Search for Articles:

MECS Press Menu

Abdul-Hafeez Baig

Work place: University of Southern Queensland, School of Management and Enterprise, Toowoomba, QLD, Australia

E-mail: Abdul.Hafeez-Baig@usq.edu.au

Website:

Research Interests:

Biography

Abdul-Hafeez Baig received the master’s degree in MIS and MBA from Griffith University, Brisbane, Australia, and the Ph.D. degree in the domain of healthcare and information systems from USQ. Since joining USQ, in January 2004, he has published several refereed publications and has numerous research grants in the domains of health and education regarding technology management. He is very conversant with wireless technology as well as emerging technologies and learning management systems. He teaches information systems concepts to both undergraduate and postgraduate students, including MBA students. He also has numerous publications in academic and scholarly journals and has a vast array of scholarly conference papers, all of which have been focused on the domain of information systems. He has extensive experience in the area of information systems, especially related to the healthcare sector. He is quite interested in wireless healthcare applications, systems analysis and design, adoption, the infusion and diffusion of information technology, m-learning and e-commerce, outsourcing, networking, healthcare and information technology, and the re-engineering of business processes.

Author Articles
Spectrogram-based Deep Learning Approach for Anomaly Detection from Cough Sounds

By Tugce Keles Sengul Dogan Abdul-Hafeez Baig Turker Tuncer

DOI: https://doi.org/10.5815/ijitcs.2025.03.01, Pub. Date: 8 Jun. 2025

Artificial intelligence is now applied in many fields beyond computer science. In healthcare, it enables early disease detection and improves patient outcomes. This study develops a model that uses AI to find abnormal patterns in cough sounds. A cough is a key symptom of asthma and other respiratory diseases. Previous research has focused on raw audio signals of coughs. In contrast, we analyze spectrogram images derived from these sounds to improve accuracy. We designed a new convolutional neural network (CNN) for this purpose and the recommended CNN is termed as TwoConvNeXt. To showcase the classification performance of the recommended TwoConvNeXt model, a cough sound dataset has been utilized and the recommended TwoConvNeXt achieved 99.66% classification test accuracy. 
These results illustrate that the presented TwoConvNeXt CNN architecture can be useful in both research and clinical settings. This CNN model can be utilized for other image classification problems. It may aid in the early diagnosis of respiratory conditions. Future work will expand the dataset and test the model on larger, more diverse samples.

[...] Read more.
Other Articles

Subscribe to receive issue release notifications and newsletters from MECS Press journals