Location Estimation in Sensor Networks - Unknown Noise Parameters

Unknown Noise Parameters

A noise model may be sometimes available while the exact PDF parameters are unknown (e.g. a Gaussian PDF with unknown ). The idea proposed in for this setting is to use two thresholds, such that sensors are designed with, and the other sensors use . The processing center estimation rule is generated as follows:

$\hat{q}_1=\frac{2}{N}\sum\limits_{n=1}^{N/2}m_A(x_n), \quad \hat{q}_2=\frac{2}{N}\sum\limits_{n=1+N/2}^{N}m_B(x_n)$

$\hat{\theta}=\frac{F^{-1}(\hat{q}_2)\tau_1-F^{-1}(\hat{q}_1)\tau_2}{F^{-1}(\hat{q}_2)-F^{-1}(\hat{q}_1)},\quad F(x)=\frac{1}{\sqrt{2\pi}}\int\limits_{x}^{\infty}e^{-v^2/2}dw$

As before, prior knowledge is necessary to set values for to have an MSE with a reasonable factor of the unconstrained MLE variance.

Read more about this topic: Location Estimation In Sensor Networks

Famous quotes containing the words unknown, noise and/or parameters:

“So that this beautiful realm of hers was held in her mind extended, or lengthened: it had been finite, bounded, known utterly and in every detail, self-enclosed ... but now it lapped and rippled out and upwards beyond there into hinterlands that were like unknown possibilities in her own mind.”
—Doris Lessing (b. 1919)

“While we were thus engaged in the twilight, we heard faintly, from far down the stream, what sounded like two strokes of a woodchopper’s axe, echoing dully through the grim solitude.... When we told Joe of this, he exclaimed, “By George, I’ll bet that was a moose! They make a noise like that.” These sounds affected us strangely, and by their very resemblance to a familiar one, where they probably had so different an origin, enhanced the impression of solitude and wildness.”
—Henry David Thoreau (1817–1862)

“What our children have to fear is not the cars on the highways of tomorrow but our own pleasure in calculating the most elegant parameters of their deaths.”
—J.G. (James Graham)