The importance of identifying plant diseases has risen recently due to the adverse effect they have on agricultutal production. Plant diseases have been a big concern in agriculture, as they affect crop production, and constitute a major threat to global food security. In the domain of modern agriculture, effective plant disease management is vital to ensure healthy crop yields and sustainable practices. Traditional means of identifying plant disease are faced with lots of challenges and the need for better and efficient detection methods cannot be overemphazised. The emergence of advanced technologies, particularly deep learning and content-based filtering techniques, if integrated together can changed the way plant diseases are identified and treated. Such as speedy and correct identification of plant diseases and efficient treatment recommendations which are keys for sustainable food production. In this work, We try to investigate the current state of research, identified gaps and limitations in knowledge, and suggests future directions for researchers, experts and farmers that could help to provide better ways of mitigating plant disease problems.

Artificial Intelligence (AI) in Smart Agricultural Facilities (SAF) often lacks explainability, hindering farmers from taking full advantage of their capabilities. This study tackles this gap by introducing a model that combines eXplainable Artificial Intelligence (XAI), with Predictive Maintenance (PdM). The model aims to provide both predictive insights and explanations across four key dimensions, namely data, model, outcome, and end-user. This approach marks a shift in agricultural AI, reshaping how these technologies are understood and applied. The model outperforms related studies, showing quantifiable improvements. Specifically, the Long-Short-Term Memory (LSTM) classifier shows a 5.81% rise in accuracy. The eXtreme Gradient Boosting (XGBoost) classifier exhibits a 7.09% higher F1 score, 10.66% increased accuracy, and a 4.29% increase in Receiver Operating Characteristic-Area Under the Curve (ROC-AUC). These results could lead to more precise maintenance predictions in real-world settings. This study also provides insights into data purity, global and local explanations, and counterfactual scenarios for PdM in SAF. It advances AI by emphasising the importance of explainability beyond traditional accuracy metrics. The results confirm the superiority of the proposed model, marking a significant contribution to PdM in SAF. Moreover, this study promotes the understanding of AI in agriculture, emphasising explainability dimensions. Future research directions are advocated, including multi-modal data integration and implementing Human-in-the-Loop (HITL) systems aimed at improving the effectiveness of AI and addressing ethical concerns such as Fairness, Accountability, and Transparency (FAT) in agricultural AI applications.

Soft-computing and statistical learning models have gained substantial momentum in predicting type 2 diabetes mellitus (T2DM) disease. This paper reviews recent soft-computing and statistical learning models in T2DM using a meta-analysis approach. We searched for papers using soft-computing and statistical learning models focused on T2DM published between 2010 and 2021 on three different search engines. Of 1215 studies identified, 34 with 136952 patients met our inclusion criteria. The pooled algorithm’s performance was able to predict T2DM with an overall accuracy of 0.86 (95% confidence interval [CI] of [0.82, 0.89]). The classification of diabetes prediction was significantly greater in models with a screening and diagnosis (pooled proportion [95% CI] = 0.91 [0.74, 0.97]) when compared to models with nephropathy (pooled proportion = 0.48 [0.76, 0.89] to 0.88 [0.83, 0.91]). For the prediction of T2DM, the decision trees (DT) models had a pooled accuracy of 0.88 [95% CI: 0.82, 0.92], and the neural network (NN) models had a pooled accuracy of 0.85 [95% CI: 0.79, 0.89]. Meta-regression did not provide any statistically significant findings for the heterogeneous accuracy in studies with different diabetes predictions, sample sizes, and impact factors. Additionally, ML models showed high accuracy for the prediction of T2DM. The predictive accuracy of ML algorithms in T2DM is promising, mainly through DT and NN models. However, there is heterogeneity among ML models. We compared the results and models and concluded that this evidence might help clinicians interpret data and implement optimum models for their dataset for T2DM prediction.

Medical anomaly detection is challenged by limited labeled data and domain shifts, which reduce the performance and generalization of deep learning (DL) models. Hybrid convolutional neural network–Vision Transformer (CNN–ViT) architectures have shown promise, but they often rely on large datasets. Multistage transfer learning (MTL) provides a practical strategy to address this limitation. In this study, we evaluated parallel hybrids, where convolutional neural network (CNN) and Vision Transformer (ViT) features are fused after independent extraction, and sequential hybrids, where CNN features are passed through the ViT for integrated processing. Models were pretrained on non-wrist musculoskeletal radiographs (MURA), fine-tuned on the MURA wrist subset, and evaluated for cross-domain generalization on an external wrist X-ray dataset from the Al-Huda Digital X-ray Laboratory. Parallel hybrids (Xception–DeiT, a data-efficient image transformer) achieved the strongest internal performance (accuracy 88%), while sequential DenseNet–ViT generalized best in zero-shot transfer. After light fine-tuning, parallel hybrids achieved near-perfect accuracy (98%) and recall (1.00). Statistical analyses showed no significant difference between the parallel and sequential models (McNemar’s test), while backbone selection played a key role in performance. The Wilcoxon test found no significant difference in recall and F1-score between image and patient-level evaluations, suggesting balanced performance across both levels. Sequential hybrids achieved up to 7× faster inference than parallel models on the MURA test set while maintaining similar GPU memory usage (3.7 GB). Both fusion strategies produced clinically meaningful saliency maps that highlighted relevant wrist regions. These findings present the first systematic comparison of CNN–ViT fusion strategies for wrist anomaly detection, clarifying trade-offs between accuracy, generalization, interpretability, and efficiency in clinical AI.

This review thoroughly explores the valorization of Arachis hypogaea (groundnut) residues for producing high-value bioproducts such as biofuels, biocatalysts, biochar, and nanomaterials through processes like pyrolysis, gasification, and enzymatic conversion. Optimization techniques, including Response Surface Methodology (RSM), Artificial Neural Networks (ANNs), and Adaptive Neuro-Fuzzy Inference Systems (ANFIS), have led to significant enhancements in bioproduct yields. A detailed bibliometric analysis spanning from 2000 to the present highlights key research trends and influential contributors, reflecting the increasing global focus on groundnut residue valorization. The study emphasizes the environmental and economic benefits, such as improved waste management, reduced greenhouse gas emissions, and contributions to a circular bioeconomy. It advocates for policy frameworks that support these biotechnological advancements and recommends further research on process scalability, long-term stability, and life cycle assessments to ensure the environmental and economic viability of groundnut residue utilization in sustainable development.

Deep reinforcement learning-based approaches to mapless navigation have relied on the distance to the goal state being known a priori or that the distance to the goal can be obtained at each timestep. In artificial or simulated environments, obtaining the distance to the goal is considered a trivial task. Still, when applied to a real-world scenario, the distance must be obtained through complex localization techniques, and the use of localization techniques increases the complexity of the agent design. However, for agents navigating in unknown environments, using information about the goal to either form part of the state representation or act as the reward mechanism is usually expensive for both the robot design and for computing costs. This paper proposes using a pre-trained Siamese convolutional neural network (SCNN) to estimate the distance between an agent and its goal, thus enabling agents equipped with onboard cameras to navigate an unknown environment without needing localization sensors. This technique can be applied to environments where a goal location may be unknown, and the only information regarding the goal maybe a description of the goal state. Our experiments show that the Siamese network can learn the distance between the agent and its goal using relatively few training samples. Therefore, it is useful for mapless navigation using only visual state information and reduces the need for complex localization techniques.