SearcharxivSearch

arXiv subjects

William Payne

Publications and source records attributed to William Payne.

3 recordsLinked to original sources

Making Sense of Machine Learning: Integrating Youth's Conceptual, Creative, and Critical Understandings of AI

Understanding how youth make sense of machine learning and how learning about machine learning can be supported in and out of school is more relevant than ever before as young people interact with machine learning powered applications everyday; while connecting with friends, listening to music, playing games, or attending school. In this symposium, we present different perspectives on understanding how learners make sense of machine learning in their everyday lives, how sensemaking of machine learning can be supported in and out of school through the construction of applications, and how youth critically evaluate machine learning powered systems. We discuss how sensemaking of machine learning applications involves the development and integration of conceptual, creative, and critical understandings that are increasingly important to prepare youth to participate in the world.

cs.CY

Impact of Device Thermal Performance on 5G mmWave Communication Systems

5G millimeter wave (mmWave) cellular networks have been reported to deliver 1-2 Gbps downlink throughput, via speed-tests. However, these speed-tests capture only a few seconds of throughput and are not representative of sustained throughput over several minutes. We report the first measurements of sustained throughput in three cities, Miami, Chicago, and San Francisco, where we observe throughput throttling due to rising skin temperature of the phone when it is connected to a deployed 5G mmWave base-station (BS). Radio Resource Control (RRC) messaging between the phone and the BS indicates the reduction in the number of aggregated mmWave channels from 4 to 1 followed by a switch to 4G. We corroborate these measurements with infra-red images as the phone heats up. Thus, mmWave throughput will be limited not by network characteristics but by device thermal management.

cs.NI

A Comparison Study of Cellular Deployments in Chicago and Miami Using Apps on Smartphones

Cellular operators have begun deploying 5G New Radio (NR) in all available bands: low (< 1 GHz), mid (1 - 6 GHz), and high (> 24 GHz) to exploit the different capabilities of each. At the same time, traditional 4G Long Term Evolution (LTE) deployments are being enhanced with the addition of bands in the unlicensed 5 GHz (using License Assisted Access, or LAA) and the 3.5 GHz Citizens Broadband Radio Service (CBRS) resulting in throughput performance comparable to 5G in mid-band. We present a detailed study comparing 4G and 5G deployments, in all bands in Chicago, and focused mmWave measurements and analysis in Miami. Our methodology, based on commercial and custom apps, is scalable for crowdsourcing measurements on a large scale and provides detailed data (throughput, latency, signal strength, etc.) on actual deployments. Our main conclusions based on the measurements are (i) optimized 4G networks in mid-band are comparable in both throughput and latency to current deployments of 5G (both standalone (SA) and non-standalone (NSA)) and (ii) mmWave 5G, even in NSA mode, can deliver multi-Gbps throughput reliably if the installation is dense enough, but performance is still brittle due to the propagation limitations imposed by distance and body loss. Thus, while 5G demonstrates significant early promise, further work needs to be done to ensure that the stated goals of 5G are met.

cs.NI