Intelligent Sensor Data Pre-processing Using Continuous Restricted Boltzmann Machine
The objective of the project is to finda solution to pre-process noisy signalfor sensors in Lab-on-a-Chip (LOC) and System-on-Chip (SOC) technologies. This solution must be able to process continuous-time, analogue sensor signals directly. It must also be amenable to hardware implementation, with...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Final Year Project |
| 语言: | English |
| 出版: |
Universiti Teknologi PETRONAS
2007
|
| 主题: | |
| 在线阅读: | http://utpedia.utp.edu.my/9537/1/2007%20-%20Intelligent%20Sensor%20Data%20Pre-Processing%20using%20Continuous%20Restricted%20Boltzmann%20Machine.pdf http://utpedia.utp.edu.my/9537/ |
| 标签: |
添加标签
没有标签, 成为第一个标记此记录!
|
| id |
my-utp-utpedia.9537 |
|---|---|
| record_format |
eprints |
| spelling |
my-utp-utpedia.95372017-01-25T09:45:54Z http://utpedia.utp.edu.my/9537/ Intelligent Sensor Data Pre-processing Using Continuous Restricted Boltzmann Machine Suhaimi, Emil Zaidan TK Electrical engineering. Electronics Nuclear engineering The objective of the project is to finda solution to pre-process noisy signalfor sensors in Lab-on-a-Chip (LOC) and System-on-Chip (SOC) technologies. This solution must be able to process continuous-time, analogue sensor signals directly. It must also be amenable to hardware implementation, with low power consumption. This solution is found in the Continuous Restricted Boltzmann Machine (CRBM), which is a type of Artificial Neural Network which exhibits probabilistic and stochastic behavior. CRBM utilizes continuous stochastic neurons, where Gaussian noise is applied to the inputofthe neurons. The noise inputs cause neurons to have continuous-valued, probabilistic outputs. The use ofstochastic neurons in CRBMgives it modelingflexibility that is useful with real data. The training algorithm of CRBM requires only addition c;nd multiplication, which is computationally inexpensive in hardware and software. The ability ofCRBM to model any given data set is shown by training the CRBM on various data sets reflecting real-world data. In this study, CRBM is shown to be suitable to be implemented in LOC andSOC applications aforementioned. Universiti Teknologi PETRONAS 2007-06 Final Year Project NonPeerReviewed application/pdf en http://utpedia.utp.edu.my/9537/1/2007%20-%20Intelligent%20Sensor%20Data%20Pre-Processing%20using%20Continuous%20Restricted%20Boltzmann%20Machine.pdf Suhaimi, Emil Zaidan (2007) Intelligent Sensor Data Pre-processing Using Continuous Restricted Boltzmann Machine. Universiti Teknologi PETRONAS. (Unpublished) |
| institution |
Universiti Teknologi Petronas |
| building |
UTP Resource Centre |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Teknologi Petronas |
| content_source |
UTP Electronic and Digitized Intellectual Asset |
| url_provider |
http://utpedia.utp.edu.my/ |
| language |
English |
| topic |
TK Electrical engineering. Electronics Nuclear engineering |
| spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Suhaimi, Emil Zaidan Intelligent Sensor Data Pre-processing Using Continuous Restricted Boltzmann Machine |
| description |
The objective of the project is to finda solution to pre-process noisy signalfor sensors in
Lab-on-a-Chip (LOC) and System-on-Chip (SOC) technologies. This solution must be
able to process continuous-time, analogue sensor signals directly. It must also be
amenable to hardware implementation, with low power consumption. This solution is
found in the Continuous Restricted Boltzmann Machine (CRBM), which is a type of
Artificial Neural Network which exhibits probabilistic and stochastic behavior. CRBM
utilizes continuous stochastic neurons, where Gaussian noise is applied to the inputofthe
neurons. The noise inputs cause neurons to have continuous-valued, probabilistic
outputs. The use ofstochastic neurons in CRBMgives it modelingflexibility that is useful
with real data. The training algorithm of CRBM requires only addition c;nd
multiplication, which is computationally inexpensive in hardware and software. The
ability ofCRBM to model any given data set is shown by training the CRBM on various
data sets reflecting real-world data. In this study, CRBM is shown to be suitable to be
implemented in LOC andSOC applications aforementioned. |
| format |
Final Year Project |
| author |
Suhaimi, Emil Zaidan |
| author_facet |
Suhaimi, Emil Zaidan |
| author_sort |
Suhaimi, Emil Zaidan |
| title |
Intelligent Sensor Data Pre-processing Using Continuous
Restricted Boltzmann Machine |
| title_short |
Intelligent Sensor Data Pre-processing Using Continuous
Restricted Boltzmann Machine |
| title_full |
Intelligent Sensor Data Pre-processing Using Continuous
Restricted Boltzmann Machine |
| title_fullStr |
Intelligent Sensor Data Pre-processing Using Continuous
Restricted Boltzmann Machine |
| title_full_unstemmed |
Intelligent Sensor Data Pre-processing Using Continuous
Restricted Boltzmann Machine |
| title_sort |
intelligent sensor data pre-processing using continuous
restricted boltzmann machine |
| publisher |
Universiti Teknologi PETRONAS |
| publishDate |
2007 |
| url |
http://utpedia.utp.edu.my/9537/1/2007%20-%20Intelligent%20Sensor%20Data%20Pre-Processing%20using%20Continuous%20Restricted%20Boltzmann%20Machine.pdf http://utpedia.utp.edu.my/9537/ |
| _version_ |
1739831684675665920 |
| score |
13.251813 |