Loading Events

« All Events

  • This event has passed.

CESG Seminar: Special Two-Part Presentation

March 29 @ 4:10 pm - 5:10 pm

Free

CESG Seminar
Friday, March 29, 2019
Emerging Technologies Building (ETB) 1037

Talk 1: Vamsi Amalladinne, Texas A&M University – “Coded Compressed Sensing for Unsourced Multiple Access”
Talk 2: Rajarshi, Texas A&M University – “QFlow: A Reinforcement Learning approach to High QoE Video Streaming at the Wireless Edge”

 

Vamsi Amalladinne’s “Coded Compressed Sensing for Unsourced Multiple Access”

Abstract:
This work describes a new scheme for the unsourced multiple-access communication problem. The envisioned divide-and-conquer approach leverages recent advances in compressive sensing and introduces a novel error correction paradigm to produce an uncoordinated access scheme along with a computationally efficient decoding algorithm. Within this framework, every active device first partitions its data into several sub-blocks and, subsequently, adds redundancy using a systematic linear block code. Compressive sensing techniques are then employed to recover sub-blocks up to a permutation of their order. The original messages are obtained by connecting pieces together using a low-complexity, tree-based algorithm. Properties of the proposed scheme are explored.

Biography:
Vamsi Amalladinne received his M.Tech. degree in Electrical Engineering with specialization in Signal Processing and Communications from the Indian Institute of Technology Kanpur, India, in 2014. During 2014 to 2016, he was employed as a Firmware Developer for CDMA systems with Qualcomm India Private Limited, Hyderabad. Currently, he is pursuing his Ph.D. degree under the supervision of Prof. Krishna Narayanan at Texas A&M University. His research interests lie in the areas of coding theory, compressive sensing and cooperative communication.

 

 

 

 

 

 

 

 

 

Rajarshi Bhattacharyya’s “QFlow: A Reinforcement Learning approach to High QoE Video Streaming at the Wireless Edge”

Abstract:
Software reconfigurable infrastructure has become increasingly mainstream to the point that dynamic per packet and per flow decisions are possible at multiple layers of the communications stack. Exploiting such re-configurability requires the design of a system that can enable a configuration, measure the impact on the application performance (Quality of Experience), and adaptively select a new configuration. Effectively, this feedback loop is a Markov Decision Process whose parameters are unknown. The goal of this work is to design, develop and demonstrate QFlow that instantiates this feedback loop as an application of reinforcement learning (RL). Our context is that of reconfigurable (priority) queueing, and we use the popular application of video streaming as our use case. We develop both model-free and model-based RL approaches that are tailored to the problem of determining which clients should be assigned to which queue at each decision period. Through experimental validation, we show how the RL-based control policies on QFlow are able to schedule the right clients for prioritization in a high-load scenario to outperform the status quo as well as the best known solutions with over 25% improvement in QoE, and a perfect QoE score of 5 over 85% of the time.

Biography:
Rajarshi Bhattacharyya is a doctoral student in the department of Electrical and Computer Engineering at Texas A&M University where he is working with Dr. Srinivas Shakkottai. His research at Texas A&M has been on wireless communication networks with focus on the space of cross-layer optimization of reconfigurable infrastructure to maximize user-perceived Quality of Experience (QoE) under the resource constraints of the Wireless Edge.

 

 

 

 

 

 

 

Pizza Provided!

Details

Date:
March 29
Time:
4:10 pm - 5:10 pm
Cost:
Free

Venue

Emerging Technologies Bldg., 1037
101 Bizzell St.
College Station, TX 77843
Phone:
9794585005
Website:
tx.ag/GENI