Claim Missing Document
Check
Articles

Found 2 Documents
Search

Metode Composite Performance Indekx (CPI) Sistem Pendukung Keputusan Penilaian Desa Terbaik Annahl Riadi; Irvan Muzakkir
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 6 (2022): Desember 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i6.5153

Abstract

Abstrak - Kegiatan pelaksanaan penilaian desa terbaik harus dilakukan dengan terbuka dan kompetitif meskipun jumlah data yang dimasukan relatif banyak. Penilaian desa terbaik sering terkendala, karena setiap desa memiliki karakteristik yang berbeda sehingga menyebabkan nilai kriteria pada masing-masing desa berbeda. Perhitungan dari penilaian masih dilakukan dalam manual sehingga masih banyaknya kesalahan pelaksanaannya dan penilaian desa yang terbaik belum dilaksanakan secara terbuka dan transfaran. Berdasarkan permasalahan tersebut dibutuhkan sistem pendukung keputusan penilaian desa terbaik menggunakan metode Composite Performance Index (CPI) yag dapat diterapkan pada Kecamatan Patilanggio dalam pengambilan keputusan, sehingga dapat diimplementasikan. Sistem pendukung keputusan penilaian desa terbaik hasil dari perhitungan Metode Composite Performance Index (CPI) merupakan prioritas yang dibutuhkan sebagai bahan pertimbangan pada Kecamatan Patilanggio untuk menentukan Penilaian Desa Terbaik. Hasil yang diperoleh SPK Penilaian Desa Terbaik Berdasarkan Hasil Pengujian White Box Disimpulkan Bahwa Sistem Pendukung Keputusan Ini Bebas Dari Kesalahan Program Dengan Total Node(N)= 15, Edge(E)= 18, Predicate Node(P)= 7 Region(R)= 8Kata kunci: SPK, CPI, Penilaian, Desa Terbaik, Patilanggio Abstrack - The activity of implementing the best village assessment must be carried out openly and competitively even though the amount of data entered is relatively large. The assessment of the best village is often constrained, because each village has different characteristics, causing the criteria values for each village to be different. The calculation of the assessment is still done manually so there are still many implementation errors and the best village assessment has not been carried out openly and transparently. Based on these problems, a decision support system for the best village assessment is needed using the Composite Performance Index (CPI) method which can be applied to Patilanggio District in decision making, so that it can be implemented. The decision support system for the best village assessment resulting from the calculation of the Composite Performance Index (CPI) Method is a priority needed as material for consideration in Patilanggio District to determine the Best Village Assessment. The results obtained by the SPK for the Best Village Assessment Based on the White Box Test Results It was concluded that this Decision Support System was free from program errors with Total Node(N)= 15, Edge(E)= 18, Predicate Node(P)= 7 Region(R)= 8Keywords: SPK, CPI, Evaluation, Best Village, Patilanggio
Particle Swarm optimization-based Neural Network method for predicting satisfaction of recipients of internet data quota assistance from the ministry of education and culture Annahl Riadi; Irvan Muzakkir; Marniyati H. Botutihe
ILKOM Jurnal Ilmiah Vol 14, No 1 (2022)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v14i1.1094.52-56

Abstract

The free quota assistance program for students and lecturers is an assistance program provided by The Ministry of Education and Culture. This program has been implemented since the spread of the covid-19 pandemic in all regions of Indonesia. This assistance is expected to help students and lecturers carry out online learning caused by the pandemic covid-19. This study aims to predict the satisfaction level of the users so that it can help the government in advancing education. The data processing is carried out using the rapid miner application and the neural network method with particle swarm optimization. From the results of data processing, the accuracy value for the neural network algorithm model is 42.44%, and the accuracy value for the PSO-based neural network algorithm model is 91.86%.