the proposed method outperforms the beamforming method and performs well in NLOS environments.