Probabilistic Sensing: Intelligence in Data Sampling

TL;DR

This paper introduces a probabilistic sensing paradigm inspired by biological systems, enabling real-time, energy-efficient, lossless data sampling with significant operational time savings.

Contribution

It presents a novel probabilistic neuron-based sensing system that improves energy efficiency and real-time decision-making in data acquisition.

Findings

Achieved 0.41% normalized mean squared error in seismic data

Saved 93% of active operation time and samples

Enabled microsecond response times for real-time sensing

Abstract

Extending the intelligence of sensors to the data-acquisition process - deciding whether to sample or not - can result in transformative energy-efficiency gains. However, making such a decision in a deterministic manner involves risk of losing information. Here we present a sensing paradigm that enables making such a decision in a probabilistic manner. The paradigm takes inspiration from the autonomous nervous system and employs a probabilistic neuron (p-neuron) driven by an analog feature extraction circuit. The response time of the system is on the order of microseconds, over-coming the sub-sampling-rate response time limit and enabling real-time intelligent autonomous activation of data-sampling. Validation experiments on active seismic survey data demonstrate lossless probabilistic data acquisition, with a normalized mean squared error of 0.41%, and 93% saving in the active operation time of the system and the number of generated samples.