Neural network-based design and evaluation of performance metrics using adaptive line enhancer with adaptive algorithms
- PDF / 2,183,135 Bytes
- 23 Pages / 595.276 x 790.866 pts Page_size
- 112 Downloads / 240 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Neural network-based design and evaluation of performance metrics using adaptive line enhancer with adaptive algorithms for auscultation analysis S. Rajkumar1 • K. Sathesh2 • Neeraj Kumar Goyal3 Received: 27 November 2018 / Accepted: 14 March 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Auscultation is an important key for the physical (respiratory and circulatory) examination and is helpful in diagnosing various disorders. Auscultation is performed for the purposes of examining the circulatory and respiratory sounds and gastrointestinal system (bowel sounds). Besides inconsistencies in the propagation of the normal sounds, there are also several types of specific irregularities that can be heard in respiratory sounds: commonly known abnormal sounds in lung sound (wheezes, crackles, stridor, squawks, rhonchi and crackles) and heart sounds (heart murmurs). However, detection of abnormal sounds during auscultation needs extensive training and experience. Real-time separation of these heart sound signals from the lung sound signals is of great research interest and difficult to achieve. In this work, the authors proposed a novel adaptive line enhancer using nonlinear ANN design used for auscultation analysis. Our proposed designs are trained using different networks training algorithms which resulted in better mean square error reduction within compact time. Keywords Auscultation Normalized least mean square (NLMS) Adaptive line enhancer (ALE) Neural networks (NN) Performance metrics
1 Introduction Breath and heart sounds [1–3] are two major bio-sound signals. The phenomena of pathological changes in these systems produce abnormal sounds. Lung auscultation deals with abnormal lung sounds (wheezes, crackles, squawks and stridors), whereas in cardiac auscultation deals with heart murmurs. The normal lung produces sound signals at 10 Hz to 400 Hz, but the abnormal wheezes produce sound signals at 100 Hz to 1 kHz. These vibrations directly
& S. Rajkumar [email protected] 1
Department of Electronics and Communication Engineering, School of Electrical Engineering and Computing, Adama Science and Technology University (ASTU), Adama, Ethiopia
2
Department of ECE, Madanapalle Institute of Technology and Science, Madanapalle, Andhra Pradesh, India
3
School of Quality and Reliability, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India
propagate sound waves, and these are transmitted and analysed through a stethoscope. Physicians use a stethoscope to hear the input signal from the human body, but it cannot be clearly observed for several reasons, such as varied positioning of the stethoscope condenser phone, or a gap between the body and the condenser phone, or the occurrence of some external and internal noise sources along with the input signal. Thus, the observed sound signals [4] contain noise or signal interference, which masks the heart and lung sound signals leading physicians to m
Data Loading...
