Cough Detection
Cough Detection - Related Videos
04:33
Methods for Detecting Cough and Airway Inflammation in Mice
0 Views •
Cited by 1 •
2024
Here, we describe the measurement of cough using a noninvasive and real-time whole-body plethysmography (WBP) system and the normative procedures for harvesting tissue samples of mice and introduce some methods to assess airway inflammation.
09:30
Precision Induction and Distinction of Coughing and Sneezing Reflexes in Mice
0 Views •
2025
This study established cough and sneeze models in mice by applying specific stimuli to the trachea and nasal cavity, and developed an audio-based method to distinguish between mouse coughs and sneezes by analyzing differences in their acoustic signals.
05:43
Establishment of a Mouse Model with Cough Hypersensitivity via Inhalation of Citric Acid
0 Views •
2025
This protocol describes the development of a mouse model with cough hypersensitivity, which can serve as an ideal model for studying the mechanisms of chronic cough.
06:22
Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
0 Views •
2025
This study effectively accomplished the automated classification of two distinct categories by acquiring cough sound data from patients diagnosed with chronic obstructive pulmonary disease (COPD) and respiratory tract infections (RTI), utilizing an integration of speech signal processing techniques and machine learning algorithms.
08:13
A Cre-Lox P Recombination Approach for the Detection of Cell Fusion In Vivo
0 Views •
Cited by 11 •
2012
A method to track cell fusion in living organisms over time is described. The approach utilizes Cre-LoxP recombination to induce luciferase expression upon cell fusion. The luminescent signal generated can be detected in living organisms using biophotonic imaging systems with a sensitivity of detection of ˜1,000 cells in peripheral tissues.
FAQs
Each input captures a different aspect of the event. Audio records sound patterns, while wearable sensors provide physiological or movement-related signals, and video supplies visual information about the person or surrounding activity. Combining these sources can expand the available evidence for classification, although the useful signal depends on whether the system is analyzing sound, timing, intensity, physiology, or visible behavior.
Cough detection systems can examine acoustic patterns together with event timing and intensity. These features help separate cough-like signals from speech, normal breathing, movement, and environmental noise. Signal-processing methods organize or clarify the captured data, while machine-learning methods use extracted patterns to classify events. The result is a quantitative assessment rather than reliance only on subjective symptom descriptions.
Movement, speech, breathing, and environmental sounds can resemble or obscure cough signals in recorded data. If a system does not distinguish these competing signals, its event counts and classifications may become less reliable. Treating these sources as classification challenges is therefore central to cough detection, because accurate separation affects symptom monitoring and the interpretation of respiratory research measurements.
Timing shows when events occur and can reveal temporal patterns, while intensity adds information about how strongly the event appears in the captured signal. Together, these measures provide more structure than a single total count. In medical studies, that richer description can support evaluation of respiratory symptoms and help researchers examine changes associated with treatment or observation periods.
A typical workflow captures an audio, wearable-sensor, or video signal, identifies relevant features such as sound patterns, timing, or intensity, and applies signal-processing or machine-learning methods to classify events. The resulting output can include cough frequency and temporal patterns. This sequence converts continuous or recorded observations into quantitative measures suitable for clinical assessment or research analysis.
Medical teams may use cough detection for continuous symptom monitoring, clinical evaluation, and respiratory disease research. Treatment studies can also use quantitative cough measures to examine symptom patterns over time. Because the method reduces dependence on patient recall, it may provide a more consistent record of observed events, particularly when symptoms fluctuate or monitoring extends beyond a single clinical encounter.
By analyzing signals collected outside a clinic, cough detection can support remote monitoring of symptom frequency and timing. Its measurements may complement clinical evaluation by providing an objective record for later analysis rather than relying only on recalled symptoms. In respiratory research and treatment studies, these data can help quantify symptom behavior across observation periods and compare patterns over time.