This study aims to assess and compare the performance of three forecasting models—Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Gated Recurrent Unit (GRU)—in predicting Toyota car sales in Indonesia. The dataset exhibits intricate seasonal patterns and non-linear fluctuations, posing significant challenges for conventional statistical approaches. The ARIMA model, typically suited for linear and stationary data, struggled to capture the complexities of these sales trends. Similarly, despite being designed to handle seasonal components, the SARIMA model failed to provide accurate predictions and demonstrated high error rates. In contrast, the deep learning-based GRU model exhibited superior predictive accuracy, achieving significantly lower values across all evaluation metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Ultimately, the findings confirm that the GRU model outperforms traditional statistical methods, offering highly accurate and reliable forecasts to support complex business decision-making in the automotive industry.
University ranking prediction requires adaptive models to capture temporal dynamics and handle data anomalies. This study develops a time-adaptive ensemble framework integrating outlier-aware scoring and hybrid feature selection. Using Times Higher Education data (2011–2024), we applied windowed outlier detection with clipping and masking, alongside ANOVA, permutation importance, and SHAP values for dynamic feature selection. The framework ensembles linear moving-average, temporal Random Forest, and LSTM models via optimized weights. Rolling forecasts (2016–2024) yielded a low mean rank deviation of 1.2 positions and a Top-1000 classification accuracy of 0.96, outperforming single baselines. This robust, interpretable framework effectively supports strategic decision-making and resource allocation in higher education
This study applies deep learning methods to predict ransomware using hybrid analysis samples. To understand current detection methods, prior research was analyzed, guiding the creation of an experiment that tests a model built from ransomware hybrid analysis. A training dataset of over 500 samples, encompassing 38 ransomware families and benign Windows programs, was utilized. The resulting model was subsequently evaluated against a testing dataset containing novel ransomware families not represented during training, revealing a notable performance decrease. Comparing these findings with existing literature highlights potential flaws in how artificial intelligence models are tested and reported. Consequently, this paper advocates for more complex prediction methods and alternative strategies to guarantee models maintain external effectiveness.
This study investigates how DevOps can enhance efficiency and foster innovation within public sector institutions. While widely adopted in the private sector to bridge software development and IT operations through collaboration and automation, DevOps remains underutilized in government frameworks. Focusing on Saudi Arabia's digital transformation under Vision 2030, this research utilizes surveys, interviews, and case studies to examine the core benefits and operational challenges of this methodology. The findings indicate that DevOps significantly accelerates service delivery and stimulates innovative public applications. However, cultural resistance and technical skill gaps present substantial barriers. The study concludes that structured training and strategic partnerships with private sector experts are essential for modernizing government services.
In high-speed networks such as 4G/5G, bandwidth constraints remain a major challenge for digital communication systems, where Inter-Symbol Interference (ISI) significantly degrades signal quality. This study investigates the application of raised cosine filtering to mitigate ISI and enhance signal integrity across several modulation schemes, including BPSK, QPSK, and M-PSK. MATLAB simulations were conducted using roll-off factor values ranging from 0.1 to 0.9, and system performance was evaluated in terms of Bit Error Rate (BER), Peak-to-Average Power Ratio (PAPR), and signal quality represented by eye diagrams. The results indicate that higher roll-off factors provide better ISI mitigation and improved signal clarity, although at the expense of increased bandwidth consumption. The findings highlight the trade-off between bandwidth efficiency and ISI reduction, which is essential for designing optimized filters in modern high-speed communication systems. These results can support the development of more efficient filtering techniques for practical communication networks such as 4G/5G and Wi-Fi, thereby providing valuable insights for communication system designers.
