Generating Synthetic Schematics with Generative Adversarial Networks

Generating Synthetic Schematics with Generative Adversarial Networks

This study investigates synthetic schematic generation using conditional generative adversarial networks, specifically the Pix2Pix algorithm was implemented for the experimental phase of the study. With the increase in deep neural network’s capabilities and availability, there is a demand for verbos...

Full description

Bibliographic Details
Main Author: Daley Jr, John
Format: Others
Language:English
Published: Högskolan Kristianstad, Fakulteten för naturvetenskap 2020
Subjects:
Synthetic data
generative adversarial network
machine learning
convolutional neural network
python
tensorflow
blueprints
Pix2Pix
Computer Sciences
Datavetenskap (datalogi)
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:hkr:diva-20901
id ndltd-UPSALLA1-oai-DiVA.org-hkr-20901
record_format oai_dc
spelling ndltd-UPSALLA1-oai-DiVA.org-hkr-209012020-07-22T05:48:24ZGenerating Synthetic Schematics with Generative Adversarial NetworksengDaley Jr, JohnHögskolan Kristianstad, Fakulteten för naturvetenskap2020Synthetic datagenerative adversarial networkmachine learningconvolutional neural networkpythontensorflowblueprintsPix2PixComputer SciencesDatavetenskap (datalogi)This study investigates synthetic schematic generation using conditional generative adversarial networks, specifically the Pix2Pix algorithm was implemented for the experimental phase of the study. With the increase in deep neural network’s capabilities and availability, there is a demand for verbose datasets. This in combination with increased privacy concerns, has led to synthetic data generation utilization. Analysis of synthetic images was completed using a survey. Blueprint images were generated and were successful in passing as genuine images with an accuracy of 40%. This study confirms the ability of generative neural networks ability to produce synthetic blueprint images. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:hkr:diva-20901application/pdfinfo:eu-repo/semantics/openAccess
collection NDLTD
language English
format Others
sources NDLTD
topic Synthetic data
generative adversarial network
machine learning
convolutional neural network
python
tensorflow
blueprints
Pix2Pix
Computer Sciences
Datavetenskap (datalogi)
spellingShingle Synthetic data
generative adversarial network
machine learning
convolutional neural network
python
tensorflow
blueprints
Pix2Pix
Computer Sciences
Datavetenskap (datalogi)
Daley Jr, John
Generating Synthetic Schematics with Generative Adversarial Networks
description This study investigates synthetic schematic generation using conditional generative adversarial networks, specifically the Pix2Pix algorithm was implemented for the experimental phase of the study. With the increase in deep neural network’s capabilities and availability, there is a demand for verbose datasets. This in combination with increased privacy concerns, has led to synthetic data generation utilization. Analysis of synthetic images was completed using a survey. Blueprint images were generated and were successful in passing as genuine images with an accuracy of 40%. This study confirms the ability of generative neural networks ability to produce synthetic blueprint images.
author Daley Jr, John
author_facet Daley Jr, John
author_sort Daley Jr, John
title Generating Synthetic Schematics with Generative Adversarial Networks
title_short Generating Synthetic Schematics with Generative Adversarial Networks
title_full Generating Synthetic Schematics with Generative Adversarial Networks
title_fullStr Generating Synthetic Schematics with Generative Adversarial Networks
title_full_unstemmed Generating Synthetic Schematics with Generative Adversarial Networks
title_sort generating synthetic schematics with generative adversarial networks
publisher Högskolan Kristianstad, Fakulteten för naturvetenskap
publishDate 2020
url http://urn.kb.se/resolve?urn=urn:nbn:se:hkr:diva-20901
work_keys_str_mv AT daleyjrjohn generatingsyntheticschematicswithgenerativeadversarialnetworks
_version_ 1719331336004567040

Similar Items