ABSTRACT
The need for online meetings increased drastically during the COVID-19 pandemic. Wearing headphones for this purpose makes it difficult to know when a headphone wearing person is available or in a meeting. In this work, we explore the design possibilities of headphones as wearable public displays to show the current status or additional information of the wearer to people nearby. After two brainstorming sessions and specifying the design considerations, we conducted an online survey with 63 participants to collect opinions of potential users. Besides the preference of the colors red and green as well as using text to indicate availability, we found that only 54 % of our participants would actually wear headphones with public displays attached. The benefit of seeing the current availability status of a headphone-wearing person in an online meeting or phone call scenario were nonetheless mentioned even by participants that would not use such headphones. © 2022 ACM.
ABSTRACT
Time series forecasting with additional spatial information has attracted a tremendous amount of attention in recent research, due to its importance in various real-world applications on social studies, such as conflict prediction and pandemic forecasting. Conventional machine learning methods either consider temporal dependencies only, or treat spatial and temporal relations as two separate autoregressive models, namely, space-time autoregressive models. Such methods suffer when it comes to long-term forecasting or predictions for large-scale areas, due to the high nonlinearity and complexity of spatio-temporal data. In this paper, we propose to address these challenges using spatio-temporal graph neural networks. Empirical results on Violence Early Warning System (ViEWS) dataset and U.S. Covid-19 dataset indicate that our method significantly improved performance over the baseline approaches. © 2021 ACM.