Garuda - Garba Rujukan Digital

ANT COLONY OPTIMIZATION UNTUK MENYELEKSI FITUR DAN KLASIFIKASI ARTIKEL nugroho, arief kelik; Permadi, Ipung
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 10, No 1 (2019): JURNAL SIMETRIS VOLUME 10 NO 1 TAHUN 2019
Publisher : Universitas Muria Kudus

Algoritma koloni semut dapat diterapkan dalam pengklasifikisian dengan menerapkan mekanisme perilaku semut dalam mencari sumber makanan. Semut memberikan kemungkinan hasil terbaik/optimal berdasar intensitas pheromone. Himpunan fitur pada artikel diseleksi berdasarkan topik atau jenis kelas yang diinputkan dalam sistem kemudian dievaluasi dengan mengecek kesesuaian masing-masing semut. Berdasarkan 10 percobaan yang telah dilakukan, percobaan dengan hasil terbaik didapatkan pada percobaan pertama dan terakhir yang menyeleksi/memilih 66 fitur yang artinya berhasil mengurangi fitur sebanyak 96,34% dengan akurasi pelatihan 52%.

RANCANG BANGUN SISTEM PENGUKURAN PERGESERAN TANAH MENGGUNAKAN SENSOR VARIABEL RESISTOR Sugito, Sugito; Hartono, Hartono; Permadi, Ipung
BERKALA FISIKA 2015: Berkala Fisika Vol. 18 No. 1 Tahun 2015
Publisher : BERKALA FISIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (731.753 KB)

The phenomenon of ground motion are things that need serious attention. The impact that can be caused by the ground motion can not be underestimated. The velocity of ground motion at each area has different characteristics. Monitoring of ground motion continuously is one way to be able to determine the policy relating to protection measures. Variable resistor is a component that can be used to detect the presence of such a shift. Variable resistor connected to the shear plane using a cord will be amended proportionalÂ with the shift in resistance value of shear plane. Variable resistor arranged with others resistor to form a Wheatstone bridge circuit. Thus the change in resistance on the variable resistor will produce a voltage change. Value of voltage changes were characterized to obtain the calibration equations, response time and stability of the sensor. Data acquisition is done by using a personal computer and the device interface DAQ NI USB6009. While programming created using LabView 7.1 software. Based on the results obtained by testing the sensor response time is very good sensor is equal to 0.47 seconds. Highly stable sensors to take measurements, look at the value of the average reading deviation of 1.14 %. The sensor has a measurement in the range of 0 to 17 cm. Keywords : variable resistor, sensor, Wheatstone bridge, characterization

APLIKASI FUZZY BERBASIS WEB UNTUK REKOMENDASI PEMILIHAN UNIVERSITAS SWASTA Afuan, Lasmedi; Permadi, Ipung
Proceedings of KNASTIK 2009
Publisher : Duta Wacana Christian University

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

Perkembangan teknologi komputer dewasa ini telah mengalami banyak perubahan yang sangat pesat, seiring dengan tuntutan kebutuhan manusia yang semakin hari semakin banyak dan kompleks. Memilih universitas yang tepat adalah salah satu hal yang sangat penting dalam hidup. Salah satu permasalahan yang dihadapi para siswa (dan otomatis orang tuanya juga) adalah terdapat banyaknya pilihan universitas yang dapat membingungkan calon mahasiswa. Menyadari betapa pentingnya memilih universitas yang tepat, maka perlu dirancang program aplikasi pada bidang pendidikan khususnya untuk aplikasi fuzzy dalam mendukung keputusan pemilihan universitas berbasis web. Aplikasi fuzzy ini dibangun dengan menggunakan variabel fuzzy antara lain fakultas, jurusan , akreditasi , biaya kuliah, jumlah dosen, sarana yang dimiliki, jumlah alumni, jurusan yang dimiliki, umur universitas , dan jarak universitas dari pusat kota. Aplikasi web yang menggunakan media internet dimaksudkan agar dapat diakses secara luas oleh masyarakat dan membantu siswa dalam pengambilan keputusan untuk memilih universitas yang tepat.

ANT COLONY OPTIMIZATION UNTUK MENYELEKSI FITUR DAN KLASIFIKASI ARTIKEL nugroho, arief kelik; Permadi, Ipung
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 10, No 1 (2019): JURNAL SIMETRIS VOLUME 10 NO 1 TAHUN 2019
Publisher : Universitas Muria Kudus

Algoritma koloni semut dapat diterapkan dalam pengklasifikisian dengan menerapkan mekanisme perilaku semut dalam mencari sumber makanan. Semut memberikan kemungkinan hasil terbaik/optimal berdasar intensitas pheromone. Himpunan fitur pada artikel diseleksi berdasarkan topik atau jenis kelas yang diinputkan dalam sistem kemudian dievaluasi dengan mengecek kesesuaian masing-masing semut. Berdasarkan 10 percobaan yang telah dilakukan, percobaan dengan hasil terbaik didapatkan pada percobaan pertama dan terakhir yang menyeleksi/memilih 66 fitur yang artinya berhasil mengurangi fitur sebanyak 96,34% dengan akurasi pelatihan 52%.

SISTEM PENDUKUNG KEPUTUSAN PEREKOMENDASIAN OLI MENGGUNAKAN FUZZY MADM Nugroho, Arief Kelik; Permadi, Ipung; Hanifa, Aini
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol 9, No 1 (2020)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v9i1.22959

Perekomendasian oli secara manual, tanpa menggunakan perhitungan yang akurat cenderung bersifat subyektif serta cukup sulit mengenali karakteristik oli yang paling tepat untuk jenis motor tertentu. Proses analisis data transaksi secara manual berdasarkan pada pengamatan akan mempengaruhi kualitas mesin. Sebagai contoh untuk memberikan rekomendasi oli terbaik bagi seorang konsumen, maka sebuah perusahaan/bengkel sepeda motor harus melihat data transaksi ganti oli yang lalu untuk mendapatkan data tentang oli yang digunakan untuk mengganti oli motor konsumen tersebut. . Penggunaan perangkat komputer dapat digunakan sebagai pendukung keputusan menjadi lebih cepat, tepat, dan akurat. Proses perekomendasian oli terbaik bagi kendaraan bermotor menggunakan metode fuzzy. Hasil perhitungan diperoleh direkomendasikan A3=0.72, A2 = 0.66, A1= 0.55, A4= 0.40.

OPTIMIZING COURSE SCHEDULING FACULTY OF ENGINEERING UNSOED USING GENETIC ALGORITHMS Nugroho, Arief Kelik; Permadi, Ipung; Yasifa, Ana Romadhona
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol 7 No 2 (2022): JITK Issue February 2022
Publisher : LPPM Nusa Mandiri

In carrying out an activity regularly and smoothly, it is necessary to make an activity schedule that can manage the time of one activity with another so that unwanted things do not happen such as the same time, the same place, and others. Making a schedule of activities is quite easy to do if there are not too many entities involved and if the entities are not tied to each other, but for larger cases, creating a schedule of activities manually will take quite a lot of time and can result in errors in the schedule or shortages. effectiveness in the resulting schedule. This is commonly experienced in making course schedules at universities because there are a lot of course data and lecturers can teach several courses at once and at different times, therefore in making course schedules can be done by applying genetic algorithms so that the time required needed in making the course schedule shorter and the results obtained can be more optimal than the results of making the course schedule manually. In this study, the optimal course schedule was obtained in the 31st generation using data on rooms, courses, study time, lecturers, and departments so that one chromosome has 154 gen, then the population length is made up to 9 individuals or chromosomes, the mutation rate is set at 0.1, and the method used in the individual selection stage is the tournament selection method where the tournament size is set at 3. The fitness value is taken so that a schedule is said to be optimal, i.e. if the fitness value is equal to 1 because then it shows that there are no errors or problems (such as time, lecturers, conflicting rooms) that occur in the schedule.

Improvement Of Image Quality Using Convolutional Neural Networks Method Nugroho, Arief Kelik; Permadi, Ipung; Faturrahim, Muhammad
Scientific Journal of Informatics Vol 9, No 1 (2022): May 2022
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v9i1.30892

Abstract. Purpose: This desire for high resolution stems from two main application areas, namely improving pictorial information for human interpretation and assisting automatic machine perception in representing images or videos. Image resolution describes the detail contained in an image, the higher the resolution, the more detail there is. The resolution of a digital image can be classified into various types, namely pixel resolution, spatial resolution, temporal resolution, and radiometric resolution. In this context, we are interested in spatial resolution.Methods: Elements of a digital image consist of a collection of small images called pixels. Spatial resolution refers to the pixel density of an image and is measured in pixels per unit area. A quality digital image is determined by the size of the resolution it has. A low resolution or low-resolution is a drawback of a digital image because the information contained in the image means little compared to a high-resolution image.Result: Therefore, in this study, a digital image processing program was created in the form of Image Super-Resolution with the Convolutional Neural Network method to utilize low-resolution images to produce high-resolution images. With a fairly short training process, namely 6050 datasets with 100 CNN epochs, the average PSNR image is 5% higher.Novelty: Image quality can be improved by changing the parameters in the CNN method so that image quality can be improved.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search