| 2 | Dual ultra-wideband(UWB)radar-based sleep posture recognition system:Towards ubiquitous sleep monitoring显示文摘Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideband radar system.We collected radiofrequency data from two radars positioned over and at the side of the bed for 16 patients performing four sleep postures(supine,left and right lateral,and prone).We proposed and evaluated deep learning approaches that streamlined feature extraction and classification,and the traditional machine learning approaches that involved different combinations of feature extractors and classifiers.Our results showed that the dual radar system performed better than either single radar.Predetermined statistical features with random forest classifier yielded the best accuracy(0.887),which could be further improved via an ablation study(0.938).Deep learning approach using transformer yielded accuracy of 0.713. | Derek Ka-Hei Lai Li-Wen Zha Tommy Yau-Nam Leung Andy Yiu-Chau Tam Bryan Pak-Hei So Hyo-Jung Lim Daphne Sze Ki Cheung Duo Wai-Chi Wong James Chung-Wai Cheung | 2023 | Engineered Regeneration2023，4，1： | 0 |
| 3 | Wind regime features and their impacts on the middle reaches of the Yarlung Zangbo River on the Tibetan Plateau, China显示文摘The wide valley of the Yarlung Zangbo River is one of the most intense areas in terms of aeolian activity on the Tibetan Plateau,China.In the past,the evaluation of the intensity of aeolian activity in the Quxu–Sangri section of the Yarlung Zangbo River Valley was mainly based on data from the old meteorological stations,especially in non-sandy areas.In 2020,six new meteorological stations,which are closest to the new meteorological stations,were built in the wind erosion source regions(i.e.,sandy areas)in the Quxu–Sangri section.In this study,based on mathematical statistics and empirical orthogonal function(EOF)decomposition analysis,we compared the difference of the wind regime between new meteorological stations and old meteorological stations from December 2020 to November 2021,and discussed the reasons for the discrepancy.The results showed that sandy and non-sandy areas differed significantly regarding the mean velocity(8.3(±0.3)versus 7.7(±0.3)m/s,respectively),frequency(12.9%(±6.2%)versus 2.9%(±1.9%),respectively),and dominant direction(nearly east or west versus nearly north or south,respectively)of sand-driving winds,drift potential(168.1(±77.3)versus 24.0(±17.9)VU(where VU is the vector unit),respectively),resultant drift potential(92.3(±78.5)versus 8.7(±9.2)VU,respectively),and resultant drift direction(nearly westward or eastward versus nearly southward or northward,respectively).This indicated an obvious spatial variation in the wind regime between sandy and non-sandy areas and suggested that there exist problems when using wind velocity data from non-sandy areas to evaluate the wind regime in sandy areas.The wind regime between sandy and non-sandy areas differed due to the differences in topography,heat flows,and their coupling with underlying surface,thereby affecting the local atmospheric circulation.Affected by large-scale circulations(westerly jet and Indian monsoon systems),both sandy and non-sandy areas showed similar seasonal variations in their respective wind regime.These findings provide a credible reference for re-understanding the wind regime and scientific wind-sand control in the middle reaches of the Yarlung Zangbo River Valley. | ZHANG Yan ZHANG Zhengcai MA Pengfei PAN Kaijia ZHA Duo CHEN Dingmei SHEN Caisheng LIANG Aimin | 2023 | Journal of Arid Land2023，15，10： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员