No abstract

Myocardial Infarction is one of the leading causes of death worldwide. This paper presents a Convolutional Neural Network (CNN) architecture which takes raw Electrocardiography (ECG) signal from lead II, III and AVF and differentiates between inferior myocardial infarction (IMI) and healthy signals. The performance of the model is evaluated on IMI and healthy signals obtained from Physikalisch-Technische Bundesanstalt (PTB) database. A subject-oriented approach is taken to comprehend the generalization capability of the model and compared with the current state of the art. In a subject-oriented approach, the network is tested on one patient and trained on rest of the patients. Our model achieved a superior metrics scores (accuracy= 84.54%, sensitivity= 85.33% and specificity= 84.09%) when compared to the benchmark. We also analyzed the discriminating strength of the features extracted by the convolutional layers by means of geometric separability index and euclidean distance and compared it with the benchmark model.

No abstract

To treat the diseases or injuries of the joints, bones, muscles, and spine in both adult and pediatric imaging the musculoskeletal radiographs bring a significant depth of expertise. Abnormality detection in the musculoskeletal study is backbreaking as more than 1.7 billion people are affected by musculoskeletal condition (BMU, 2017). Hence if we want to create enough opportunity to treat a maximum amount of patients, machine learning and deep learning can play a crucial role. CNN is an excellent deep learning method for image classification and other computer vision tasks. But CNN has exhibited some serious limitations when the images are rotated and deformed. Hence capsule network architecture is introduced in this paper for musculoskeletal radiographs abnormality detection and this capsnet architecture has shown very promising features that can help to vanquish the limitations of CNN. In addition, this capsule network has scored 10% higher kappa score than 169 layer densenet using less training data in the case of musculoskeletal radiographs abnormality detection. This feature of capsule network can help to use deep learning in such cases where an aggregate of a large amount of data is not possible. For image quality investigation, blind image spatial quality evaluator (BRISQUE) and naturalness image quality evaluator (NIQE) scores are measured and it is found that when the pixel size of the resized images are more close to the pixel size of the original images, we get a better approximation. Hence in the case of musculoskeletal radiographs abnormality detection, our method outperforms state-of-the-art method using a less amount of training data.

This paper presents a speech enhancement approach, where an adaptive threshold is statistically determined based on Student t Modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to obtain an enhanced speech, the threshold thus derived is applied upon the PWP coefficients by employing a Student t pdf dependent custom thresholding function, which is designed based on a combination of modified hard and semisoft thresholding functions.Extensive simulations are carried out using the NOIZEUS database to evaluate the effectiveness of the proposed method for car and multi-talker babble noise corrupted speech signals. Several standard objective measures and subjective evaluations including formal listening tests show that the proposed method outperforms some of the state-of-the-art speech enhancement methods at high as well as low levels of SNRs.