VGAResNet: A Unified Visibility Graph Adjacency Matrix-Based Residual Network for Chronic Obstructive Pulmonary Disease Detection Using Lung Sounds

Article Engineering, Electrical & Electronic

Time-Frequency Multiscale Convolutional Neural Network for RF-Based Drone Detection and Identification

Sayantika Mandal et al.

Summary: Due to recent advancements in technology and cost reductions, drones are gaining popularity rapidly. With their increased accessibility, the need for reliable drone detection and identification systems is becoming more critical. In this study, we propose a deep learning model based on a time-frequency multiscale convolutional neural network to detect and identify drones using raw and frequency domain radio frequency signals. Our model outperforms state-of-the-art methods in drone detection and identification using deep neural networks, as evaluated on a publicly accessible database.

IEEE SENSORS LETTERS (2023)

Add to Collection

Article Engineering, Electrical & Electronic

A Novel Melspectrogram Snippet Representation Learning Framework for Severity Detection of Chronic Obstructive Pulmonary Diseases

Arka Roy et al.

Summary: Chronic obstructive pulmonary disease (COPD) is a major global public health concern. Early detection and accurate diagnosis are crucial for preventing disease progression. Lung sounds provide reliable prognoses for respiratory disease identification. This article proposes a melspectrogram snippet representation learning framework for COPD classification and achieves superior accuracy compared to existing methods.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2023)

Add to Collection

Article Computer Science, Information Systems

Cuff-Less Blood Pressure Estimation From Photoplethysmography via Visibility Graph and Transfer Learning

Weinan Wang et al.

Summary: This method utilizes VG images to extract feature vectors and solves the relationship between feature vectors and reference blood pressure using ridge regression, achieving transfer learning for cuff-less blood pressure monitoring. Experimental results demonstrate that the proposed method achieves good BP estimation performance on the UCI database, attaining ratings under the BHS protocol.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2022)

Add to Collection

Article Automation & Control Systems

Nonintrusive Perceptual Audio Quality Assessment for User-Generated Content Using Deep Learning

Deebha Mumtaz et al.

Summary: With the rise of social media communication, teleconferencing, and online classes, audiovisual communication has become a crucial part of our lives. This article addresses the need for algorithms to measure and enhance user experience, focusing on the quality assessment of user-generated multimedia (UGM). The lack of a standard dataset and the significant differences between speech and UGM audio properties are challenges that are overcome with the development of the IIT-JMU-UGM audio dataset. The proposed non-intrusive audio quality assessment metric, based on a deep learning framework, outperforms other methods and effectively reflects human auditory perception.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Automated Detection of Pulmonary Diseases From Lung Sound Signals Using Fixed-Boundary-Based Empirical Wavelet Transform

Rajesh Kumar Tripathy et al.

Summary: This letter proposes a promising method for automatically detecting pulmonary diseases by using lung sound signals. The method evaluates the modes of the lung sound signal and extracts time-domain and frequency-domain features to detect diseases using different classifiers. The performance of the method is evaluated using a publicly available database, and high detection accuracy values are obtained.

IEEE SENSORS LETTERS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

On-Device Implementation for Deep-Learning-Based Cognitive Activity Prediction

Manali Saini et al.

Summary: In this study, a lightweight 1-D convolutional neural network method is proposed for predicting cognitive activity from electroencephalogram signals. The real-time recorded results demonstrate high prediction accuracy and low power consumption on resource-constrained edge devices.

IEEE SENSORS LETTERS (2022)

Add to Collection

Article Multidisciplinary Sciences

A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects

Thao Thi Ho et al.

Summary: A new classification method for COPD grouping based on deep learning and parametric-response mapping (PRM) was introduced in this study, achieving high accuracy in lung disease classification through image processing and neural network technology, providing new possibilities for the diagnosis of COPD.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Multidisciplinary Sciences

A dataset of lung sounds recorded from the chest wall using an electronic stethoscope

Mohammad Fraiwan et al.

Summary: The advancement of stethoscope technology allows for high quality recording of patient sounds, including lung sounds from both healthy and unhealthy subjects. The dataset includes recordings from seven different ailments and normal breathing sounds, providing valuable information for automated methods in detecting pulmonary diseases or identifying lung sound types.

DATA IN BRIEF (2021)

Add to Collection

Article Computer Science, Information Systems