Study of Adventitious Lung Sounds of Paediatric Population using Artificial Neural Network Approach

Journal Title: International Journal of Current Research and Review - Year 2017, Vol 9, Issue 9

Abstract

Objectives: Human lung sounds are important indicators of underlying lung pathology. The prime objective of this work is to classify normal and adventitious lung sounds in paediatric population using spectral features and artificial neural networks. Material and Method: 3M Littmann 3200 electronic stethoscope was used to record the lung sounds. After pre-processing ten spectral features were extracted. For classification, comparative performance of different artificial neural networks is studied and GFF neural network with calculated optimum parameters is selected. Results: For testing data Out of 49 normal subjects 48 were classified successfully and out of 52 pathological subjects 48 were classified successfully. The classification sensitivity and specificity obtained is 92.30% and 97.95% respectively. Conclusion: Early diagnosis of lung disorder is important especially in childhood so that further progress of the disease could be prevented. New approach to detect adventitious lung sounds is being proposed utilizing electronic stethoscope as a recording device. Combination of spectral features and artificial neural networks has provided classification accuracy of 95.12%.

Authors and Affiliations

Sibghatullah I. Khan

Keywords

Related Articles

Mediastinal Pancreatic Pseudocyst - A Rare Cause of Dysphagia (Case Report)

Pseudocyst is a common complication of both acute & chronic pancreatitis due to any cause. It is a localised fluid collection, rich in pancreatic enzymes surrounded by a wall of non- epithelialized fibrous tissue. Mostly...

Reflection of Syrian Refugees to Pediatric Surgery

Objective: Migration is an emergency in all aspects. Since the war began many of Syrian refugees were treated in our country. We aimed to evaluate pediatric surgical outcomes of these children in a tertiary center in Tur...

Significance of Secreted Frizzled Related Protein 4 (SFRP4) in Type 2 Diabetic and non Diabetic Subjects in the Rural Agricultural Population Who are Exposed to Pesticides for the Prediction of Diabetes Mellitus

Introduction: Diabetes mellitus and its complications have become a major health problem for the public of South East Asians especially in India. Exposure to organophosphorus pesticides which are very much in use for the...

Ovarian Neoplasms- Histopathological Patterns and Relative Frequencies in an Indian Tertiary Care Hospital

Introduction: Ovarian neoplasms are tumors or cancer of the ovary. These neoplasms can be benign or malignant and are classified according to the tissue of origin, such as the surface epithelium, the stromal endocrine ce...

Changes in Levels of Soil Carbon and Forest Floor Carbon Stocks in the different Temperate Forests of Garhwal Himalaya

Objectives: Since soil carbon (C) is a principal source of energy for the nutrient-recycling activities of heterotrophic soil organisms, the maintenance of belowground C stocks is vital for sustaining forest productivity...

Download PDF file
  • EP ID EP609752
  • DOI 10.7324/IJCRR.2017.993745
  • Views 130
  • Downloads 0

How To Cite

Sibghatullah I. Khan (2017). Study of Adventitious Lung Sounds of Paediatric Population using Artificial Neural Network Approach. International Journal of Current Research and Review, 9(9), 37-45. https://europub.co.uk/articles/-A-609752