skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: DeepRange: Acoustic Ranging via Deep Learning
Acoustic ranging is a technique for estimating the distance between two objects using acoustic signals, which plays a critical role in many applications, such as motion tracking, gesture/activity recognition, and indoor localization. Although many ranging algorithms have been developed, their performance still degrades significantly under strong noise, interference and hardware limitations. To improve the robustness of the ranging system, in this paper we develop a Deep learning based Ranging system, called DeepRange. We first develop an effective mechanism to generate synthetic training data that captures noise, speaker/mic distortion, and interference in the signals and remove the need of collecting a large volume of training data. We then design a deep range neural network (DRNet) to estimate distance. Our design is inspired by signal processing that ultra-long convolution kernel sizes help to combat the noise and interference. We further apply an ensemble method to enhance the performance. Moreover, we analyze and visualize the network neurons and filters, and identify a few important findings that can be useful for improving the design of signal processing algorithms. Finally, we implement and evaluate DeepRangeusing 11 smartphones with different brands and models, 4 environments (i.e., a lab, a conference room, a corridor, and a cubic area), and 10 users. Our results show that DRNet significantly outperforms existing ranging algorithms.  more » « less
Award ID(s):
1718585
PAR ID:
10253874
Author(s) / Creator(s):
Date Published:
Journal Name:
Proceedings of the ACM on interactive mobile wearable and ubiquitous technologies
Volume:
4
Issue:
4
ISSN:
2474-9567
Page Range / eLocation ID:
1-23
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Global Oceans 2020: Singapore – U.S. Gulf Coast)
    Underwater acoustic communications provide promising solutions for remote and real-time aquatic exploration and monitoring. However, the underwater environment is rich in various kinds of interferences. Those interferences could severely degrade the acoustic communication performance. This work tackles interference cancellation in a single-carrier modulated communication system. Based on the Nyqusit sampling theorem, the interference is parameterized by a finite number of unknown parameters. The Page test is applied to detect the presence of an interfering waveform in the received signal. An iterative receiver is developed, which iteratively performs the interference estimation/cancellation and traditional receiver processing. The proposed receiver is evaluated when the communication waveform is interfered by the ice-cracking impulsive noise and the sonar signal collected from the Arctic. The data processing results reveal that the proposed receiver achieves considerable decoding performance improvement through the iterative interference estimation and cancellation. 
    more » « less
  2. ; ; (, Applied Sciences)
    Photo-Acoustic Tomography (PAT) is an emerging non-invasive hybrid modality driven by a constant yearning for superior imaging performance. The image quality, however, hinges on the acoustic reflection, which may compromise the diagnostic performance. To address this challenge, we propose to incorporate a deep neural network into conventional iterative algorithms to accelerate and improve the correction of reflection artifacts. Based on the simulated PAT dataset from computed tomography (CT) scans, this network-accelerated reconstruction approach is shown to outperform two state-of-the-art iterative algorithms in terms of the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) in the presence of noise. The proposed network also demonstrates considerably higher computational efficiency than conventional iterative algorithms, which are time-consuming and cumbersome. 
    more » « less
  3. ; ; (, IEEE)
    Constructive interference exploited by symbol-level (SL) signal processing is a promising solution for addressing the inherent interference problem in dual-functional radar-communication (DFRC) signal designs. This paper considers an SL-DFRC signal design problem which maximizes the radar performance under communication performance constraints. We exploit the symmetrical non-convexity property of the communication-independent radar sensing metric to develop low- complexity yet efficient algorithms. We first propose a radar-to- DFRC (R2DFRC) algorithm that relies on the non-convexity of the radar sensing metric to find a set of radar-only solutions. Based on these solutions, we further exploit the symmetrical property of the radar sensing metric to efficiently design the DFRC signal. Since the radar sensing metric is independent of the communication channel and data symbols, the set of radar-only solutions can be constructed offline, therefore reducing the computational complexity. We then develop an accelerated R2DFRC algorithm that further reduces the complexity. Finally, we demonstrate the superiority of the proposed algorithms compared to existing methods in terms of both radar sensing and communication performance as well as computational complexity. 
    more » « less
  4. ; (, Proc. of the Review of Nondestructive Evaluation)
    Damage detection and localization remain challenging research areas in structural health monitoring. Guided wave-based methods that utilize signal processing tools (e.g., matched field processing and delay-and-sum localization) have enjoyed success in damage detection. To locate damage, such techniques rely on a model of wave propagation through materials. Measured data is then compared with these models to determine the origin of a wave. As a result, the analytical model and actual data may have a mismatch due to environmental variations or a lack of knowledge about the material. Deep neural networks are a class of machine learning algorithms that learn a non-linear functional mapping. The paper presents a deep neural network-based approach to damage localization. We use simulated data to assess the performance of localization frameworks under varying levels of noise and other uncertainty in our ultrasonic signals. 
    more » « less
  5. ; (, 2022 IEEE Wireless Communications and Networking Conference (WCNC))
    Signal anomaly detection is commonly used to detect rogue or unexpected signals. It has many applications in interference mitigation, wireless security, optimized spectrum allocation, and radio coordination. Our work proposes a new method for anomaly detection on signal detection metadata using generative adversarial network output processed by a long short term memory recurrent neural network. We provide a performance analysis and comparison to baseline methods, and demonstrate that through the usage of metadata for analytics, we can provide robust detection, while also minimizing computation and bandwidth, and generalizing to numerous effects which differs from many prior works that focus on A.D. based signal processing on the raw RF sample data. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email