Article Per Year (5 Year)
p-Index From 2020 - 2025
0.778
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Kursor INOVTEK Polbeng - Seri Informatika Jurnal Infomedia Aiti: Jurnal Teknologi Informasi
Ronny Susetyoko
Politeknik Elektronika Negeri Surabaya
Computer Science & IT Decision Sciences, Operations Research & Management

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Peramalan Gabungan Rantai Markov dan Model Deret Waktu Pada Kasus Peramalan Kurs Nilai Mata Uang Ronny Susetyoko
AITI Vol 13 No 2 (2016)
Publisher : Fakultas Teknologi Informasi Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (575.585 KB)

Abstract

This research aims to model forecasting of dollar against rupiah by combining the Markov chains and time series models. Probability transition matrix arranged based on 459 time series data of the exchange rates for Australia Dollar (AUD) from October 20, 2014 until August 31, 2016. There are ten classifications were determined based on the exchange rates from sharply lower to sharply higher. Forecast results based on summation of forecast results with the magnitude of the change based on the state prediction probability. Evaluation of the best models are based on the value of Mean Squared Error (MSE) preliminary models. Then, the best models are based on Mean Absolute Percentage Error (MAPE) and Mean Absolute Deviation (MAD) forecast result. The result, there are three models that are considered the best: MC-SMA18, MC-DES10, and MC-DES10.S. The model chosen for this case is MC-DES10.S with MAPE = 0,352% and MAD = 35,107.
Pemodelan Regresi Logistik Biner dan Ordinal Pada Proses Seleksi Mahasiswa Baru Program D3KPLN PENS Ronny Susetyoko
AITI Vol 15 No 1 (2018)
Publisher : Fakultas Teknologi Informasi Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (328.534 KB) | DOI: 10.24246/aiti.v15i1.56-66

Abstract

Starting in 2016, Politeknik Elektronika Negeri Surabaya (PENS) accept new students D3KPLN. D3KPLN scheme is a joint program between PENS with PT. PLN(Persero) as a form of link and match between higher education and industry needs. In the program, student candidates must go through five stages of selection, namely: academic potential test (stage-1), psychotest (stage-2), physical test (stage-3), medical tests (stage 4), and interview ( stage-5). To know the probability characteristics of the selection process generally used ordinal logistic regression model. As for knowing the accepted probability characteristics at each stage of selection used binary logistic regression model. Based on testing at each stage, the academic potential test scores are not the only determinants of acceptance as a student D3KPLN. However, other factors such as physical condition, medical test results, and interviews were also decisive. In general, theacademic potential test scores significantly affect the results of the selection phase by phase (phase-1 until phase-5). Binary logistic regression model of the final stage is = exp (-4.788 + 0.02127 Score) / (1 + (exp (-4.788 + 0.02127 Score)). This indicates that an increase of one score of the academic potential test increases probability of the applicants be accepted as student to 1.0215 times. The results of this modeling can be used as a reference to determine the passing grade in selection process next year.
Perbandingan Metode Random Forest, Regresi Logistik, Naïve Bayes, dan Multilayer Perceptron Pada Klasifikasi Uang Kuliah Tunggal (UKT) Ronny Susetyoko; Wiratmoko Yuwono; Elly Purwantini; Nana Ramadijanti
Jurnal Infomedia:Teknik Informatika, Multimedia & Jaringan Vol 7, No 1 (2022): Jurnal Infomedia
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jim.v7i1.2916

Abstract

Uang Kuliah Tunggal (UKT) adalah biaya yang dikenakan kepada setiap mahasiswa untuk digunakan dalam proses pembelajaran untuk program diploma dan program sarjana dari setiap jalur penerimaan yang ditetapkan oleh pemimpin perguruan tinggi negeri (PTN). Penetapan UKT masing-masing mahasiswa baru mengikuti kebijakan masing-masing PTN, tergantung ketersediaan informasi maupun target finansial berupa pendapatan negara bukan pajak (PNBP) yang tetapkan. Rumusan atau algoritma klasifikasi UKT yang digunakan tentunya akan berdampak pada distribusi dan ekspektasi rerata UKT. Tujuan dari penelitian ini adalah membandingkan kinerja beberapa metode yaitu Random Forest, Regresi Logistik, Naïve Bayes, dan Multilayer Perceptron dalam mengklasifikasi UKT. Beberapa atribut atau fitur yang digunakan dalam model adalah status rumah, penghasilan, jumlah rumah, jumlah motor, jumlah mobil, daya listrik, kepemilikan tanah, dan jumlah anak. Dataset sebanyak 873 record dibagi menjadi data training dan data testing masing-masing sebanyak 80% dan 20%. Untuk mendapatkan metode yang terbaik, dilakukan evaluasi kinerja empat metode tersebut didasarkan pada rerata akurasi, karakteristik fungsi tingkat akurasi terhadap jumlah fitur, dan nilai ekspektasi UKT. Hasil dari penelitian ini,  metode Random Forest, Regresi Linier, dan Multilayer Perceptron dapat digunakan sebagai model klasifikasi UKT karena memiliki rerata akurasi lebih dari 85%. Namun dari ketiga model tersebut, Random Forest dapat dipilih sebagai model klasifikasi terbaik dengan rerata akurasi 97,9%. Berdasarkan karakteristik fungsi tingkat akurasi, penggunaan metode Random Forest tidak harus melibatkan banyak fitur dalam model. Dengan menerapkan metode tersebut, ekspektasi rerata UKT sebesar Rp. 3,833,811 dan simpangan baku Rp. 2,123,758.
Perbandingan metode ARIMA dan ARIMAX dalam Memprediksi Jumlah Wisatawan Nusantara di Pulau Bali Faiq Riestiansyah; Devina Damayanti; Miranda Reswara; Ronny Susetyoko
Jurnal Infomedia:Teknik Informatika, Multimedia & Jaringan Vol 7, No 2 (2022): Jurnal Infomedia
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jim.v7i2.3336

Abstract

Indonesia memiliki berbagai potensi pemanfaatan yang berbeda tergantung dari sumber daya alamnya seperti bahan tambang, lahan pertanian, pariwisata dan lain-lain. Untuk meningkatkan pendapatan pada sektor pariwisata diperlukan data peramalan jumlah wisatawan yang berkunjung ke Pulau Bali. Data hasil peramalan tersebut dapat menjadi acuan untuk pengembangan dan pengoptimalisasian hal yang perlu diperbaiki di sektor kepariwisataan ini. Tujuan dari dilakukannya penelitian ini adalah untuk mengetahui perbandingan hasil prediksi terhadap Jumlah Wisatawan Nusantara yang berkunjung ke Pulau Bali. Salah satu model yang sering digunakan untuk masalah peramalan adalah model ARIMA. Model ARIMA yang juga disebut Runtut Waktu Box-Jenkins ini hanya cocok digunakan untuk kasus peramalan jangka pendek, karena jika digunakan untuk peramalan jangka panjang, model ini biasanya akan cenderung menghasilkan grafik time series datar. Setelah melakukan kedua pemodelan (ARIMA dan ARIMAX) selanjutnya membandingkan performa kedua model tersebut dalam melakukan prediksi Jumlah Wisatawan Nusantara yang berkunjung ke Pulau Bali dalam waktu tertentu dengan melihat error (RMSE) dari masing - masing model. Semakin rendah nilai RMSE maka semakin baik model tersebut bekerja dalam melakukan prediksi. Harapannya hasil dari penelitian ini dapat dimanfaatkan oleh siapapun yang memiliki kepentingan dalam pengembangan sektor pariwisata di Pulau Bali.
Sistem Deteksi Lampu Lalu Lintas Sebagai Asisten Pengemudi Menggunakan Convolutional Neural Network Akhmad Hendriawan; Muhammad Iqbal Millyniawan Pradana; Ronny Susetyoko
Jurnal Inovtek Polbeng Seri Informatika Vol 8, No 1 (2023)
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/isi.v8i1.3155

Abstract

Accident cases in Indonesia are increasing along with the increase in the number of motorized vehicles. From 2016 to 2017, speed limit violations increased by 96.20% and violations of road markings or signs also increased by 5.54%. Intelligent transportation system is one solution to reduce the number of accidents. Currently Driver Assistance Systems (DAS) are being developed in the automotive world. The purpose of this research is to design a watershed based on three input parameters for determining recommended actions, namely: 1) distance to the vehicle behind; 2) vehicle speed; and 3) traffic light status with recommendation action using fuzzy rule base. Lidar sensor for distance detection and GPS for monitoring vehicle speed. The YOLOv4 Algorithm method is used to detect traffic lights. The results of this study, the accuracy of sign color recognition is 92.831% with a detection speed of up to 8.94 FPS. The most stable reading distance is between 1 – 8-meters with a light intensity of 10 – 3200 lux and a tilt angle of up to 90 degrees. There is a drop in processing speed of up to 1.5 FPS during system integration. This DAS is effective enough to be applied to two-wheeled and fourwheeled motorized vehicles.
APPLICATION OF MULTISTAGE CLUSTERING FOR MAPPING ECONOMIC POTENTIAL IN EAST JAVA PROVINCE Ronny Susetyoko; Edi Satriyanto; Alfi Fadliana; Muhammad Syahfitra
Jurnal Ilmiah Kursor Vol 12 No 1 (2023)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v12i01.325

Abstract

This study aims to map the economic potential in East Java Province based on GRDP according to business field category. Multistage clustering is a method developed for outlier data and datasets with large variance. Multistage clustering is a combination of Ordering Points to Identify the Clustering Structure (OPTICS) and K-Means. The first stage was grouped using OPTICS. The outlier data resulting from the clustering stage is used as a dataset in the second stage using K-Means. The performance of this method is compared with several other methods, namely: K-Means, DBSCAN – K-Means, Agglomerative, Fuzzy C-Means (FCM), Possibilistic C-Means (PCM), and Fuzzy Possibilistic C-Means (FPCM) based on the characteristics of the Silhouette score and Davies-Bouldin score. Multistage clustering was chosen as the best method with a Silhouette score of 0.442 and Davies-Bouldin score of 0.388. With the Elbow method and the two metrics, the optimum number of clusters is 8 clusters. The results of this mapping method, the City of Surabaya forms a separate cluster which has the highest economic potential in 15 categories of business fields. Next Gresik, Pasuruan, Sidoarjo, and Probolinggo have the second highest economic potential with 10 categories of business fields ranking in the top 3.
Co-Authors Akhmad Hendriawan Alfi Fadliana Devina Damayanti Edi Satriyanto Elly Purwantini Faiq Riestiansyah Miranda Reswara Muhammad Iqbal Millyniawan Pradana Muhammad Syahfitra Nana Ramadijanti Wiratmoko Yuwono