An official website of the United States government
In this paper, we propose a novel, generalizable, and scalable idea that eliminates the need for collecting Radio Frequency (RF) measurements, when training RF sensing systems for human-motion-related activities. Existing learning-based RF sensing systems require collecting massive RF training data, which depends heavily on the particular sensing setup/involved activities. Thus, new data needs to be collected when the setup/activities change, significantly limiting the practical deployment of RF sensing systems. On the other hand, recent years have seen a growing, massive number of online videos involving various human activities/motions. In this paper, we propose to translate such already-available online videos to instant simulated RF data for training any human-motion-based RF sensing system, in any given setup. To validate our proposed framework, we conduct a case study of gym activity classification, where CSI magnitude measurements of three WiFi links are used to classify a person's activity from 10 different physical exercises. We utilize YouTube gym activity videos and translate them to RF by simulating the WiFi signals that would have been measured if the person in the video was performing the activity near the transceivers. We then train a classifier on the simulated data, and extensively test it with real WiFi data of 10 subjects performing the activities in 3 areas. Our system achieves a classification accuracy of 86% on activity periods, each containing an average of 5.1 exercise repetitions, and 81% on individual repetitions of the exercises. This demonstrates that our approach can generate reliable RF training data from already-available videos, and can successfully train an RF sensing system without any real RF measurements. The proposed pipeline can also be used beyond training and for analysis and design of RF sensing systems, without the need for massive RF data collection.
more »
« less
RF-optical signal conversion via Dual Active-Cavity modulator in a Monolithic Electronic-Photonic SOI Platform
We demonstrate a Dual Active-Cavity RF modulator combining T-shaped spoked junction with a novel “half-rib” waveguide in a monolithic electronic-photonic platform. We measure a sideband efficiency of -52 dB at 66 GHz RF carrier frequency.
more »
« less
- Award ID(s):
- 2328946
- PAR ID:
- 10542003
- Publisher / Repository:
- Optica Publishing Group
- Date Published:
- Format(s):
- Medium: X
- Location:
- Denver, CO
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
With the increase in GPU register file (RF) size, its power consumption has also increased. Since RF exists at the highest level in cache hierarchy, designing it with memories with high write latency/energy (e.g., spin transfer torque RAM) can lead to large energy loss. In this paper, we present an spin orbit torque RAM (SOT-RAM) based RF design which provides higher energy efficiency than SRAM and STT-RAM RFs while maintaining performance same as that of SRAM RF. To further improve energy efficiency of SOT-RAM based RF, we propose avoiding redundant bit-writes to RF. Compared to SRAM RF, SOT-RAM RF saves 18.6% energy and by using our technique for avoiding redundant writes, the energy saving can be increased to 44.3%, without harming performance.more » « less
-
Radio frequency (RF) signals are frequently used in emerging quantum applications due to their spin state manipulation capability. Efficient coupling of RF signals into a particular quantum system requires the utilization of carefully designed and fabricated antennas. Nitrogen vacancy (NV) defects in diamond are commonly utilized platforms in quantum sensing experiments with the optically detected magnetic resonance (ODMR) method, where an RF antenna is an essential element. We report on the design and fabrication of high efficiency coplanar RF antennas for quantum sensing applications. Single and double ring coplanar RF antennas were designed with −37 dB experimental return loss at 2.87 GHz, the zero-field splitting frequency of the negatively charged NV defect in diamond. The efficiency of both antennas was demonstrated in magnetic field sensing experiments with NV color centers in diamond. An RF amplifier was not needed, and the 0 dB output of a standard RF signal generator was adequate to run the ODMR experiments due to the high efficiency of the RF antennas.more » « less
-
null (Ed.)The widespread availability of low-cost RF sensors has made it easier to construct RF sensor networks for motion recognition, as well as increased the availability of RF data across a variety of frequencies, waveforms, and transmit parameters. However, it is not effective to directly use disparate RF sensor data for the training of deep neural networks, as the phenomenological differences in the data result in significant performance degradation. In this paper, we consider two approaches for the exploitation of multi-frequency RF data: 1) a single sensor case, where adversarial domain adaptation is used to transform the data from one RF sensor to resemble that of another, and 2) a multi-sensor case, where a multi-modal neural network is designed for joint target recognition using measurements from all sensors. Our results show that the developed approaches offer effective techniques for leveraging multi-frequency RF sensor data for target recognition.more » « less
-
We propose an on-chip triply resonant electro-optic modulator architecture for RF-to-optical signal conversion and provide a detailed theoretical analysis of the optimal “circuit-level” device geometries and their performance limits. The designs maximize the RF-optical conversion efficiency through simultaneous resonant enhancement of the RF drive signal, a continuous-wave (CW) optical pump, and the generated optical sideband. The optical pump and sideband are resonantly enhanced in respective supermodes of a two-coupled-cavity optical resonator system, while the RF signal can be enhanced in addition by an LC circuit formed by capacitances of the optical resonator active regions and (integrated) matching inductors. We show that such designs can offer 15-50 dB improvement in conversion efficiency over conventional microring modulators. In the proposed configurations, the photon lifetime (resonance linewidth) limits the instantaneous RF bandwidth of the electro-optic response but does not limit its central RF frequency. The latter is set by the coupling strength between the two coupled cavities and is not subject to the photon lifetime constraint inherent to conventional singly resonant microring modulators. This feature enables efficient operation at high RF carrier frequencies without a reduction in efficiency commonly associated with the photon lifetime limit and accounts for 10-30 dB of the total improvement. Two optical configurations of the modulator are proposed: a “basic” configuration with equal Q-factors in both supermodes, most suitable for narrowband RF signals, and a “generalized” configuration with independently tailored supermode Q-factors that supports a wider instantaneous bandwidth. A second significant 5-20 dB gain in modulation efficiency is expected from RF drive signal enhancement by integrated LC resonant matching, leading to the total expected improvement of 15-50 dB. Previously studied triply-resonant modulators, with coupled longitudinal (across the free spectral range (FSR)) modes, have large resonant mode volume for typical RF frequencies, which limits the interaction between the optical and RF fields. In contrast, the proposed modulators support maximally tightly confined resonant modes, with strong coupling between the mode fields, which increases and maintains high device efficiency across a range of RF frequencies. The proposed modulator architecture is compact, efficient, capable of modulation at high RF carrier frequencies and can be applied to any cavity design or modulation mechanism. It is also well suited to moderate Q, including silicon, implementations, and may be enabling for future CMOS RF-electronic-photonic systems on chip.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
