Personalized Emotion-Aware Video Streaming for the Elderly
We consider the problem of video therapy services for the elderly based on their current emotional status. Given long hours watching TV in the elder population, most of the existing TV services are not geared for them. The elderly cannot tolerate complexity and negativity due to decline in cognitive abilities. In addition, the program is not adapted to the user’s current emotional status. As a result, existing TV services can not achieve optimal performance across a broad set of user types and context. To provide content tailored to individual needs, and interests of the elderly, caregivers have to select an appropriate program manually. However, this can not scale well due to shortage of caregivers and high monetary cost. We present the personalized emotion-aware video streaming system, a redesign of conventional TV system to provide appropriate program flexibly, efficiently and responsively. Our proposed architecture adds video affective profiling, real-time emotion detection and Markov decision process based video program generation to the streaming service to this end. We present a complete implementation of our design. Trace-driven simulation has shown the effectiveness of our system.
This research is supported by the National Research Foundation, Prime Minister’s Office, Singapore under its IDM Futures Funding Initiative; Nanyang Technological University, Nanyang Assistant Professorship and the Interdisciplinary Graduate School, Nanyang Technological University, Singapore.
- 2.National Collaborating Centre: Dementia: A nice-scie guideline on supporting people with dementia and their carers in health and social care. British Psychological Society (2007)Google Scholar
- 4.Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent developments in opensmile, the munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM International Conference on Multimedia, MM 2013, pp. 835–838. ACM, New York (2013)Google Scholar
- 6.Gao, G., Wen, Y., Hu, H.: Qdlcoding: Qos-differentiated low-cost video encoding scheme for online video service. In: IEEE INFOCOM 2017 - IEEE Conference on Computer Communications, pp. 1–9, May 2017Google Scholar
- 9.Hu, H., Jin, Y., Wen, Y., Chua, T.S., Li, X.: Toward a biometric-aware cloud service engine for multi-screen video applications. In: Proceedings of the 2014 ACM Conference on SIGCOMM. SIGCOMM 2014, pp. 581–582. ACM, New York (2014)Google Scholar
- 14.Lux, M., Chatzichristofis, S.A.: Lire: lucene image retrieval: an extensible java CBIR library. In: Proceedings of the 16th ACM International Conference on Multimedia, pp. 1085–1088. ACM (2008)Google Scholar
- 15.Robinson, J., Godbey, G.: Time for Life: The Surprising Ways Americans Use Their Time. Penn State Press (2010)Google Scholar
- 16.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge, MA (2017)Google Scholar
- 17.Zhu, Y., Hanjalic, A., Redi, J.A.: QoE prediction for enriched assessment of individual video viewing experience. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 801–810. ACM (2016)Google Scholar