Responsive image

Practicable Soundmapping: JavaScript enabled Edge Compute

TH Park, M Yoo
In this paper, we report on developments of the Citygram, a comprehensive sensor network platform for capturing, streaming, analyzing, mapping, visualizing, and providing easy access to spatiotemporal soundscape data. Launched in 2011, Citygram's recent strategic decision has resulted in system redesign to enable migration from a codebase built on multiple computer languages to a cross-platform single JavaScript codebase. Citygram now runs on V8 engines including standard web-browsers and in the node.js environment. The Citygram sensor network significantly alleviates problems concerning soundmapping complexities including operating system limitations, hardware dependency, software update and dissemination issues, data access mechanism, data visualization, and cost. This strategy has made practicable a key design philosophy for soundmapping: rapid sensor network growth for capturing spatiotemporally granular soundscapes. We summarize research and development for the following Citygram modules (1) cost-effective sensor module allowing high-value data transmission through edge compute paradigms, (2) machine learning module focusing on environmental sound classification, and (3) visualization and data access prototypes.
            
@inproceedings{2017_59,
  abstract = {In this paper, we report on developments of the Citygram, a comprehensive sensor network platform for capturing, streaming, analyzing, mapping, visualizing, and providing easy access to spatiotemporal soundscape data. Launched in 2011, Citygram's recent strategic decision has resulted in system redesign to enable migration from a codebase built on multiple computer languages to a cross-platform single JavaScript codebase. Citygram now runs on V8 engines including standard web-browsers and in the node.js environment. The Citygram sensor network significantly alleviates problems concerning soundmapping complexities including operating system limitations, hardware dependency, software update and dissemination issues, data access mechanism, data visualization, and cost. This strategy has made practicable a key design philosophy for soundmapping: rapid sensor network growth for capturing spatiotemporally granular soundscapes. We summarize research and development for the following Citygram modules (1) cost-effective sensor module allowing high-value data transmission through edge compute paradigms, (2) machine learning module focusing on environmental sound classification, and (3) visualization and data access prototypes.},
  address = {London},
  author = {Park, TH and Yoo, M},
  booktitle = {Proceedings of the International Web Audio Conference},
  editor = {Thalmann, Florian and Ewert, Sebastian},
  month = {August},
  pages = {},
  publisher = {Queen Mary University of London},
  series = {WAC '17},
  title = {Practicable Soundmapping: JavaScript enabled Edge Compute},
  year = {2017},
  ISSN = {2663-5844}
}