GUNTARA, YUSA VIRGINIAWAN and Samsuryadi, Samsuryadi and Sukemi, Sukemi (2023) PENGENALAN KEPRIBADIAN MELALUI TULISAN TANGAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN LS CLASSIFIERS. Masters thesis, Sriwijaya University.
Text
RAMA_55101_09012681923008.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy |
|
Text
RAMA_55101_09012681923008_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (585kB) |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (297kB) | Request a copy |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (175kB) | Request a copy |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (685kB) | Request a copy |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (189kB) | Request a copy |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (120kB) | Request a copy |
|
Text
RAMA_55101_09012681923008_00040271011_00031266042_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy |
Abstract
A person's handwriting is different and unique, even though it looks similar it is certainly not the same as someone else's writing. One's personality traits can be identified based on handwriting. One of the implementations is (handwriting recognition). To identify a person's personality, it can be classified by handwriting using the 'Graphology' field. The computational system to identify handwritten images can use the Convulution Neural Network method. Using the CNN method is expected to produce good accuracy with a low error rate. The CNN method is able to predict a person's personality through manuscripts as images. In addition, to increase the diversity of classifications, the Least Squared Classifiers method is needed. . LS Classifiers are designed to increase the variety of CNN methods in feature extraction and classification. The LS Classifier method is a classification method that estimates the w parameter vector and takes the best linear classifier based on the w parameter vector. Research has functions for users, including to find out someone's personality, especially extrovert and introvert personality. In this study CNN serves as Feature Extraction to classify Image and Ls Classifiers serves to increase diversity into 2 personality groups. The level of accuracy of the performance of the CNN & Ls Classifiers method in carrying out feature extraction and classification of handwritten images in determining personality has a good level of accuracy. Keywords: Handwriting, CNN, Ls Classifiers, Graphology, classification
Item Type: | Thesis (Masters) |
---|---|
Subjects: | Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. T Technology > T Technology (General) > T58.4 Managerial control systems Information technology. Information systems (General) |
Divisions: | 09-Faculty of Computer Science > 55101-Informatics (S2) |
Depositing User: | Yusa Virginiawan Guntara |
Date Deposited: | 23 Nov 2023 09:05 |
Last Modified: | 23 Nov 2023 09:05 |
URI: | http://repository.unsri.ac.id/id/eprint/130955 |
Actions (login required)
View Item |