Maaz Bin Safeer Ahmad

Research Associate at LUMS, 2013 - Present
Research Assistant at LUMS, 2012 - 2013
Research Intern at LUMS, Summer 2012
Web Developer at ProtonLabs, 2011 - 2012
B.S. Computer Science from NUCES, 2010 - 2014
Teaching Assistant for Introduction to Computer Science course at NUCES, Fall 2012

About Me

I am a final year undergraduate student majoring in Computer Science from the National University of Computer & Emerging Sciences, Lahore, and a research associate at NEWT Lab, Lahore University of Management Sciences. My primary research interests are computing for the developing world, machine learning, artificial intelligence and systems/networking. Currently my work at NEWT focuses on real-time diseases surveillance, early outbreak detection and cold chain equipment management. I am researching in collaboration with Dr. Umar Saif, Dr. Lakshminarayanan Subramanian and Dr. Richard Anderson.

Download my CV

Research Projects

[1] Disease Surveillance and Outbreak Detection using Newspaper Articles

With Dr. Lakshminarayanan and Dr. Umar Saif

Due to the unavailability of complete and timely reports from hospitals and health facilities in developing regions, there is a need for disease surveillance systems which rely on readily available unconventional data sources such as internet media. We are working to build an autonomous system which utilizes local newspaper articles for early outbreak detection and monitors disease spread at a fine-grained level. The system removes erroneous articles by cross-referencing the information within amongst other sources. Each validated piece of information is then tagged with the appropriate date and location. A trained model uses past data to compute the severity of the spread. The system is currently being designed for long term dengue and malaria surveillance in Pakistan.

[2] Intelligent Disease Surveillance System for Punjab

With Dr. Umar Saif

I am working in collaboration with the Punjab IT Board to develop and sustain a web based analytics module for intelligent, real-time disease surveillance in Punjab. The module is fed incoming reports (geo-tagged patients data) from a network of government correspondents working at different hospitals and health facilities across Punjab. Spatio-temporal analysis is performed on the data to identify clusters of activity and generate appropriate outbreak alerts and warnings. The results are displayed on a Google map for easy visualization of disease spread and outbreak severity. Furthermore, we have overlapped the UC* grid for major cities such as Lahore and Multan on our map so that affected regions can be easily identified right health offices can be promptly notified. The system, currently operational for Dengue, Dengue Larvae and Measles, is being expanded to 10 diseases. Our system is being rigorously used by the Punjab government in their battle against viral diseases. Click here to see a public interface of this system.

*UC is the smallest administrative area, spanning approximately 1000 to 5000 houses.

[3] Cold Chain Equipment Management For the Developing World

With Dr. Richard Anderson and Dr. Umar Saif

We are working to create software to support immunization logistics for developing regions. Our goal is to build an adaptive web based application that can seamlessly integrate into the different existing health informatics systems across the developing countries. The software will provide powerful analytical and modeling functions to aid in effective administration of the vaccine inventory. We are working with several countries across Africa and many states in India to learn the typical challenges and identify recurring problems. Furthermore, we are attempting to establish a set of CCEM standards appropriate for developing countries. The system is intended to be used by managers and administrators in addition to domain expert. This provides the challenge of designing a robust yet easy to understand mechanism for specifying the model and its constraints.

[4] Characterizing dengue spread and severity using internet media sources

With Dr. Lakshminarayanan and Dr. Umar Saif

In 2011, Pakistan was hit by one of its deadliest dengue outbreaks resulting in hundreds of fatalities across the country. This epidemic could have been largely prevented if it weren't for the low awareness and monitoring of the disease prior to the outbreak. This provided us with the motivation to build a system which monitors the spread and severity of diseases using internet media. In developing regions, often enough infrastructure is not available to track and monitor each disease using traditional methods and thus we need low-maintenance and low-cost systems which can generate appropriate warnings and detect an outbreak in its early stages. Our research resulted in the development of DengueBreaks, a system which uses newspaper reports to estimate the activity of Dengue in Pakistan.

Click here to view our system or read our paper for more details.


  • Talal Ahmad, Nabeel Abdur Rehman, Fahad Pervaiz, Shankar Kalyanaraman, Maaz Bin Safeer Ahmad, Sunandan Chakraborty, Umar Saif, Lakshminarayanan Subramanian. "Characterizing Dengue Spread and Severity using Internet Media Sources", Proceedings of the 3rd ACM Symposium on Computing for Development(DEV) [Read this paper]


Neighbourhood for Emerging World Technologies (NEWT)
Computer Science Department
Lahore University of Management Sciences
Lahore, Pakistan