• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Deteksi Kepribadian Melalui Sketsa Pohon Menggunakan Algoritma LVQ

    View/Open
    fulltext (2.351Mb)
    Date
    2018
    Author
    Siregar, Devi Novella Putri
    Advisor(s)
    Amalia
    Aulia, Indra
    Metadata
    Show full item record
    Abstract
    Human resources are the most important source for a company. One method to find qualified resources is by personality test. Personality test are usually performed by psychologists. One of the methods used is by sketching the trees by the respondents. The purpose of this research is the identification of personality with image processing from sketh tree. Detection using learning vector quantization (LVQ) algorithm. This detection stage starts from the training dataset and testing the dataset of the process of entering the pre-processing stage, in the pre-processing stage there are two stage : segmentation and image enhancement. After that enter the next stage of thresholding, after going through the stage local thresholding and then enter the stage featuren extraction, where in this stage the process to get the edge value with thesobel method and the latter will be detected again similarity sketh pattern by using learning vector quantization (LVQ). In this detection using by 60 training data, it consisted of 10 training by many roots and 10 training by some little roots or no roots, 10 training by leaves without fruit and 10 training by leaves with fruit, 10 training by rod with no scratches and 10 training by rod with a scratch and with 20 data testing. The result of this detection is 85% accuracy.
     
    Sumber daya manusia merupakan sumber daya yang paling penting bagi suatu perusahaan. Salah satu metode untuk mencari sumber daya manusia yang berkualitas yaitu dengan test kepribadian. Tes kepribadian biasanya dilakukan oleh psikolog. Salah satu metode yang digunakan yaitu dengan sketsa pohon oleh responden. Tujuan penelitian ini adalah identifikasi kepribadian dengan image processing dari sketsa pohon. Pendeteksian menggunakan algoritma learning vector quantization (LVQ). Tahapan pendeteksian ini dimulai dari training dataset dan testing dataset kemudian masuk tahap pre-proccesing, didalam pre-proccesing ada dua tahap yaitu segmentasi dan image enhancement. Setelah itu masuk tahap selanjutnya yaitu thresholding dengan menggunakan local thresholding lalu masuk ketahap feature extraction dimana didalam tahap tersebut dilakukan proses untuk mendapatkan nilai tepi dengan metode sobel dan terakhir akan dideteksi lagi kemiripan pola sketsa dengan menggunakan Learrning Vector Quantization (LVQ). Pada pendeteksian ini menggunakan 60 data training yang terdiri dari 10 training akar banyak dan 10 training akar sedikit atau tidak ada akar, 10 training daun tanpa buah dan 10 training daun dengan buah, 10 training batang tanpa goresan dan 10 training batang dengan goresan serta dengan 20 data testing. Hasil dari pendetaksian ini didapatkan akurasi sebesar 85%.

    URI
    http://repositori.usu.ac.id/handle/123456789/4345
    Collections
    • Undergraduate Theses [767]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV