Dhia Rafifah Thifal
Teknik Elektro dan Informatika, Universitas Negeri Malang, Malang, Indonesia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimalisasi Rekonstruksi Data Hilang untuk Meningkatkan Presisi Prediksi Waktu Salat Berbasis GRU di Wilayah Empat Musim Adelia Khansa Ristiaputri; Aji Prasetya Wibawa; Adhelia Wida Khaidir; Dhia Rafifah Thifal; Adelia Desyana Eka Putri; Agung Bella Putra Utama
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 2 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i2.3458

Abstract

Peramalan waktu sholat di wilayah empat musim menghadapi tantangan besar akibat variabilitas musiman ekstrem dan risiko ketidaklengkapan data sensorik yang mengganggu kontinuitas informasi. Penelitian ini bertujuan untuk mengevaluasi pengaruh berbagai metode imputasi terhadap kinerja model peramalan GRU pada data deret waktu yang merepresentasikan dinamika astronomi dan meteorologi. Metodologi penelitian melibatkan pengujian enam teknik imputasi pada tiga dataset dengan karakteristik berbeda, yaitu variabilitas musiman jangka panjang, pola siklik non-linear, dan dinamika jangka pendek resolusi tinggi. Model GRU dioptimasi menggunakan PSO untuk memastikan akurasi parameter yang maksimal. Hasil eksperimen menunjukkan bahwa model GRU secara konsisten mengungguli arsitektur LSTM, Bi-LSTM, dan RNN pada seluruh skenario pengujian. Metode imputasi sederhana yang menjaga autokorelasi temporal, seperti Mean dan LOCF, terbukti lebih efektif dibandingkan metode berbasis kedekatan ruang fitur seperti KNN dan MICE. Pada Dataset 1, kombinasi imputasi Mean dan GRU menghasilkan skor R-Squared sebesar 0.92828, sementara pada Dataset 2 yang memiliki dinamika tinggi, metode LOCF mencapai skor R-Squared tertinggi sebesar 0.93766. Penelitian ini menyimpulkan bahwa preservasi integritas temporal melalui strategi imputasi yang tepat merupakan faktor kunci dalam meningkatkan reliabilitas model peramalan waktu sholat pada wilayah dengan variasi musim yang signifikan.
Assessing the Effectiveness of Statistical and Temporal Imputation Methods for Bi-LSTM-Based Forecasting on Environmental and Climate Time Series Data Adelia Desyana Eka Putri; Aji Prasetya Wibawa; Adelia Khansa Ristiaputri; Adhelia Wida Khaidir; Dhia Rafifah Thifal; Agung Bella Putra Utama
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 25 No. 3 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v25i3.6026

Abstract

Time series data in climatology and environmental research are highly susceptible to missing values that can disrupt temporal structures and degrade forecasting performance. This study evaluates the effectiveness of several imputation methods in improving the predictive performance of a Bidirectional Long Short-Term Memory model across three missing-data mechanisms: Missing Completely at Random, Missing at Random, and Missing Not at Random. The compared methods include mean, median, mode, k-nearest neighbors, multiple imputation by chained equations, and last observation carried forward, with data deletion serving as the baseline. All datasets were normalized using the min–max technique, and model hyperparameters were optimized through Particle Swarm Optimization. Performance was assessed using mean absolute percentage error, root mean square error, and the coefficient of determination. The findings indicate that proper imputation significantly enhances forecasting accuracy compared to deleting incomplete observations. In Dataset 1, the last observation carried forward achieved the best performance with a coefficient of determination of 0.923 and a root mean square error of 3.373. Similarly, Dataset 2 showed optimal results with the same method, producing a coefficient of determination of 0.950 and a root mean square error of 14.458. The most substantial improvement was observed in Dataset 3, where mean imputation reduced the mean absolute percentage error from 3.219 to 0.329 while increasing the coefficient of determination to 0.986. These results highlight the critical role of selecting an imputation strategy in deep learning-based time series forecasting and provide practical guidance for handling incomplete environmental datasets.