Salam

I am Sakib Mahmud, currently working as a Research Assistant at Qatar University (QU) and Hamad Medical Corporation (HMC). My research field primarily revolves around Artificial Intelligence (AI) applications in the HealthCare sector.

Notable Publications

I have 43 publications in peer-reviewed journals and 3 in conference proceedings. Notable mentions:

Our proposed NABNet [1] can continuously reconstruct ABP waveforms from PPG and ECG signals (2023, BSPC Elsevier, IF: 5.076), inspired by our pioneering study PPG2ABP first appeared during 2020 [2].
Our proposed QUCoughScope [3] is able to reliably detect COVID-19 from cough and breath sounds (2022, Diagnostics MDPI, IF: 3.992).
We also reliably detected and quantified the lung infections caused by COVID-19 from Chest X-Ray images (2021, CIBM Elsevier, IF: 6.698) [4] and from Chest CT scans (2021, Diagnostics MDPI, IF: 3.992) [5].
Can COVID-19 be reliably estimated from wearable data? We replied to that question in PCovNet [6] (2022, CIBM Elsevier, IF: 6.698).
Our team in Qatar University (QU) developed electronic [7] (2022, Sensors MDPI, IF: 3.847) and optoelectronic [8] (2022, JSNA: Physical Elsevier, IF: 4.291) sensor based smart insoles for real-time plantar pressure and temperature data acquisition for home monitoring of patients with foot complications such as Diabetic Neuropathy.

Please visit my Google Scholar and ResearchGate profiles for more details.

Tools I Use

Current GitHub Stats

Connect or Follow Me Here

Sakib Mahmud's Projects

ahn-severity-stratification

This repository contains the codes for our study involving an end-to-end deep machine learning framework developed to ‎sequentially detect ultrasound regions of interest, ‎segment kidneys from US images, and classify AHN severity.‎

covid-19-vaccine-willingness-and-hesitancy-among-residents-in-qatar

A Machine Learning-based approach to classify COVID-19 Vaccine Willingness and Hesitancy severity among people in Qatar based on survey outcomes.

densenet-1d-2d-tensorflow-keras

Models Supported: DenseNet121, DenseNet161, DenseNet169, DenseNet201 and DenseNet264 (1D and 2D version with DEMO for Classification and Regression)

inception-inceptionresnet-seinception-seinceptionresnet-1d-2d-tensorflow-keras

Models Supported: Inception [v1, v2, v3, v4], SE-Inception, Inception_ResNet [v1, v2], SE-Inception_ResNet (1D and 2D version with DEMO for Classification and Regression)

mobilenet-1d-2d-tensorflow-keras

Supported Models: MobileNet [V1, V2, V3_Small, V3_Large] (Both 1D and 2D versions with DEMO, for Classification and Regression)

nabnet

NABNet: A Nested Attention-guided BiConvLSTM Network for a robust ‎prediction of Blood Pressure components from reconstructed Arterial Blood ‎Pressure waveforms using PPG and ECG Signals

tf-1d-2d-resnetv1-2-seresnet-resnext-seresnext

Models supported: ResNet, ResNetV2, SE-ResNet, ResNeXt, SE-ResNeXt [layers: 18, 34, 50, 101, 152] (1D and 2D versions with DEMO for Classification and Regression).