Articles
IMPLEMENTASI MOVING AVERAGE FILTER PADA MIKROKONTROLER SEBAGAI PEREDAM NOISE SENSOR PIEZO ELEKTRIK UNTUK MENDETEKSI GELOMBANG SEISMIK (GEMPA BUMI)
Zulharbi Zulharbi;
Firdaus Firdaus;
Yul Antonisfia;
Sarjon Defit
Prosiding Semnastek PROSIDING SEMNASTEK 2014
Publisher : Universitas Muhammadiyah Jakarta
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Getaran akibat gempa bumi akan mengakibatkan adanya frekuensi gelombang seismik denganfrekuensi rendah (0Hz - 20Hz), untuk mendeteksi keberadaan frekuensi gelombang seismiktersebut dapat menggunakan sensor piezo elektrik. Piezo elektrik adalah sebuah sensor seismikyang mempunyai getaran gempa beramplitudo rendah dan sangat mudah terkontaminasi noisesehingga dibutuhkan filter untuk meredam sinyal noise tersebut. Moving Average (MA) filteradalah suatu metode yang sederhana dan berguna untuk menapis derau acak yang terdapat padaderau asli. MA filter bekerja dengan cara meratakan sejumlah titik tertentu dari isyarat masukanuntuk menghasilkan tiap titik dari isyarat luaran. Gelombang seismic (getaran buatan) padapenelitian ini adalah dengan memberikan amplitudo sensor piezo PVDF antara 3mm, 5mm, 7mm,9mm dan 12mm pada frekuensi 2 Hz (konstan). Sensor piezo mendeteksi kekuatan getaran buatandengan menggunakan Moving Average Filter yang menghasilkan nilai SNR (signal to noiseratio) lebih kecil dibandingkan tidak menggunakan MAF Nilai PGA (peak groundacceleration) dalam satuan grafitasi akan tinggi pada saat sinyal amplitude getaran yangdiberikan juga tinggi (PGA = 0,01G pada saat amplitude getaran 3mm dan 1,43G pada saatamplitude getaran 12 mm).
Classification of Customer Loans Using Hybrid Data Mining
Eka Praja Wiyata Mandala;
Eva Rianti;
Sarjon Defit
JUITA : Jurnal Informatika JUITA Vol. 10 No. 1, May 2022
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (903.223 KB)
|
DOI: 10.30595/juita.v10i1.12521
At this time, loans are one of the products offered by banks to their customers. BPR is an abbreviation of Bank Perkreditan Rakyat. BPR is one of the banks that provide loans to their customers. The problem that occurs is that the number of loans given to customers is often not on target and does not meet the criteria. We propose a hybrid data mining method which consists of two phases, first, we will cluster the eligibility of customers to be given a loan using the k-means algorithm, second, we will classify the loan amount using data from the clustering of eligible customers using k-nearest neighbors. As a result of this study, we were able to cluster 25 customers into 2 clusters, 10 customers into the "Not Feasible" cluster, 15 customers into the "Feasible" cluster. Then we also succeeded in classifying customers who applied for new loans with occupation is Entrepreneur, salary is ≥ IDR 5000000, loan guarantees Proof of Vehicle Owner, account balance is < IDR 5000000 and family members is ≥ 4. And the results, classified as Loans with a small amount. We obtained the level of validity of the data testing of each input variable to the target variable reached 97.57%.
Penerapan Algoritma C4.5 untuk Klasifikasi Data Rekam Medis berdasarkan International Classification Diseases (ICD-10)
Yudha Aditya Fiandra;
Sarjon Defit;
Yuhandri Yuhandri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 1 No 2 (2017): Agustus 2017
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (579.053 KB)
|
DOI: 10.29207/resti.v1i2.48
Abstract The medical record data is the patient's current record of medical records, the medical record data only being data stacked and not traced to generate useful knowledge for the hospital. This study can process the medical record data to classify the disease that occurs in sleeping sickness based on ICD-10. The method used in this research is C4.5 algorithm method by using attribute of international disease code as attribute of destination label as many as 21 international disease group, that is: A00-B99 up to Z00-Z99. This study yields a decision of the value code, C4.5 code can represent as many as 14 attribute values ​​of disease code objectives and data percentage that read more than 66%. The conclusion of this research is C4.5 algorithm help classify international disease code based on ICD-10 and decision tree making which can give information of any disease that often happened at hospital Keywords: data mining, classification, C4.5, medical records, ICD-10
Identifikaasi Tingkat Kerusakan Peralatan Laboratorium Komputer Menggunakan Metode Rough Set
Hengki Juliansa;
Sarjon Defit;
Sumijan Sumijan
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 2 No 1 (2018): April 2018
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (256.204 KB)
|
DOI: 10.29207/resti.v2i1.274
Computer laboratory is a means to support college pratikum. This equipment should always be in a ready-made state or suiTabel for use, whether computer or other means. In case of damage, it should be promptly resolved. To further accelerate the handling of damage, it is necessary a method to identify it. The Rought set method is a solution for this identification by means of several stages: Infomation System; Decision System; Equivalence Class; Descernibilty matrix and Descernibilty matrix of module D; Reduction; Generate Rules. The results of this study from 5 equipment in the computer laboratory STMIK Bina Nusantara Jaya Lubuklinggau after performing the steps of settlement by rough set method found 8 rules to get a new decision is whether the equipment is still worthy of use, repaired or replaced, then this method is very suiTabel applied in identifying the extent of damage.
Analisis Rekam Medis untuk Menentukan Pola Kelompok Penyakit Menggunakan Algoritma C4.5
Rian Rafiska;
Sarjon Defit;
Gunadi Widi Nurcahyo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 2 No 1 (2018): April 2018
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (440.523 KB)
|
DOI: 10.29207/resti.v2i1.275
The Medical Record contains records and documents of patient identity, examination results, treatment, actions and services provided to the patient. Medical records are very important for patient care because with complete data can provide information in determining diagnostic and clinical decisions. The completeness of the medical record determines the quality of the services provided. Regarding the pattern of the tendency of disease suffered by a group of people still not excavated to be used as a reference when doing panyuluhan or prevention of disease. Finding a common pattern of disease groups in the community based on the International Classification of Diseases (ICD) -X. In this study used the classification method with algorithm C4.5 with the amount of data as much as 709 sourced from the Medical Record of General Hospital General Hospital (RSUD) Major General H.A Thalib Kerinci. Determination of the next analysis is to apply the grouping into several attributes, namely group of regions, age groups, disease groups and groups of sex. Further data is processed and done by using Rapid Miner software. The results of the calculation is a pattern that can be used to analyze patterns of disease tendency experienced by the community.
Identifikasi Anggota dalam Penempatan pada Struktur Organisasi menggunakan Metode Profile Matching
Ahmadi Ahmadi;
Sarjon Defit;
Jufriadif Na’am
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 2 No 2 (2018): Agustus 2018
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (448.767 KB)
|
DOI: 10.29207/resti.v2i2.358
The organization of a political party is one organization that must have an organizational structure. Each cadre who sits in the structure must have skills that match his field. The goal is for the organization to grow better. For each cadre to occupy the appropriate structure, identification must be performed. The method used to identify is Profile Matching on the data of each prospective member. Based on the test results obtained cadre with a special aspect of 60% and the general aspect of 40% is the right one. Then this method is suiTabel to be used in identifying cadres who will occupy positions in organizational structure.
Prediksi Hasil Ujian Kompetensi Mahasiswa Program Profesi Dokter (UKMPPD) dengan Pendekatan ANFIS
Fajri Marindra Siregar;
Gunadi Widi Nurcahyo;
Sarjon Defit
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 2 No 2 (2018): Agustus 2018
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (925.046 KB)
|
DOI: 10.29207/resti.v2i2.388
The main objective of this study was to predict the outcome of student's competency exam of the medical profession (UKMPPD) using Adaptive Neuro-Fuzzy Inference System (ANFIS). Data obtained from the Faculty of Medicine Universitas Riau’s student database in 2015 which amounted to 170 data. Input variables were membership status, length of study, and grade point average. Furthermore, the data were analyzed using MATLAB software by setting the number of membership function 2 2 2 and Gbell membership function. The results showed that the method is able to predict the outcome of UKMPPD with Mean Average Percentage Error (MAPE) 0.07%, minimum 0.00%, and maximum 0.44%.
Algoritma Fungsi Perlatihan pada Machine Learning berbasis ANN untuk Peramalan Fenomena Bencana
Anjar Wanto;
Sarjon Defit;
Agus Perdana Windarto
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 2 (2021): April 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (628.416 KB)
|
DOI: 10.29207/resti.v5i2.3031
Research has been carried out with several training functions using standard backpropagation methods, One-Step Secant (OSS), and Bayesian regulation. The purpose of this study was to (i) analyze the Performance accuracy (Performance) of the standard backpropagation method and (ii) optimize the training function with the One-Step Secant (OSS) and Bayesian regulation methods to obtain comparison results of the three methods in the search for the best results implementation of disaster phenomenon forecasting data. The research method is based on quantitative methods with times-series data on disaster phenomena in Indonesia over the last ten years (2011-2020) which were analyzed using two network architecture models, namely 4-8-1 and 4-10-1. The results showed that the 4-8-1 architectural model with the Bayesian regulation training function method was able to optimize quite well through accelerating training time and resulted in a low MSE measurement, although not the lowest with an epoch value of 197 iterations and a Performance of 0.0148480766. The lowest epoch value is generated by the OSS method, but it Performs poorly. The best Performance is produced by the standard backpropagation method with the traingd training function, but the training process for achieving convergence is also too long. In general, it can be concluded that the 4-8-1 architectural model with Bayesian regulation can be used to predict (predict) the phenomenon of natural disasters in Indonesia because the training time to achieve convergence is not too long and Performs exceptionally well.
The Application of C4.5 Algorithm for Selecting Scholarship Recipients
Fristi Riandari;
Sarjon Defit
ComTech: Computer, Mathematics and Engineering Applications Vol. 13 No. 1 (2022): ComTech
Publisher : Bina Nusantara University
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21512/comtech.v13i1.7307
The scholarship program is one of the promotional techniques used by many universities, and the right scholarship award will certainly be an attraction for many people. STMIK Pelita Nusantara is one of the universities that organizes a scholarship program. In the current difficult economic conditions, the scholarship program is the target of many prospective students who want to continue their education in higher education. However, the absence of tools to process large amounts of data make determining scholarship recipients less effective and time-consuming. This situation is seen by the fact that some students are still unable to maintain the scholarships they receive. In the research, a classification model was proposed using the C4.5 algorithm approach by utilizing past data to facilitate the decision making of the scholarship program. This classification process produced a decision tree that could be used as a decision-making tool. Scholarships were awarded based on several criteria: academic potential, vocational potential, parents’ income, number of dependents, and employment status. Based on the data processing results of students who apply for scholarships in 2020 with predetermined criteria, the highest root is obtained. It consists of node 1 for academic potential, node 1.1 for vocational potential, and node 1.2 for parental income. The resulting decision tree model is expected to help to make decisions quickly and on target.
Data Mining Menggunakan Metode K-Means Clustering Untuk Menentukan Besaran Uang Kuliah Tunggal
Haris Kurniawan;
Sarjon Defit;
Sumijan
Journal of Applied Computer Science and Technology Vol 1 No 2 (2020): Desember 2020
Publisher : Indonesian Society of Applied Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52158/jacost.v1i2.102
Digitalisasi dan otomasi dalam pelayanan mahasiswa di Perguruan Tinggi dapat menghasilkan big data. Amanat pemerintah dalam Peraturan Mentri Riset Teknologi dan Pendidikan Tinggi agar besaran Uang Kuliah Tunggal (UKT) di Perguruan Tinggi Negeri dibagi ke dalam 5 kelompok berdasarkan tingkatan kondisi sosial ekonomi orang tua. Dalam proses menetapkan UKT begitu banyak indikator sosial ekonomi orang tua yang harus dijadikan acuan sehingga menyulitkan dalam mengidentifiksi dan mencari formula yang tepat. Untuk mengelompokkan data mahasiswa ini dilakukan dengan teknik data mining menggunakan metode K-Means Clustering. Metode ini mengelompokkan besaran UKT mahasiswa berdasarkan pola atau kemiripan data sosial ekonomi orang tua. Data yang digunakan dalam penelitian ini adalah data calon mahasiswa baru Unversitas Negeri Padang. Pengelompokan ini bertujuan untuk membantu menetapkan besaran UKT calon mahasiswa baru pada Perguruan Tinggi Negeri. Hasil dari penelitian diperoleh 5 kelompok besaran UKT, terdiri dari UKT kategori 1 Rp. 500.000, UKT kategori 2 Rp. 1.000.000, UKT kategori 3 Rp. 2.000.000, UKT kategori 4 Rp. 3.000.000 dan UKT kategori 5 Rp. 4.000.000.