An embedded system capable of fusing sensory data is demanded for many portable or implantable microsystems. The continuous restricted Boltzmann machine (CRBM) is a probabilistic neural network not only capable of classifying data reliably but also amenable to very-large-scale-integration (VLSI) implementation. Although the embedded system based on the CRBM has been demonstrated with analog VLSI, the precision required by the learning algorithm is hardly achievable with analog circuits. Therefore, this paper investigates the feasibility of realizing the CRBM as a digital embedded system for fusing the sensory data of an electronic nose (eNose). The fusion here refers to data clustering and dimensional reduction that facilitates reliable classification. The capability of the CRBM to model different types of eNose data is first examined by MATLAB simulation. Afterward, the CRBM algorithm is customdesigned as a digital embedded system within an eNose microsystem. The functionality of the embedded CRBM system is then tested and discussed. With on-chip learning ability, the CRBM-embedded eNose is able to adapt its parameters in response to new data inputs or environmental changes.
This research output has an Altmetric Attention Score of 4. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 27 March 2018.
All research outputs
#8,262,981
of 25,377,790 outputs
Outputs from IEEE Transactions on Neural Networks and Learning Systems
#492
of 3,393 outputs
Outputs of similar age
#125,842
of 405,869 outputs
Outputs of similar age from IEEE Transactions on Neural Networks and Learning Systems
#7
of 50 outputs
Altmetric has tracked 25,377,790 research outputs across all sources so far. This one has received more attention than most of these and is in the 66th percentile.
So far Altmetric has tracked 3,393 research outputs from this source. They receive a mean Attention Score of 2.7. This one has done well, scoring higher than 83% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 405,869 tracked outputs that were published within six weeks on either side of this one in any source. This one has gotten more attention than average, scoring higher than 68% of its contemporaries.
We're also able to compare this research output to 50 others from the same source and published within six weeks on either side of this one. This one has done well, scoring higher than 80% of its contemporaries.
