Article Per Year (5 Year)
p-Index From 2020 - 2025
1.325
P-Index
This Author published in this journals
All Journal Jurnal Buana Informatika Jurnal EECCIS Jurnal Teknologi Informasi dan Ilmu Komputer J-Dinamika: Jurnal Pengabdian Kepada Masyarakat Jurnal Teknologi Informasi dan Terapan (J-TIT) JUKI : Jurnal Komputer dan Informatika Journal of Information System and Technology (JOINT) Jurnal Informatika Polinema (JIP) SEJAGAT : Jurnal Pengabdian Masyarakat
Aji Seto Arifianto
Politeknik Negeri Jember
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Library & Information Science Public Health Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
PERBANDINGAN METODE CBR, NN-5 DAN NAÏVE BAYES UNTUK KLASIFIKASI INFEKSI NOSOKOMIAL Taufiq Rizaldi; Aji Seto Arifianto
Jurnal Teknologi Informasi dan Terapan Vol 1 No 2 (2014)
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

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

Abstract

Classification method is a method that is widely used for the completion of the diagnosis of disease, particularly in humans. One type of disease that is dangerous is potentially emerging nosocomial infection in patients postoperatively. Approach classification method based upon the similarity of character data, there is also a reference to the emergence of statistical data. Some methods of classification needs to be tested in order to obtain the appropriate reference method for this case. The purpose of this study was to compare the performance of three methods of classification that Case Based Reasoning method (CBR), Neirest Neighbor-5 (NN-5) and Naïve Bayes for diagnosis of nosocomial infection. Test results showed that the method of CBR and NN-5 has a very good degree of accuracy than Naïve Bayes, Naïve Bayes but has a faster processing time.
PENERAPAN AGYLE METHODOLOGY DALAM PENGEMBANGAN SISTEM INFORMASI GEOGRAFIS PEMETAAN DAERAH PERTAMBANGAN Aji Seto Arifianto; Nugroho Setyo Wibowo
Jurnal Teknologi Informasi dan Terapan Vol 2 No 1 (2015)
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

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

Abstract

Indonesia is one country which has a wealth of natural resources in Asia's largest mine. Indonesian mining products are exported to many foreign countries and is able to produce a deficit for the country. So that natural resources mining Indonesia became one of the main commodities. The objectives of this study was to develop a geographic information system of the mining area is expected to provide an overview and information for stakeholders regarding mining areas in Indonesia. This system can provide convenience in data storage and geographic system application program can be accessed directly and can provide accurate data on the mining areas across Indonesia. The advantages of the system to be developed compared with the manual map is able t o update the information contained in it quickly and accurately as well as information in the form of digital maps. The development of geographic information system mapping mining areas is done by using Agyle Methodology. Results of this study include the design in the form of a global system in the form of Use Case Diagram, Class Diagram, Sequence Diagram, Collaboration Diagram, Activity Diagram, and Statechart Diagram and a geographic information system application program created using Microsoft Visual Basic.Net and MySQL as the database.
PREDIKSI MISSING IMPUTATION UNTUK DATA PENYEBARAN MENGGUNAKAN NAÏVE BAYES Aji Seto Arifianto; Didit Rahmat Hartadi; Anik Nur Novitasari E S
Jurnal Teknologi Informasi dan Terapan Vol 3 No 1 (2016)
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

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

Abstract

Dengue fever is a disease caused by dengue virus by Aedes Aegypti mosquitoes intermediary. There are four dengue virus serotypes, called DEN-1, DEN-2, DEN-3, and DEN-4, each of them can lead to dengue fever, either mild or fatal. Based on a survey of public health in Jember, recorded during January 2015 there were 300 cases of dengue fever, and seven of them died. Previous research using fuzzy method to determined the potential spread of Dengue in Jember. Para meters that used is the amount of rain in a period, the amount of rain in one month, free amount of larva and house index. Data that used is taken from 2009 until 2012 from 31 districts. The weaknesses in this study were not contain a way to resolve the imputation of missing data. In fact, survey data is often incomplete. Based on these issues, it will be created a prediction system of imputation of missing data on the spread of dengue by using Naïve Bayes method. The data refers to the prediction of the mi ssing data and the data were used as training data, so it can be processed further. This research has been successfully predicting missing data imputation using existing data, so that the missing data can be completed with high degree of accuracy.
PERBANDINGAN METODE K-NN DAN BAYES PADA MISSING IMPUTATION Taufiq Rizaldi; Fendik Eko Purnomo; Aji Seto Arifianto
Jurnal Teknologi Informasi dan Terapan Vol 5 No 2 (2018)
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v5i2.84

Abstract

The problem of data loss in a dataset is experienced in surveys for data collection which are usually caused by no response from units or items during the survey data collection process. The loss of a data can significantly influence the results of a study. The inaccuracy in choosing a solution to overcome these problems can result in a less than optimal outcome that tends to be biased. Some methods that are widely used to solve these problems are using the K Nearest Neighbor (K-NN) and Naïve Bayes methods, the main purpose of this study is to compare the performance of the two methods. From the results of the K-NN, the results were better, where the Mean Square Error (MSE) is bigger than 1 and MAPE around 10-16%, while Naïve Bayes got MSE values bigger than 1 and MAPE ​​around 26%.
Klasifikasi Stroke Berdasarkan Kelainan Patologis dengan Learning Vector Quantization Aji Seto Arifianto; Moechammad Sarosa; Onny Setyawati
Jurnal EECCIS Vol 8, No 2 (2014)
Publisher : Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (702.634 KB)

Abstract

Dampak yang ditimbulkan stroke diantaranya kelumpuhan sebagian atau keseluruhan organ tubuh sampai kematian. Tingginya angka kematian akibat stroke disebabkan karena penanganan yang lambat. Diagnosis stroke harus dilakukan dengan cepat dan tepat agar segera mengetahui tipe klasifikasi patologinya termasuk dalam stroke infark atau hemorrhagic guna pemberian tindakan medis dan obat yang tepat pula. Prosedur wajib atau Gold Standart Procedure untuk klasifikasi stroke menggunakan Computed Tomograph Scan atau Magnetic Resonance Imaging, permasalahannya di Indonesia terkendala biaya yang mahal dan tidak semua rumah sakit memilikinya. Jika prosedur standar tidak dapat dilakukan maka diagnosis stroke dapat dilakukan melalui analisis terhadap data klinis pasien. Data klinis terdiri dari 32 fitur berisi tentang hasil pemeriksaan fisik, gejala yang dirasakan pasien, riwayat penyakit dan pemeriksaan laboratorium darah. Dalam penelitian ini diusulkan sebuah klasifikasi stroke secara komputerisasi menggunakan metode Learning Vector Quantization yang merupakan pengembangan dari Kohonen Self-Organizing Map, bersifat supervised dan competitive learning, struktur jaringannya single layer-net. Hasil dari penelitian ini tingkat akurasinya mencapai 96%. Uji diagnosis ditunjukkan dengan nilai Area Under Curve (AUC) sebesar 0,952 yang tergolong dalam kategori excellent.Kata Kunci— Klasifikasi, Stroke, Learning Vector Quantization.
Pelatihan Pengembangan Media Pembelajaran Berbasis Multimedia untuk Meningkatkan Kualitas dan Kreativitas Guru SMA Hendra Yufit Riskiawan; Dwi Putro Sarwo Setyohadi; Aji Seto Arifianto
J-Dinamika : Jurnal Pengabdian Masyarakat Vol 1 No 1 (2016): Juni
Publisher : Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/j-dinamika.v1i1.134

Abstract

Kemajuan teknologi informasi menjadi salah satu peluang yang dapat dimanfaatkan guru dalam meningkatkan pola pembelajarannya. Banyaknya perangkat lunak yang tersedia dapat dimanfaatkan untuk mengembangkan media pembelajaran yang lebih interaktif dan menarik minat belajar para murid peserta didiknya. Fasilitas internet yang tersedia juga menjadi peluang besar untuk dapat memperkaya konten materi yang dapat disiapkan untuk disampaikan kepada peserta didiknya yang diharapkan mampu meningkatkan kualitas peserta didiknya. Oleh karena itu diperlukan kegiatan guna meningkatkan kualitas dan kreativitas guru dalam mengembangkan media pembelajaran. Berdasarkan pemikiran tersebut maka tim pengabdian pada masyarakat mengadakan kegiatan Pelatihan Teknologi Informasi dan Pengenalan Aplikasi Komputer, dengan Tema Kegiatan: “Pelatihan Pengembangan Media Pembelajaran Berbasis Multimedia untuk Meningkatkan Kualitas dan Kreativitas Guru SMA”. Melalui kegiatan ini diharapkan para guru yang ada di SMA ISLAM AL-HIDAYAH JEMBER, mampu menguasai aplikasi teknologi informasi khususnya multimedia dan memanfaatkan teknologi tersebut dalam mengembangkan media pembelajaran yang akan digunakannya.
Sistem Peramalan Waktu Masak Fisiologis Benih Padi Menggunakan Double Exponential Smoothing Najmi Nurus Shofi; Aji Seto Arifianto; Mochamat Bintoro
Jurnal Teknologi Informasi dan Terapan Vol 9 No 1 (2022)
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v9i1.196

Abstract

The success of the rice harvest is influenced by various factors, one of which is the selection of quality seeds. Good rice seeds are those obtained during physiological maturity where the moisture content in the seeds is not too low/high. The physiological cooking time of rice seeds can be done by calculating heat accumulation and testing germination. Heat accumulation is the total heat energy from solar radiation received by rice plants, this value can be calculated by recording the maximum, minimum, and humidity temperature data continuously for 90-120 days. Meanwhile, post-harvest laboratory tests were carried out for germination. Temperature and humidity data that were stored and processed quickly of course could be predicted the physiological ripening time of seeds better. Therefore in this article, a web-based forecasting system with the double exponential smoothing method was developed and supported by a graphical display of the data development. This research was conducted on 3 rice varieties namely IR64, Sinta Nur, and Ciherang. The yield that could be conveyed for the IR64 variety reached 85% germination with heat accumulation of 1147 and 105 DAS. The Sinta Nur variety had 92% germination and 86% Ciherang variety with heat accumulation of 1266 at 115 DAS. In this forecasting process, the MAPE value is 0.205 with alpha 0.9 and beta 0.1.
Pengaruh Prediksi Missing Value pada Klasifikasi Decision Tree C4.5 Aji Seto Arifianto; Kursita Dewi Safitri; Khafidurrohman Agustianto; I Gede Wiryawan
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 9 No 4: Agustus 2022
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2022944778

Abstract

Pendekatan klasifikasi data bersifat supervised learning menuntut adanya dataset yang lengkap. Permasalahan yang muncul adanya missing value yaitu hilangnya nilai suatu atribut yang diakibatkan kesalahan dalam pengumpulan data, kesalahan saat memasukkan data, dan ketidakmampuan responden untuk memberikan jawaban yang akurat. Penelitian ini melakukan uji coba pengembangan rule decision tree C4.5 untuk data penyakit ginjal kronis. Dataset terdiri dari 400 record, 24 atribut dan 1 kelas target. Karakteristik data yang digunakan meliputi 11 data bertipe numerik dan 14 data bertipe nominal. Jumlah data kelas positif penyakit ginjal kronis 250, sedangkan negatif ginjal kronis 150. Total data yang tidak lengkap (missing value) 1012 records. Perlakuan pertama dibangun rule dengan menghitung entropy dan gain pada 360 data training yang terdapat missing value diperoleh 21 rules. Kemudian pada perlakuan kedua diterapkan prediksi missing value menggunakan rumus mean dan modus sebelum pembetukan rule tree, didapatkan 24 rules. Mengukur akurasi kedua rules tree C4.5 dilakukan menguji 40 data test, hasilnya 90% untuk rule dengan missing value dan 95% untuk dataset yang telah diprediksi nilainya. AbstractThe supervised learning approach to data classification requires a complete dataset. The problem that arises was the existence of missing value, namely the loss of the value of an attribute due to errors in data collection, errors when entering data, and the inability of respondents to provide accurate answers. This study conducted a trial on the development of the C4.5 rule decision tree for chronic kidney disease data. The dataset consisted of 400 records, 24 attributes and 1 target class. The data characteristics included 11 numeric data and 14 nominal data types. The number of positive data for kidney disease was 250, while the number of negative for kidney disease was 150 and the total of missing value was 1012 records. The first treatment was building a rule by calculating the entropy and gain on 360 training data where missing value was obtained, it was 21 rules. Then in the second treatment, the prediction of missing value was applied using the mean and mode formula before the formation of the rule tree, obtained 24 rules. Researcher was measuring the accuracy of the two rules tree C4.5 is done by using 40 data-testing, the result is 90% for rules with missing value and 95% for datasets whose value has been predicted.
Deteksi Keaslian Uang Kertas Berdasarkan Fitur Gray Level Co-Occurrence Matrix (GLCM) Menggunakan K-Nearest Neighbor Defi Tamara; M. Haerul Anam; Wike Sri Widari; Ardan Venora Falahudin; Widya Yuristika Oktavia; Zilvanhisna Emka Fitri; Aji Seto Arifianto
Jurnal Buana Informatika Vol. 13 No. 02 (2022): Jurnal Buana Informatika, Volume 13, Nomor 2, Oktober 2022
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v13i02.5716

Abstract

Abstract. Rupiah is the currency of Indonesia. One form is rupiah banknotes. The issuance and circulation of rupiah banknotes are under the authority of Bank Indonesia (BI) as the central bank. Currently, many incidents of counterfeiting are troubling the public. One of the characteristics of the authenticity of money that has not yet been found in counterfeit money is invisible ink, which is an invisible print that can only be seen when the money is exposed to ultraviolet light. Behind it, prolonged exposure to ultraviolet light harms eye and skin health. A system for detecting the authenticity of banknotes was created to overcome these problems using image processing techniques. The research stages are literature study, collecting banknote images illuminated by ultraviolet light, image processing (rotation, cropping, and resizing), RGB color component solving, GLCM feature extraction, and classification using the k-Nearest Neighbor (KNN) method. The KNN method can classify the authenticity of banknotes with an accuracy of 88% using the values of K = 3 and 7.Keywords: Rupiah Banknotes, Authenticity of Money, Gray Level Co-occurrence Matrix, K-Nearest Neighbor Abstrak. Rupiah merupakan mata uang Indonesia. Salah satu bentuknya adalah uang kertas rupiah. Penerbitan dan pengedaran uang kertas rupiah menjadi kewenangan Bank Indonesia (BI) sebagai bank sentral. Meski demikian, saat ini banyak kejadian pemalsuan uang yang meresahkan masyarakat. Salah satu ciri keaslian uang yang sampai saat ini belum ditemukan juga ada pada uang palsu ialah invisible ink, yaitu cetakan tidak kasat mata yang hanya terlihat ketika uang disinari cahaya ultraviolet. Dibalik hal itu, pancaran sinar ultraviolet yang berkepanjangan rupanya berbahaya bagi kesehatan mata dan kulit. Untuk mengatasi permasalahan tersebut, dibuatlah sistem pendeteksi keaslian uang kertas yang memanfaatkan teknik image processing. Tahapan penelitian yaitu studi literatur, pengumpulan citra uang kertas yang disinari sinar ultraviolet, pengolahan citra (rotasi, cropping, dan resize), pemecahan komponen warna RGB, ekstraksi fitur GLCM, dan klasifikasi dengan metode k-Nearest Neighbor (KNN). Metode KNN mampu mengklasifikasi keaslian uang kertas dengan perolehan akurasi 88% menggunakan nilai K = 3 dan 7.Kata Kunci: Uang Kertas Rupiah, Keaslian Uang, Gray Level Co-occurrence Matrix, KNearest Neighbor
Deteksi Kendaraan Truk pada Video Menggunakan Metode Tiny-YOLO v4 Primasdika Yunia Putra; Aji Seto Arifianto; Zilvanhisna Emka Fitri; Trismayanti Dwi Puspitasari
Jurnal Informatika Polinema Vol. 9 No. 2 (2023): Vol 9 No 2 (2023)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v9i2.1243

Abstract

Computer vision mampu meniru kemampuan manusia dalam hal mengenali sesuatu dengan ciri visual, dikarenakan bersifat konsisten. Deteksi kendaraan secara real-time dalam video pengamatan di jalan raya menjadi salah satu topik yang menarik diangkat dalam riset. Mendeteksi truk memiliki tantangan tersendiri karena memiliki kesamaan dimensi dengan bus dan struktur mekanis yang menyerupai pikap. Mendeteksi objek dengan metode YOLO (You Only Look Once) sangat populer. Langkah awal dilakukan percobaan dengan bobot dan model asli YOLO, namun hanya mampu mendeteksi bagian kepala dan bak truk saja, jika ada truk bermuatan maka bounding box tidak berhasil menandainya. Sehingga dilakukan custom dataset dengan cara membuat bounding box untuk seluruh bagian kepala, bak serta truk yang bermuatan. Tiny-YOLO sebagai varian dari YOLO dipilih karena strukturnya lebih sederhana dan kompatibel dengan perangkat low-end hingga high-end. Tiny-YOLO v4diimplementasikan pada 3 perangkat dengan spesifikasi berbeda, menghasilkan akurasi pengujian 98,2% (13FPS) pada perangkat A, 98% (28FPS) pada perangakt B dan 97,5% (38FPS) pada perangkat C. Pengaruh spesifikasi perangkat keras terhadap perolehan FPS yang didapat dan akurasi pendeteksian ditandai dengan perbedaan hasil yang signifikan pada saat pengujian. Semakin tinggi FPS maka semakin menurun akurasi pendeteksian. Untuk perangkat B dan C dengan spesifikasi CPU diatas 3.0 GHz, RAM minimum 16 GB, GPU lebih dari 4GB, dapat menjalankan pendeteksian truk menggunakan Tiny-Yolo v4 secara real-time dengan baik.
Co-Authors Achmad Sirojudin Alfiani Nur Aziza Anfasa Syahrul Habibie Anik Nur Novitasari E S Ardan Venora Falahudin Ayunda Kusuma Wardani Bachtiar Juli Anandi Defi Tamara Didit Rahmat Hartadi Dwi Putro Sarwo Setyohadi Fendik Eko Purnomo Hariyono Rakhmad Hendra Yufit Riskiawan I Gede Wiryawan Kasiyati Kasiyati Khafidurrohman Agustianto Kursita Dewi Safitri M. Haerul Anam Mariska, Alvia Rizqi Mochamat Bintoro Moechammad Sarosa Moh. Miqdad Nidhom Fahmi MUHAMMAD HAFIDH FIRMANSYAH Najmi Nurus Shofi Nugroho Setyo Wibowo Onny Setyawati Primasdika Yunia Putra Taufiq Rizaldi Taufiq Rizaldi Trismayanti Dwi Puspitasari Wahyu Kurnia Dewanto Widya Yuristika Oktavia Wike Sri Widari Zilvanhisna Emka Fitri Zilvanhisna Emka Fitri