This paper presents a hybrid mutual coupling reduction technique applied onto a dual-band textile MIMO antenna for wireless body area network and 5G applications. The MIMO antenna consists of two hexagonal patch antennas, each integrated with a split-ring (SR) and a bar slot to operate in dual-band mode at 2.45 GHz and 3.5 GHz. Each patch is dimensioned at $47.2 \times 31$ mm ² . This hybrid technique results in a simple structure, while enabling significant reduction of mutual coupling (MC) between the closely spaced patches (up to $0.1\lambda$ ). This technique combines a line patch and a patch rotation technique, explained as follows. First, a line patch is introduced at an optimized distance to enable operation with a broad impedance bandwidth at both target frequencies. One of the patches is then rotated by 90° at an optimized distance, resulting in a significant MC suppression while maintaining the dual and broad impedance bandwidth. The proposed MIMO antenna is further evaluated under several bending configurations to assess its robustness. A satisfactory agreement between simulated and measured results is observed in both planar and bending conditions. Results show that the MIMO antenna achieves an impedance bandwidth of 4.3 % and 6.79 % in the 2.45 GHz and 3.5 GHz band, respectively. Moreover, very low MC ( $S_{21} < -30$ dB) is achieved, with a low (< 0.002) envelop correlation coefficient, and about 10 dB of diversity gain at both desired frequencies using this technique. Even when bent at an angle of 50° at the $x$ - and $y$ -axes, the antenna bent maintained a realized gain of 1.878 dBi and 4.027 dBi in the lower and upper band, respectively. A robust performance is offered by the antenna against the lossy effects of the human body with good agreements between simulated and measured results.

Early and accurate breast cancer diagnosis remains critical yet challenging in routine practice. This study proposes a simple, reproducible pipeline that combines deep feature extraction from pre-trained CNNs (ResNet50, VGG16, EfficientNet-B0, DenseNet121, MobileNetV2) with classical machine-learning classifiers (logistic regression, SVM, k-NN, decision tree, random forest, gradient boosting, XGBoost, LightGBM, Naïve Bayes, and MLP). Features are computed after standardized preprocessing; class imbalance is addressed with SMOTE when present. We evaluate three image datasets (binary and multiclass) using accuracy, precision, recall/sensitivity, F1, and confusion matrices, and apply paired statistical tests across cross-validation splits. Findings: EfficientNet-B0+MLP and ResNet50+MLP achieve peak accuracies up to 99.6% on high-quality, balanced data, while DenseNet121+MLP with SMOTE attains 97.8% on imbalanced multiclass data. SMOTE yields substantial gains on imbalanced data and negligible effect on balanced sets; decision trees underperform consistently. Novelty/Improvement: Rather than a monolithic end-to-end network, we provide a modular, resource-aware blueprint that (i) disentangles feature extraction from classification, (ii) quantifies when imbalance correction matters, and (iii) reports clinically relevant error types. We further outline explainability with Grad-CAM/SHAP and discuss inference-time trade-offs and real-world workflow integration, offering an interpretable and deployment-friendly alternative to heavier end-to-end models.

The paper outlines a methodology to diminish mutual coupling in 4-port dual-band MIMO textile antenna for biomedical applications. This antenna leverages MIMO technology and Wireless Body Area Network (WBAN) for operation in two distinct frequency bands at (3.5 & 2.45 GHz). The antenna is made up of four octagonal patch antennas, each having a bar and a split-ring (SR) slot with 47.2 × 31 mm² dimensions for each patch. A hybrid mutual coupling (MC) approach was investigated with closely spaced patches (up to 0.05λ). Various bending setups have been selected along with flat case to examine the antennas’ resilience which demonstrate such agreement between measured and simulated findings. Furthermore, the MC is only −20 dB, the envelope correlation coefficient (ECC) is 0.001, and maximum peak measured gain of 5.2 dBi is achieved with lowest peak specific absorption rate (SAR) value. Even when bent at a 60° angle along with y-axis and x-axis, the antenna retains a decent gain of 1.861 dBi in the low frequency region and 5.479 dBi at high frequency band. Surprisingly, the antenna outperforms the attenuation produced by the lossy effects of the human body, indicating a favorable alignment between the modelled and observed findings.

The super-resolution (SR) of Magnetic Resonance Imaging (MRI) is essential for utilizing clinical scans with limited resolution, noise, and anisotropic sampling, such as multi-modal brain tumor imaging. In this work, we propose a Tri-Representation hybrid framework for MRI SR, TRT-GLA, that redefines the MRI SR task as a joint spatial–spectral–structural high-resolution image generation problem. TRT-GLA utilizes (i) spatial global–local attentions for modeling the spatial anatomy, (ii) a Fourier spectral transfer mechanism for upholding spectral consistency, and (iii) multi-scale hierarchical spectral decomposition for improved edge details. To adapt the learning framework to medical imaging characteristics, we introduce a tri-representation consistent loss function that explicitly combines pixel-wise, spectral, and edge structure priors from the high-resolution ground-truth, as well as a progressive resolution learning strategy. Our large-scale brain tumor experiments, on the IXI, BraTS 2019, 2020, and 2023 datasets, show that TRT-GLA achieves state-of-the-art results at upsampling factors of ×2, ×4, and ×8, respectively, achieving substantial improvements across CNN, GAN, and transformer-based methods in Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Multi-scale Structural Similarity Index (MS-SSIM). We further demonstrate how SR benefits brain tumor segmentation through the downstream task evaluation of a dual-branch segmentation framework. TRT-GLA produces highly accurate tumor segmentation results from low-resolution inputs, improving over native high-resolution inputs at ×8 in critical tumor boundary regions and in small tumor regions. There remains a small gap between native, high-resolution imaging and SR-enhanced performance, which TRT-GLA nearly closes under realistic scenarios. Our results highlight the importance of synthesizing unified priors over spatial, spectral, and structural domains within a transformer for anatomically faithful reconstructions. Importantly, we also establish the utility of TRT-GLA in supporting quantitative analysis through a downstream tumor segmentation experiment that is clinically relevant.

The purpose of this research was to create a fully automatic deep-learning method to accurately classify different types of cardiac arrhythmias based on patterns observed in electrocardiograms (ECGs). There are several challenges that arise when manually interpreting cardiac arrhythmias. These include variability in how different observers interpret arrhythmias and variability in the diagnostic results obtained by different clinicians. To address these issues, we propose an architecture that includes both residual transfer learning and transformer encoder blocks. In our proposed architecture, the residual learning block uses Conv1D layers with skip connections to learn hierarchical representations of features in the ECG signal. The transformer block uses multi-head self-attention to identify longer-range dependencies in the ECG sequence. Our proposed model is tested on two publicly available benchmark databases of ECG recordings, namely the MIT-BIH Arrhythmia Database and the PTBDB Diagnostic ECG Database. We evaluate the performance of our model using a stratified 10-fold cross-validation procedure as well as Receiver Operating Characteristic (ROC) analysis. The proposed model achieved a classification accuracy of 99% on both datasets, with precision scores of 0.88 to 0.99 and recall scores of 0.87 to 0.99 for each arrhythmia class. Furthermore, the AUC values of the ROC analysis ranged from 0.98 to 1.0, indicating high levels of discrimination against minority classes, including supraventricular ectopic beats and fusion beats.

Super-resolution (SR) facilitates high-fidelity mapping beyond the spatial resolution capacity of clinical neuro-oncology MRI. While state-of-the-art deep learning algorithms have augmented this domain, such methods exclusively learn from spatial or spectral domains and are often compounded by tumor boundary over-smoothing and geometrically inconsistent pathologies. In this paper, we introduce Hy-DTGL, a hybrid-domain transformer with a global–local attention modal super-resolution (SR) framework that learns a joint reconstruction across four inter-dependent knowledge domains: local spatial, global spatial, spectral and wavelet. Using windowed self-attention, Hy-DTGL learns highly localized pathologic textures; pooled global attention constrains anatomical plausibility; Fourier-learnable modulation provides spectral energy per semblance; and multi-scale discrete wavelet tiling preserves multi-scale tumor morphology. Optimization occurs via a hybrid objective, combining Charbonnier loss, gradient edge-loss, and spectral domain loss. The proposed framework was trained on BraTS 2019 (BT_19) and evaluated on BT_19, BraTS 2020 (BT_20), BraTS 2023 (BT_23), and IXI under both in-domain and strict zero-shot settings, and achieves competitive performance relative to the evaluated baselines under the adopted degradation and evaluation protocol at ×2, ×4, and ×8 SR factors. In the BraTS 2020 ×4 test resolution, 37.46 dB PSNR and 0.986 SSIM are attained, outperforming deep learning CNN-based SR (ECFNet) by 2.47 dB and transformer-based (WavTrans) by 4.05 dB in PSNR. Ablative studies reveal the spatial, spectral and multi-scale constraints notably converge to a faithfully mapped image space with restored tumor boundary delineation and global-structure consistency. We also show the Hy-DTGL generalizability by how it improves downstream tumor segmentation metrics: the super-resolved scans improve the segmentation Dice coefficient by 0.063 and significant reductions are observed in the Hausdorff Distance from 19.05 mm to 13.01 mm relative to the original low-resolution images, suggesting potential utility for downstream neuro-oncological image analysis.