https://www.um.edu.mt/library/oar/handle/123456789/16863 2026-07-20T15:22:20Z 2026-07-20T15:22:20Z Ashok, P. Tran, Tien Anh Srithar, A. Manimala, G. https://www.um.edu.mt/library/oar/handle/123456789/148036 2026-07-14T09:47:07Z 2026-01-01T00:00:00Z

Title: Hybrid Swin vision transformer with IMFCC for enhanced underwater acoustic noise reduction Authors: Ashok, P.; Tran, Tien Anh; Srithar, A.; Manimala, G. Abstract: Underwater wireless communication is essential for deep-sea exploration, environmental monitoring, and Autonomous Underwater Vehicle (AUV) coordination. Its performance is severely affected by ambient noise, multipath propagation, reverberation, and non-stationary interference, which degrade acoustic signal quality. Existing noise reduction techniques, such as Wiener filtering, spectral subtraction, and wavelet denoising, struggle to adapt to rapidly changing underwater conditions. Centralized Deep Learning (DL) based enhancement models are also unsuitable for distributed Underwater Wireless Sensor Networks (UWSNs) due to privacy, bandwidth, and real-time constraints. To overcome these challenges, this work proposes a Federated Learning–Driven Hybrid Swin Vision Transformer with Improved MFCCs (Fed-SVTIMFCC) for intelligent underwater acoustic noise reduction. Federated learning enables multiple underwater nodes to collaboratively train a denoising model without sharing raw acoustic data, ensuring data privacy and adaptability. The Swin Vision Transformer (SVT) captures local spectral cues and long-range dependencies to enhance reconstruction, while IMFCCs provide robust features for distinguishing noise from useful signals. Experimental results on real underwater datasets demonstrate significant improvements in SNR (26.94 dB), PSNR (33.28 dB), and SSIM (0.947), establishing Fed-SVT-IMFCC as a powerful solution for next-generation underwater communication systems.

2026-01-01T00:00:00Z Haider, Rizwan Shi, Wei Lin, Zaibin Tran, Tien Anh Wu, Ji Li, Xin https://www.um.edu.mt/library/oar/handle/123456789/147132 2026-06-05T10:18:42Z 2026-01-01T00:00:00Z

Title: Wave-dependent predictability of floating offshore wind turbine responses : a BiLSTM study based on fully coupled CFD simulations Authors: Haider, Rizwan; Shi, Wei; Lin, Zaibin; Tran, Tien Anh; Wu, Ji; Li, Xin Abstract: Reliable short-term prediction of floating offshore wind turbine (FOWT) responses under complex wave conditions remains challenging due to nonlinear aero–hydro–mooring interactions and transient wave-induced effects. This study evaluates the predictability of coupled FOWT responses using a Bidirectional Long Short-Term Memory (BiLSTM) framework trained on high-fidelity datasets generated from a fully coupled aero–hydro–mooring computational fluid dynamics (CFD) model of the National Renewable Energy Laboratory (NREL) 5 MW OC4 semi-submersible system. Two excitation conditions are examined: regular waves representing periodic steady-state behavior and focused waves representing transient amplified responses. The model simultaneously predicts platform motions, mooring-line tensions, aerodynamic power, and total thrust. Hyperparameter optimization is performed to ensure stable convergence and robust model performance. Predictability is assessed across multiple prediction-ahead times (PATs). Results show that regular-wave responses maintain high accuracy at longer horizons (R² > 96% at 2.5 s and 5.0 s), whereas focused-wave cases exhibit decreasing accuracy with increasing PAT, achieving R² values above 95%, 90%, and 85% at 0.5 s, 1.0 s, and 1.5 s, respectively. These findings demonstrate that forecasting performance strongly depends on wave type, emphasizing the need to consider wave conditions when predicting coupled FOWT dynamic responses.

2026-01-01T00:00:00Z Shaheen, Momina Pandey, Jay Kumar Tran, Tien Anh https://www.um.edu.mt/library/oar/handle/123456789/147080 2026-06-03T09:42:55Z 2026-01-01T00:00:00Z

Title: Intelligent systems and sustainable solutions for AIOT-powered environmental monitoring Authors: Shaheen, Momina; Pandey, Jay Kumar; Tran, Tien Anh Abstract: The integration of artificial intelligence (AI) and the Internet of Things (IoT), collectively known as AIoT, revolutionizes environmental monitoring by enabling intelligent, data-driven, and sustainable solutions. AIoT-powered systems combine real-time data collection from sensors with advanced analytics and machine learning algorithms to monitor, predict, and manage environmental changes. These intelligent systems detect pollution levels, track climate patterns, optimize resource usage, and support early warning systems for natural disasters, promoting environmental sustainability. By harnessing the connection between AI and IoT, researchers and policymakers may develop smarter, more adaptive frameworks that enhance environmental protection while contributing to global sustainability goals. Intelligent Systems and Sustainable Solutions for AIOT-Powered Environmental Monitoring provides a comprehensive overview of the integration of AI and IoT in environmental monitoring and sustainability. It explores how intelligent, connected systems transform monitoring, analysis, and response to environmental changes. This book covers topics such as data science, smart technology, and sustainable development, and is a useful resource for engineers, academicians, researchers, and scientists.

2026-01-01T00:00:00Z Nandy Pal, Mahua Bose, Avijit Tran, Tien Anh https://www.um.edu.mt/library/oar/handle/123456789/146251 2026-05-08T08:28:38Z 2026-01-01T00:00:00Z

Title: RealEstateBlock : a real estate application using blockchain Authors: Nandy Pal, Mahua; Bose, Avijit; Tran, Tien Anh Abstract: The rapid asset transactions in the real estate sector are a time-consuming process that may take months to complete. The transactions are also costly and involve fraudulent activities. So, despite the importance of real estate in our country, many problems arise in this sector, like property searching, property sale and purchase, money dealings, lease agreements, involvement of third parties, etc. Blockchain is an emerging technology that can solve different problems the real estate sector is facing. It provides secure and more manageable land or property transactions. This paper proposes a Blockchain-based real estate app that leverages Blockchain technology to revolutionize the traditional real estate industry. It utilizes Blockchain’s transparency, security, and immutability to create a decentralized platform for buying, selling, renting, and managing properties. With this app, buyers and sellers can interact directly with each other without the help of a real estate agent. It will be a valuable tool for both buyers and sellers, allowing buyers to find properties that meet their needs and allowing sellers to reach a wider audience. In this paper, we formulate a Blockchain contract that successfully deals with selling, buying, and renting properties, resulting in developing a Decentralized Application Program. We tested the contract in Ethereum Remix, and it was successful.

2026-01-01T00:00:00Z