Machine Learning

Machine Learning to Manage Cellular Network Faults and Improve Voice-Over-LTE Service

We present two examples of using machine learning to improve end-user quality of experience (QoE) in cellular networks operating today. In particular, we demonstrate how to automate the clearing of operational faults in outdoor networks and compensation of signal impairments in indoor networks for voice-over-LTE (VoLTE) applications. Our proposed methods are compatible with 3GPP LTE Release 8 and higher.

Profs. Gerstlauer and John Receive Collaborative NSF Grant on Predictive Modeling for Next-Generation Heterogeneous Computer System Design

Texas ECE Professors Andreas Gerstlauer and Lizy K. John together with collaborators at the University of California, Riverside have been awarded a $1M grant by the National Science Foundation (NSF) to study application of machine learning techniques for performance and power prediction in early design stages of future computer systems.

The project is described below:

Texas ECE PhD Alum Jette Henderson Wins Best Student Paper at KDD MLMH workshop on Machine Learning for Healthcare

Texas ECE alumna Jette Henderson, who completed her PhD in August, received the Best Student Paper award for the paper "PIVETed-Granite: Computational Phenotypes through Constrained Tensor Factorization" at the KDD MLMH Workshop on Machine Learning for Healthcare in London in August. Jette worked under the supervision of Texas ECE professor Joydeep Ghosh. The paper uses a special kind of tensor factorization that is guided by supporting evidence from PubMed, a huge repository of medical literature, to extract meaningful insights from electronic health records.

Diligent Robotics Brings Socially Intelligent Robots to Healthcare Teams

Picture your typical hospital scene: Patients being admitted at the front desk, doctors performing consultations, nurses administering medicine … and robots wandering the hallways toward the supply closet?

Robots in the storeroom may not be the norm quite yet, but it’s happening in Austin thanks to WNCG professor Andrea Thomaz and her company, Diligent Robotics.

Machine Learning to Improve Success Rates for Handovers from Sub-6 GHz LTE to Millimeter Wave Bands

Transmission over millimeter wave (mmWave) frequency bands is being adopted in fifth generation (5G) wireless communications.  Even though the sub-6 GHz frequency bands continue to dominate deployments due to their better ability to penetrate and provide in-building coverage, the handover between mmWave and sub-6 GHz frequency bands is nonetheless inevitable to support higher data rates.  The cost of a handover is a reduction in data rate, which 5G promises to increase.

Quadratic Maximization Problems

Several optimization problems in machine learning, data mining and graph theory can be expressed as quadratic maximization problems, subject to integrality, positivity, or sparsity constraints. These include Sparse PCA, Densest Subgraph, Nonnegative matrix factorization, MaxCut, Maximum clique and many others. These problems are known to be computationally intractable and, in many cases, hard to approximate. WNCG Profs.

Community Detection in Massive Graphs

WNCG Ph.D Students Dimitris Papailiopoulos and Yannis Mitliagkas, along with WNCG Professors Alex Dimakis and Constantine Caramanis, have developed an efficient low-rank framework for finding dense components of graphs with billions of connections.


Subscribe to RSS - Machine Learning