This paper presents a unique hybrid classifier that combines deep neural networks with a type-III fuzzy system for decision-making. The ensemble incorporates ResNet-18, Efficient Capsule neural network, ResNet-50, the Histogram of Oriented Gradients (HOG) for feature extraction, neighborhood component analysis (NCA) for feature selection, and Support Vector Machine (SVM) for classification. The innovative inputs fed into the type-III fuzzy system come from the outputs of the mentioned neural networks. The system’s rule parameters are fine-tuned using the Improved Chaos Game Optimization algorithm (ICGO). The conventional CGO’s simple random mutation is substituted with wavelet mutation to enhance the CGO algorithm while preserving non-parametricity and computational complexity. The ICGO was evaluated using 126 benchmark functions and 5 engineering problems, comparing its performance with well-known algorithms. It achieved the best results across all functions except for 2 benchmark functions. The introduced classifier is applied to seven malware datasets and consistently outperforms notable networks like AlexNet, ResNet-18, GoogleNet, and Efficient Capsule neural network in 35 separate runs, achieving over 96% accuracy. Additionally, the classifier’s performance is tested on the MNIST and Fashion-MNIST in 10 separate runs. The results show that the new classifier excels in accuracy, precision, sensitivity, specificity, and F1-score compared to other recent classifiers. Based on the statistical analysis, it has been concluded that the ICGO and propose method exhibit significant superiority compared to the examined algorithms and methods. The source code for ICGO is available publicly at https://nimakhodadadi.com/algorithms-%2B-codes. Graphical abstract

Advances in generative and federated artificial intelligence enable privacy-aware diagnostic systems that integrate multimodal reasoning and explainability. This work introduces DermaGPT, a federated multimodal framework for dermatology decision support that emphasizes trustworthy use under heterogeneous, privacy-sensitive data. The system combines a PaLI-Gemma 2 vision–language backbone, fine-tuned with low-rank adaptation, with a retrieval-augmented large language model that generates clinically coherent and patient-friendly explanations. To improve robustness and calibration across sites, a meta-learned trust function (MLTF) dynamically re-weights client updates based on uncertainty, calibration, and domain-shift indicators. Evaluated on four institutional datasets and an external cohort of 4,452 biopsy-confirmed clinical and dermoscopic images, DermaGPT achieved 90.2% diagnostic accuracy across 11 lesion types and 93.3% accuracy in malignancy prediction, with well-calibrated outputs under federated training. Expert dermatologists rated its explanations as clear and clinically relevant; these ratings were obtained on class-level canonical exemplars rather than per-image reports. In our deployment threat model, images are processed locally by the vision module; when a third-party LLM is used, only text (a short diagnostic summary and the user question) is transmitted, which may still be considered sensitive health data. Taken together, these results indicate that a trust-aware, federated multimodal design can deliver interpretable, efficient, and privacy-aware dermatology decision support that is intended to augment rather than replace clinician judgment.

Fault detection and isolation (FDI) in gas turbines is pivotal to maximizing efficiency, avoiding catastrophic damage, and minimizing unplanned outages. Yet data-driven FDI schemes remain brittle: they lack self-organizing, adaptable structures, rely on limited validation, and degrade under noise and uncertainty. We propose a Self-organizing Type-3 Fuzzy Rough Wavelet Neural Network (ST3FRWNN) that addresses these gaps. First, we introduce a bell-shaped Type-3 membership function that enhances uncertainty handling. Second, we train a neuro-fuzzy architecture with a hybrid Adam–Unscented Kalman Filter optimizer for fast convergence. Third, we embed a self-organizing mechanism that grows and prunes rules adaptively, yielding compact models without sacrificing accuracy. Evaluations on a high-fidelity 163-MW Siemens gas-turbine simulator (Case 1) show average FDI rates of 99.302% (detection) and 99.324% (isolation) and real acoustic-emission signals (Case 2). ST3FRWNN surpasses state-of-the-art fuzzy systems, including FSRE-AdaTSK and TSK-SRB, while using fewer rules, and remains competitive with deep learning baselines (Transformers, LSTMs, CNNs) at a fraction of their parameters. These results, together with robustness to 20-dB SNR and rigorous five-fold cross-validation, demonstrate superior computational efficiency and make ST3FRWNN a practical, deployable solution for real-world gas-turbine health monitoring.