Publication Search

Cloud job-length prediction remains challenging when the target distribution is highly skewed and contains rare extreme values. This study proposes a log-transformed, regime-based machine learning framework for robust prediction of cloud job length, represented in million instructions (MI). The approach integrates sequential feature engineering, logarithmic target transformation, weighted learning, and regime-aware modeling to distinguish between normal and extreme job-length behavior. Using an ordered GoCJ-derived cloud job-length sequence of 1000 jobs, the dataset exhibits a heavy-tailed distribution, with a mean of 129,662 MI, a median of 93,000 MI, a 95th percentile of 525,000 MI, a 99th percentile of 900,000 MI, and a skewness of 3.695. The proposed model is evaluated against sequential baselines and stronger machine learning baselines, including Naive_Last, RollingMean_5, Global_Log_ExtraTrees, RandomForest, GradientBoosting, and MLP_Log. On the main test split, the proposed Regime_Log_ExtraTrees achieved the best RMSE of 206,255.66 and the least negative R² of −0.01062, while Global_Log_ExtraTrees remained competitive in terms of MAE, MedAE, and RMSLE. Additional walk-forward validation confirms that the regime-aware model consistently achieves the best mean RMSE and mean R² across temporal folds. Ablation results further show that regime-aware learning is the primary contributor to robustness, although accurate prediction of extreme jobs remains challenging. These findings indicate that log-transformed, regime-based learning provides a practical and more robust strategy for cloud job-length prediction under heavy-tailed workload conditions.

Polusi udara partikulat halus (PM2,5) merupakan ancaman serius bagi kesehatan masyarakat di Kabupaten Brebes, Jawa Tengah. Faktor penyumbang utamanya adalah emisi kendaraan di jalur Pantura, aktivitas industri perikanan, serta konsentrasi tinggi selama musim kemarau (Juni–November). Tidak adanya model peramalan sub-jam yang akurat menghambat pengembangan sistem peringatan dini yang efektif. Penelitian ini mengembangkan dan mengevaluasi model deep learning berbasis Transformer untuk memprediksi konsentrasi PM2,5 dengan resolusi waktu 15 menit. Data yang digunakan berasal dari NASA GEOS-CF (band PM25_RH35_GCC) yang diakses melalui Google Earth Engine menggunakan API Python. Dataset mencakup periode 1 Januari hingga 22 November 2025, menghasilkan 7.813 observasi per jam, yang kemudian diinterpolasi linear menjadi 31.249 titik data dengan resolusi 15 menit. Arsitektur Transformer terdiri dari 3 lapis enkoder, 4 kepala perhatian multi-head, dimensi embedding 128, dimensi feed-forward 256, panjang sekuen 60 timestep, dan augmentasi fitur menggunakan rerata bergulir (*rolling mean*, jendela = 3) dan beda pertama (*first difference*). Pelatihan dilakukan dengan TensorFlow-Keras, pengoptimal Adam, penjadwal peluruhan kosinus (*cosine decay scheduler*), dan fungsi kerugian Huber. Pembagian data dilakukan secara kronologis: 70% pelatihan, 30% validasi. Evaluasi pada set uji independen (16 Agustus–21 November 2025, 9.357 observasi atau 97 hari 11 jam 15 menit) menghasilkan MAE 0,7691 µg/m³, RMSE 1,2052 µg/m³, R² 0,9945, dan *Explained Variance Score* 0,9948. Model ini mampu menggambarkan variasi diurnal dan anomali musiman secara akurat, jauh melampaui model LSTM dan GTWR konvensional. Penelitian ini memberikan kontribusi signifikan di bidang Teknologi Informasi melalui kerangka kerja pengolahan *big data* satelit untuk aplikasi lingkungan.

This research was conducted to overcome the unmet criteria for completeness in learning front-rolling gymnastics in class IX C SMP N 22 Semarang. This research aimed to improve the learning of front rolling through the Jigsaw approach in class IX C SMP N 22 Semarang. This research is a classroom action research consisting of two cycles, each consisting of two meetings. The research subjects were 33 students of class IX C SMP N 22 Semarang (14 boys and 19 girls). The data collection instruments used include observation, questionnaire, and front roll learning outcomes test. Data analysis techniques were carried out qualitatively and quantitatively. The results showed that the Jigsaw approach can improve front-roll learning in class IX C SMP N 22 Semarang students. Based on the analysis conducted by collaborators and researchers, the value in Cycle I was 54% and in Cycle II reached 100%, so it can be concluded that learning floor exercises through the Jigsaw approach has increased in class IX C SMP N 22 Semarang.

This research aims to find out whether the application of auxiliary media on an inclined plane mattress can improve the learning process and students' skills in learning floor exercise front rolls. The research method used to answer the research objectives was the class-room action research method. The subjects of this research were 33 students of class XI AKL 2 SMKN 6 Surakarta, consisting of 33 female students. The results of the pre-cycle research showed that the majority of students did not understand the front roll movement skill, so the pre-cycle scores were 42.42% (very good category), 15.15 (good category), 21.21 (fair category), 3 .03% (poor category) and 18.18% (very poor category. With an average student score of 7.0 (good category), and class learning completeness of 57.57% (low category). In the first cycle with learning through the application of incline mattress supporting media obtained a score from observations of student activities was 7 (good category), and the observation of teacher activities was also 7 (good category). The increase in students' skills in carrying out forward rolling skills is affected by the use of supporting media. Based on the results above, it can be concluded that the application of supporting media in learning has been proven to improve forward rolling skills.