Wheat is recognized as one of the most essential crops and a major food source worldwide. Ensuring an adequate balance of nutrient elements, such as Nitrogen (N), is crucial for healthy crop growth. The primary aim of this study is to classify nutrient deficiencies in leaf images. To achieve this, a genetic algorithm is applied to optimize the hyperparameters of a convolutional neural network for an image classification task. Convolutional neural networks have become increasingly prevalent in practical computer vision applications in recent years. The proposed convolutional network is trained with a wheat leaf images dataset. These images are categorized based on leaf color charts as 1, 2, 3, 4, 5, and 6 level. The primary goal is to enhance model accuracy by wisely searching through a predefined space of model architecture and training parameters. The initial accuracy of the model was 93.37% before applying the genetic algorithm for hyperparameter optimization. After optimization, the model achieved a final accuracy of 96.19%. The final model, trained using the best hyperparameters identified by the genetic algorithm, demonstrated improved performance on the validation set, indicating that hyperparameter optimization can significantly enhance CNN-based nutrient deficiency classification in wheat leaves. Earlier studies relied on a 4-strip LCC and achieved 94.22% accuracy, while the proposed method achieved a GA-optimized CNN with 6-strip LCC framework, improving accuracy to 96.19% and enabling finer nitrogen-level differentiation.

The objective of computer vision is extracting useful information by assessing snapshots. It can be used for radiography, industrial inspection, document processing, microscopy, robot navigation and remote sensing. Swarm intelligence is flattering a gradually applicable research topic for economists, computer geniuses, functional investigators and engineers. It is well-defined as the combined behaviour of isolated as well as self-organized groups. The distinguished models of swarm are communal insect colonies similar to ants, termites, bees, fish schools and bird flocks. The intellect of the swarm originates in the form of communication networks that happen amongst both elementary agents and the external environment. Computational models encouraged by natural swarm structures are identified as swarm intelligence models. This model consists of particle swarm optimization, cat swarm optimization, ant colony optimization, and artificial bee colony, glowworm swarm optimization and other algorithms. A natural swarm-based approach is being used to address complicated issues in a variety of fields, including engineering, medicine, and robotics. In this study, a review of computer vision approach using various nature inspired algorithms is discussed.

Crop yield prediction is one of the key factors that need to be considered for sustainable agriculture and food security due to climate change and increasing population. A reliable prediction model is required to determine how much yield will be produced since climate variability exacerbates global food scarcity. Existing methodologies do not account for sequential relationships and complex interactions existing in agricultural data. Moreover, another drawback with traditional methods is that their generalization is low, and hyperparameter optimization is limited, which results in inefficient models. Therefore, this study proposes a hybrid predictive method to overcome the mentioned problems. It includes 1D CNN and BiLSTM branches optimized with the Ant Colony Optimization (ACO) and Whale Optimization Algorithm (WOA), respectively. Both branches operate on the input time series simultaneously. What makes this research unique is the fact that previously there has been no research done where the CNN and BiLSTM branches have been optimized separately using different metaheuristic approaches in the agroclimatic yield prediction scenario. The CNN helps achieve effective feature extraction, whereas the BiLSTM models capture bidirectional temporal relations. The separately optimized features are aggregated to form the final predictions. Benchmarks for statistical accuracy are used to evaluate the performance of the proposed model compared to various baseline models, including the CNN–BiLSTM model with and without attention mechanisms and optimization algorithms. With RMSE = 132.1194, MAE = 104.3635, MAE ± SD of 104.3635 ± 81.0172, and R2 = 0.9678, the proposed attention-based metaheuristic CNN–BiLSTM model has produced satisfactory results. These findings show improved performance over baseline models and competitive results against existing hybrid and attention-based methods.

Real-time epileptic seizure detection from multichannel EEG signals remains a challenging clinical problem due to high inter-patient variability, severe class imbalance, and complex multi-scale ictal dynamics. Existing deep learning approaches predominantly rely on computationally intensive architectures such as Bidirectional GRU (BiGRU), increasing model complexity. This paper proposes SE-TCN-MGRU, a novel lightweight framework integrating three modules: a Squeeze-and-Excitation Network (SE-Net) for adaptive channel-wise recalibration; a Temporal Convolutional Network (TCN) with dilated causal convolutions for multi-scale temporal feature extraction; and an enhance Multilayer GRU (MGRU) with residual connections and Layer Normalization as a parameter-efficient, unidirectional replacement for BiGRU. A strict cross-patient LOOCV protocol with an independent validation strategy is applied on the CHB-MIT dataset to evaluate the proposed model. SE-TCN-MGRU achieves an accuracy 95.82%, sensitivity of 88.72%, specificity of 97.24%, F1-score of 87.83%, MCC of 86.17%,ROC-AUC of 0.9659 \(\pm\) 0.0659, and PR-AUC of 0.9314 \(\pm\) 0.1133. The proposed framework contains only 345,330 trainable parameters, corresponding to a 47.8% reduction compared with the reproduced SE-TCN-BiGRU baseline, while maintaining competitive seizure detection performance. These results demonstrate strong cross-patient generalization and computational efficiency, highlighting the potential of SE-TCN-MGRU for real-time wearable EEG-based seizure monitoring. This work supports United Nations Sustainable Development Goal 3 (SDG-3: Good Health and Well-being) by promoting accessible and automated monitoring of neurological disorders in epilepsy patients globally.