Home / Talks & Presentations / IMAGEin Ecology

Abstract There exist many natural phenomena where direct measurement is either impossible or extremely invasive. To obtain approximate measurements of these phenomena we can build prediction models based on other sensing modalities such as features extracted from data collected by an imager. These models are derived from controlled experiments performed under laboratory conditions, and can then be applied to the associated event in nature. In this paper we explore various different methods for generating such models and discuss their accuracy, robustness, and computational complexity. Given sufficiently computationally simple models, we can eventually push their computation down towards the sensor nodes themselves to reduce the amount of data required to both flow through the network and be stored in a database. The addition of these models turn in-situ imagers into powerful biological sensors, and image databases into useful records of biological activity. I presented this presentation with Teresa Ko.

Resources Slides (Power Point) (3.5MB) Slides (PDF) (6.8MB)

CENS [1] is a major research enterprise engaged in the development of wireless sensor systems and the application of revolutionary sensing technology to critical scientific and social applications. Each year, members of the Center and partners from across the world gather for a day-long symposium [2] to communicate recent results and accomplishments in this rapidly developing field. We invite you to join us as we highlight our measurement and sensing technologies and look forward to future developments.

[1] Center for Embedded Networked Sensing (CENS)
[2] CENS Annual Research Review 2007