Hafiz Muhammad Hassan

Application of Federated Learning

23 Aug 2022

https://arxiv.org/abs/2208.10993

Artificial Intelligence-based (AI) analysis of large, curated medical datasets is promising for providing early detection, faster diagnosis, and more effective treatment using low-power Electrocardiography (ECG) monitoring devices information. However, accessing sensitive medical data from diverse sources is highly restricted since improper use, unsafe storage, or data leakage could violate a person's privacy. This work uses a Federated Learning (FL) privacy-preserving methodology to train AI models over heterogeneous sets of high-definition ECG from 12-lead sensor arrays collected from six heterogeneous sources. We evaluated the capacity of the resulting models to achieve equivalent performance compared to state-of-the-art models trained in a Centralized Learning (CL) fashion. Moreover, we assessed the performance of our solution over Independent and Identical distributed (IID) and non-IID federated data. Our methodology involves machine learning techniques based on Deep Neural Networks and Long-Short-Term Memory models. It has a robust data preprocessing pipeline with feature engineering, selection, and data balancing techniques. Our AI models demonstrated comparable performance to models trained using CL, IID, and non-IID approaches. They showcased advantages in reduced complexity and faster training time, making them well-suited for cloud-edge architectures.

Masters in Data Science

Sep 2018 – July 2022

Sapienza University – Rome, Lazio, Italy

This Master's program supplies a solid and modern preparation to understand and manage multi-side aspects of carrying out a complete data analysis, including acquisition, management and statistical analysis. (“Data Science Program by Sapienza University of Rome |Top Universities”)
• Cloud Computing
• Data Management of Data Science
• Fundamentals of Data Science and Laboratory
• Algorithmic Methods of data mining and Laboratory
• Optimization Methods of Machine Learning
• Big Data for Official statistics
• Neural Networks For Data Science Applications
• Data Privacy and Security
• Earth Observation data Analysis
• Advanced Machine Learning
All of the above subject related projects you can find on my educational github repository at https://github.com/ihassantariq/mdss

Bachelors of Science in Software Engineering

Oct 2012 – July 2016

Punjab University College of Information and Technology – Canal Road, Lahore, Pakistan

• Software Engineering
• Software Design and Architecture
• Database Systems
• Artificial Intelligence
• Human Computer Interaction

.NET Team Lead/Project Manager

July 2022 – March 2024

Dataduopoly, https://www.dataduopoly.com

• Worked on XplorFALMOUTH application which was designed to encourage exploration, engagement with local businesses and connect spaces, places and people together. My responsibilities constituted of managing the team, looking at requirements, making sure that the end functionality meets the requirement constrains, reviewing the pull requests, managing the whole cloud infrastructure on aws, building pipelines, deploying applications and working on difficult tasks which team is having problem with. Also, solely working on Xamarin.IOS native application, also jumping on Xamarin.Android and API tasks whenever needed
• Technologies:
• .NET Core
• Entity framework(Code First Approach)
• MSSQL
• Native Xamarin.IOS and Xamarin.Android
• AWS Elastic Beanstalk
• Angular
• Typescript
• Jira

.NET Team Lead/Project Manager

July 2020 – July 2022

Pryzebox

• Pryzebox started as mobile application to full fledge application with having presence on Shopify, Google Play Store and App store. Due to funding issues it has stopped and I removed it from all above places as suggested by Pryzebox CEO. My responsibilities constitutes of managing the team, looking at requirements, making sure that the end functionality meets the requirement constrains, reviewing the pull requests, managing the whole cloud infrastructure on azure, building pipelines and working on difficult tasks which team is having problem to complete.
• Technologies:
• .NET Core
• Entity framework (Code First Approach)
• PostgreSQL
• Xamarin.Forms(IOS, Android)
• MVVM
• Azure Devops
• Jira

Xamarin Developer

July 2020 – July 2022

Vivomi Inc. Snohomish, Washington

• Working with Vivomi Inc gave me experience developing mobile application as a team member. My responsibilities were building IOS and Android application on UI and UX. It gave me exposure working with startup which finds itself solving problem to help others.
• Technologies:
• Xamarin.Forms(IOS, Android)
• MVVM
• Azure Devops
• Jira

Software Engineer

July 2016 – Dec 2017

DevTract private limited, 257 – G4 Johar Town, Lahore

• Develop and support mobile application.
• Completing complex projects on time
• Maintaining good relationship with clients

Internee Software Engineer

July 2016 – Dec 2017

DevTract private limited, 257 – G4 Johar Town, Lahore

• Learned development in Xamarin Platform.
• Worked on extensive camera application and website builder applications.