NTNhien Q. T. Thoong

Nhien Q. T. Thoong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nhien Q. T. Thoong has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Quantum Federated LSTM Approach for Fall Detection With Wearable IoT Devices

    by Senthan Prasanth, Quan Thanh Dao, Nhien Q. T. Thoong, Elif Ak, Trung Q. Duong

    Falls are common among older adults, but wearable fall-detection models often perform well on the dataset on which they are trained, yet lose accuracy when the user, device, or sensor location changes. This article studies a privacy-preserving approach that learns from distributed wearable data while still adapting to each person. We propose a hybrid quantum long short-term memory (QLSTM) model and train it in a three-stage workflow: a public pretraining step to learn general motion patterns, federated training to learn from multiple users without sharing raw data, and a lightweight personalization step for each client. To support this setting, we collect a new inertial dataset with multiple body locations and time-annotated fall events, and we align its activity labels with common public benchmarks to enable consistent evaluation and facilitate federated transfer learning. Results show that the QLSTM transfers better than a classical LSTM when applied to new users and unseen sensor placements, achieving nearly 90% average accuracy after federated training and personalization. Compared with the traditional machine-learning (ML) approach, the proposed quantum ML (QML) model also uses fewer trainable parameters, which reduces the size of updates exchanged during federated training.


  • Quantum Machine Learning for Channel Estimation in Reconfigurable Intelligent Surfaces-Assisted 6G Networks

    by Nhien Q. T. Thoong, Quang Nhat Le, Minh-Hien T. Nguyen, Vishal Sharma, Adnan A. Cheema, Mehmet Özdem, Berk Canberk, Trung Q. Duong


  • Channel Estimation for Reconfigurable Intelligent Surface-Aided 6G NOMA Systems: A Quantum Machine Learning Approach

    by Nhien Q. T. Thoong, Adnan A. Cheema, Berk Canberk, Dung Thanh Tran, Octavia A. Dobre, Trung Q. Duong

    The integration of reconfigurable intelligent surfaces (RISs) and non-orthogonal multiple access (NOMA) is considered a promising technique to enhance spectral efficiency and connectivity in future 6G networks. Accurate channel estimation remains a critical challenge in RIS-NOMA systems due to the increased complexity introduced by the combination of RIS and NOMA technologies. While quantum machine learning (QML) has demonstrated potential in wireless communications, its application in channel estimation remains underexplored. This paper investigates the effectiveness of a hybrid quantum-classical machine learning (ML) model for channel estimation in RIS-NOMA systems. We propose a hybrid architecture that integrates convolutional neural networks (CNNs) with quantum long short-term memory (QLSTM) networks, where CNNs perform spatial feature extraction while QLSTMs capture temporal dependencies in the time-varying channel. Extensive simulations are conducted to evaluate the performance of the model under various network configurations, considering different power allocation factors, the number of RIS elements, and signal-to-noise ratios (SNRs). The performance of the proposed model is benchmarked against both pure quantum and classical ML models, including a quantum neural network (QNN), a CNN, a long short-term memory (LSTM) model, a bidirectional LSTM (BiLSTM) model, and a CNN-LSTM model. The results demonstrate that the proposed CNN-QLSTM model outperforms all baseline methods in terms of root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). These findings highlight the potential of quantum-enhanced ML for channel estimation in next-generation communication networks.