Optimizing Exploratory Workflows for Embedded Platform Trace Analysis and its Application to Cellular Modems

Ah Sue J, Brand P, Falk J, Hasholzner R, Teich J (2019)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2019

Publisher: Springer

City/Town: New York, NY, USA

Pages Range: 1-12

Conference Proceedings Title: HCII 2019 Late Breaking Work Papers Proceedings

Event location: Orlando, Florida, USA US

DOI: 10.1007/978-3-030-30033-3_10

Abstract

As 5G wireless communication technology will be deployed in the next few years, an increasing amount
of data becomes available from mobile devices tested out in the field. Exploiting this data, recent
investigations show the potential to improve the wireless modem design and performance using data-
centric approaches, e.g., power optimization with machine learning (ML) algorithms [1]. As depicted in
Figure 1, such data-centric workflows are exploratory and iterative by nature. For instance, time pattern
identification is performed by domain experts to derive assumptions on potential optimizations and these
assumptions are continuously refined during multiple iterations of data collection and exploration. In this
context, we propose 3 ideas to increase the exploration speed: (i) a methodology to minimize the data
pre-processing duration in each iteration, (ii) a novel entropy-based data interaction technique for visual
event sequence exploration and (iii) a similarity measure to perform subsequence matching in order to
identify frequent modem behaviors to be optimized.

Authors with CRIS profile

Jonathan Ah Sue Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design) Peter Brand Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design) Jürgen Teich Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)

Involved external institutions

Intel Mobile Communications DE Germany (DE)

How to cite

APA:

Ah Sue, J., Brand, P., Falk, J., Hasholzner, R., & Teich, J. (2019). Optimizing Exploratory Workflows for Embedded Platform Trace Analysis and its Application to Cellular Modems. In HCII 2019 Late Breaking Work Papers Proceedings (pp. 1-12). Orlando, Florida, USA, US: New York, NY, USA: Springer.

MLA:

Ah Sue, Jonathan, et al. "Optimizing Exploratory Workflows for Embedded Platform Trace Analysis and its Application to Cellular Modems." Proceedings of the 21st Int. Conf. on Human-Computer Interaction, Orlando, Florida, USA New York, NY, USA: Springer, 2019. 1-12.

BibTeX: Download