Ehsan Yavari
Ehsan Yavari has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Ashikur Rahman
Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI, USA
2 shared publications - Isar Mostafanezhad
Nalu Scientific, LLC,Honolulu,HI,USA,96822
2 shared publications - Olga Boric-Lubecke
University of Hawaii at Manoa
2 shared publications - Takuya Sakamoto
Department of Electrical, Electronic, and Digital Science and Engineering, Graduate School of Engineering, Kyoto University, Kyoto, Japan
2 shared publications - Victor M. Lubecke
Department of Electrical and Computer Engineering, University of Hawaii at Mnoa, Honolulu, HI, USA
2 shared publications - Xiaomeng Gao
Electrical Engineering Department, University of Hawaii at Manoa, Honolulu, HI, USA
2 shared publications
Latest Publications
- 31 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Measurements on All-In-One Digitizer System-an-chip (AODS): a High Dynamic Range Front-End Digitizer for Particle Physics Experiments
Readout front-end electronics for modern particle physics experiments must be compact, low power, provide high timing resolution, have high dynamic range, and require minimal cabling infrastructure. The solution is to integrate full waveform sampling, analog buffering, feature extraction and digital signal processing into a single All-In-One Digitizer System-on-chip (AODS). Due to its low size, weight, and power (SWaP), AODS can be used as a building block for large readout systems that require high channel density, remote sensor positions, and large instantaneous power fluctuations. The fabricated prototype AODS has 1 effective channel, can operate between 1 to 2 GSa/s, with an analog buffer of up to 16µs, and uses multiple cascaded gain stages to realize at least 80 dB of dynamic range.
- 31 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Measurements on All-In-One Digitizer System-an-chip (AODS): a High Dynamic Range Front-End Digitizer for Particle Physics Experiments
Readout front-end electronics for modern particle physics experiments must be compact, low power, provide high timing resolution, have high dynamic range, and require minimal cabling infrastructure. The solution is to integrate full waveform sampling, analog buffering, feature extraction and digital signal processing into a single All-In-One Digitizer System-on-chip (AODS). Due to its low size, weight, and power (SWaP), AODS can be used as a building block for large readout systems that require high channel density, remote sensor positions, and large instantaneous power fluctuations. The fabricated prototype AODS has 1 effective channel, can operate between 1 to 2 GSa/s, with an analog buffer of up to 16µs, and uses multiple cascaded gain stages to realize at least 80 dB of dynamic range.
- Open Access
- 21 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 2  (3) , 1-4
Hand Gesture Recognition Using a Radar Echo I–Q Plot and a Convolutional Neural Network
We propose a hand gesture recognition technique using a convolutional neural network applied to radar echo inphase/quadrature (I/Q) plot trajectories. The proposed technique is demonstrated to accurately recognize six types of hand gestures for ten participants. The system consists of a low-cost 2.4-GHz continuous-wave monostatic radar with a single antenna. The radar echo trajectories are converted to low-resolution images and are used for the training and evaluation of the proposed technique. Results indicate that the proposed technique can recognize hand gestures with average accuracy exceeding 90%.
- 21 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 2  (3) , 1-4
Open AccessHand Gesture Recognition Using a Radar Echo I–Q Plot and a Convolutional Neural Network
We propose a hand gesture recognition technique using a convolutional neural network applied to radar echo inphase/quadrature (I/Q) plot trajectories. The proposed technique is demonstrated to accurately recognize six types of hand gestures for ten participants. The system consists of a low-cost 2.4-GHz continuous-wave monostatic radar with a single antenna. The radar echo trajectories are converted to low-resolution images and are used for the training and evaluation of the proposed technique. Results indicate that the proposed technique can recognize hand gestures with average accuracy exceeding 90%.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 393-395
Radar-based hand gesture recognition using I-Q echo plot and convolutional neural network
The present paper proposes a technique for the automatic recognition of hand gestures using a 2.4-GHz continuous radar and a convolutional neural network. The proposed technique applies the neural network to the time-domain I-Q plot of radar echoes. The accurate recognition capability of the technique was established with a set of radar data for three types of hand gesture performed by a participant. The radar echo trajectories were converted to low-resolution images to achieve fast signal processing, and the neural network was trained using the images. Another set of I-Q plot images were used for the evaluation of the recognition accuracy. The results indicate that the proposed technique is able to recognize hand gestures with accuracy exceeding 90%.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 393-395
Radar-based hand gesture recognition using I-Q echo plot and convolutional neural network
The present paper proposes a technique for the automatic recognition of hand gestures using a 2.4-GHz continuous radar and a convolutional neural network. The proposed technique applies the neural network to the time-domain I-Q plot of radar echoes. The accurate recognition capability of the technique was established with a set of radar data for three types of hand gesture performed by a participant. The radar echo trajectories were converted to low-resolution images to achieve fast signal processing, and the neural network was trained using the images. Another set of I-Q plot images were used for the evaluation of the recognition accuracy. The results indicate that the proposed technique is able to recognize hand gestures with accuracy exceeding 90%.
- 1 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 0149645X,p. 1-4
A low cost simple RF front end using time-domain multiplexing for direction of arrival estimation of physiological signals
Doppler radar has been used for vital signs monitoring. Multiple subject monitoring and direction of arrival estimation is possible by using multiple antennas and receivers. The homodyne receiver requires a quadrature demodulator for each antenna. The complexity of the system and the number of baseband channels will increase with the number of antennas. In this paper we propose time-domain multiplexing of the RF outputs of a four element antenna array and down-conversion using a single IQ demodulator. We de-multiplex the outputs in baseband and estimate the DOA for mechanical targets and a human subject breathing in front of the radar.
- 1 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 0149645X,p. 1-4
A low cost simple RF front end using time-domain multiplexing for direction of arrival estimation of physiological signals
Doppler radar has been used for vital signs monitoring. Multiple subject monitoring and direction of arrival estimation is possible by using multiple antennas and receivers. The homodyne receiver requires a quadrature demodulator for each antenna. The complexity of the system and the number of baseband channels will increase with the number of antennas. In this paper we propose time-domain multiplexing of the RF outputs of a four element antenna array and down-conversion using a single IQ demodulator. We de-multiplex the outputs in baseband and estimate the DOA for mechanical targets and a human subject breathing in front of the radar.