Secure communication in resource-constrained Internet of Things (IoT) deployments—such as consumer electronics and smart city infrastructures—faces persistent challenges from both limited processing capacity and increasingly adaptive cyber threats. This work introduces the Adversarial Neural Encryption Framework (ANEF), which models encryption as a non-invertible mapping trained through an adversarial three-agent setup comprising an encoder (Alice), a decoder (Bob), and an adversary (Eve). The framework integrates entropy-regularized encryption, dynamic key scheduling with periodic reseeding, and quantization-aware optimization to support 8-bit inference on constrained hardware. Adversarial resistance is reinforced through residual masking and curvature-based penalties, improving robustness against adaptive attacks. Training is guided by a hybrid objective that balances reconstruction fidelity, orthogonality preservation, and adversarial minimization, applied over sequential encryption states. Experiments using the UNSW-NB15 dataset evaluate accuracy, communication overhead, and adversary success rate across diverse packet sizes. ANEF achieves 94.7% decryption accuracy with a 10.3% transmission overhead, while maintaining a 4.1% adversary success rate.

Human locomotion and localization recognition are of critical importance in the development of intelligent systems with the capability of monitoring, analyzing, and responding to human behavior in the real world. This research proposes a robust yet computationally efficient approach by exploiting the sensors of a smartphone, such as accelerometers, gyroscopes, and Global Positioning System (GPS). The proposed approach improves the accuracy of localization and locomotion recognition. The proposed approach is computationally efficient and yet robust. The approach begins with the preprocessing of the sensor signals by using the Savitzky-Golay filter for noise reduction. The signals are then subjected to overlap-add windowing. The signals are then subjected to a comprehensive feature extraction process. To ensure the discriminability of the features and eliminate redundant features, Luca-measure Fuzzy Entropy (LFE) optimization technique has been used. The technique helps in identifying non-linear relationships effectively. The features are then subjected to a Graph Convolutional Network (GCN) for classification. The proposed approach has been tested with the ExtraSensory and Sussex-Huawei Locomotion (SHL) datasets. The results show localization accuracy of 92.57%, 89.83%, locomotion recognition of 93.18%, and 91.75%, respectively.

Cardiovascular disease diagnosis requires accurate and timely analysis of electrocardiogram (ECG) signals to support reliable clinical decision-making. However, ECG signals are inherently non-stationary, exhibit substantial inter-patient variability, and may share similar morphological patterns across different cardiac disorders, making automated multi-class diagnosis challenging. This study proposes a multi-domain machine learning framework for automated ECG-based cardiac disease classification, integrating signal preprocessing, heartbeat segmentation, Variational Mode Decomposition (VMD), multi-domain feature extraction, minimum Redundancy Maximum Relevance (mRMR) feature selection, and hybrid CNN–Transformer learning. Experiments are conducted on the PTB-XL database using five diagnostic superclasses: NORM, MI, STTC, CD, and HYP. First, a fourth-order Butterworth band-pass filter (0.5–40 Hz) is applied to remove baseline wander and high-frequency noise, followed by adaptive Symlet-8 wavelet denoising with soft thresholding to suppress residual high-frequency fluctuations while preserving the P-wave, QRS complex, and T-wave morphology, after which the signal is z-score normalized. R-peaks are subsequently detected to segment standardized cardiac cycles. VMD is then employed to decompose the heartbeat signals into intrinsic modes, from which the most informative modes are retained using correlation-based mode selection. Temporal, statistical, spectral, and nonlinear features are extracted to capture complementary characteristics of cardiac electrical activity, while mRMR selects the eight most informative features by maximizing feature relevance and minimizing redundancy. The resulting representation is processed through a hybrid CNN–Transformer architecture, in which convolutional layers learn local morphological patterns and Transformer-based attention captures long-range dependencies within the cardiac feature representation. The proposed framework achieves 93.60% accuracy, 93.61% macro precision, 93.60% macro recall, 93.60% macro F1-score, and 98.40% macro specificity across the five diagnostic classes. Confusion-matrix analysis, receiver operating characteristic (ROC) analysis, comparative evaluation, and ablation experiments further demonstrate the discriminative capability and robustness of the proposed approach. These findings indicate that multi-domain biomedical feature learning combined with attention-based deep learning can provide an effective and robust strategy for automated ECG-based cardiac disease classification, highlighting the potential of machine learning for intelligent biomedical signal analysis and computer-aided clinical diagnosis.

Coordinating multi-agent unmanned aerial vehicle (UAV) swarms is challenging in disaster scenarios where communications are dynamic, unreliable, and subject to UAV losses. While distributed artificial intelligence has enabled unprecedented levels of autonomous multi-agent coordination, most methods implicitly take communication topology as a given, not accounting for its limited maintenance in such scenarios. As a result, communication fragmentation can undermine autonomous mission progress during highly dynamic communications conditions. This paper proposes the Adaptive k-Truss-Constrained Agentic AI Framework (ATAC), an AI-based decentralized coordination framework for multi-agent UAV systems, which explicitly factors in graph-theoretic structural considerations during decision-making. The swarm is modeled as a graph, where an adaptive k-truss backbone is maintained during dynamic communication conditions to preserve triangle-based redundancy. Each agent acts as a graph-aware AI entity which bases its decentralized decisions on local information and descriptors of the communication backbone. A closed-loop evolutionary process is used to rebuild the backbone after significant communication link losses while UAVs make mission progress decisions based on information from the current backbone, enabling continuous adaption of the swarm structure to the communication state. The efficacy of the proposed framework is demonstrated through a comprehensive simulation campaign which includes communication link losses, UAV failures, adaptive truss selection, ablation studies, reward sensitivity analysis, and computational performance assessments. ATAC is compared to alternative graph-aware coordination approaches, showing consistent improvements in maintaining communication, preserving backbone structure, enabling triangle-based connectivity, and overall structural recovery while still achieving high-levels of mission progress during dynamic disaster response scenarios. The results highlight the effectiveness of explicitly tying AI-driven decentralized decision-making to maintenance of a graph-theoretic backbone structure for resilient UAV swarm coordination.

Sports activity recognition in aerial videos has emerged to be a crucial area of study with the escalating use of uncrewed aerial vehicles (UAVs) in sports. Nevertheless, sports activity recognition in aerial views turns out to be an extremely difficult assignment because of small activity recognition targets, varying camera views, motion, occlusion, and multi-player sports activity recognition. Keeping these factors in mind, this study tends to introduce a multi-modal deep learning model for robust sports activity recognition in aerial videos. Based on this, the proposed model uses self-supervised learning visual features obtained via Self-DIstillation with NO labels version 2 (DINOv2), motion features obtained via dense optical flows, body geometry features via ellipsoidal modeling, pose features via multi-person pose estimation, and lastly, features related to social sports activity via graph modeling, and hypergraphs. These different features can be optimally combined via Bayesian optimization, with compact-bilinear pooling, which employs Graph SAmple and aggreGatE (GraphSAGE) to model the interpersonal associations, and ultimately, employs a gated recurrent unit (GRU) with a temporal attention model. This multi-modal deep learning model will be tested on two challenging athletic benchmarks: event recognition in aerial videos (ERA), which focuses on recognizing sports activity in the aerial context, and the other, named Collective Sports (C-Sports), which tends to recognize sports activity and group sports activity. Eventually, it becomes clear through the proposed model, which provides a top-1 accuracy measure of 59.8% (83.4% top-5), a top-1 measure of 93.8% on sports activity, and a top-1 measure of sports group activity recognition of 76.8%, which outperforms other methods and turns out to be close to other recent methods.