Usama Masood

Usama Masood
AT&T · Labs Research

▪️ Network Analytics & Automation ▪️ AI ▪️ Machine Learning

About

22
Publications
15,684
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
615
Citations
Citations since 2017
21 Research Items
615 Citations
2017201820192020202120222023050100150200250
2017201820192020202120222023050100150200250
2017201820192020202120222023050100150200250
2017201820192020202120222023050100150200250
Introduction
Usama Masood is currently working at AT&T Labs as a Senior MTS in the Network Analytics and Automation organization. He is a PhD researcher with cross-domain knowledge in both Machine Learning and Wireless Networks. He has a track record of innovation and 7+ years of research and industry experience in leading multi-disciplinary teams of data scientists, software engineers and RAN engineers, designing Artificial Intelligence (AI)-based solutions for emerging networks.
Additional affiliations
May 2021 - June 2022
T-Mobile USA
Position
  • Technology Strategy Intern: AI/ML & 5G
August 2018 - July 2022
University of Oklahoma
Position
  • Graduate Researcher
Description
  • • Research and design data-driven Zero Touch Deep Automation solutions for Future Cellular Networks • Developing state-of-the-art 5G Testbed (TurboRAN), enabling unprecedented experimental research on multi-band, multi-tier artificial intelligence enabled wireless networks of future
September 2016 - May 2018
Lahore University of Management Sciences
Position
  • Research Assistant
Education
August 2018 - July 2022
University of Oklahoma
Field of study
  • Electrical & Computer Engineering
September 2014 - December 2016
Lahore University of Management Sciences
Field of study
  • Electrical Engineering

Publications

Publications (22)
Article
Full-text available
In modern wireless communication systems, radio propagation modeling to estimate pathloss has always been a fundamental task in system design and optimization. The state-of-the-art empirical propagation models are based on measurements in specific environments and limited in their ability to capture idiosyncrasies of various propagation environment...
Conference Paper
Full-text available
Fault diagnosis is turning out to be an intense challenge due to the increasing complexity of the emerging cellular networks. The root-cause analysis of coverage-related network anomalies is traditionally carried out by human experts. However, due to the vast complexity and the increasing cell density of the emerging cellular networks, it is neithe...
Article
Cough acoustics contain multitudes of vital information about pathomorphological alterations in the respiratory system. Reliable and accurate detection of cough events by investigating the underlying cough latent features and disease diagnosis can play an indispensable role in revitalizing the healthcare practices. The recent application of Artific...
Preprint
Full-text available
In modern wireless communication systems, radio propagation modeling to estimate pathloss has always been a fundamental task in system design and optimization. The state-of-the-art empirical propagation models are based on measurements in specific environments and limited in their ability to capture idiosyncrasies of various propagation environment...
Article
Full-text available
Prior to standardization, new features, algorithms, and solutions have to be rigorously evaluated and verified using different methods. In this regard, testbeds are considered as one of the most important and effective experimental platforms for performing tests, thus paving the way towards the real-world implementation of many solutions, from the...
Article
Full-text available
Diminishing viability of manual fault diagnosis in the increasingly complex emerging cellular network has motivated research towards artificial intelligence (AI)-based fault diagnosis using the minimization of drive test (MDT) reports. However, existing AI solutions in the literature remain limited to either diagnosis of faults in a single base sta...
Conference Paper
Full-text available
Minimization of Drive Test (MDT) reports are a key enabler for Machine Learning (ML)-based zero-touch automation envisioned for emerging cellular networks. However, due to numerous factors, the MDT reports are spatially sparse in nature. This sparsity undermines the performance of ML models that are built on the MDT data to estimate and optimize ne...
Article
Full-text available
Background The inability to test at scale has become humanity's Achille's heel in the ongoing war against the COVID-19 pandemic. A scalable screening tool would be a game changer. Building on the prior work on cough-based diagnosis of respiratory diseases, we propose, develop and test an Artificial Intelligence (AI)-powered screening solution for C...
Preprint
Full-text available
Current LTE network is faced with a plethora of Configuration and Optimization Parameters (COPs), both hard and soft, that are adjusted manually to manage the network and provide better Quality of Experience (QoE). With 5G in view, the number of these COPs are expected to reach 2000 per site, making their manual tuning for finding the optimal combi...
Preprint
Full-text available
Mobile cellular network operators spend nearly a quarter of their revenue on network maintenance and management. A significant portion of that budget is spent on resolving faults diagnosed in the system that disrupt or degrade cellular services. Historically, the operations to detect, diagnose and resolve issues were carried out by human experts. H...
Preprint
Full-text available
Inability to test at scale has become Achille's heel in humanity's ongoing war against COVID-19 pandemic. An agile, scalable and cost-effective testing, deployable at a global scale, can act as a game changer in this war. To address this challenge, building on the promising results of our prior work on cough-based diagnosis of a motley of respirato...
Preprint
Full-text available
5G is bringing new use cases to the forefront, one of the most prominent being machine learning empowered health care. Since respiratory infections are one of the notable modern medical concerns and coughs being a common symptom of this, a system for recognizing and diagnosing infections based on raw cough data would have a multitude of beneficial...
Poster
Full-text available
➢ Motivation In modern wireless communication systems, radio propagation modeling has always been a fundamental task in system design and performance optimization. These models are used in cellular networks and other radio systems to estimate the pathloss or the received signal strength (RSS) at the receiver or characterize the environment traverse...
Conference Paper
Full-text available
In modern wireless communication systems, radio propagation modeling has always been a fundamental task in system design and performance optimization. These models are used in cellular networks and other radio systems to estimate the pathloss or the received signal strength (RSS) at the receiver or characterize the environment traversed by the sign...
Article
In this letter, we propose a novel network health estimation technique for wireless cellular networks. The proposed scheme makes use of graph signal processing techniques to estimate network health over the entire coverage area with sparse availability of measured data. To achieve this objective, we solve an optimization problem on graph using prox...
Conference Paper
Full-text available
The growing subscriber Quality of Experience demands are posing significant challenges to the mobile cellular network operators. One such challenge is the autonomic detection of sleeping cells in cellular networks. Sleeping Cell (SC) is a cell degradation problem, and a special case in Cell Outage Detection (COD) because it does not trigger any ala...
Thesis
Mobile wireless network service providers make tremendous efforts to ensure wide network coverage for their customers. Service providers routinely monitors their networks to detect RF coverage holes. They rely on drive tests, regularly scheduled visits to the equipment sits, use of alarms and sensors, reports generated by diagnostic software within...

Network

Cited By

Projects

Projects (7)
Project
A space communication network suitable for planned lunar missions requires a new architectural paradigm that is dynamic, scalable, and capable of supporting diverse mission types at unprecedented communication speed with high reliability, continuous coverage, and minimum latency. Considering the low data rate of radio frequency (RF) systems and the outage vulnerability of optical channels, we propose a hybrid approach, incorporating both RF and optical communication elements within a smart networking framework. Our theoretical and experimental effort will integrate RF and optical communication systems for small satellites (SmallSats) and will design an encompassing network architecture that leverages this combination among Earth stations, a LEO SmallSat constellation, the Lunar Gateway, and Moon explorers. The project will pursue three key research thrusts: (i) Hybrid RF/optical communication system design and integration, (ii) Network design for lunar communication architecture with hybrid RF/optical links, (iii) Systemlevel testing and evaluations. We will investigate the proposed architecture from several perspectives including operational frequency bands, data rates, integration, signal acquisition, quality of service, power requirements, appropriate protocols such as delay/disruption tolerant networking (DTN), access strategies, outage recovery, and communication-aware SmallSat constellation topologies. RF/optical communication modalities and low-cost SmallSats are both growing interests of NASA and bring critical forward progress to important NASA missions, partnering international space agencies, and private industry, such as Iridium, OneWeb, and Starlink (SpaceX). Funding Agency: NASA Director/PI: Dr. Andrew Arena Science PI: Dr. Sabit Ekin NASA MD: HEOMD, STMD, SMD
Project
With anticipated conglomeration of technologies that have to be leveraged to achieve the performance expected form emerging wireless networks, the complexity of operation and resultant resource inefficiency and shrinking profit margins are to become the biggest challenges in 5G and beyond. This means automation of the post-deployment operation and optimization for reducing costs, handling complexity and maximizing resources efficiency will not only become a necessity, but the future mobile cellular networks’ (MCN) technical and commercial viability may hinge on it. The overarching goal of this project is to address these challenges by building an Artificial Intelligence (AI)- Based Self Organizing Network (SON) Framework for Fully Autonomous Operation and Optimization of 5G and beyond cellular networks, hereafter referred to as I-NET. The proposed research towards I-NET builds on two observations: 1) Continual adaptation of Configuration and Optimization Parameters (COPs) is needed as user behavior is dynamic and is currently treated as largely unknown; 2) The adaptation of COPs currently relies on hit and trial or heuristics based SON features because relationships between COPs and performance metrics also remain largely unknown. I-NET will enable a paradigm shift from the traditional semi-manual sub-optimal operation towards autonomous & highly optimal operation in next-generation MCNs such as 5G and beyond.