Graphics Reference
In-Depth Information
and recognition systems, users are interested in both short-term performance and
long-term performance.
12.7 Conclusion
In this chapter, we have introduced the emerging area of adaptive stream mining
systems for embedded computer vision, and we have discussed important research
challenges in this area. We have emphasized key challenges in integrating methods of
Dynamic Data Driven Applications Systems (DDDAS) rigorously in the design and
implementation process for the targeted class of embedded computer vision systems.
We have discussed the Lightweight Dataflow for Dynamic Data-Driven Application
Systems Environment (LiD4E) as a recently-introduced design tool for experiment-
ing with DDDAS-enabled stream mining methods. As a concrete example of recent
advances in DDDAS-enabled adaptive stream mining, we have presented a case
study involving learning based on multi-armed bandits. As motivated in this chapter,
addressing the future challenges of adaptive stream mining systems for embedded
computer vision will require interdisciplinary advances in areas that include machine
learning, DDDAS design methods, and distributed embedded systems.
Acknowledgments
This work is supported by the USAir Force Office of Scientific Research under
the DDDAS Program.
References
1. Amini L, Andrade H, Eskesen F, King R, Park Y, Selo P, Venkatramani C (2005) The stream
processing core. Technical Report RSC 23798
2. Atan O, Andreopoulos Y, Tekin C (2014) Bandit framework for systematic learning in wireless
video-based face recognition. In: Proceedings of the international conference on acoustics,
speech, and signal processing
3. Auer P, Cesa-Bianchi N, Fischer P (2002) Finite-time analysis of the multiarmed bandit prob-
lem. Mach Learn 47(2-3):235-256
4. Babcock B, Babu S, Datar M, Motwani R (2003) Chain: operator scheduling for memory
minimization in data stream systems. In: ACM SIGMOD
5. Babcock B, Datar M, Motwani R (2003) Cost-efficient mining techniques for data streams. In:
Proceedings of the workshop on management and processing of data streams
6. Balazinska M, Balakrishnan H, Madden S, Stonebraker M (2005) Fault tolerance in the bore-
alis distributed stream processing system. In: Proceedings of the international conference on
management of data
7. Becker BC, Ortiz EG (2008) Evaluation of face recognition techniques for application to
facebook. In: Proceedings of the IEEE international conference on automatic face and gesture
recognition, pp 1-6
8. Bhattacharyya SS, Deprettere E, Leupers R, Takala J (eds) (2013) Handbook of signal process-
ing systems, 2nd edn. Springer, New York.
http://dx.doi.org/10.1007/978-1-4614-6859-2.
ISBN: 978-1-4614-6858-5 (Print); 978-1-4614-6859-2 (Online)
