Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Transformatika

Comparasion Support Vector Machine And K-Nearest Neighbor for Classification fertile And Infertile Eggs Based on GLCM Texture Analysis Nurdiyah, Dewi; Muwakhid, Indra Abdam
Jurnal Tr@nsForMat!ka Vol 13, No 2 (2016)
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Fertility eggs test are steps that must be performed in an attempt to hatch eggs. Fertility test usually use egg candling. The purpose of observation is to choose eggs fertile  (eggs contained embryos) and infertile eggs (eggs that are no embryos). And then fertilized egg will be entered into the incubator for hatching eggs and infertile can be egg consumption. However, there are obstacles in the process of sorting the eggs are less time efficient and inaccuracies of human vision to distinguish between fertile and infertile eggs. To overcome this problem, it can be used  Computer Vision technology is having such a principle of human vision. It used to identify an object based on certain characteristics, so that the object can be classified. The aim of this study to comparasion classify image fertile and infertile eggs with SVM (Support Vector Machine) algorithm and K-Nearest Neighbor Algorithm based on input from bloodspot texture analysis and blood vessels with GLCM (Gray Level Co-ocurance Matrix).  Eggs image  studied are 6 day old eggs. It is expected that the proposed method is an appropriate method for classification image fertile and infertile eggs.
Analisis Sentimen Terhadap Aplikasi Whatsapp Menggunakan Naïve Bayes Berdasarkan Seleksi Fitur Chi-Square Kristian, Daniel Johan; Kristian, Daniel Johan Kristian; Nurdiyah, Dewi
Jurnal Transformatika Vol. 23 No. 2 (2026): January 2026
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v23i2.12310

Abstract

Penelitian ini bertujuan untuk membandingkan penelitian sebelumnya dengan peneliti, dengan menganalisis sentimen terhadap pengguna aplikasi whatsapp di google playstore, menggunakan pendekatan machine learning. Pengambilan data sebanyak 1000 dan menggunakan 3 kategori pelabelan yaitu positif, netral, dan negatif. Dengan melalui proses ekstraksi fitur menggunakan fitur TF-IDF yang mengahasilkan 1935 fitur, untuk mendapatkan nilai yang maksimal maka menggunakan seleksi fitur Chi-Square yang terpilih 85% fitur terbaik. Setelah dilakukan ekstraksi fitur yaitu proses klasifikasi menggunakan algoritma Naive Bayes, dengan proses pembagian data training dan data testing menggunakan rasio perbandingan 80 untuk data training dan 20 untuk data testing. hasil evaluasi mengalami peningkatan sebanyak 5,6% untuk nilai akurasi, untuk nilai presisi sebanyak 5,94%, dan untuk nilai recall sebanyak 1,51%.