Article Per Year (5 Year)
p-Index From 2021 - 2026
1.407
P-Index
This Author published in this journals
All Journal Voteteknika (Vocational Teknik Elektronika dan Informatika) Sisfo: Jurnal Ilmiah Sistem Informasi Jurnal Sains Informatika Terapan (JSIT) Jurnal Pengabdian Masyarakat Bangsa ANTHOR: Education and Learning Journal
Rafika Sani
Institut Pendidikan Dan Teknologi ‘Aisyiyah Riau
Religion Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Mechanical Engineering Social Sciences

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Penerapan Metode Neural Network untuk Prediksi Harga Bawang Putih di Kota Singkawang Fadlul Hamdi; Hendro Budiantoro; Rafika Sani; Rezki Rusydi; Sarjon Defit
Voteteknika (Vocational Teknik Elektronika dan Informatika) Vol 12, No 2 (2024): Vol. 12, No 2, Juni 2024
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/voteteknika.v12i2.128039

Abstract

Bawang putih adalah komoditas penting dalam perekonomian Kota Singkawang. Penelitian ini bertujuan untuk menerapkan metode Neural Network dalam meramalkan harga bawang putih di kota tersebut. Data harga bawang putih dari Badan Pusat Statistik Kota Singkawang untuk periode tahun 2016-2023 digunakan dalam penelitian ini. Setelah melalui proses analisis dan pengolahan data, model Neural Network dilatih menggunakan data historis untuk memprediksi harga bawang putih di masa mendatang. Hasil prediksi menunjukkan bahwa harga bawang putih cenderung stabil selama dua tahun ke depan, dengan nilai tetap pada angka 30,701 untuk bulan 1 tahun 2024, 30,303 untuk bulan 2 tahun 2024, dan seterusnya hingga tahun 2025. Penelitian ini memberikan wawasan penting bagi para pelaku pasar dalam mengantisipasi perilaku pasar dan pengambilan keputusan di sektor bawang putih di Kota Singkawang.Kata kunci : bawang putih, harga, prediksi, Neural Network, Kota Singkawang Garlic is an important commodity in the economy of Singkawang City. This research aims to apply the Neural Network method in forecasting the price of garlic in the city. Garlic price data from the Central Bureau of Statistics of Singkawang City for the period 2016-2023 is used in this study. After going through the data analysis and processing process, the Neural Network model was trained using historical data to predict future garlic prices. The prediction results show that the price of garlic tends to stabilise over the next two years, with a fixed value of 30.701 for month 1 of 2024, 30.303 for month 2 of 2024, and so on until 2025. This research provides important insights for market players in anticipating market behaviour and decision-making in the garlic sector in Singkawang City.Keywords: garlic, price, prediction, Neural Network, Singkawang City
Perancangan Media Pembelajaran Berbasis Augmented Reality pada Pembelajaran Matematika untuk Kelas VIII di MTsN 2 Pasaman Sani, Rafika; Efriyanti, Liza; Supriadi, Supriadi; Derta, Sarwo
ANTHOR: Education and Learning Journal Vol 1 No 5 (2022): Vol 1 No 5. Page: 240 - 293
Publisher : Institut Teknologi Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/anthor.v1i5.46

Abstract

This research was conducted from the problems that the authors found during observations at MTsN 2 Pasaman which so far the teacher has not maximized the use of technology in learning mathematics, students only rely on learning from the teacher verbally, so students get bored quickly when learning takes place and have difficulty understanding the material taught by the teacher. Therefore, the authors design learning media based on Augmented Reality so that it can be an alternative learning media. The purpose of this research is to produce an Augmented Reality-based supporting media design for mathematics learning that is valid, practical and effective. The method used in this study is the Research andDevelopment (R&D) method using the Luther-Sutopo version of the Multimedia Development Life Cycle (MDLC), which consists of six stages, namely concept (conception), design (design), collecting material (material collection). assembly (manufacture), testing (testing), and distribution (distribution). And the product test was carried out in this study, namely the validity test given to lecturers of field experts or field experts, practicality tests carried out by mathematics subject teachers and effectiveness tests given to students at MTsN 2 Pasaman class VIII. Based on the results of product tests that have been carried out by the author of the validity test, the average value is 0.84 which is declared valid, for the practicality test, the average value is 0.88 which is declared practical and for the effectiveness test, the average value is obtained. the average is 0.87 which is declared effective.
Pelatihan Digital Marketing Tahap Pengembangan Teknik Iklan dan Pemahaman Indikator Analisis Periklanan Produk Masyarakat Desa Hangtuah Kecamatan Perhentian Raja Sukasih; Arham, Budi; Sani , Rafika
Jurnal Pengabdian Masyarakat Bangsa Vol. 4 No. 1 (2026): JURMAS BANGSA
Publisher : Riset Sinergi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jurmas.v4i1.936

Abstract

Kegiatan pengabdian kepada masyarakat ini dilatarbelakangi oleh masih rendahnya pemahaman pelaku Usaha Mikro, Kecil, dan Menengah (UMKM) di Desa Hangtuah Kecamatan Perhentian Raja terhadap teknik pengembangan iklan digital serta indikator analisis periklanan produk. Banyak pelaku usaha telah menggunakan media digital sebagai sarana promosi, namun belum mampu mengukur efektivitas iklan yang dijalankan. Tujuan kegiatan ini adalah untuk meningkatkan kemampuan masyarakat dalam mengembangkan teknik iklan digital serta memahami indikator analisis periklanan seperti impresi, jangkauan, click through rate, conversion rate, dan return on investment. Metode pengabdian yang digunakan meliputi penyuluhan, pelatihan praktis, simulasi pembuatan iklan, serta evaluasi pemahaman peserta. Hasil kegiatan menunjukkan adanya peningkatan pengetahuan dan keterampilan peserta dalam merancang iklan digital yang lebih terarah serta kemampuan membaca data kinerja iklan sebagai dasar pengambilan keputusan pemasaran. Kegiatan ini diharapkan dapat mendukung peningkatan efektivitas promosi produk dan keberlanjutan usaha masyarakat.
Comparative Analysis of SVM Accuracy and Effectiveness on Weka and Google Colab for Job Recommendations Rafika Sani; Nopa Wilyanita; Suparmi Suparmi; Tasya Maulidia
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 1 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2026
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i1.27101

Abstract

Data Mining is a crucial technique for processing large and complex datasets to uncover hidden patterns that support strategic decision-making. This study evaluates the effectiveness of the Support Vector Machine (SVM) method implemented using Weka and Google Colab to classify employees into two categories: those recommended for promotion (positive class) and those not recommended (negative class). The research aims to compare the performance of both implementations in providing accurate and objective job recommendations. The dataset used in this study consists of employee performance evaluation records. The SVM model was trained and tested using different implementation platforms: Weka and Google Colab. In Weka, the model was configured with a polynomial kernel and achieved an accuracy of 99.62%, with precision, recall, and F-measure values of 1.000, 0.952, and 0.975 for the "recommended" class and 0.996, 1.000, and 0.998 for the "not recommended" class. Meanwhile, the implementation in Google Colab, using the LIBSVM library with a polynomial kernel, produced an accuracy of 97.85%, with precision, recall, and F-measure values of 0.984, 0.932, and 0.957 for the "recommended" class and 0.978, 0.986, and 0.982 for the "not recommended" class. The comparison results indicate that the Weka implementation provides slightly higher accuracy and better classification performance. However, Google Colab offers more flexibility and scalability, making it suitable for handling larger datasets. The findings of this study highlight the potential of SVM as a reliable tool for employee performance evaluation and job promotion recommendations. The use of machine learning in human resource management can enhance decision-making processes, ensuring fairness and efficiency in personnel assessments.
Stacking Ensemble Model berbasis SVM, Random Forest, dan XGBoost untuk Klasifikasi Emosi dari Sinyal EEG Rafika Sani; Sukasih; Budi Arham
Jurnal Sains Informatika Terapan Vol. 5 No. 1 (2026): Jurnal Sains Informatika Terapan (Februari, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i1.930

Abstract

Klasifikasi emosi berbasis sinyal EEG (Electroencephalography) merupakan bidang penting dalam pemrosesan sinyal biomedis karena perannya dalam pengambilan keputusan, interaksi sosial, dan evaluasi kondisi psikologis. Namun, tingginya dimensi data, kompleksitas pola, serta kerentanan terhadap noise menjadi tantangan utama dalam analisis EEG. Penelitian ini menerapkan Stacking Ensemble Model yang mengombinasikan Support Vector Machine (SVM), Random Forest (RF), dan XGBoost (XGB) dengan Logistic Regression sebagai meta-learner untuk meningkatkan akurasi dan stabilitas prediksi emosi. Dataset yang digunakan berasal dari Kaggle dengan 2132 data dan 2549 fitur, mencakup tiga kelas emosi: negatif, netral, dan positif. Tahapan penelitian meliputi pengecekan missing value, normalisasi menggunakan StandardScaler, encoding label, serta pembagian data menjadi data latih dan uji. Hasil eksperimen menunjukkan akurasi model tunggal yang tinggi, yaitu SVM 94,8%, RF 98,6%, dan XGB 99,5%, sedangkan model stacking mencapai akurasi 99,5% dengan nilai precision, recall, dan f1-score mendekati 1,00. Hasil ini menunjukkan bahwa stacking ensemble mampu meningkatkan keandalan klasifikasi emosi berbasis EEG dan berpotensi diterapkan pada HCI, pemantauan kesehatan mental, serta sistem pengenalan emosi real-time.
Prediksi Harga Emas Harian Dan Multi-Horizon Menggunakan ARIMA, LSTM Dan Model Hybrid ARIMA-LSTM Budi Arham; Sukasih; Rafika Sani
Jurnal Sains Informatika Terapan Vol. 5 No. 1 (2026): Jurnal Sains Informatika Terapan (Februari, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i1.935

Abstract

Gold price forecasting is a crucial task in financial analysis due to high market volatility and dynamic price movements. This study aims to predict daily gold prices and perform multi-horizon forecasting up to 10 days ahead using Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and a hybrid ARIMA-LSTM model. The dataset consists of daily gold closing price data from January 2022 to December 2024 obtained from Yahoo Finance. Data preprocessing includes handling missing values, normalization using Min–Max scaling, and stationarity testing. ARIMA and LSTM models are developed independently to capture linear and nonlinear patterns, respectively, while the hybrid model combines both approaches by modeling ARIMA residuals using LSTM. Experimental results show that the hybrid ARIMA-LSTM model achieves the lowest prediction error compared to individual models, as indicated by RMSE, MAE, and MAPE values. Furthermore, multi-horizon forecasting results demonstrate that the hybrid model provides more stable and accurate short-term gold price predictions. These findings confirm that the hybrid modeling approach is effective and can support investors and analysts in decision-making processes.
Stacking Ensemble Model berbasis SVM, Random Forest, dan XGBoost untuk Klasifikasi Emosi dari Sinyal EEG Rafika Sani; Sukasih; Budi Arham
Jurnal Sains Informatika Terapan Vol. 5 No. 1 (2026): Jurnal Sains Informatika Terapan (Februari, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i1.930

Abstract

Klasifikasi emosi berbasis sinyal EEG (Electroencephalography) merupakan bidang penting dalam pemrosesan sinyal biomedis karena perannya dalam pengambilan keputusan, interaksi sosial, dan evaluasi kondisi psikologis. Namun, tingginya dimensi data, kompleksitas pola, serta kerentanan terhadap noise menjadi tantangan utama dalam analisis EEG. Penelitian ini menerapkan Stacking Ensemble Model yang mengombinasikan Support Vector Machine (SVM), Random Forest (RF), dan XGBoost (XGB) dengan Logistic Regression sebagai meta-learner untuk meningkatkan akurasi dan stabilitas prediksi emosi. Dataset yang digunakan berasal dari Kaggle dengan 2132 data dan 2549 fitur, mencakup tiga kelas emosi: negatif, netral, dan positif. Tahapan penelitian meliputi pengecekan missing value, normalisasi menggunakan StandardScaler, encoding label, serta pembagian data menjadi data latih dan uji. Hasil eksperimen menunjukkan akurasi model tunggal yang tinggi, yaitu SVM 94,8%, RF 98,6%, dan XGB 99,5%, sedangkan model stacking mencapai akurasi 99,5% dengan nilai precision, recall, dan f1-score mendekati 1,00. Hasil ini menunjukkan bahwa stacking ensemble mampu meningkatkan keandalan klasifikasi emosi berbasis EEG dan berpotensi diterapkan pada HCI, pemantauan kesehatan mental, serta sistem pengenalan emosi real-time.
Prediksi Harga Emas Harian Dan Multi-Horizon Menggunakan ARIMA, LSTM Dan Model Hybrid ARIMA-LSTM Budi Arham; Sukasih; Rafika Sani
Jurnal Sains Informatika Terapan Vol. 5 No. 1 (2026): Jurnal Sains Informatika Terapan (Februari, 2026)
Publisher : Riset Sinergi Indonesia (RISINDO)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jsit.v5i1.935

Abstract

Gold price forecasting is a crucial task in financial analysis due to high market volatility and dynamic price movements. This study aims to predict daily gold prices and perform multi-horizon forecasting up to 10 days ahead using Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and a hybrid ARIMA-LSTM model. The dataset consists of daily gold closing price data from January 2022 to December 2024 obtained from Yahoo Finance. Data preprocessing includes handling missing values, normalization using Min–Max scaling, and stationarity testing. ARIMA and LSTM models are developed independently to capture linear and nonlinear patterns, respectively, while the hybrid model combines both approaches by modeling ARIMA residuals using LSTM. Experimental results show that the hybrid ARIMA-LSTM model achieves the lowest prediction error compared to individual models, as indicated by RMSE, MAE, and MAPE values. Furthermore, multi-horizon forecasting results demonstrate that the hybrid model provides more stable and accurate short-term gold price predictions. These findings confirm that the hybrid modeling approach is effective and can support investors and analysts in decision-making processes.
Pelatihan Digital Marketing Tahap Pengembangan Teknik Iklan dan Pemahaman Indikator Analisis Periklanan Produk Masyarakat Desa Hangtuah Kecamatan Perhentian Raja Sukasih; Budi Arham; Rafika Sani
Jurnal Pengabdian Masyarakat Bangsa Vol. 4 No. 1 (2026): JURMAS BANGSA
Publisher : Riset Sinergi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62357/jurmas.v4i1.936

Abstract

Kegiatan pengabdian kepada masyarakat ini dilatarbelakangi oleh masih rendahnya pemahaman pelaku Usaha Mikro, Kecil, dan Menengah (UMKM) di Desa Hangtuah Kecamatan Perhentian Raja terhadap teknik pengembangan iklan digital serta indikator analisis periklanan produk. Banyak pelaku usaha telah menggunakan media digital sebagai sarana promosi, namun belum mampu mengukur efektivitas iklan yang dijalankan. Tujuan kegiatan ini adalah untuk meningkatkan kemampuan masyarakat dalam mengembangkan teknik iklan digital serta memahami indikator analisis periklanan seperti impresi, jangkauan, click through rate, conversion rate, dan return on investment. Metode pengabdian yang digunakan meliputi penyuluhan, pelatihan praktis, simulasi pembuatan iklan, serta evaluasi pemahaman peserta. Hasil kegiatan menunjukkan adanya peningkatan pengetahuan dan keterampilan peserta dalam merancang iklan digital yang lebih terarah serta kemampuan membaca data kinerja iklan sebagai dasar pengambilan keputusan pemasaran. Kegiatan ini diharapkan dapat mendukung peningkatan efektivitas promosi produk dan keberlanjutan usaha masyarakat.
Co-Authors Arham, Budi Budi Arham Efriyanti, Liza Fadlul Hamdi Hendro Budiantoro Nopa Wilyanita Rezki Rusydi Sarjon Defit Sarwo Derta Sukasih Sukasih Sukasih Suparmi Suparmi Supriadi Supriadi Tasya Maulidia