Creating agents as artificial computer users
This project is concerning with creating agent as artificial computer user. The author has successfully implemented a FALCON agent that can learn from human activity patterns and can perform it own activities like an artificial computer user. The result is in the form of a log that records all activ...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2010
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/39691 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-39691 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-396912023-03-03T20:38:24Z Creating agents as artificial computer users Duc Tri, Duong Ngo. Tan Ah Hwee School of Computer Engineering DRNTU::Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence This project is concerning with creating agent as artificial computer user. The author has successfully implemented a FALCON agent that can learn from human activity patterns and can perform it own activities like an artificial computer user. The result is in the form of a log that records all activities performed in one whole day. Activities performed by human user will be recorded and used as training data to train the agent. In order to support the training, pre-processing of data is needed. The agent has been tested and been proved that more than half of its result can deceive human judges. The user interface allows the user to monitor the training and execution of the agent. The users can choose to perform automatically and receive the result or they can choose to go through the performing step by step and to monitor the changing in the states of the agent. Bachelor of Engineering (Computer Science) 2010-06-03T01:14:52Z 2010-06-03T01:14:52Z 2010 2010 Final Year Project (FYP) http://hdl.handle.net/10356/39691 en Nanyang Technological University 47 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
spellingShingle |
DRNTU::Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Duc Tri, Duong Ngo. Creating agents as artificial computer users |
description |
This project is concerning with creating agent as artificial computer user. The author has successfully implemented a FALCON agent that can learn from human activity patterns and can perform it own activities like an artificial computer user. The result is in the form of a log that records all activities performed in one whole day.
Activities performed by human user will be recorded and used as training data to train the agent. In order to support the training, pre-processing of data is needed.
The agent has been tested and been proved that more than half of its result can deceive human judges. The user interface allows the user to monitor the training and execution of the agent. The users can choose to perform automatically and receive the result or they can choose to go through the performing step by step and to monitor the changing in the states of the agent. |
author2 |
Tan Ah Hwee |
author_facet |
Tan Ah Hwee Duc Tri, Duong Ngo. |
format |
Final Year Project |
author |
Duc Tri, Duong Ngo. |
author_sort |
Duc Tri, Duong Ngo. |
title |
Creating agents as artificial computer users |
title_short |
Creating agents as artificial computer users |
title_full |
Creating agents as artificial computer users |
title_fullStr |
Creating agents as artificial computer users |
title_full_unstemmed |
Creating agents as artificial computer users |
title_sort |
creating agents as artificial computer users |
publishDate |
2010 |
url |
http://hdl.handle.net/10356/39691 |
_version_ |
1759855701929230336 |