Modern factories still struggle with unexpected machine failures because traditional maintenance systems depend on fixed rules and threshold-based alerts. These older approaches often overlook subtle or complex patterns in multimodal sensor data, causing them to miss early signs of wear and leading to late or incorrect maintenance decisions. As a result, production can slow down, costs increase and equipment reliability suffers. To address this challenge, this study introduces a smart and interpretable fault diagnosis and predictive maintenance framework designed to detect wear, degradation and potential failures before they disrupt operations. The proposed framework integrates multiscale feature extraction, multimodal sensor fusion and cross-sensor correlation analysis with advanced temporal modeling using a Temporal Convolutional Network (TCN). By jointly performing tool-health classification and Remaining Useful Life (RUL) estimation, the framework provides a comprehensive assessment of machine condition. When evaluated on the NASA Ames milling dataset, the model achieved an overall accuracy of 86%, correctly classifying healthy and failed tools in more than 88% of cases and worn tools in over 75%, demonstrating consistent performance across different stages of tool wear. Explainable artificial intelligence (XAI) techniques, including attention-based visualizations and SHAP-based feature attribution, reveal that electrical and vibration signals are the most influential early indicators of tool degradation. The proposed framework exhibits low computational latency and minimal memory requirements, making it suitable for real-time fault diagnosis and deployment on industrial edge devices. Overall, the framework balances predictive accuracy, interpretability and practical applicability, enabling proactive and reliable maintenance decisions that enhance machine uptime and support efficient smart manufacturing operations.

Global plant diseases represent a major threat to agriculture and represent significant economic losses constituting an important threat to food security. This study introduces a transformative hybrid framework for plant disease diagnosis and severity estimation, combining the strengths of advanced deep learning architectures: Detection Transformer (DETR), Swin Transformer and SAM2-UNet. The proposed methodology incorporates classification, detection, segmentation, and severity estimation in the form of a unified pipeline to address the complexities of real-world agricultural settings, including variable lighting, background variety and large-scale fields. With a hierarchical attention mechanism for efficient feature extraction, the Swin Transformer achieves a top 1 accuracy of 85.6%, and a top 5 accuracy of 96.2%. Utilizing its encoder-decoder attention technique, Detection Transformer (DETR) effectively detects diseases by employing an encoder to forecast bounding boxes and class labels for affected areas. Segmentation performance is enhanced with SAM2-UNet, achieving a pixel-level segmentation with a Dice Similarity Coefficient (DSC) of 94.7%, cleanly delineating disease-affected areas. Finally, disease impact is quantified in the final severity prediction stage to allow for targeted interventions based on disease intensity. The framework has been extensively validated through experiments, and it performs significantly better on all the evaluation metrics: Average ROC AUC of 99.97%, Average Precision-Recall AUC of 98.47%, and F1-score of 94.46%. The suggested system improves precision agriculture by making disease detection and management reliable, scalable, and efficient. This work applies cutting-edge deep learning to sustainable agriculture to reduce crop losses, optimise resource use, and provide farmers with proactive disease management knowledge.

The cultivation of date palm (Phoenix dactylifera L.) is acutely impacted by numerous fungal, bacterial, and pest-related diseases that diminish yield, spoil fruit quality, and undermine long-term agricultural sustainability. The traditional methods of monitoring diseases, which rely heavily on expert knowledge, are not scalable and depend heavily on classical models that do not generalize readily to real-world conditions. Recent improvements in deep learning over the last two decades, particularly with Convolutional Neural Networks (CNNs), have led to significantly greater automation. However, CNNs still require relatively large labeled datasets and struggle with ambiguous or complex background features, small lesions, and overlapping symptoms when diagnosing plant diseases. To address these difficulties, we introduce an innovative hybrid Transformer deep learning framework based on four sophisticated modules: 1) Swin Transformer for hierarchical image classification, 2) YOLOv12 for real-time detection, 3) Grounding DINO with SAM2.1 for zero-shot segmentation, and 4) Vision Transformer (ViT) and a regression head for predicting disease severity. This collective architecture can deliver accurate detection, the most accurate segmentation, and quantification of disease severity in real-world, low-annotation-based scenarios and adverse environmental context situations. Experimental findings on a curated dataset of 13,459 palm leaf images show that the proposed model outperforms all previous CNN-based models with a classification accuracy of 98.91%, a precision of 98.85%, a recall of 96.8%, and an F1-score of 96.4%. These results represent a new standard for automated, scalable, and interpretable disease diagnosis in precision agriculture.

Artificial intelligence (AI) is the main branch of computer science that permits advanced machines to interpret and analyze complex healthcare data elaborating the recent challenges in the medical field of study. The current state of AI applications in healthcare is examined in this systematic literature review, with an emphasis on the technology's accomplishments, difficulties, and potential. The wide breadth of AI technologies used in healthcare settings, such as robots, computer vision, machine learning, and natural language processing, is highlighted in this review through an extensive analysis of peer-reviewed publications. It talks about how customized medicine, predictive analytics, illness detection, and treatment planning are just a few of the areas of healthcare delivery that AI-driven technologies are transforming. According to research by investment bank Goldman Sachs, 300 million full-time employees could be replaced by artificial intelligence (AI). In the US and Europe, it might replace 25% of labor duties, but it might also lead to an increase in productivity and the creation of new jobs. Additionally, it might eventually result in a 7% rise in the global annual value of products and services produced. Additionally, the paper projects that approximately 25% of all employment might be performed totally by AI and that two-thirds of jobs in the U.S. and Europe "are exposed to some degree of AI automation. "The most likely groups to be impacted by workforce automation are educated white-collar workers making up to $80,000 annually, according to research from OpenAI and the University of Pennsylvania. According to a McKinsey Global Institute study, developments in digitalization, robots, and artificial intelligence may require at least 14% of workers worldwide to change jobs by 2030.

Cloud computing now supports large-scale maritime analytics, yet offloading rich Automatic Identification System (AIS) data to the cloud exposes sensitive operational patterns and complicates compliance withcross-border privacy regulations. This work addresses the gap between growing demand for AI-driven vessel intelligence and the limited availability of practical, privacy-preserving cloud solutions. We introduce a privacy-by-designedge-cloud framework in which ports and vessels serve as federated clients, training vessel-type classifiers on local AIStrajectories while transmitting only clipped, Gaussian-perturbed updates to a zero-trust cloud coordinator employingsecure and robust aggregation. Using a public AIS corpus with realistic non-IID client partitions, our evaluationshows that non-private FedAvg attains validation AUC ≈ 0.90 and test AUC ≈ 0.78, closely matching a centralizedbaseline. Moderate differential privacy noise (δ ≤ 0.5) preserves most of this utility across KRUM and trimmedmean aggregation. Communication analysis indicates that secure aggregation introduces negligible overhead comparedwith standard FedAvg, while homomorphic encryption increases payload size by roughly an order of magnitude.Membership-inference experiments further demonstrate strong privacy protection, yielding ROC AUC ≈ 0.51 withno correctly inferred training members. Overall, the findings show that effective, regulation-conscious maritimeanalytics can be achieved without centralizing raw AIS data, offering a practical pathway for deploying resilient,privacy-enhanced AI services in distributed maritime environments.

Conversational systems are becoming a primary interface for services and enterprise automation, and rapid market growth is pushing deployments into safety- and cost-sensitive settings. Reliability remains a bottleneck when interactions span multiple domains: an orchestrator must choose the next specialist, maintain shared dialogue state, and recover from mistakes before they cascade across handoffs. Despite rising interest in swarm-like multi-agent designs, orchestration is rarely evaluated with coordination-centric metrics, making it hard to compare routing policies beyond surface fluency. We present an evaluation-first pipeline for multi-domain task-oriented dialogue on MultiWOZ 2.2 that decouples routing from generation and exposes measurable failure modes. A DeBERTa-based router selects domain specialists, while a FLAN-T5 generator produces structured actions and belief-state updates under a shared memory interface. The protocol tracks delegation correctness, slot-progress coverage, switching and bouncing instability, loop behavior, and recovery after misroutes, and it links early-turn errors to downstream collapse using cascading-error attribution. We further introduce stress tests that simulate reformulation, long-horizon corrections, and tool-latency delays to probe robustness beyond static annotations. Across routing variants, confidence-aware gating yields the strongest stability improvement, achieving routing accuracy of 0.77 while substantially reducing handoff churn, with switching 0.11 and bounce 0.01, relative to a learned baseline with 0.65 accuracy, switching 0.44, and bounce 0.09. At the same time, confidence gating can trade progress for precision when it suppresses belief updates, highlighting an accuracy-progress tension that is important for deployment tuning. Diagnostic summaries identify misrouting and empty-state updates as dominant contributors, while looping is comparatively rare. Finally, applying the same evaluation to SGD shows that coordination challenges persist under schema shift. Overall, the proposed metrics and implementation blueprint provide a reproducible basis for diagnosing coordination failures and selecting orchestration policies for deployment.