Arslan Manzoor - Academia.edu (original) (raw)
Uploads
Papers by Arslan Manzoor
Lung diseases are among the most widely recognized reasons for serious disease and passing around... more Lung diseases are among the most widely recognized reasons for serious disease and passing around the world. The timely analysis is crucial to lessen the risk of any disease and if any disease is diagnosed, then precautions or medicines are immediately given. Therefore, for the diagnosis of lung sound auscultation, progressive computational tools are established and play a very vital role in the detection of diseaserelated anomalies. The aim of this study is the joint learning of the model that only extracts important breathing samples without generating redundant noise, and then uses this information to train lung sounds into four categories: normal, wheezes, crackles, and wheezes and crackles. This paper signified an unsupervised approach that depends on a Denoising Auto-Encoder (DAE). It utilizes the rebuild errors between the input and the output of the Auto-encoder as an activation audio signal to identify noisiness. A novel design of Recurrent Neural Network (RNN) called noise-masking anomalies recurrent neural network (NMA-RNN) for lung sound order is projected. ICBHI database used in this paper and some results of previous models were compared and achieved 95% accuracy.
Lung diseases are among the most widely recognized reasons for serious disease and passing around... more Lung diseases are among the most widely recognized reasons for serious disease and passing around the world. The timely analysis is crucial to lessen the risk of any disease and if any disease is diagnosed, then precautions or medicines are immediately given. Therefore, for the diagnosis of lung sound auscultation, progressive computational tools are established and play a very vital role in the detection of diseaserelated anomalies. The aim of this study is the joint learning of the model that only extracts important breathing samples without generating redundant noise, and then uses this information to train lung sounds into four categories: normal, wheezes, crackles, and wheezes and crackles. This paper signified an unsupervised approach that depends on a Denoising Auto-Encoder (DAE). It utilizes the rebuild errors between the input and the output of the Auto-encoder as an activation audio signal to identify noisiness. A novel design of Recurrent Neural Network (RNN) called noise-masking anomalies recurrent neural network (NMA-RNN) for lung sound order is projected. ICBHI database used in this paper and some results of previous models were compared and achieved 95% accuracy.