Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : SMATIKA

Pengolahan Nilai Berbasis Database Di MTS Miftahul Ulum Wonokoyo Setyorini, Setyorini; Riska, Suastika Yulia; Indah Sari, Rina Dewi
SMATIKA JURNAL Vol 5 No 02 (2015): Smatika Jurnal : STIKI Informatika Jurnal
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1257.729 KB)

Abstract

Kegiatan yang dilakukan merupakan sosialiasi penggunaan software pengolah nilai siswa dan penggunaan software pendataan guru dan siswa berbasis database. Software berbasis database dibangun menggunakan microsoft access. Software pengolahan nilai dapat mempermudah wali kelas untuk melakukan perangkingan dalam satu kelas di mata pelajaran yang sama. Tujuan adanya perangkingan ini adalah untuk memberikan reward kepada siswa yang memiliki prestasi. Sehingga siswa tersebut dapat termotivasi untuk terus meningkatkan prestasinya dan dapat memotivasi teman-teman lain untuk lebih berprestasi.
Klasifikasi Bumbu Dapur Indonesia Menggunakan Metode K-Nearest Neighbors (K-NN) Suastika Yulia Riska; Lia Farokhah
SMATIKA JURNAL Vol 11 No 01 (2021): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v11i01.568

Abstract

Seasoning is one of the most important elements in a dish. Indonesian herbs or spices have a very wide variety of types. Mistakes in choosing spices have a big effect on the taste of the dish. Image processing is a branch of science in the field of technology that can be used to recognize image objeks captured by the camera. This study will classify the types of spices that are almost similar, namely ginger, galangal, turmeric and kencur. The classification method used is K-Nearest Neighbor (K-NN). In this study we tested how to split training data and data testing, namely 66.7%: 33.33%, 75%: 25% and 90%: 10%. The sharing of training data and testing data uses 90%: 10% has the greatest average accuracy compared to other distribution methods. The selection of K = 3 or K = 5 has an average accuracy that is almost the same in all methods of split training data and testing data, namely 64.66%: 65%. At K = 1 it has a fairly high accuracy compared to the previous K, which is 73%.