Article Per Year (5 Year)
p-Index From 2021 - 2026
1.588
P-Index
This Author published in this journals
All Journal JURNAL INSTEK (Informatika Sains dan Teknologi) Jurnal Sistem Informasi dan Informatika (SIMIKA) Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika MATHunesa: Jurnal Ilmiah Matematika Journal of Information Systems and Technology Research SAINTEK
Aviolla Terza Damaliana
Unknown Affiliation
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mathematics

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
MODEL VECTOR AUTOREGRESSIVE (VAR) UNTUK PREDIKSI INDEKS HARGA KONSUMEN, HARGA BERAS, DAN INFLASI KOTA SURABAYA Suprapto, Rheinka Elyana; Trimono, Trimono; Aviolla Terza Damaliana
Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Vol. 6 No. 1 (2025): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/lb.v6i1.965

Abstract

The current global economic conditions face increasingly complex challenges, with projections of economic weakness continuing until 2025. Globalization has reduced the role of domestic factors and strengthened the impact of the global economy on the formation of inflation. From a macroeconomic perspective, the level of economic growth is often used as a leading indicator of a country's success, reflecting continuous changes in the economy with the aim of achieving better conditions over a certain period of time. Historically, the inflation rate in Indonesia tends to be higher compared to other developing countries. Data shows that during the 2010–2020 period, Indonesia's quarterly inflation was consistently higher than other developing countries. This study uses time series data analysis with a multivariate approach that includes three main variables: inflation, rice prices, and the consumer price index (CPI). The method used is Vector Autoregressive (VAR), which is an analysis technique for data with more than one related variable. The results of the analysis show that the VAR method produces a Mean Absolute Percentage Error (MAPE) value of 32.73% for inflation, 6.24% for CPI, and 5.78% for rice prices. These findings indicate that the VAR model has varying levels of accuracy for each variable, with more accurate predictions for CPI and rice prices compared to inflation.
Klasterisasi Kabupaten/Kota di Provinsi Jawa Tengah berdasarkan Komponen Indeks Pembangunan Manusia Menggunakan Metode UMAP dan K-MEANS Difta Alzena Sakhi; Friza Nur Fatmala; Karina Auralia; Alfan Rizaldy Pratama; Aviolla Terza Damaliana
MATHunesa: Jurnal Ilmiah Matematika Vol. 13 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

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

Abstract

Ketimpangan pembangunan manusia di Provinsi Jawa Tengah tetap menjadi tantangan besar yang memerlukan pendekatan berbasis data. Penelitian ini mengelompokkan kabupaten/kota berdasarkan komponen Indeks Pembangunan Manusia (IPM) tahun 2019–2024 menggunakan algoritma K-Means. Variabel yang dianalisis meliputi Usia Harapan Hidup, Harapan Lama Sekolah, Rata-Rata Lama Sekolah, dan Pengeluaran per Kapita. Data diproses melalui tahapan penting, seperti standarisasi, deteksi outlier, dan reduksi dimensi menggunakan Uniform Manifold Approximation and Projection (UMAP), serta penentuan jumlah klaster optimal dengan Elbow Method dan Silhouette Score. Hasil analisis menunjukkan empat klaster optimal dengan nilai Silhouette Score sebesar 0,71, yang mengelompokkan data tahunan seluruh kabupaten/kota ke dalam kelompok-kelompok dengan tingkat pembangunan manusia yang berbeda secara signifikan. Klaster dengan nilai IPM tertinggi terdiri dari kota-kota besar, seperti Semarang, Salatiga, dan Surakarta, sementara klaster terendah mencakup wilayah yang masih menghadapi berbagai kendala dalam aspek kesehatan, pendidikan, dan ekonomi. Visualisasi UMAP membantu interpretasi distribusi klaster dan memberikan masukan strategis bagi kebijakan pembangunan wilayah yang lebih merata. Kata Kunci: klasterisasi, indeks pembangunan manusia, K-Means, UMAP, Jawa Tengah
Analisis Sentimen Pada Komentar Aplikasi Sehat Indonesiaku Menggunakan Metode Machine Learning Dan Klasifikasi Positif-Negatif Nabila Yudhitya Larasati; Marthalia Kusumarima; Karina Auralia; Shindi Shella May Wara; Aviolla Terza Damaliana
MATHunesa: Jurnal Ilmiah Matematika Vol. 13 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

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

Abstract

Perkembangan aplikasi kesehatan digital seperti Aplikasi Sehat Indonesiaku (ASIK) memerlukan pemahaman terhadap persepsi pengguna guna meningkatkan kualitas layanan. Penelitian ini bertujuan untuk mengembangkan sistem analisis sentimen terhadap komentar pengguna ASIK di Google Play Store. Sebanyak 1.053 komentar dikumpulkan melalui teknik web scraping, lalu diproses menggunakan tahapan normalisasi, case folding, stemming, penghapusan stopwords, dan pembobotan TF-IDF. Visualisasi word cloud digunakan untuk mengidentifikasi kata-kata dominan dalam komentar positif dan negatif. Proses klasifikasi sentimen dilakukan dengan tiga algoritma machine learning, yaitu Random Forest, Gradient Boosting, dan Logistic Regression. Hasil analisis menunjukkan bahwa komentar positif banyak memuat kata seperti “mudah” dan “bermanfaat”, sementara komentar negatif didominasi oleh kata “perbaiki” dan “lama”. Model Gradient Boosting menunjukkan performa terbaik dengan accuracy sebesar 87,83%, precision 87,47%, dan F1-Score 87,31%. Temuan ini menggambarkan persepsi publik terhadap ASIK serta menyoroti pentingnya perbaikan teknis guna meningkatkan kepuasan pengguna terhadap layanan digital pemerintah.
Forecasting USD to Rupiah Exchange Rate with the Fuzzy Time Series Singh Approach Santika, Reghina Ajeng; Aviolla Terza Damaliana; Mohammad Idhom
Journal of Information Systems and Technology Research Vol. 4 No. 3 (2025): September 2025
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v4i3.1238

Abstract

The exchange rate plays a crucial role in determining a country's economic stability, especially for countries like Indonesia that rely heavily on international trade. In recent years, the fluctuations in global currency values have intensified, particularly after the trade war between the United States and China began in 2018. These fluctuations have significantly impacted the exchange rate between the Indonesian Rupiah and the US Dollar, which in turn affects the competitiveness of Indonesian exports, increases the cost of imports, and influences key economic decisions made by investors, importers, and exporters. The problem of this research lies in the challenge of predicting exchange rate movements amidst economic uncertainty and currency volatility.  This study aims to address this problem by forecasting the exchange rate of the Indonesian Rupiah against the US Dollar using the Fuzzy Time Series Singh method. This method is chosen due to its ability to capture complex data patterns with high accuracy and simpler computational requirements. The primary objective of the research is to evaluate the effectiveness and accuracy of the Fuzzy Time Series Singh method in predicting the exchange rate of the Rupiah against the US Dollar. The results of this study show that the forecasting model achieved an accuracy rate with a MAPE value of less than 10%, indicating that the method can provide highly reliable predictions, which can assist economic actors in making better-informed decisions in the face of currency volatility.
Comparative Analysis of Deep Learning Models for Wind Speed Prediction Using LSTM, TCN and RBFNN Wardani, Firly Setya; Idhom, Mohammad; Aviolla Terza Damaliana
Journal of Information Systems and Technology Research Vol. 4 No. 3 (2025): September 2025
Publisher : Ali Institute or Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/jistr.v4i3.1298

Abstract

Wind speed forecasting plays a vital role in various sectors, including renewable energy management and disaster preparedness for extreme weather events. Accurate prediction models are essential to support decision-making processes, especially in regions with dynamic seasonal patterns. This study compares the performance of three time series prediction models Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Radial Basis Function Neural Network (RBFNN) for forecasting daily wind speed. The dataset consists of historical wind speed data that underwent multiple preprocessing steps, including seasonal-based missing value imputation, stationarity testing, supervised transformation, normalization, and hyperparameter tuning to optimize model performance. The models were evaluated using four standard regression metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-Squared (R²), and Mean Absolute Percentage Error (MAPE). The results show that the TCN model outperformed the others, achieving an MAE of 1.117, RMSE of 1.524, R² of 0.120, and MAPE of 20.95%. The LSTM model ranked second with competitive performance, while the RBFNN model produced consistent but slightly lower accuracy. The findings highlight the superiority of TCN in capturing complex sequential and seasonal patterns in wind speed data. The unique contribution of this research lies in integrating seasonal-based preprocessing with a comparative evaluation of three advanced models under varying conditions, including extreme weather scenarios. This study serves as a foundation for developing more accurate and reliable wind speed forecasting systems to support renewable energy planning and enhance disaster risk mitigation strategies.
PERBANDINGAN FUNGSI AKTIVASI GAUSSIAN DAN MULTIKUADRATIK PADA RADIAL BASIS FUNCTION NEURAL NETWORK UNTUK PREDIKSI INDEKS HARGA KONSUMEN DI SURABAYA Fiqih Pavita Andharluana; Aviolla Terza Damaliana; Trimono
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 10 No 2 (2025): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v10i2.56751

Abstract

Indeks Harga Konsumen (IHK) merupakan indikator penting dalam mengukur tingkat inflasi yang digunakan sebagai dasar pengambilan kebijakan ekonomi, termasuk penyesuaian gaji, upah, dan kontrak kerja. Karena IHK memiliki pengaruh penting terhadap perubahan laju inflasi perekonomian Indonesia, maka perlu dilakukan prediksi terhadap IHK untuk membantu pemerintah dalam merumuskan kebijakan yang tepat, baik dalam stabilisasi harga maupun perlindungan terhadap kesejahteraan masyarakat terutama di wilayah dengan aktivitas ekonomi tinggi seperti Kota Surabaya, yang memiliki pertumbuhan Produk Domestik Regional Bruto (PDRB) signifikan. Penelitian ini bertujuan untuk membandingkan kinerja dua fungsi aktivasi dalam model Radial Basis Function Neural Network (RBFNN), yaitu Gaussian dan Multiquadratik, dalam memprediksi laju IHK di Surabaya. Metode RBFNN dipilih karena kemampuannya dalam menangkap pola non-linear pada data deret waktu. Metodologi penelitian meliputi pengumpulan data dari Badan Pusat Statistik (BPS), pra-pemrosesan data, pengembangan model, dan evaluasi menggunakan data uji. Model RBFNN dibangun dengan menentukan kluster, nilai spread, fungsi aktivasi, dan output, serta dievaluasi menggunakan Symmetric Mean Absolute Percentage Error (sMAPE). Data yang digunakan berupa deret waktu Indeks Harga Konsumen (IHK) Kota Surabaya periode Januari 2006 hingga Desember 2024 dengan frekuensi bulanan, sehingga diperoleh 228 data observasi. Berdasarkan hasil analisis, diperoleh bahwa fungsi aktivasi Gaussian memberikan hasil prediksi terbaik dengan nilai SMAPE sebesar 0.70%, yang menunjukkan tingkat akurasi sangat tinggi. Hasil prediksi IHK untuk bulan Januari hingga Mei 2025 berturut-turut adalah 107.61, 108.09, 108.54, 108.95, dan 108.32.
ARIMAX DENGAN VARIASI KALENDER IDUL ADHA DAN NATAL UNTUK PREDIKSI HARGA KOMODITAS CABAI KERITING DI JAWA TIMUR Salsabila, Nada; Aviolla Terza Damaliana; Wahyu Syaifullah Jauharis Saputra
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 10 No 2 (2025): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v10i2.59520

Abstract

Tingginya konsumsi cabai di Jawa Timur menjadikan komoditas ini sebagai salah satu kebutuhan yang sangat diperhatikan oleh masyarakat. Dari fenomena tersebut timbul permasalahan adanya data yang menunjukkan kondisi fluktuasi harga dari tanaman itu sendiri, salah satunya cabai keriting. Ketidakstabilan harga tersebut dapat menimbulkan dampak terhadap daya beli masyarakat, serta menyulitkan pemerintah dalam merumuskan strategi distribusi dan pengendalian pasokan komoditas secara tepat waktu. Oleh karena itu, untuk mengurangi pola fluktuasi harga yang semakin tidak stabil di masa mendatang, penting untuk dilakukan prediksi harga komoditas cabai keriting di Jawa Timur. Pendekatan yang digunakan pada penelitian ini adalah metode Autoregressive Integrated Moving Average with Exogenous Variables (ARIMAX) untuk memprediksi harga harian cabai keriting periode 1 Januari 2022 hingga 31 Desember 2024, dengan menambahkan variasi kalender Idul Adha dan Natal sebagai variabel eksogen. Data yang digunakan merupakan data sekunder harian harga cabai keriting di Provinsi Jawa Timur yang diperoleh dari situs resmi SISKAPERBAPO. Hasil pemodelan menunjukkan bahwa model terbaik adalah ARIMAX(3,1,2) dengan nilai AIC sebesar 17794,185 dan MAPE sebesar 12,04%, yang lebih baik dibandingkan model ARIMA tanpa variabel eksogen dengan MAPE sebesar 17,50%. Hasil ini menunjukkan bahwa penambahan faktor variasi kalender keagamaan mampu meningkatkan akurasi prediksi dan memberikan kontribusi penting dalam upaya stabilisasi harga komoditas pangan di Jawa Timur.
SENTIMENT ANALYSIS THE DAMAGE ESAF FRAME WITH SUPPORT VECTOR MACHINE AND IMPACT ON HONDA MOTORCYCLE SALES Kinanthi Putri Ariyani; Aviolla Terza Damaliana; Trimono Trimono
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v8i2.3921

Abstract

Damage to the Enhanced Smart Architecture Frame (eSAF) on Honda motorcycles has triggered consumer concerns and has become a public spotlight. This study analyzes public sentiment towards the problem using the Support Vector Machine (SVM) and its impact on sales at one of the dealerships in Surabaya. The data used was in the form of comments from Twitter social media which were classified into two classes, namely positive and negative. Based on the results of the analysis, the majority of 589 public sentiments (59.7%) tended to be negative towards the problem of damage to the eSAF frame, while 397 public sentiments (40.3%) showed positive sentiment. Sales results showed significant fluctuations after this issue emerged, along with increasing negative sentiment. SVM models with a Linear kernel provide the best results with 85% accuracy, 84% precision, 85% recall, and 85% f1-score. SVM was chosen because it excels in text classification compared to algorithms such as K-Nearest Neighbors (KNN), C4.5, and Naïve Bayes, and has been applied in areas such as face detection, bioinformatics, and text processing. This research provides insights for manufacturers to improve product quality, improve customer service, and restore public trust. In addition, the use of the Support Vector Machine algorithm in sentiment analysis can be a reference for similar research in other fields.
LONGITUDINAL MODELING OF E-COMMERCE CHOICE USING LATENT GROWTH CURVE TO ASSESS INFLUENCING FACTORS AMONG LATE ADOLESCENTS Fadlila Agustina; Dwi Arman Prasetya; Aviolla Terza Damaliana
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v8i2.3923

Abstract

The rapid growth of e-commerce in Indonesia has significantly influenced consumer behavior, particularly among late adolescents aged 18–21 years. This study examines the dynamic factors affecting e-commerce preferences, including price, service quality, and customer loyalty, using Latent Growth Curve Modeling (LGCM). This method was chosen for its ability to analyze variable changes longitudinally, allowing the identification of growth patterns and factors influencing shifts in consumer behavior over time. Data were collected through an online survey involving 400 respondents over three time periods. The study’s findings reveal that price is the most stable variable (intercept 0.5302, slope 0.0811), whereas service quality (intercept 0.8127, slope -0.0285) and loyalty (intercept 0.8508, slope -0.0188) show slight declines. Innovation, functioning as a covariate, significantly affects the intercept of all variables, particularly loyalty, although its impact on growth rates varies. The model demonstrates a good fit, with RMSEA (0.0730), CFI (0.9844), and TLI (0.9402), confirming its validity. Visualizations indicate that loyalty evolves more dynamically than service quality, highlighting the crucial role of innovation in customer engagement. This study emphasizes the need for e-commerce platforms to prioritize innovation and service quality improvements to foster long-term loyalty. These findings provide valuable insights into consumer behavior dynamics and offer strategic recommendations for achieving competitive advantage in the digital marketplace.
KLASTERING WILAYAH DI JAWA TIMUR BERDASARKAN FAKTOR UNMET NEED MENGGUNAKAN FUZZY GUSTAFSON-KESSEL Chrysilla Citra Windyadari; Aviolla Terza Damaliana; Mohammad Idhom
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 8 No. 2 (2025): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v8i2.3976

Abstract

The Family Planning Program is an effort to control the rate of population growth by regulating desired pregnancies. In its realization, the family planning program faces challenges in the form of unmet need (couples of childbearing age who do not use contraception). East Java Province in 2023 was recorded as the province with the third highest number of unmet need cases in Java. One method that can be used to analyze the phenomenon of unmet need is clustering analysis. Clustering analysis will help identify areas in East Java based on the priority level of the family planning program. Fuzzy Gustafson-Kessel (FGK) is one of the clustering methods developed as a refinement of the Fuzzy C-Means method. This study implements the Fuzzy Gustafson-Kessel (FGK) method with and without Principal Component Analysis (PCA) to cluster regions in East Java based on unmet need and determinant factors such as the availability of family planning facilities and resources. The results showed that the best model was obtained when using FGK with PCA, with the highest FSI value of 0.668 and XB of 0.235 at configuration c = 4 and m = 3.5. The clusters formed consist of 5 medium priority areas, 12 low priority areas, 9 high priority areas, and 12 developing priority areas. The results of this clustering can be used as a basis for policy makers in designing more effective intervention strategies to address unmet need in East Java.
Co-Authors Alfan Rizaldy Pratama Chrysilla Citra Windyadari Difta Alzena Sakhi Dwi Arman Prasetya Fadlila Agustina Fiqih Pavita Andharluana Friza Nur Fatmala idhom, Mohammad Karina Auralia Kinanthi Putri Ariyani M Naswan Izzudin Akmal Marthalia Kusumarima Mohammad Idhom Nabila Yudhitya Larasati Salsabila, Nada Santika, Reghina Ajeng Shindi Shella May Wara Suprapto, Rheinka Elyana Trimono Trimono Trimono Trimono, Trimono Wahyu Syaifullah Jauharis Saputra Wardani, Firly Setya