The Performance Analysis of Deep Belief Networks: A Case Study of PM2.5
碩士 === 國立暨南國際大學 === 資訊管理學系 === 107 === This study mainly discusses whether data preprocessing is helpful for training of Deep Belief Networks(DBN). Using air pollution data, we first lower the noise by preprocessing and fill the missing values. Then we use logarithm(LOG), verification, stepwise r...
Main Authors: | LAI,MENG-NAN, 賴孟南 |
---|---|
Other Authors: | PAI,PING-FENG |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/rax6j4 |
Similar Items
-
A Deep Belief Network Combined with Modified Grey Wolf Optimization Algorithm for PM2.5 Concentration Prediction
by: Yin Xing, et al.
Published: (2019-09-01) -
Development and Validation of an Aerial Robot for PM2.5 Detection
by: Meng-Ying Hsieh, et al.
Published: (2017) -
A prediction model of PM2.5 in Central Taiwan
by: Yu-Chen Lai, et al.
Published: (2016) -
Correlation networks of air particulate matter ( $$\hbox {PM}_{2.5}$$ PM 2.5 ): a comparative study
by: Dimitrios M. Vlachogiannis, et al.
Published: (2021-04-01) -
A sampling and measurement system for motorcycle exhaust PM2.5
by: Ji-Ying Lai, et al.
Published: (2015)