Browsing by Author "Liao, I-No"

Now showing 1 - 2 of 2

A Millimeter-Wave In-Phase Gate-Boosting Rectifier
(2014-11-01)
Wang, Yu-Jiu
;
Liao, I-No
;
Tsai, Chao-Han
;
Pakasiri, Chatrpol
;
電子工程學系及電子研究所
This paper introduces a new class of RF-to-dc rectifiers called the in-phase gate-boosting rectifier (IGR). An IGR utilizes an in-phase passive voltage multiplier (IPVM) to boost in-phase swing from the driving swing. This design simultaneously reduces the effective threshold voltage, forward resistance, and the reverse leakage current of the rectifying transistor. As a consequence, the sensitivity and the efficiency of a high-frequency rectifier can be improved. Furthermore, a C-G-loaded IPVM presents low input conductance and is shunted with the drains/sources of the rectifying transistors. This makes the realization of the input matching network between the IGR core and the antenna easier, and achieves a higher voltage swing at the input terminals of the IGR core. The criteria, properties, and relating proofs of the IPVM are also discussed. A differential seven-stage millimeter-wave IGR is implemented in a 65-nm RF CMOS process. In this design, an interleaving internal threshold cancellation bias scheme is also introduced to further suppress the power consumption due to biasing circuitry without increasing the layout area. The implemented integrated circuit achieves a state-of-the-art -7-dBm sensitivity with 20% peak efficiency at 53 GHz and a bandwidth of 10 GHz from 46 to 56 GHz.
TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications
(2019-01-01)
Huang, Yu-Chuan
;
Liao, I-No
;
Chen, Ching-Hsuan
;
Ik, Ts I-Ui
;
Peng, Wen-Chih
Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. It is still challenging to recognize and position a high-speed and tiny ball accurately from an ordinary video. In this paper, we develop a deep learning network, called TrackNet, to track the tennis ball from broadcast videos in which the ball images are small, blurry, and sometimes with afterimage tracks or even invisible. The proposed heatmap-based deep learning network is trained to not only recognize the ball image from a single frame but also learn flying patterns from consecutive frames. The network is evaluated on the video of the men's singles final at the 2017 Summer Universiade, which is available on YouTube. The precision, recall, and F1-measure reach 99:7%, 97:3%, and 98:5%, respectively. To prevent overfitting, 9 additional videos are partially labeled together with a subset from the previous dataset to implement 10-fold cross-validation, and the precision, recall, and F1-measure are 95:3%, 75:7%, and 84:3%, respectively.