Garuda - Garba Rujukan Digital

p-Index From 2020 - 2025

1.829

P-Index

This Author published in this journals

All Journal Seminar Nasional Aplikasi Teknologi Informasi (SNATI) TELKOMNIKA (Telecommunication Computing Electronics and Control) Jurnal IPTEK Seminar Nasional Teknologi Informasi Komunikasi dan Industri Jurnal Teknologi Informasi dan Terapan (J-TIT) JEECS (Journal of Electrical Engineering and Computer Sciences) West Science Social and Humanities Studies Science Information System and Technology

Eko Prasetyo

Universitas Bhayangkara Surabaya

Author-ID : 861361

Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Mathematics Mechanical Engineering Public Health Social Sciences

Published : 27 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3

Multi-class K-support Vector Nearest Neighbor for Mango Leaf Classification Eko Prasetyo; R. Dimas Adityo; Nanik Suciati; Chastine Fatichah
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 16, No 4: August 2018
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v16i4.8482

K-Support Vector Nearest Neighbor (K-SVNN) is one of methods for training data reduction that works only for binary class. This method uses Left Value (LV) and Right Value (RV) to calculate Significant Degree (SD) property. This research aims to modify the K-SVNN for multi-class training data reduction problem by using entropy for calculating SD property. Entropy can measure the impurity of data class distribution, so the selection of the SD can be conducted based on the high entropy. In order to measure performance of the modified K-SVNN in mango leaf classification, experiment is conducted by using multi-class Support Vector Machine (SVM) method on training data with and without reduction. The experiment is performed on 300 mango leaf images, each image represented by 260 features consisting of 256 Weighted Rotation- and Scale-invariant Local Binary Pattern features with average weights (WRSI-LBP-avg) texture features, 2 color features, and 2 shape features. The experiment results show that the highest accuracy for data with and without reduction are 71.33% and 71.00% respectively. It is concluded that K-SVNN can be used to reduce data in multi-class classification problem while preserve the accuracy. In addition, performance of the modified K-SVNN is also compared with two other methods of multi-class data reduction, i.e. Condensed Nearest Neighbor Rule (CNN) and Template Reduction KNN (TRKNN). The performance comparison shows that the modified K-SVNN achieves better accuracy.

Reduksi Data Latih pada K-Support Vector Nearest Neighbor Menggunakan Entropy Eko Prasetyo; R. Dimas Adityo; Nanik Suciati; Chastine Fatichah
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2018
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Pemilihan sebagian data latih atau reduksi data latih yang mempunyai pengaruh pada garis keputusan klasifikasi penting dilakukan. Tujuannya untuk mengurangi beban sistem pada tahap pelatihan. Sebagai metode reduksi data, K-Support Vector Nearest Neighbour (K-SVNN) mendapatkan hasil berdasarkan ketinggian nilai Significant Degree (SD) masing- masing data. Nilai SD dihitung menggunakan variabel LVRV (Left Value dan Right Value). Sayangnya, LVRV hanya dapat digunakan pada kasus klasifikasi biner. Penelitian ini melakukan uji coba penggunaan Entropy untuk menghitung SD. Secara konseptual, Entropy memberikan nilai kemurnian distribusi kelas data sehingga dimungkinkan penggunaan Entropy untuk menghitung SD pada kasus multi kelas. Pada makalah ini, disajikan analisis perbandingan perilaku nilai SD antara menggunakan LVRV dan Entropy. Hasil reduksi data menggunakan threshold (T) > 0, didapatkan akurasi yang sama pada kedua metode, sedangkan klasifikasi dengan reduksi data latih memberikan nilai akurasi lebih tinggi daripada tanpa reduksi. Hal ini membuktikan bahwa entropy dapat digunakan untuk menggantikan LVRV untuk menghitung SD.

ANALISIS FITUR TEKSTUR DAUN MANGGA DENGAN FISHER’S DISCRIMINANT RATIO UNTUK PENCAPAIAN FITUR YANG INFORMATIF Eko Prasetyo
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

Mango tree species recognition system based on the texture of leaves on the previous system gives accuracy up to 88.89%. This indicates that feature selection of research on the mango tree species recognition need to be taken into account. In this research, analysis of mango leaf texture features are used. There are 3 types of features that is: statistics, invariant moment, and the co- occurrence matrix. Methods for analyzing the feature is Fisher's Discriminant Ration (FDR). This method obtained from a number of informative features, that is: energy (co-occurrence), uniformity (statistics), the third moment (statistics), entropy (co-occurrence), entropy (statistical), and homogeneity (co-occurrence). Performance testing is done by comparing the use of old and new features on the K-Nearest Neighbor method with the value K is 3, 5, 7, and 11. The results showed that the accuracy of the K-NN method with new features reach 0.90, and tend to be better than the old features.

DETEKSI WILAYAH CAHAYA INTENSITAS TINGGI PADA CITRA DAUN MANGGA UNTUK KLASIFIKASI JENIS POHON MANGGA Eko Prasetyo; R. Dimas Adityo; Nanik Suciati; Chastine Fatichah
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2017: SNTIKI 9
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (537.616 KB)

Masalah yang dihadapi pada citra daun mangga hasil akuisisi dalam klasifikasi jenis pohon mangga adalah adanya wilayah dalam citra yang terpapar cahaya tinggi. Jika wilayah ini tergabung dalam wilayah pembangkitan fitur warna dan tekstur maka nilai fitur yang dibangkitkan dapat terdistorsi dari hasil yang benar. Untuk menghindari masalah tersebut maka wilayah ini harus dipisahkan. Untuk mendeteksi wilayah cahaya intensitas tinggi penulis menggunakan dua threshold yang dikembangkan dari threshold T. Threshold T didapatkan dengan metode Otsu. Nilai threshold atas (Ta) didapat dengan menaikkan nilai T beberapa persen. Nilai threshold bawah (Tb) didapat dengan menurunkan nilai T beberapa persen. Dalam penelitian ini, penulis menggunakan Saturation sebagai basis deteksi, karena merupakan komponen yang memberikan informasi kekuatan warna yang dipengaruhi oleh cahaya. Nilai piksel rendah pada komponen ini menyatakan pengaruh cahaya yang tinggi. Dari hasil uji coba 30 citra, rata-rata dua nilai threshold, Ta dan Tb, masing-masing Ta = 0.9T atau T-10%T dan Tb = 1.7T atau T+70%T. Hasil yang didapatkan dari penelitian ini adalah wilayah intensitas tinggi pada citra daun mangga dapat dideteksi dengan cukup baik. Kinerja recall 0.78, ini berarti ada sekitar 22% wilayah yang gagal dideteksi, sedangkan precision 0.57 berarti sekitar 43% piksel bukan intensitas tinggi yang terdeteksi.

Design of Expert System Diagnosis of Catfish Disease with Forward Chaining Method Erwin Dwi Riyanto; Eko Prasetyo; Rifki Fahrial Zainal; Rani Pubaningtyas; Fardanto Setyatama; Wiwiet Herulambang; Syariful Alim; Rahmawati Febriyaning Tias
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 7 No. 1 (2022): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

The expert system can be used as a means for consulting and assisting experts and catfish breeders who areexperiencing problems in identifying catfish diseases and their solutions. So that this expert system can be accessedeasily by anyone and anywhere connected to the internet network, this expert system is made web-based. The MySQLdatabase used in this system will store facts that were built using the PHP programming language. Likewise, systemdevelopment is only limited to diagnosing catfish diseases. The output of this system is in the form of diseaseinformation in catfish and how to handle it. The form of research used by the author is a literature study and is appliedto experimental research. The software development method used by the author is to use the Forward Chaining methodwhich consists of rules. The results of the research that have been made, it is found that this website and expert systemmake it easy for ordinary people or beginners to cultivate catfish in order to produce healthy and superior catfish.

Application of Obligatory Prayer Learning Based on Augmented Reality Rahmawati Febriyaning Tias; M. Mahaputra Hidayat; Eko Prasetyo; Ari Tria Widagda; Anis Suryaningrum
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 6 No. 2 (2021): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Prayer is a physical, mental, and spiritual activity that gives good meaning to relationships with Allah, fellow human beings, and oneself. Prayer begins with ablution first to remove najis and hadats. Religion is a rule, guideline, teaching, or system that governs beliefs, beliefs, or beliefs. Islam was revealed by Allah SWT. In Islam, expressing gratitude for every Muslim to the Creator is by praying. Moreover, at this time, the current guidance book on prayer procedures is still running in the delivery of information in the form of text and 2D images. This way is not valuable because it is not mobile style, while currently, human mobility is higher. In this study, we are designing and building a learning application of obligatory prayer based on augmented reality to run on Android-based smartphones and can be studied anywhere and anytime without being limited by space and time. This application contains procedures for ablution and movements of people praying in the form of 3D animation and audio.

Classification of The Nutrition Status Toddler Using the SVM Method (Case Study: Banjaragung Village, Bareng, Jombang) Eko Prasetyo; Rahmawati Febrifyaning Tias; Efilah Risqi Maulana
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 6 No. 1 (2021): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Improving the health status of children under five is very necessary in determining the next generation of the Indonesian nation. One of the efforts that can be realized is to maintain the nutrition of children under five in the community. Balanced nutrition can increase immunity and increase intelligence so as to make normal growth. In social life, nutritional status is obtained through anthropometric measurements at a posyandu where people generally use the BB/U index or body weight compared to age to determine the nutritional status of toddlers. This study aims to make it easier to identify the nutritional status of toddlers using Data Mining with Support Vector Machine (SVM). system built with PHP programming language and postgreSQL database. This study uses data on 314 toddlers in 4 groups of posyandu in the village. The data was tested 2 times, the first with a 50:50 comparison and the second 70:30 for training data and testing data. The results showed an accuracy of 96% and 98%, in other words, SVM was categorized as good for testing the nutritional status of children under five.

Expert System for Diagnosis of Blood Fever Disease Dengue Using the Chaining and Backward Method Certainty Factor Rifki Fahrial Zainal; Eko Prasetyo; Achmad Irfan Ferdiansyah
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 2 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Dengue Hemorrhagic Fever is a disease that is quite popular in Indonesia. Judging from the large number of patients infected with the disease and not a small number of patients died due to not being helped immediately. Lack of public sensitivity to the symptoms of dengue hemorrhagic fever is what ultimately causes many casualties,due to late getting medical treatment. Thus, accurate analytical skills are needed in assisting the patient diagnosis process. The Backward Chaining method is a chain that is traversed from a hypothesis back to the facts that support the hypothesis, and the Certainty Factor is a method to prove whether a fact is certain. The system can be run if the user enters the symptoms experienced and provides a confidence value for the symptoms they are experiencing and then gets a diagnosis and a solution.

Study Program Classification System Informatics Engineering of Ubhara Surabaya Wahyu Dyah Rizki Septiana; Eko Prasetyo; Rani Purbaningtyas
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 1 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

One indicator to improve the quality of a university is the number of students who graduate on time. But the problem that often occurs at Bhayangkara University in Surabaya is the number of students entering and the number of students graduating unbalanced. Therefore this research was made to classify the period of study of students by using variables in the form of social studies semester 1-4, school origin, work status, morning / evening class status, and sex. This study aims to classify the length of time a student studies on time or late using the naïve bayes method. The results of this study indicate that the system is able to classify training data and test data on experiments conducted in each batch, the highest accuracy results are 59% and the lowest accuracy results are 56%.

Applying the Weighted Product Method for The Best Selection of Personal Quality Control in Pt. Pacific Equinox Surabaya M Mahaputra Hidayat; Eko Prasetyo; Sona Ahmad Susanto
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 1 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

The aim of this research is to design and implement a decision support system software for the selection of the best quality control at PT. Pacific Equinox Surabaya. The intent and purpose of this research is to study the process of selecting the best employees who have been working on a manual system into a computerized system and use the Weighted Product method as an algorithm to facilitate the process of selecting the best employees.This system also has the advantage of helping the management process data and values of PT. Pacific Equinox Surabaya employees. In addition, more efficient time efficiency and also helps in the process of making reports required by management.The results of this study are applications that can make it easier to analyze a number of data, in order to help provide information as a result of the best employee decision making. But this system also still has weaknesses in terms of facilities and program appearance so that it still needs improvement

Co-Authors Achmad Irfan Ferdiansyah Achmad Kiki Qushayri Wahyu Kusuma Afif Nuzia Al-Asadi Ahmad Sarif Hikmawan Alamsyah Anis Suryaningrum Ari Tria Widagda Arif Arizal Arif Mardi Waluyo Azziyati Nur Bambang Teguh Wicaksono Budi Endarto Chastine Fatichah Devit Hari Firmanto Dita Mustika Anggraeni Efilah Risqi Maulana Erwin Dwi Riyanto Fardanto Setyatama Haryono Haryono Ida Lailatul Qurnia Indah Epriliati M Mahaputra Hidayat M. Mahaputra Hidayat Mas Nurul Hamidah Mochammad Muchid Nanik Suciati R Dimas Adityo R Dimas Prasetyo R. Dimas Adityo Rahmawati Febrifyaning Tias Rahmawati Febriyaning Tias Rani Pubaningtyas Rani Purbaningtyas Rifki Fahrial Zainal Riyan Sukma Sasongko Sona Ahmad Susanto Sutrisno Syariful Alim Wahyu Dyah Rizki Septiana Wildansyah Rokhmana Putra Wiwiet Herulambang

Title

Found 27 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 27 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 27 Documents
Search