arXiv subjects

Amir Ali

Publications and source records attributed to Amir Ali.

4 recordsLinked to original sources

arXiv2026

ECG Classification on PTB-XL: A Data-Centric Approach with Simplified CNN-VAE

Automated electrocardiogram (ECG) classification is essential for early detection of cardiovascular diseases. While recent approaches have increasingly relied on deep neural networks with complex architectures, we demonstrate that careful data preprocessing, class balancing, and a simplified convolutional neural network combined with a variational autoencoder (CNN-VAE) architecture can achieve competitive performance with significantly reduced model complexity. Using the publicly available PTB XL dataset, we achieve 87.01% binary accuracy and 0.7454 weighted F1-score across five diagnostic classes (CD, HYP, MI, NORM, STTC) with only 197,093 trainable parameters. Our work emphasises the importance of data-centric machine learning practices over architectural complexity, demonstrating that systematic preprocessing and balanced training strategies are critical for medical signal classification. We identify challenges in minority class detection (particularly hypertrophy) and provide insights for future improvements in handling imbalanced ECG datasets. Index Terms: ECG classification, convolutional neural networks, class balancing, data preprocessing, variational autoencoders, PTB-XL dataset

cs.LG↗

arXiv2023

Deep Learning Models for Classification of COVID-19 Cases by Medical Images

In recent times, the use of chest Computed Tomography (CT) images for detecting coronavirus infections has gained significant attention, owing to their ability to reveal bilateral changes in affected individuals. However, classifying patients from medical images presents a formidable challenge, particularly in identifying such bilateral changes. To tackle this challenge, our study harnesses the power of deep learning models for the precise classification of infected patients. Our research involves a comparative analysis of deep transfer learning-based classification models, including DenseNet201, GoogleNet, and AlexNet, against carefully chosen supervised learning models. Additionally, our work encompasses Covid-19 classification, which involves the identification and differentiation of medical images, such as X-rays and electrocardiograms, that exhibit telltale signs of Covid-19 infection. This comprehensive approach ensures that our models can handle a wide range of medical image types and effectively identify characteristic patterns indicative of Covid-19. By conducting meticulous research and employing advanced deep learning techniques, we have made significant strides in enhancing the accuracy and speed of Covid-19 diagnosis. Our results demonstrate the effectiveness of these models and their potential to make substantial contributions to the global effort to combat COVID-19.

eess.IV↗

arXiv2020

An Implementation of Partial Transmit Sequences to Design Energy Efficient Underwater Acoustic OFDM Communication System

In this article we research about underwater acoustics transceivers. As Underwater acoustic transceivers consume more power than Radio frequency transceivers. The techniques which are being utilized in radio frequency cannot be implemented directly in underwater acoustic system it needs to be re investigated to design new methods. To achieve reliable acoustic data transmission new techniques should be achieved or the traditional Orthogonal frequency divisional multiplexing techniques should be revised. The power consumption also relies upon underwater acoustic signal propagation and transmission distances. Several underwater acoustic applications require long-term monitoring of the sea. For the battery powered modems, it becomes very serious problem. By designing an Energy efficient OFDM Communication system we can solve this problem. We study about peak to average power ratio in an Orthogonal frequency divisional multiplexing system by reducing the major draw-back of OFDM system. The PAPR reduction utilized in this paper is Partial Transmit Sequences for underwater acoustic OFDM communication system which has lesser complexity. The results have provided better performance in underwater acoustic OFDM communication system.

eess.SP↗

arXiv2010

Breathing modes of long Josephson junctions with phase-shifts

We consider a spatially inhomogeneous sine-Gordon equation with a time-periodic drive, modeling a microwave driven long Josephson junction with phase-shifts. Under appropriate conditions, Josephson junctions with phase-shifts can have a spatially nonuniform ground state. In recent reports, it is experimentally shown that a microwave drive can be used to measure the eigenfrequency of a junction's ground state. Such a microwave spectroscopy is based on the observation that when the frequency of the applied microwave is in the vicinity of the natural frequency of the ground state, the junction can switch to a resistive state, characterized by a non-zero junction voltage. It was conjectured that the process is analogous to the resonant phenomenon in a simple pendulum motion driven by a time periodic external force. In the case of long junctions with phase-shifts, it would be a resonance between the internal breathing mode of the ground state and the microwave field. Nonetheless, it was also reported that the microwave power needed to switch the junction into a resistive state depends on the magnitude of the eigenfrequency to be measured. Using multiple scale expansions, we show here that an infinitely long Josephson junction with phase-shifts cannot be switched to a resistive state by microwave field with frequency close to the system's eigenfrequency, provided that the applied microwave amplitude is small enough, which confirms the experimental observations. It is because higher harmonics with frequencies in the continuous spectrum are excited, in the form of continuous wave radiation. The presence of applied microwaves balances the nonlinear damping, creating a stable breather mode oscillation. We confirm our analytical results numerically.

nlin.PS↗