skip to main content


Title: Investigating the Relationship between Cough Detection and Sampling Frequency for Wearable Devices
Cough detection can provide an important marker to monitor chronic respiratory conditions. However, manual techniques which require human expertise to count coughs are both expensive and time-consuming. Recent Automatic Cough Detection Algorithms (ACDAs) have shown promise to meet clinical monitoring requirements, but only in recent years they have made their way to non-clinical settings due to the required portability of sensing technologies and the extended duration of data recording. More precisely, these ACDAs operate at high sampling frequencies, which leads to high power consumption and computing requirements, making these difficult to implement on a wearable device. Additionally, reproducibility of their performance is essential. Unfortunately, as the majority of ACDAs were developed using private clinical data, it is difficult to reproduce their results. We, hereby, present an ACDA that meets clinical monitoring requirements and reliably operates at a low sampling frequency. This ACDA is implemented using a convolutional neural network (CNN), and publicly available data. It achieves a sensitivity of 92.7%, a specificity of 92.3%, and an accuracy of 92.5% using a sampling frequency of just 750 Hz. We also show that a low sampling frequency allows us to preserve patients’ privacy by obfuscating their speech, and we analyze the trade-off between speech obfuscation for privacy and cough detection accuracy. Clinical relevance—This paper presents a new cough detection technique and preliminary analysis on the trade-off between detection accuracy and obfuscation of speech for privacy. These findings indicate that, using a publicly available dataset, we can sample signals at 750 Hz while still maintaining a sensitivity above 90%, suggested to be sufficient for clinical monitoring [1].  more » « less
Award ID(s):
1915599
NSF-PAR ID:
10351528
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Page Range / eLocation ID:
7103 to 7107
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Despite the advent of numerous Internet-of-Things (IoT) applications, recent research demonstrates potential side-channel vulnerabilities exploiting sensors which are used for event and environment monitoring. In this paper, we propose a new side-channel attack, where a network of distributed non-acoustic sensors can be exploited by an attacker to launch an eavesdropping attack by reconstructing intelligible speech signals. Specifically, we present PitchIn to demonstrate the feasibility of speech reconstruction from non-acoustic sensor data collected offline across networked devices. Unlike speech reconstruction which requires a high sampling frequency (e.g., > 5 KHz), typical applications using non-acoustic sensors do not rely on richly sampled data, presenting a challenge to the speech reconstruction attack. Hence, PitchIn leverages a distributed form of Time Interleaved Analog-Digital-Conversion (TIADC) to approximate a high sampling frequency, while maintaining low per-node sampling frequency. We demonstrate how distributed TI-ADC can be used to achieve intelligibility by processing an interleaved signal composed of different sensors across networked devices. We implement PitchIn and evaluate reconstructed speech signal intelligibility via user studies. PitchIn has word recognition accuracy as high as 79%. Though some additional work is required to improve accuracy, our results suggest that eavesdropping using a fusion of non-acoustic sensors is a real and practical threat. 
    more » « less
  2. Marc'Aurelio Ranzato, Alina Beygelzimer (Ed.)
    Implementations of the exponential mechanism in differential privacy often require sampling from intractable distributions. When approximate procedures like Markov chain Monte Carlo (MCMC) are used, the end result incurs costs to both privacy and accuracy. Existing work has examined these effects asymptotically, but implementable finite sample results are needed in practice so that users can specify privacy budgets in advance and implement samplers with exact privacy guarantees. In this paper, we use tools from ergodic theory and perfect simulation to design exact finite runtime sampling algorithms for the exponential mechanism by introducing an intermediate modified target distribution using artificial atoms. We propose an additional modification of this sampling algorithm that maintains its ǫ-DP guarantee and has improved runtime at the cost of some utility. We then compare these methods in scenarios where we can explicitly calculate a δ cost (as in (ǫ, δ)-DP) incurred when using standard MCMC techniques. Much as there is a well known trade-off between privacy and utility, we demonstrate that there is also a trade-off between privacy guarantees and runtime. 
    more » « less
  3. Bipolar Disorder, a mood disorder with recurrent mania and depression, requires ongoing monitoring and specialty management. Current monitoring strategies are clinically-based, engaging highly specialized medical professionals who are becoming increasingly scarce. Automatic speech-based monitoring via smartphones has the potential to augment clinical monitoring by providing inexpensive and unobtrusive measurements of a patient’s daily life. The success of such an approach is contingent on the ability to successfully utilize “in-the-wild” data. However, most existing work on automatic mood detection uses datasets collected in clinical or laboratory settings. This study presents experiments in automatically detecting depression severity in individuals with Bipolar Disorder using data derived from clinical interviews and from personal conversations. We find that mood assessment is more accurate using data collected from clinical interactions, in part because of their highly structured nature. We demonstrate that although the features that are most effective in clinical interactions do not extend well to personal conversational data, we can identify alternative features relevant in personal conversational speech to detect mood symptom severity. Our results highlight the challenges unique to working with “in-the-wild” data, providing insight into the degree to which the predictive ability of speech features is preserved outside of a clinical interview. 
    more » « less
  4. Distributed acoustic sensing (DAS) is a technique that measures strain changes along an optical fiber to distances of ∼100 km with a spatial sensitivity of tens of meters. In November 2021, 4 days of DAS data were collected on two cables of the Ocean Observatories Initiative Regional Cabled Array extending offshore central Oregon. Numerous 20 Hz fin whale calls, northeast Pacific blue whale A and B calls, and ship noises were recorded, highlighting the potential of DAS for monitoring the ocean. The data are publicly available to support studies to understand the sensitivity of submarine DAS for low-frequency acoustic monitoring.

     
    more » « less
  5. Open-top light-sheet (OTLS) microscopy offers rapid 3D imaging of large optically cleared specimens. This enables nondestructive 3D pathology, which provides key advantages over conventional slide-based histology including comprehensive sampling without tissue sectioning/destruction and visualization of diagnostically important 3D structures. With 3D pathology, clinical specimens are often labeled with small-molecule stains that broadly target nucleic acids and proteins, mimicking conventional hematoxylin and eosin (H&E) dyes. Tight optical sectioning helps to minimize out-of-focus fluorescence for high-contrast imaging in these densely labeled tissues but has been challenging to achieve in OTLS systems due to trade-offs between optical sectioning and field of view. Here we present an OTLS microscope with voice-coil-based axial sweeping to circumvent this trade-off, achieving 2 µm axial resolution over a 750 × 375 µm field of view. We implement our design in a non-orthogonal dual-objective (NODO) architecture, which enables a 10-mm working distance with minimal sensitivity to refractive index mismatches, for high-contrast 3D imaging of clinical specimens.

     
    more » « less