Zhihua Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhihua Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Binjie Zhu
Yiemed Company,Beijing,China
1 shared publication - Chun Zhang
Institute of Microelectronics, Tsinghua University, BeiJing, p. R. China
1 shared publication - Hanjun Jiang
Tsinghua University
1 shared publication - Jirong Ma
Institute of Microelectronics, Tsinghua University, BeiJing, p. R. China
1 shared publication - Kang Zhao
Huawei Technologies, Beijing, China
1 shared publication - Ping Chen
Department of Research and Development, YieMed Medical Technology Company Ltd., Beijing, China
1 shared publication
Latest Publications
- 24 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 14 (5) , 985-996
Long-Term Bowel Sound Monitoring and Segmentation by Wearable Devices and Convolutional Neural Networks
Bowel sounds (BSs), typically generated by the intestinal peristalses, are a significant physiological indicator of the digestive system's health condition. In this study, a wearable BS monitoring system is presented for long-term BS monitoring. The system features a wearable BS sensor that can record BSs for days long and transmit them wirelessly in real-time. With the system, a total of 20 subjects' BS data under the hospital environment were collected. Afterward, CNNs are introduced for BS segment recognition. Specifically, this study proposes a novel CNN design method that makes it possible to transfer the popular CNN modules in image recognition into the BS segmentation domain. Experimental results show that in holdout evaluation with corrected labels, the designed CNN model achieves a moderate accuracy of 91.8% and the highest sensitivity of 97.0% compared with the similar works. In cross validation with noisy labels, the designed CNN delivers the best generability.
- 24 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 14 (5) , 985-996
Long-Term Bowel Sound Monitoring and Segmentation by Wearable Devices and Convolutional Neural Networks
Bowel sounds (BSs), typically generated by the intestinal peristalses, are a significant physiological indicator of the digestive system's health condition. In this study, a wearable BS monitoring system is presented for long-term BS monitoring. The system features a wearable BS sensor that can record BSs for days long and transmit them wirelessly in real-time. With the system, a total of 20 subjects' BS data under the hospital environment were collected. Afterward, CNNs are introduced for BS segment recognition. Specifically, this study proposes a novel CNN design method that makes it possible to transfer the popular CNN modules in image recognition into the BS segmentation domain. Experimental results show that in holdout evaluation with corrected labels, the designed CNN model achieves a moderate accuracy of 91.8% and the highest sensitivity of 97.0% compared with the similar works. In cross validation with noisy labels, the designed CNN delivers the best generability.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 847-850
A 1V Ultra-Low Power High Precision CMOS Voltage Reference
A 1V ultra-low power high precision voltage reference is designed and implemented with UMC mixed-signal 0.18-mum CMOS technology. A novel low-voltage high-precision current mirror is introduced in the voltage reference in order to reduce temperature coefficient and line regulation. Post simulation results show that the reference voltage and total power dissipation are 406.5 mV and 0.83 muW, respectively. Temperature coefficient of the voltage reference is 18.5 ppm/degC when temperature ranges from -45degC to 90degC, while line regulation is 1%/V when the supply voltage ranges from 1 V to 2.4 V. The circuit layout occupies approximately 106 mum times 81 mum.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 847-850
A 1V Ultra-Low Power High Precision CMOS Voltage Reference
A 1V ultra-low power high precision voltage reference is designed and implemented with UMC mixed-signal 0.18-mum CMOS technology. A novel low-voltage high-precision current mirror is introduced in the voltage reference in order to reduce temperature coefficient and line regulation. Post simulation results show that the reference voltage and total power dissipation are 406.5 mV and 0.83 muW, respectively. Temperature coefficient of the voltage reference is 18.5 ppm/degC when temperature ranges from -45degC to 90degC, while line regulation is 1%/V when the supply voltage ranges from 1 V to 2.4 V. The circuit layout occupies approximately 106 mum times 81 mum.