skip to main content

Explore Research Products in the NSF-PAR

Title: An Empirical Study of Deep Learning Models for LED Signal Demodulation in Optical Camera Communication
Optical camera communication is an emerging technology that enables communication using light beams, where information is modulated through optical transmissions from light-emitting diodes (LEDs). This work conducts empirical studies to identify the feasibility and effectiveness of using deep learning models to improve signal reception in camera communication. The key contributions of this work include the investigation of transfer learning and customization of existing models to demodulate the signals transmitted using a single LED by applying the classification models on the camera frames at the receiver. In addition to investigating deep learning methods for demodulating a single VLC transmission, this work evaluates two real-world use-cases for the integration of deep learning in visual multiple-input multiple-output (MIMO), where transmissions from a LED array are decoded on a camera receiver. This paper presents the empirical evaluation of state-of-the-art deep neural network (DNN) architectures that are traditionally used for computer vision applications for camera communication.  more » « less
Award ID(s):
2000475
NSF-PAR ID:
10317912
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Network
Volume:
1
Issue:
3
ISSN:
2673-8732
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , Electronics)
    null (Ed.)
    The directionality of optical signals provides an opportunity for efficient space reuse of optical links in visible light communication (VLC). Space reuse in VLC can enable multiple-access communication from multiple light emitting transmitters. Traditional VLC system design using photo-receptors requires at least one receiving photodetector element for each light emitter, thus constraining VLC to always require a light-emitter to light-receptor element pair. In this paper, we propose, design and evaluate a novel architecture for VLC that can enable multiple-access reception using a photoreceptor receiver that uses only a single photodiode. The novel design includes a liquid-crystal-display (LCD) based shutter system that can be automated to control and enable selective reception of light beams from multiple transmitters. We evaluate the feasibility of multiple access on a single photodiode from two light emitting diode (LED) transmitters and the performance of the communication link using bit-error-rate (BER) and packet-error-rate (PER) metrics. Our experiment and trace based evaluation through proof-of-concept implementation reveals the feasibility of multiple LED reception on a single photodiode. We further evaluate the system in controlled mobile settings to verify the adaptability of the receiver when the LED transmitter changes position. 
    more » « less
  2. ; ; ( , 2021 IEEE International Symposium on Circuits and Systems (ISCAS))
    null (Ed.)
    This paper presents a single-aperture, single-pixel reader for communication with Optical Frequency Identification (OFID) tags. OFID tags use solar cells to transmit and receive information wirelessly as well as to harvest radiant energy. Due to its single-aperture architecture, the reader's optical system provides a shared optical path for reception and transmission. Also, physical alignment between the reader and an OFID tag is visually guided using the reader's emitted light, securing a robust data link as long as the OFID tag is illuminated. In this paper, a description of the reader's optical and electronic sub-systems are presented. The transmitter and receiver circuits are described in detail. The transmitter, built with a linear LED driver, achieves a power efficiency of nearly 87%. The receiver, featuring a third-order bandpass filter, reduces both low-frequency and high-frequency ambient noise. A prototype of the reader was fabricated and housed in a custom 3D-printed enclosure. Test results show that the reader is able to receive modulated luminescent signals from an OFID tag at a distance of 1 m and at a data rate of 3 kbps. 
    more » « less
  3. ; ; ; ; ( , 19th Theory of Cryptography Conference (TCC))
    Nissim, K. ; Waters, B. (Ed.)
    Recent new constructions of rate-1 OT [Döttling, Garg, Ishai, Malavolta, Mour, and Ostrovsky, CRYPTO 2019] have brought this primitive under the spotlight and the techniques have led to new feasibility results for private-information retrieval, and homomorphic encryption for branching programs. The receiver communication of this construction consists of a quadratic (in the sender's input size) number of group elements for a single instance of rate-1 OT. Recently [Garg, Hajiabadi, Ostrovsky, TCC 2020] improved the receiver communication to a linear number of group elements for a single string-OT. However, most applications of rate-1 OT require executing it multiple times, resulting in large communication costs for the receiver. In this work, we introduce a new technique for amortizing the cost of multiple rate-1 OTs. Specifically, based on standard pairing assumptions, we obtain a two-message rate-1 OT protocol for which the amortized cost per string-OT is asymptotically reduced to only four group elements. Our results lead to significant communication improvements in PSI and PIR, special cases of SFE for branching programs. - PIR: We obtain a rate-1 PIR scheme with client communication cost of $O(\lambda\cdot\log N)$ group elements for security parameter $\lambda$ and database size $N$. Notably, after a one-time setup (or one PIR instance), any following PIR instance only requires communication cost $O(\log N)$ number of group elements. - PSI with unbalanced inputs: We apply our techniques to private set intersection with unbalanced set sizes (where the receiver has a smaller set) and achieve receiver communication of $O((m+\lambda) \log N)$ group elements where $m, N$ are the sizes of the receiver and sender sets, respectively. Similarly, after a one-time setup (or one PSI instance), any following PSI instance only requires communication cost $O(m \cdot \log N)$ number of group elements. All previous sublinear-communication non-FHE based PSI protocols for the above unbalanced setting were also based on rate-1 OT, but incurred at least $O(\lambda^2 m \log N)$ group elements. 
    more » « less
  4. ; ; ( , Bioengineering)
    Image reconstruction is the process of recovering an image from raw, under-sampled signal measurements, and is a critical step in diagnostic medical imaging, such as magnetic resonance imaging (MRI). Recently, data-driven methods have led to improved image quality in MRI reconstruction using a limited number of measurements, but these methods typically rely on the existence of a large, centralized database of fully sampled scans for training. In this work, we investigate federated learning for MRI reconstruction using end-to-end unrolled deep learning models as a means of training global models across multiple clients (data sites), while keeping individual scans local. We empirically identify a low-data regime across a large number of heterogeneous scans, where a small number of training samples per client are available and non-collaborative models lead to performance drops. In this regime, we investigate the performance of adaptive federated optimization algorithms as a function of client data distribution and communication budget. Experimental results show that adaptive optimization algorithms are well suited for the federated learning of unrolled models, even in a limited-data regime (50 slices per data site), and that client-sided personalization can improve reconstruction quality for clients that did not participate in training. 
    more » « less
  5. ; ; ; ; ; ; ( , Communications Medicine)
    Abstract Background Mortality research has identified biomarkers predictive of all-cause mortality risk. Most of these markers, such as body mass index, are predictive cross-sectionally, while for others the longitudinal change has been shown to be predictive, for instance greater-than-average muscle and weight loss in older adults. And while sometimes markers are derived from imaging modalities such as DXA, full scans are rarely used. This study builds on that knowledge and tests two hypotheses to improve all-cause mortality prediction. The first hypothesis is that features derived from raw total-body DXA imaging using deep learning are predictive of all-cause mortality with and without clinical risk factors, meanwhile, the second hypothesis states that sequential total-body DXA scans and recurrent neural network models outperform comparable models using only one observation with and without clinical risk factors. Methods Multiple deep neural network architectures were designed to test theses hypotheses. The models were trained and evaluated on data from the 16-year-long Health, Aging, and Body Composition Study including over 15,000 scans from over 3000 older, multi-race male and female adults. This study further used explainable AI techniques to interpret the predictions and evaluate the contribution of different inputs. Results The results demonstrate that longitudinal total-body DXA scans are predictive of all-cause mortality and improve performance of traditional mortality prediction models. On a held-out test set, the strongest model achieves an area under the receiver operator characteristic curve of 0.79. Conclusion This study demonstrates the efficacy of deep learning for the analysis of DXA medical imaging in a cross-sectional and longitudinal setting. By analyzing the trained deep learning models, this work also sheds light on what constitutes healthy aging in a diverse cohort. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email