Smart Computing and Systems Engineering - 2025 (SCSE 2025)

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/30037

Browse

Author: search.filters.author.Fernando, K. J. P.Start date: 2025

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Hybrid Deep Learning for Portable Weather Forecasting: Real-Time Predictions Using CNN- LSTM-Transformer Models
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Perera, K. P. V. D. U. P.; Fernando, K. J. P.; Lakmak, H. K. I. S.; Nirmal, W. C.
    Accurate weather forecasting is critical for agriculture, disaster management, and transportation sectors. However, traditional forecasting systems often require extensive computational resources and centralized infrastructure, limiting their accessibility in remote and underserved regions. This study introduces a Portable Weather Forecasting Station that combines real-time sensor-based data acquisition with advanced deep learning techniques. The station integrates sensors to measure parameters such as temperature, humidity, wind speed, and solar radiation, processed by a Raspberry Pi for localized predictions. A hybrid deep learning model comprising Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), and Transformers is developed to capture both short-term patterns and long-term dependencies in the data. The system's performance is enhanced through hyperparameter optimization using Optuna, with metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Skill Score used for evaluation. The hybrid model demonstrated superior accuracy compared to standalone architectures. Designed for autonomy with battery backup, the station operates independently of external infrastructure, making it ideal for deployment in resource-constrained environments. This research offers an innovative approach to localized, real-time weather forecasting, addressing the limitations of traditional methods while ensuring accessibility and scalability.
  • No Thumbnail Available
    Item
    Optimizing Predictive Maintenance in Industrial Machinery with Data Smoothing and Machine Learning
    (Department of Industrial Management, Faculty of Science, University of Kelaniya., 2025) Nirmal, W. C.; Lakmak, H. K. I. S.; Fernando, K. J. P.
    Unplanned machinery breakdowns result in significant financial losses, making predictive maintenance essential in industrial operations. This study focuses on fault detection in a single-phase induction motor used in jewelry manufacturing by analyzing vibration data under normal and abnormal conditions. Data was collected using an accelerometer, and three preprocessing techniques—Kalman Filter, Moving Average Filter, and Fast Fourier Transform (FFT)—were applied to reduce noise and improve data quality. Six supervised classification algorithms were evaluated on both raw and preprocessed data. Results demonstrate that preprocessing significantly enhances model accuracy, with the Moving Average Filter enabling Random Forest to achieve the highest accuracy of 99.77%. Kalman Filter also improved model performance, while FFT was particularly beneficial for Logistic Regression. This research highlights the importance of combining machine learning with effective preprocessing to optimize predictive maintenance strategies, reduce downtime, and minimize maintenance costs in industrial environments. By demonstrating the practical implications of these methods, this study contributes to the advancement of reliable fault detection systems for critical machinery components.