Wenyan Qian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Wenyan Qian has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
D. Taylor
1 shared publication- Hongchang Xue
School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing 210023, China
1 shared publication - John C. H. Spence
Department of Physics, Arizona State University, Tempe, Arizona, 85287-1504 USA; Department of Applied Mathematics, Lawrence Berkeley Laboratory, Berkeley, CA 94720 USA; Center for Advanced Mathematics for Energy Research Applications, Lawrence Berkeley National Laboratory, Berkeley, CA 94720 USA
1 shared publication K. Taylor
1 shared publicationLi Xing
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 20444, China
1 shared publication- Shuqin Yang
School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing 210023, China
1 shared publication
Latest Publications
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 20 (24) , 14950-14957
Robust Navigation Method for Wearable Human–Machine Interaction System Based on Deep Learning
When the wearer of Wearable Human-Machine Interaction System (WHMIS) is talking a strenuous walk, the Inertial Measurement Units (IMUs) installed on the extremities are likely to be beyond the range of design specification of the IMU sensors. This overrange leads to poor navigation performances of the system. To overcome the problem, this paper proposes a deep learning-based method to realize robust autonomous navigation. Specifically, the Faster Region-Convolutional Neural Network (R-CNN) is built to recognize the gait types of the wearer. For each gait type, the inertial data of the wearer's thigh and the foot are collected at the same frequency as the training samples, and then used to construct a correspondent Gated Recurrent Unit-Support Vector Regression (GRU-SVR) deep hybrid neural network model for virtual IMU simulation. Then, the virtual foot-mounted IMU will be constructed in real-time by the physical thigh-mounted IMU based on the neural network models mentioned above. Once the over-range of the physical foot-mounted IMU is detected, the virtual foot inertial information will be used to reconstruct the WHMIS navigation system. Experimental results show that the proposed navigation method has the ability of fault tolerance in complex gaits, and the 3D positioning performance of the reconstructed navigation system is approximately equivalent to that of the fault-free WHMIS navigation system.
- 20 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 20 (24) , 14950-14957
Robust Navigation Method for Wearable Human–Machine Interaction System Based on Deep Learning
When the wearer of Wearable Human-Machine Interaction System (WHMIS) is talking a strenuous walk, the Inertial Measurement Units (IMUs) installed on the extremities are likely to be beyond the range of design specification of the IMU sensors. This overrange leads to poor navigation performances of the system. To overcome the problem, this paper proposes a deep learning-based method to realize robust autonomous navigation. Specifically, the Faster Region-Convolutional Neural Network (R-CNN) is built to recognize the gait types of the wearer. For each gait type, the inertial data of the wearer's thigh and the foot are collected at the same frequency as the training samples, and then used to construct a correspondent Gated Recurrent Unit-Support Vector Regression (GRU-SVR) deep hybrid neural network model for virtual IMU simulation. Then, the virtual foot-mounted IMU will be constructed in real-time by the physical thigh-mounted IMU based on the neural network models mentioned above. Once the over-range of the physical foot-mounted IMU is detected, the virtual foot inertial information will be used to reconstruct the WHMIS navigation system. Experimental results show that the proposed navigation method has the ability of fault tolerance in complex gaits, and the 3D positioning performance of the reconstructed navigation system is approximately equivalent to that of the fault-free WHMIS navigation system.
- 13 August 1995
- Published by Cambridge University Press (CUP) in Proceedings, annual meeting, Electron Microscopy Society of America
- Vol. 53, 846-847
Fresnel interference in point-projection imaging of purple membrane
Experimental point-projection shadow microscope (PPM) images of uncoated, unstained purple membrane (PM, bacteriorhodopsin, a membrane protein from Halobacterium holobium) were obtained recently using 100 volt electrons. The membrane thickness is about 5 nm and the hexagonal unit cell dimension 6 nm. The images show contrast around the edges of small holes, as shown in figure 1. The interior of the film is opaque. Since the inelastic mean free path for 100V electrons in carbon (about 6 Å) is much less than the sample thickness, the question arises that how much, if any, transmission of elastically scattered electrons occurs. A large inelastic contribution is also expected, attenuated by the reduced detection efficiency of the channel plate at low energies. Quantitative experiments using an energy-loss spectrometer are planned. Recently Shedd has shown that at about 100V contrast in PPM images of thin gold films can be explained as Fresnel interference effects between different pinholes in the film, separated by less than the coherence width.
- 13 August 1995
- Published by Cambridge University Press (CUP) in Proceedings, annual meeting, Electron Microscopy Society of America
- Vol. 53, 846-847
Fresnel interference in point-projection imaging of purple membrane
Experimental point-projection shadow microscope (PPM) images of uncoated, unstained purple membrane (PM, bacteriorhodopsin, a membrane protein from Halobacterium holobium) were obtained recently using 100 volt electrons. The membrane thickness is about 5 nm and the hexagonal unit cell dimension 6 nm. The images show contrast around the edges of small holes, as shown in figure 1. The interior of the film is opaque. Since the inelastic mean free path for 100V electrons in carbon (about 6 Å) is much less than the sample thickness, the question arises that how much, if any, transmission of elastically scattered electrons occurs. A large inelastic contribution is also expected, attenuated by the reduced detection efficiency of the channel plate at low energies. Quantitative experiments using an energy-loss spectrometer are planned. Recently Shedd has shown that at about 100V contrast in PPM images of thin gold films can be explained as Fresnel interference effects between different pinholes in the film, separated by less than the coherence width.