arXiv subjects

Shahzad Younis

Publications and source records attributed to Shahzad Younis.

3 recordsLinked to original sources

arXiv2024

Advancing ECG Diagnosis Using Reinforcement Learning on Global Waveform Variations Related to P Wave and PR Interval

The reliable diagnosis of cardiac conditions through electrocardiogram (ECG) analysis critically depends on accurately detecting P waves and measuring the PR interval. However, achieving consistent and generalizable diagnoses across diverse populations presents challenges due to the inherent global variations observed in ECG signals. This paper is focused on applying the Q learning reinforcement algorithm to the various ECG datasets available in the PhysioNet/Computing in Cardiology Challenge (CinC). Five ECG beats, including Normal Sinus Rhythm, Atrial Flutter, Atrial Fibrillation, 1st Degree Atrioventricular Block, and Left Atrial Enlargement, are included to study variations of P waves and PR Interval on Lead II and Lead V1. Q-Agent classified 71,672 beat samples in 8,867 patients with an average accuracy of 90.4% and only 9.6% average hamming loss over misclassification. The average classification time at the 100th episode containing around 40,000 samples is 0.04 seconds. An average training reward of 344.05 is achieved at an alpha, gamma, and SoftMax temperature rate of 0.001, 0.9, and 0.1, respectively.

eess.SP↗

arXiv2020

Transfer Learning for Improving Speech Emotion Classification Accuracy

The majority of existing speech emotion recognition research focuses on automatic emotion detection using training and testing data from same corpus collected under the same conditions. The performance of such systems has been shown to drop significantly in cross-corpus and cross-language scenarios. To address the problem, this paper exploits a transfer learning technique to improve the performance of speech emotion recognition systems that is novel in cross-language and cross-corpus scenarios. Evaluations on five different corpora in three different languages show that Deep Belief Networks (DBNs) offer better accuracy than previous approaches on cross-corpus emotion recognition, relative to a Sparse Autoencoder and SVM baseline system. Results also suggest that using a large number of languages for training and using a small fraction of the target data in training can significantly boost accuracy compared with baseline also for the corpus with limited training examples.

cs.CV↗

arXiv2017

Feasibility, Architecture and Cost Considerations of Using TVWS for Rural Internet Access in 5G

The cellular technology is mostly an urban technology that has been unable to serve rural areas well. This is because the traditional cellular models are not economical for areas with low user density and lesser revenues. In 5G cellular networks, the coverage dilemma is likely to remain the same, thus widening the rural-urban digital divide further. It is about time to identify the root cause that has hindered the rural technology growth and analyse the possible options in 5G architecture to address this issue. We advocate that it can only be accomplished in two phases by sequentially addressing economic viability followed by performance progression. We deliberate how various works in literature focus on the later stage of this two-phase problem and are not feasible to implement in the first place. We propose the concept of TV band white space (TVWS) dovetailed with 5G infrastructure for rural coverage and show that it can yield cost-effectiveness from a service provider perspective.

cs.NI↗