Journal of Artificial Intelligence and Metaheuristics

The growing complexity of engineering optimization problems has revealed significant limitations in traditional mathematical programming approaches, necessitating the development of innovative metaheuristic algorithms capable of handling high-dimensional, multi-modal, and discontinuous objective functions. This paper presents the Somersaulting Spider Optimizer (SSO), a novel bio-inspired metaheuristic algorithm that draws inspiration from the extraordinary locomotion mechanisms of Somersaulting Spider, a desert-dwelling arachnid species renowned for its acrobatic somersaulting capabilities. The proposed algorithm incorporates dual movement mechanisms that effectively balance global exploration through somersaulting behavior and local exploitation via controlled rolling movements. A distinctive feature of SSO lies in its adaptive energy management system, which dynamically regulates exploration-exploitation transitions based on solution improvement patterns and stagnation detection. The algorithm employs complementary adaptive parameters that ensure perfect balance between global search and local refinement throughout the optimization process. Comprehensive experimental evaluation was conducted on four challenging benchmark engineering design problems: pressure vessel design, welded beam optimization, three-bar truss design, and cantilever beam optimization. A comparison with known metaheuristic algorithms, such as the Genetic Algorithm, Whale Optimization Algorithm, Harris Hawks Optimization, and Bat Algorithm, shows that SSO outperforms all of them on the test problems. ANOVA and Wilcoxon signed-rank tests statistically validate the significance of performance improvement, and SSO has the lowest optimization cost without compromising the high-performance consistency. The results confirm that SSO is an effective and powerful optimization method for complex engineering design problems, and that the method shows significant improvements in solution quality, convergence stability, and computational efficiency.

The importance of network security has greatly been enhanced in the modern digital environment that continuously changes. Network security, on the other hand, is a multi-layered defense mechanism that seeks to protect networks, data, and systems from malpractices such as unauthorized access breaches or activities. Cyber threats become ever more advanced, and traditional protective measures can no longer prove to be adequate. Given the necessity of such a threat to adapt and be intelligent, an active intrusion detection system must necessarily rapidly evolve its methods in response. The central element contained in this research is the proposal of a novel algorithm, BBERSC (Balance Between Al Biruni Earth Radius Optimization and Sine Cosine Algorithm). This algorithm is carefully crafted to achieve a compromise between the means for local search provided by Al-Biruni Earth Radius Optimization and probabilistic improvement, which are characteristic of the Swine Cosine Algorithm. BBERSC brings forward the cause of harmonizing these two optimization methods to revolutionize model accuracy and credibility, which may be achieved for network security’s distinctiveness. One of the crucial elements of this study lies in the fact that hyperparameter tuning is quite a detailed process, especially for Random Forest. Parameters, including the number of trees, maximum depth, and minimum samples, are systematically employed to vary to augment pattern recognition capability by employing model processing network traffic. To ensure the validation of the effectiveness of the proposed models and algorithms, statistical analysis is carried out through ANOVA test & Wilcoxon Signed Rank Test. These tests show the models’ results through rigorous assessments and emphasize differences between them. As the conclusion of this study, It is displayed that the Random Forest model utilized inside BBERSC algorithmic framework facilitates operational accuracy level 0.9901719, which is incomparable among all other machine learning algorithms.

A brain stroke represents a deadly health condition that emerges from poor blood flow to the brain. Brain tissue affected by a stroke will completely cease regular operations. Immediate detection of a brain stroke leads to better treatment success. Images from computed tomography (CT) provide a quick diagnosis of stroke. But time is passing quickly as the physicians examine each brain CT scan. This situation could cause therapy to be delayed and mistakes to be made. Thus, we focused on using a practical artificial intelligence algorithm for stroke detection. This paper proposes several deep neural network models, such as DenseNet121, ResNet50, Xception, and EfficientNetV2S, for transfer learning to study the features of stroke lesions and achieve complete intelligent automatic detection by classifying CT images into two categories (stroke and normal). The dataset comprises 437 testing, 235 validation, and 1843 training photos. Using the same dataset, the experimental findings outperform all state-of-the-art. The optimal model utilizing the EfficientNetV2S model for transfer learning has an overall accuracy of 99.57% and the same value for precision and recall.

This study presents a comprehensive evaluation of metaheuristic-optimized machine learning models for automated apple quality classification, addressing the critical need for accurate and consistent fruit grading systems in agricultural applications. The research integrates four bio-inspired optimization algorithms—Whale Optimization Algorithm (WOA), Salp Swarm Algorithm (SSA), Cuckoo Search (CS), and Bat Algorithm (BAT)—with Multi-Layer Perceptron (MLP) classifiers to enhance fruit quality assessment performance. Experimental validation was conducted using a comprehensive apple quality dataset containing seven key attributes: size, weight, sweetness, crunchiness, juiciness, ripeness, and acidity. The results demonstrate that WOA-MLPClassifier achieves superior performance with 95.37% accuracy, 95.99% sensitivity, and balanced effectiveness across all evaluation metrics including specificity, positive predictive value, negative predictive value, and F1 Score. Statistical validation through one-way ANOVA and Wilcoxon signed-rank tests confirms significant performance improvements over baseline models and alternative optimization approaches, with p-values less than 0.001. The proposed framework exhibits remarkable consistency across multiple evaluation runs, with perfect positive rank sums indicating reliable optimization behavior. These findings establish a new benchmark for automated fruit quality classification systems and provide valuable insights for deploying bio-inspired optimization techniques in agricultural machine learning applications where both accuracy and reliability are essential for commercial viability.

Retinal diseases lead to the loss of vision and are a significant burden to health, and a timely and accurate diagnosis should be conducted to maximize treatment and clinical outcome. The research has been applied in the holistic examination of various eye health diseases such as cataracts, glaucoma and retinary aberrations which are separated into normal eye related cases and artificial networks. Using a large set of retinal images, the study conducts a thorough quantitative analysis of both complicated models like CNN, K-NN, and SVM in the form of parameters of accuracy, sensitivity, specificity, and F-Score. The CNN model had a better performance with a fantastic overall accuracy 94.05% and good sensitivity in classifying pathological states. It can be proven by the comparative analysis that CNN architecture is an effectual diagnostic instrument in the sphere of ophthalmology and demonstrates tremendous prospects in the replication of ophthalmology screening screening with the help of ophthalmology automation. This timely and vast assessment of the machine learning methods contributes a lot to the literature not only in terms of establishing relative lines between different technological solutions but also in helping style the advanced technological solutions to carry out screening to help the ophthalmologist make reliable diagnostic prescriptions.