Rahim Rahmani

Autonomous Unmanned Aerial Vehicle (UAV) swarms operating in dynamic and uncertainenvironmentsrequiredistributedArtificialIntelligence(AI)andMachineLearning(ML)frame-works capable of simultaneously providing energy-efficient perception, adaptive coordination,scalable decision-making, and real-time optimization. This paper proposes LoihiQ-Swarm, aneuron-dynamics-awaredistributedneuromorphic–quantummulti-agentintelligenceframeworkthat integrates neuromorphic AI, spiking neural networks (SNNs), distributed multi-agentlearning, adaptive event-driven intelligence, Quadratic Unconstrained Binary Optimization(QUBO),andquantumoptimizationintoaunifiedclosed-looparchitecture.Akeyinnovationisaneuron-dynamics-awarequantuminvocationmechanismthatcontinuouslyanalyzesmembranedynamics, spike activity, and synaptic traces to determine when computationally intensiveoptimization should be activated. The proposed AI/ML framework enables adaptive transitionsbetween local neuromorphic inference, QUBO generation, and quantum-assisted optimizationaccording to mission complexity. The application of the proposed framework is demonstratedforautonomousUAVswarmintelligence,includingdistributedobjectdetection,targettracking,collaborativetaskallocation,andlarge-scalesearch-and-rescueoperations.Experimentalresultsdemonstrate improvements in mission success rate, coordination efficiency, latency, energyconsumption, scalability, precision, recall, and F1-score compared with representative baselineapproaches. The results demonstrate that combining neuromorphic AI, distributed machinelearning,andquantumoptimizationprovidesaneffectivefoundationfornext-generationintelli-gent autonomous swarm systems operating in complex edge environments.

Neuromorphic computing has emerged as a promising paradigm forenabling energy-efficient and low-latency intelligence at the edge, partic-ularly for applications requiring real-time multimodal perception. Thispaper presents NEMESIS-Edge, a novel neuromorphic multimodal edgearchitecture designed to integrate heterogeneous sensory data under strictresource constraints. The proposed framework leverages spiking neuralnetworks (SNNs) for event-driven processing, significantly reducing com-putational overhead compared to conventional deep learning approaches.At the core of the architecture is SpikeFusion-X, a spike-domain multi-modal fusion algorithm that preserves temporal dynamics while enablingefficient cross-modal interaction. The framework supports multiple sens-ing modalities, including RGB visual data, polarimetric infrared sensing,and physiological signals, making it suitable for both UAV-based percep-tion and healthcare monitoring applications. A hardware-aware designstrategy is incorporated to ensure compatibility with neuromorphic pro-cessors and edge devices by considering sparsity, quantization, and mem-ory efficiency constraints. Experimental evaluation is conducted using a benchmark-driven method-ology aligned with emerging neuromorphic evaluation standards. Resultsdemonstrate that NEMESIS-Edge achieves up to 6× lower latency and 8×higher energy efficiency compared to baseline approaches while maintain-ing competitive perception accuracy. Additional ablation and robustnessanalyses further validate the effectiveness of the proposed spike-domainfusion mechanism under heterogeneous sensing conditions.Overall, NEMESIS-Edge provides a scalable and efficient frameworkfor real-time neuromorphic edge intelligence across diverse multimodalapplication domains.

Background: Atrial fibrillation (AFib) is the most common sustained arrhythmia in the world, imposing a heavy clinical and economic burden on global healthcare systems. Early detection of AFib can reduce mortality and morbidity, while helping to alleviate the growing economic burden of cardiovascular diseases. With the increasing availability of digital health technologies, computational solutions have great potential to support the timely diagnosis of cardiac abnormalities. Objectives: With the increasing availability of electrocardiogram (ECG) data from clinical and wearable devices, manual interpretation has become impractical due to its time-consuming and subjective nature. Existing automated approaches often rely on single classifiers or fixed ensembles that primarily optimize predictive accuracy while neglecting model diversity, which leads to limited robustness and generalization across heterogeneous datasets. Therefore, this study aims to develop a robust and diversity-aware framework for automatic AFib detection that simultaneously improves classification performance and model generalizability. To this end, we propose MOE-ECG, a multi-objective ensemble selection and fusion framework that explicitly optimizes both predictive performance and inter-model diversity for reliable AFib detection from ECG recordings. Methods: The proposed multi-objective ensemble (MOE) framework uses ensemble selection as a bi-objective optimization problem and employs multi-objective particle swarm optimization to identify complementary classifiers from a heterogeneous model pool. Unlike conventional ensembles, it explicitly optimizes both predictive performance and diversity and integrates Dempster–Shafer theory for uncertainty-aware decision fusion. After filtering the ECG signals to remove baseline wander and noise, they were segmented into windows of 20, 60, and 120 heartbeats with 50% overlap. The proposed approach was evaluated over five independent runs to assess its stability and generalization. Fifteen statistical and nonlinear features were obtained from the RR-intervals of the pre-processed ECG signals, of which eight features were selected with correlation analysis to capture subtle information from the ECG data. We trained and evaluated the performance of the proposed model in three open source databases, namely, the MIT-BIH Atrial Fibrillation Database, Saitama Heart Database Atrial Fibrillation, and Long-Term AF Database. Results: The proposed approach achieved the best overall performance on 60-beat segments, with an average accuracy of 89.85%, precision of 91.14%, recall of 94.19%, an F ₁ -score of 92.64%, and area under the curve (AUC) of around 0.95. Statistical analysis using Holm-adjusted Wilcoxon tests confirmed significant improvements ( p < 0.05) compared to both the best individual classifier and the unoptimized average ensemble of all classifiers. These findings show that the proposed selection and evaluation methodology, rather than group aggregation alone, is the key driver of performance improvements. Conclusion: The results obtained demonstrate that the MOE-ECG model offers a robust, accurate, and reliable solution for the detection of AFib from short ECG segments. The empirical findings, in general, confirm that multi-objective ensemble fusion enhances diagnostic performance and offers robust predictions that will open up possibilities for real-time AFib detection in clinical and tele-health settings.

The Internet of Things (IoT) paradigm aims to enhance human society and living standards with the vast deployment of smart and autonomous devices, which requires seamless collaboration. The number of connected devices increases daily, introducing identity management requirements for edge IoT devices. Due to IoT devices’ heterogeneity and resource-constrained configuration, traditional identity management systems are not feasible. As a result, identity management for IoT devices is still an open issue. Distributed Ledger Technology (DLT) and blockchain-based security solutions are becoming popular in different application domains. This paper presents a novel DLT-based distributed identity management architecture for edge IoT devices. The model can be adapted with any IoT solution for secure and trustworthy communication between devices. We have comprehensively reviewed popular consensus mechanisms used in DLT implementations and their connection to IoT research, specifically identity management for Edge IoT devices. Our proposed location-based identity management model is generic, distributed, and decentralized. The proposed model is verified using the Scyther formal verification tool for security performance measurement. SPIN model checker is employed for different state verification of our proposed model. The open-source simulation tool FobSim is used for fog and edge/user layer DTL deployment performance analysis. The results and discussion section represents how our proposed decentralized identity management solution should enhance user data privacy and secure and trustworthy communication in IoT.

The concept of the Internet of Medical Things brings a promising option to utilize various electronic health records stored in different medical devices and servers to create practical but secure clinical decision support systems. To achieve such a system, we need to focus on several aspects, most notably the usability aspect of deploying it using low-end devices. This study introduces one such application, namely FedSepsis, for the early detection of sepsis using electronic health records. We incorporate several cutting-edge deep learning techniques for the prediction and natural-language processing tasks. We also explore the multimodality aspect for the better use of electronic health records. A secure distributed machine learning mechanism is essential to building such a practical internet of medical things application. To address this, we analyze two federated learning techniques. Moreover, we use two different kinds of low-computational edge devices, namely Raspberry Pi and Jetson Nano, to address the challenges of using such a system in a practical setting and report the comparisons. We report several critical system-level information about the devices, namely CPU utilization, disk utilization, process CPU threads in use, process memory in use (non-swap), process memory available (non-swap), system memory utilization, temperature, and network traffic. We publish the prediction results with the evaluation metrics area under the receiver operating characteristic curve, the area under the precision–recall curve, and the earliness to predict sepsis in hours. Our results show that the performance is satisfactory, and with a moderate amount of devices, the federated learning setting results are similar to the single server-centric setting. Multimodality provides the best results compared to any single modality in the input features obtained from the electronic health records. Generative adversarial neural networks provide a clear superiority in handling the sparsity of electronic health records. Multimodality with the generative adversarial neural networks provides the best result: the area under the precision–recall curve is 96.55%, the area under the receiver operating characteristic curve is 99.35%, and earliness is 4.56 h. FedSepsis suggests that incorporating such a concept together with low-end computational devices could be beneficial for all the medical sector stakeholders and should be explored further.

Edge-based distributed intelligence techniques, such as federated learning (FL), have recently been used in many research fields thanks, in part, to their decentralized model training process and privacy-preserving features. However, because of the absence of effective deployment models for the radio access network (RAN), only a tiny number of FL apps have been created for the latest generation of public mobile networks (e.g., 5G and 6G). There is an attempt, in new RAN paradigms, to move toward disaggregation, hierarchical, and distributed network function processing designs. Open RAN (O-RAN), as a cutting-edge RAN technology, claims to meet 5G services with high quality. It includes integrated, intelligent controllers to provide RAN with the power to make smart decisions. This paper proposes a methodology for deploying and optimizing FL tasks in O-RAN to deliver distributed intelligence for 5G applications. To accomplish model training in each round, we first present reinforcement learning (RL) for client selection for each FL task and resource allocation using RAN intelligence controllers (RIC). Then, a slice is allotted for training depending on the clients chosen for the task. Our simulation results show that the proposed method outperforms state-of-art FL methods, such as the federated averaging algorithm (FedAvg), in terms of convergence and number of communication rounds.