Mathini Sellathurai

Xiaonan Liu, Tharmalingam Ratnarajah, Mathini Sellathurai et al.

Federated learning (FL) enables distributed learning across edge devices while protecting data privacy. However, the learning accuracy decreases due to the heterogeneity of devices' data, and the computation and communication latency increase when updating large-scale learning models on devices with limited computational capability and wireless resources. We consider a FL framework with partial model pruning and personalization to overcome these challenges. This framework splits the learning model into a global part with model pruning shared with all devices to learn data representations and a personalized part to be fine-tuned for a specific device, which adapts the model size during FL to reduce both computation and communication latency and increases the learning accuracy for devices with non-independent and identically distributed data. The computation and communication latency and convergence of the proposed FL framework are mathematically analyzed. To maximize the convergence rate and guarantee learning accuracy, Karush Kuhn Tucker (KKT) conditions are deployed to jointly optimize the pruning ratio and bandwidth allocation. Finally, experimental results demonstrate that the proposed FL framework achieves a remarkable reduction of approximately 50 percent computation and communication latency compared with FL with partial model personalization.

Anis Hamadouche, Haifeng Luo, Mathini Sellathurai et al.

Real-time audio-visual speech enhancement (AVSE) is a key enabler for immersive and interactive multimedia services, yet its performance is tightly constrained by network latency, uplink capacity, and computational delay. This paper presents the design, deployment, and evaluation of a complete cloud-edge-assisted AVSE system operating over a public 5G edge network. The system integrates CNN-based acoustic enhancement and OpenCV-based facial feature extraction with an LSTM fusion network to preserve temporal coherence, and is deployed on a Vodafone-compatible AWS Wavelength edge cloud. Through extensive stress testing, we analyze end-to-end performance under varying network load and adaptive multimedia profiles. Results show that compute placement at the network edge is critical for meeting real-time coherence constraints, and that uplink capacity is often the dominant bottleneck for interactive AVSE services. Only 5G and wired Ethernet consistently satisfied the required communication delay bound for uncompressed audio-video chunks, while aggressive compression reduced payload sizes by up to 80% with negligible perceptual degradation, enabling robust operation under constrained conditions. We further demonstrate a fundamental trade-off between processing latency and enhancement quality, where reduced model complexity lowers delay but degrades reconstruction performance in low-SNR scenarios. Our findings indicate that public 5G edge environments can sustain real-time, interactive AVSE workloads when network and compute resources are carefully orchestrated, although performance margins remain tighter than in dedicated infrastructures. The architectural insights derived from this study provide practical guidelines for the design of delay-sensitive multimedia and perceptual enhancement services on emerging 5G edge-cloud platforms.

Anis Hamadouche, Mathini Sellathurai

This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. Instead of transmitting all model parameters, we propose a degrees-of-freedom (DoF) based codec that sends only the unique coefficients implied by a chosen symmetry group, enabling deterministic reconstruction of the full weight tensor at the receiver. The proposed framework is evaluated under quantization and noisy channel conditions across multiple symmetry patterns, signal-to-noise ratios, and bit-widths. To improve robustness against transmission impairments, a projection step is further applied at the receiver to enforce consistency with the symmetry-invariant subspace, effectively denoising corrupted parameters. Experimental results on MNIST and CIFAR-10 using a DeepCNN architecture demonstrate that DoF-based transmission achieves substantial bandwidth reduction while preserving significantly higher accuracy than pruning-based baselines, which often suffer catastrophic degradation. Among the tested symmetries, \textit{central-skew symmetry} consistently provides the best accuracy-compression tradeoff, confirming that structured redundancy can be leveraged for reliable and efficient neural model delivery over constrained links.

Christantus O. Nnamani, Mathini Sellathurai

This paper examines the separation of wireless communication and radar signals, thereby guaranteeing cohabitation and acting as a panacea to spectrum sensing. First, considering that the channel impulse response was known by the receivers (communication and radar), we showed that the optimizing beamforming weights mitigate the interference caused by signals and improve the physical layer security (PLS) of the system. Furthermore, when the channel responses were unknown, we designed an interference filter as a low-complex noise and interference cancellation autoencoder. By mitigating the interference on the legitimate users, the PLS was guaranteed. Results showed that even for a low signal-to-noise ratio, the autoencoder produces low root-mean-square error (RMSE) values.

Navneet Garg, Mathini Sellathurai, Tharmalingam Ratnarajah

Power consumption is one of the major issues in massive MIMO (multiple input multiple output) systems, causing increased long-term operational cost and overheating issues. In this paper, we consider per-antenna power allocation with a given finite set of power levels towards maximizing the long-term energy efficiency of the multi-user systems, while satisfying the QoS (quality of service) constraints at the end users in terms of required SINRs (signal-to-interference-plus-noise ratio), which depends on channel information. Assuming channel states to vary as a Markov process, the constraint problem is modeled as an unconstraint problem, followed by the power allocation based on Q-learning algorithm. Simulation results are presented to demonstrate the successful minimization of power consumption while achieving the SINR threshold at users.

Christantus O. Nnamani, Muhammad R. A. Khandaker, Mathini Sellathurai

This paper considers unmanned aerial vehicle (UAV)-carried intelligent reflecting surface (IRS) for secure data collection in wireless sensor networks. An eavesdropper (Eve) lurks within the vicinity of the main receiver (Bob) while several randomly placed sensor nodes beamform collaboratively to the UAV-carried IRS that reflects the signal to the main receiver (Bob). The design objective is to maximise the achievable secrecy rate in the noisy communication channel by jointly optimizing the collaborative beamforming weights of the sensor nodes, the trajectory of the UAV and the reflection coefficients of the IRS elements. By designing the IRS reflection coefficients with and without the knowledge of the eavesdropper's channel, we develop a non-iterative sub-optimal solution for the secrecy rate maximization problem. It has been shown analytically that the UAV flight time and the randomness in the distribution of the sensor nodes, obtained by varying the sensor distribution area, can greatly affect secrecy performance. In addition, the maximum allowable number of IRS elements as well as a bound on the attainable average secrecy rate of the IRS aided noisy communication channel have also been derived. Extensive simulation results demonstrate the superior performance of the proposed algorithms compared to the existing schemes.

Georgios K. Papageorgiou, Mathini Sellathurai, Yonina C. Eldar

In this work, we consider direction-of-arrival (DoA) estimation in the presence of extreme noise using Deep Learning (DL). In particular, we introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true array manifold matrix and is able to predict angular directions using the sample covariance estimate. We model the problem as a multi-label classification task and train a CNN in the low-SNR regime to predict DoAs across all SNRs. The proposed architecture demonstrates enhanced robustness in the presence of noise, and resilience to a small number of snapshots. Moreover, it is able to resolve angles within the grid resolution. Experimental results demonstrate significant performance gains in the low-SNR regime compared to state-of-the-art methods and without the requirement of any parameter tuning. We relax the assumption that the number of sources is known a priori and present a training method, where the CNN learns to infer the number of sources jointly with the DoAs. Simulation results demonstrate that the proposed CNN can accurately estimate off-grid angles in low SNR, while at the same time the number of sources is successfully inferred for a sufficient number of snapshots. Our robust solution can be applied in several fields, ranging from wireless array sensors to acoustic microphones or sonars.

Christantus O. Nnamani, Muhammad R. A. Khandaker, Mathini Sellathurai

This paper investigates unmanned aerial vehicle (UAV)-aided jamming technique for enabling physical layer keyless security in scenarios where the exact eavesdropper location is unknown. We assume that the unknown eavesdropper location is within an ellipse characterizing the coverage region of the transmitter. By sequentially optimizing the transmit power, the flight path of the UAV and its jamming power, we aim at maximizing the average secrecy rate with arbitrary eavesdropper location. Simulation results demonstrate that the optimal flight path obtains better secrecy rate performance compared to that using direct UAV flight path encasing the transmitter and the legitimate receiver. Most importantly, even with the unknown eavesdropper location, we obtained a secrecy rate that is comparable to a scenario when the eavesdropper's location is known. However, the average secrecy rate with the unknown eavesdropper location varies depending on the proximity of the eavesdropper to the known location of the transmitter. We also observe that due to the UAV-aided jamming, the average secrecy rate stabilizes at some point even though the average received envelope power of the eavesdropper increases. This essentially demonstrates the effectiveness of the proposed scheme.