Internet of Medical Things (IoMT) networks face cyberattacks that can disrupt patient care, yet most intrusion detection approaches treat all flows as structurally equivalent, cannot flag previously unseen traffic, and offer no route to a new clinical environment. Supplying those two capabilities normally means adding models a gateway cannot host, so this study derives both from a decomposition of the detector itself and measures the cost. MHFED routes each flow by three elementary statistics to one of three specialised classifiers. Every expert scores every flow, so output divergence yields a novelty signal; routing partitions the data, so experts refit independently as the environment drifts. On two public IoMT datasets the decomposition proves accuracy-neutral: MHFED reaches 98.55% macro-F1 on RT-IoT2022, separable from neither the strongest baselines nor an ensemble of equal capacity. Partitioning also makes an otherwise prohibitive model family affordable to refit in place. The disagreement signal is the only novelty score needing no extra model that ranks unseen attacks above training traffic; established confidence- and entropy-based scores are rank-inverted, hence misleading. No method transfers without target supervision, though labelling 5% of the target domain restores near-source accuracy. The results quantify what edge-deployable novelty detection and cross-environment adaptation cost.
Shirina Samreen, Hafeez Ur Rehman Siddiqui, Nada Alzaben et al.· Scientific Reports· 0 citations
Sixth generation (6G) wireless networks require three-dimensional coordination of heterogeneous network components for intelligent transportation systems (ITS). This article addresses sum rate maximization in beyond diagonal reconfigurable intelligent surface (BD-RIS)-assisted multicell transportation networks within a space-air-ground integrated network framework. Unlike conventional diagonal RIS, BD-RIS enables interelement signal coupling through nondiagonal scattering matrices, providing additional beamforming degrees of freedom. The authors formulate a joint optimization problem encompassing trajectory planning for unmanned aerial vehicles, base station power allocation, and BD-RIS phase configuration. To solve this nonconvex problem, they propose a deep reinforcement learning–based joint orchestration algorithm (DRL-JOA) employing graph attention networks. Simulation results demonstrate that the proposed framework achieves 47.3% sum rate improvement over diagonal RIS and 62.8% over non-RIS baselines, while reducing intercell interference by 34.2% in dense multicell environments.
Zuhaib Nishter, Li Gang, Nada Alzaben et al.· International Journal on Sem...· 0 citations
Existing EEG-based methods have been constrained by limited availability of labeled data, hand-crafted features, poor spatio-temporal modeling, sub-optimal cross-hardware performance, and lack of interpretability due to being expensive and intrusive. To address these limitations, this study introduces innovative neural signal decoding techniques for cognitive state modeling in order to enhance the potential of AI-integrated models for early detection of Alzheimer's disease. This research introduces a self-supervised spatio-temporal transformer (STT-EEG) for early detection of Alzheimer's disease from resting-state EEG. This framework includes four key components: first, self-supervised pretraining on 111 healthy controls using masked auto-encoding and temporal order prediction to learn robust generalisable representations. Second, a novel spatial attention module (SAM) that explicitly captures both long-range temporal dependencies and channel interactions, reflecting the distributed network pathology of AD; third, cross-dataset transfer learning from 64-channel BioSemi to 19-channel Nihon Kohden systems, which showed strong hardware generalization; and finally, analyses of attention rollout and channel perturbation for clinically interpretable insights. The model was trained in a subject-wise 5-fold cross-validation fashion on the SRM dataset and fine-tuned on the OpenNeuro dataset (ds004504) consisting of 36 AD and 29 CN. On the same dataset, the accuracy of STT-EEG was 96.42% for AD vs. CN classification. The most significant improvement +7.08% was made with the help of self-supervised pretraining, followed by data augmentation +6.30% and the SAM +4.86%, as was confirmed in the ablation studies. For continuous prediction of MMSE scores, the Pearson correlation of the model was 0.872 and the mean absolute error (MAE) was 2.34 points. Regions of T3–T6, P3–Pz–P4 and O1–O2 were identified as areas of attention-based interpretability, which were consistent with the known neuropathology of AD that involved the temporoparietal lobe. STT-EEG strengths include the high interpretability of the framework, its spatio-temporal attention, and the fact that STT-EEG is a self-supervised learning method and can be used in an efficient and generalizable way.
Syeda Shamaila Zareen, Nada Alzaben, Usman Ahmad et al.· Frontiers in Neuroinformatic...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
