Son Thai Mai

Son Thai Mai

Auto-generated profile, based on publicly available information

Son Thai Mai

Queen’s University Belfast, Belfast, UK

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 January 2021 in IEEE Access
Verified
Journal Article
Open access
MNMinh-Hien T. Nguyen
Minh-Hien T. Nguyen
EGEmiliano Garcia-Palacios
Emiliano Garcia-Palacios
TDTan Do-Duy
Tan Do-Duy
DNDinh Long Nguyen
Dinh Long Nguyen
SMSon T. Mai
Son T. Mai
Trung Q. DuongTrung Q. Duong
Trung Q. Duong
We propose an unmanned aerial vehicle (UAV) communications scheme with spectrum-sharing mechanism to provide mission-critical services such as disaster recovery and public safety. Specifically, the UAVs can serve as flying base stations to provide extended network coverage for the affected area under spectrum-sharing cognitive radio networks (CRNs). To cope with the effects of network destruction in a disaster, we propose a real-time optimisation framework for resource allocation (e.g., power and number of UAVs) for CRNs assisted by UAV relays. The proposed optimisation scheme aims at optimising the network throughput of primary and secondary networks under the stringent constraint of maximum tolerable interference impinged on the primary users. We also propose a deep neural network (DNN) model to significantly reduce the execution time under real-time solution of mixed-integer UAV deployment problems. For both primary and secondary networks, our real-time optimisation algorithms impose low computational complexity, hence, have a low execution time in solving throughput optimisation problems, which demonstrates the benefit of our approached proposed for spectrum-sharing UAV-assisted mission-critical services.

10 September 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SMSon T. Mai
Son T. Mai
JJJon Jacobsen
Jon Jacobsen
SASihem Amer-Yahia
Sihem Amer-Yahia
ISIvor Spence
Ivor Spence
NTNhat-Phuong Tran
Nhat-Phuong Tran
TNThanh Hung Nguyen
Thanh Hung Nguyen
The density-based clustering algorithm is a fundamental data clustering technique with many real-world applications. However, when the database is frequently changed, how to effectively update clustering results rather than reclustering from scratch remains a challenging task. In this work, we introduce IncAnyDBC, a unique parallel incremental data clustering approach to deal with this problem. First, IncAnyDBC can process changes in bulks rather than batches like state-of-the-art methods for reducing update overheads. Second, it keeps an underlying cluster structure called the object node graph during the clustering process and uses it as a basis for incrementally updating clusters wrt. inserted or deleted objects in the database by propagating changes around affected nodes only. In additional, IncAnyDBC actively and iteratively examines the graph and chooses only a small set of most meaningful objects to produce exact clustering results of DBSCAN or to approximate results under arbitrary time constraints. This makes it more efficient than other existing methods. Third, by processing objects in blocks, IncAnyDBC can be efficiently parallelized on multicore CPUs, thus creating a work-efficient method. It runs much faster than existing techniques using one thread while still scaling well with multiple threads. Experiments are conducted on various large real datasets for demonstrating the performance of IncAnyDBC.

7 July 2021 in IEEE Access
Verified
Journal Article
Open access
CYCheng Yin
Cheng Yin
LBLe Thanh Binh
Le Thanh Binh
Duong Tran AnhDuong Tran Anh
Duong Tran Anh
SMSon T. Mai
Son T. Mai
ALAnh Le
Anh Le
Trung Q. DuongTrung Q. Duong
Trung Q. Duong
Nha Trang Coast is located in the South Central Vietnam and the coastal erosion has occurred rapidly in recent years. Hence it is crucial to accurately monitor the shoreline changes for better coastal management and reduction of risks for communities. In this paper, we explored a statistical forecasting model, Seasonal Auto-regressive Integrated Moving Average (SARIMA), and two Machine Learning (ML) models, Neural Network Auto-Regression (NNAR) and Long Short-Term Memory (LSTM), to predict the shoreline variations from surveillance camera images. Compared to the Empirical Orthogonal Function (EOF), the most common method used for predicting shoreline changes from cameras, we demonstrate that the SARIMA, NNAR and LSTM models outperform the EOF model significantly in terms of prediction accuracy. The forecasting performance of the SARIMA model, NNAR model and LSTM model is comparable in both long and short-term predictions. The results suggest that these models are highly effective in detecting shoreline changes from video cameras under extreme weather conditions.

2 August 2023 in IEEE Access
Verified
Journal Article
Open access
TNThi-Thu-Ha Nguyen
Thi-Thu-Ha Nguyen
DVDuc-Quang Vu
Duc-Quang Vu
SMSon T. Mai
Son T. Mai
TDThanh Duc Dang
Thanh Duc Dang
In recent years, the Mekong River Basin (MRB), one of the largest river basins in Southeast Asia, has experienced severe impacts from extreme droughts and floods. Streamflow forecasting has become crucial for effective risk management strategies in the region. However, this task presents significant challenges due to rapid climate changes and the presence of numerous newly constructed upstream dams, which disrupt the natural flow. In this paper, we develop multiple deep learning models (incl. Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Long short‐term Memory (LSTM), and Transformer) to predict streamflow with different lead time forecasts based on observed meteorological variables and climatic indices (i.e., discharge, water level, precipitation, and temperature) from 1979 to 2019. The results indicate that LSTM obtains high performance for streamflow prediction in both dry and wet seasons while Transformer is not recommended for long-term prediction, especially in the dry season. The proposed deep learning models capture well the fluctuation of river flow in the MRB during the period of high-dam development, especially LSTM (NSE ≥ 0.8). The models’ performances are enhanced with the adding of temperature for short-term prediction while precipitation was the most sensitive variable for long-term one. Such proposed models are essential for government agencies to plan mitigation and adaptation strategies at different periods, which can range from days to years.

18 January 2018 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
SSSumit Sidana
Sumit Sidana
SASihem Amer-Yahia
Sihem Amer-Yahia
MCMarianne Clausel
Marianne Clausel
MRMajdeddine Rebai
Majdeddine Rebai
SMSon T. Mai
Son T. Mai
MAMassih-Reza Amini
Massih-Reza Amini
Social media has become a major source for analyzing all aspects of daily life. Thanks to dedicated latent topic analysis methods such as the Ailment Topic Aspect Model (ATAM), public health can now be observed on Twitter. In this work, we are interested in using social media to monitor people's health overtime. The use of tweets has several benefits including instantaneous data availability at virtually no cost. Early monitoring of health data is complementary to post-factum studies and enables a range of applications such as measuring behavioral risk factors and triggering health campaigns. We formulate two problems: health transition detection and health transition prediction. We first propose the Temporal Ailment Topic Aspect Model (TM-ATAM), a new latent model dedicated to solving the first problem by capturing transitions that involve health-related topics. TM-ATAM is a non-obvious extension to ATAM that was designed to extract health-related topics. It learns health-related topic transitions by minimizing the prediction error on topic distributions between consecutive posts at different time and geographic granularities. To solve the second problem, we develop T-ATAM, a Temporal Ailment Topic Aspect Model where time is treated as a random variable natively inside ATAM. Our experiments on an 8-month corpus of tweets show that TM-ATAM outperforms TM-LDA in estimating health-related transitions from tweets for different geographic populations. We examine the ability of TM-ATAM to detect transitions due to climate conditions in different geographic regions. We then show how T-ATAM can be used to predict the most important transition and additionally compare T-ATAM with CDC (Center for Disease Control) data and Google Flu Trends.

7 November 2018 in Data Science and Engineering
Verified
Journal Article
Open access
PDF file
SMSon T. Mai
Son T. Mai
SASihem Amer-Yahia
Sihem Amer-Yahia
Sébastien BaillySébastien Bailly
Sébastien Bailly
JPJean-Louis Pepin
Jean-Louis Pepin
ACAhlame Douzal Chouakria
Ahlame Douzal Chouakria
ANAnh-Duong Nguyen
Anh-Duong Nguyen
We introduce a novel interactive framework to handle both instance-level and temporal smoothness constraints for clustering large longitudinal data and for tracking the cluster evolutions over time. It consists of a constrained clustering algorithm, called CVQE+, which optimizes the clustering quality, constraint violation and the historical cost between consecutive data snapshots. At the center of our framework is a simple yet effective active learning technique, named Border, for iteratively selecting the most informative pairs of objects to query users about, and updating the clustering with new constraints. Those constraints are then propagated inside each data snapshot and between snapshots via two schemes, called constraint inheritance and constraint propagation, to further enhance the results. Moreover, a historical constraint is enforced between consecutive snapshots to ensure the consistency of results among them. Experiments show better or comparable clustering results than state-of-the-art techniques as well as high scalability for large datasets. Finally, we apply our algorithm for clustering phenotypes in patients with Obstructive Sleep Apnea as well as for tracking how these clusters evolve over time.