基於連續型波茲曼模型之電子鼻氣體訊號辨識方法研究

Research in Recognition Method Based on Continuous Restricted Boltzmann Machine

黃建銘(Chien-Ming Huang)

指導教授 ： 陳新

國立清華大學/電機資訊學院/電機工程學系/碩士(2014年)

摘要

近年來電子鼻系統於醫學方面的應用逐漸受到重視，以本論文的應用為
例，即是將電子鼻感測器陣列應用於肺炎氣體感測。藉由感測病人呼出的氣
體，來判別病人是否有感染肺炎。但是目前的感測器對於肺炎病菌的代謝氣體
仍不夠敏感，導致電子鼻得到的氣體資料中，特徵不夠明顯，導致有相當程度
的混雜。因此，本論文提出以機率模型的方式來學習肺炎氣體資料，希望可以
進一步分析混雜的肺炎氣體資料。連續侷限性波茲曼模型正是一種機率模型，
可用以分群、分類與重建。使用其分群功能時，可以將資料經由學習，重新投
影至高維或低維，使資料更容易被分類；當CRBM被加上一個新的神經元 –
標籤神經元時，則可以做為一個完整的分類器；當CRBM著重於重建功能時，
則可以透過能量函數找出重建點的機率分布，並以此作為貝氏分類器的分類依
據。
此外，本論文使用過去提出之類比CRBM晶片架構為基礎，建立一硬體平
台，用以驗證CRBM之學習方法實現。若能實現，則可以進一步使用此硬體平
台與前端感測器陣列結合，完成一具有學習能力之感測器系統。由於過去設計
之CRBM類比晶片中未加入學習機制，所以必須透過外部的連結(資料擷取卡
與FPGA卡)，來組成一個迴圈，作為學習時，資料與參數的循環機制，也就是
Chip-in-a-Loop學習的機制。

關鍵字

連續侷限性波茲曼模型 ； 電子鼻 ； 肺炎菌種 ； 辨識

並列摘要

In recent years, the biomedical application of electronic nose sensor system has
been noticed, for example, this thesis will focus on the recognition of pneumonia data
from patients. However, the sensitivity of sensor array is not high enough so that the
captured data is somewhat overlapped. In order to analyze these data further, this
thesis proposes some methods to classify them with probabilistic model, such as
CRBM. Continuous Restricted Boltzmann Machine (CRBM) is a generative
probabilistic model that can cluster and classify, and that can reconstruct data
distribution from training data. Therefore, there are 3 possible ways to classify
pneumonia data by CRBM. First, as a clusterer, CRBM can re-project data into higher
-dimensional space or lower-dimensional space so that the data will be classified more
easily. Secondly, as a classifier, CRBM uses an additional neuron as label to learn
class of training data. Finally, as a generative model, CRBM can re-generate the data
distribution of training data following its energy function so that we can estimate the
probability density in the space. After estimating the probability density, the Bayesian
Classifier can classify with it.
In addition, this thesis proposes a setup to test 3
rd
CRBM analog chip. Since
training mechanism was not designed for the this chip, so we use the data acquisition
(DAQ) system and FPGA card to implement training algorithm of CRBM. This is the
so-called Chip-in-a-Loop training. The performance of this training mechanism will
be evalutated.

並列關鍵字

Continuous Restricted Boltzmann Machine ； eNose ； Pneumoniae strains ； Recognition

參考文獻

[1] H. Bai and G. Shi, “Gas Sensors Based on Conducting Polymers,” Sensors, vol. 7,

[2] C. C. Lu, C. C. Li, and H. Chen, “How Robust Is a Probabilistic Neural VLSI

System Against Environmental Noise,” in Artificial Neural Networks in Pattern

compensate for drift and uncertainty: a stochastic ‘neural’ approach,”

[4] J. R. Movellan, “A Learning Theorem for Networks at Detailed Stochastic