Journal of Artificial Intelligence and Metaheuristics

Communication network design (CND) and wireless sensor networks (WSNs) present significant challenges, particularly in optimizing network reliability, energy efficiency, and cost-effectiveness. This literature review discusses the use of metaheuristic algorithms to solve these NP-hard problems and provide accurate results for network reliability, resource-management assignment, and energy utilization in data transmission networks. Recent advancements in hybrid metaheuristic approaches, such as combining Genetic Algorithms with Branch and Bound (GA–BB) or Particle Swarm Optimization with Simulated Annealing (PSO–SA), demonstrate their effectiveness in optimizing network performance in emerging domains such as vehicular ad-hoc networks (VANETs) and Internet of Things (IoT)-enabled WSNs. The review also discusses applications to issues such as cluster-head selection in WSNs, routing protocols in dynamic networks, and supply-chain network design. These developments are essential in evolving technologies such as 6G networks and the Internet of Everything (IoE), where complex systems demand innovative optimization strategies. By highlighting these concerns, this review calls for increased use of metaheuristic techniques to further the application of future networks in smart cities, healthcare, and secure network architectures.

A significant barrier to sustaining and achieving successful quality evaluation of apples has been the biases and inefficiencies of manual inspection, which cannot be effectively applied to large-scale industrial processing. This paper fills this gap by building an automated machine learning system for apple quality classification, which combines physical (size, weight, firmness) and sensory (sweetness, acidity, juiciness) features. Four baseline models, including K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree, and Gradient Boosting, were trained on a preprocessed dataset. Imputation, categorical encoding, and feature scaling were used. To enhance predictive accuracy, hyperparameter tuning of three metaheuristic optimization algorithms—Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Greylag Goose Optimization (GGO)—was employed. The findings indicated that KNN had the highest baseline accuracy of 93.6% and that its accuracy improved to 98.6% with GGO optimization, which was better than that of GA and PSO. These results indicate that GGO-optimized KNN can provide a high-quality and scalable approach to assessing the quality of apples in the industry, offering enhanced accuracy, reduced variability, and a high degree of practical applicability in supply chain decision-making, thereby increasing customer satisfaction and decreasing losses after harvesting.

The incidence of lung cancer varies in males and females, which occurs due to the abnormal and uncontrolled growth of cells in the lungs. It has a greater predilection in males as compared to females. Smoking is the most important risk factor for lung cancer. It causes serious breathing issues and also affects other organs. It increases the mortality rate both in young adults as well as in the older age group. Therefore, there is improvement in medical technologies to facilitate specialized diagnosis and treatment, but the mortality has not been controlled to a satisfactory extent. It is important to take preventive measures and precautions at the initial stages. Machine learning brings various advancements to the medical sector due to which various diseases can be detected at an early stage. In this paper, we presented different machine learning classifier techniques used for the classification of the present lung cancer data in the UCI machine learning repository as benign and malignant. The dataset is divided into cancerous and non-cancerous by converting the input data into binary form and using the classifier technique in the Weka tool. This specifically includes classifiers used: Logistic Regression, Random Forest, Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Decision Trees, and Naïve Bayes. In addition, we study the effect of data preprocessing methods on our prediction accuracy, such as data normalization and feature selection. The study seeks to help develop various reliable resources for lung cancer identification, which are critical for diagnosing and treating patients in a timely manner and improving their outcomes.

The study considers the community of “urban air quality improvement in modern cities” using an extensive dataset obtained from “Air quality data of Delhi, India” for the period between 25 November 2020 and 24 January 2023. Research aims to significantly reduce air pollutants, including particulate matter, including PM2.5 and PM10, NO2, SO2, CO2, O3, and others. Different machine learning models are being used for air quality level forecasts. Among the models assessed, the Nearest Neighbors algorithm comes out on top and exhibits a very low Mean Squared Error (MSE) of 0.0002. The model’s superb precision is further supported by very low statistics in other key metrics, which confirm the Nearest Neighbors approach to forecasting the quality of air in urban zones. The Nearest Neighbors algorithm is shown to have its place in the application as a tool in the hands of researchers and decision-makers pursuing the fight against air pollution is also a signal of its efficiency and broad applicability. This modeling approach has thus the potential to first identify and later pinpoint localized empirical patterns and statistical dependencies from the data set. Its high predictive precision makes it a very valuable assistant to public health and environmental management, especially so in regions like Delhi.

The utilization of artificial intelligence (AI) algorithms has significantly transformed the field of blood disease diagnosis, enabling enhanced capabilities in prediction, categorization, and optimization. However, there is still a lack of research exploring hybrid machine learning models that combine qualitative and quantitative datasets to address issues associated with blood diseases. We evaluate algorithmic combinations using datasets that include key characteristics from complete blood count (CBC) examinations. Prominent deep learning models, including CNN, RNN, and RCNN, are assessed. XGBoost is identified as the strongest machine learning algorithm and RCNN as the strongest deep learning model. We therefore propose RCNNX, a hybrid model integrating Robust Scaler, SelectKBest feature selection, RCNN, and XGBoost. RCNNX achieves testing accuracies of 100% and 95.12% on the Anemia Diagnosis Dataset and a second dataset, respectively, with recall rates of 100% and 94.64%. These findings indicate that feature selection reduces the number of input variables and the risk of overfitting, while XGBoost improves the predictive accuracy of RCNN.

The lack of water is one of the most crucial problems of our day; therefore, optimized water resource management and predictions gathered by patrons are of utmost importance. In the turmoil of a country like India, which lives a variety of lifestyles and has a complicated network of rivers, the urgent need for an active point of view to take care of water shortages becomes exceptionally vital. In this study, India’s groundwater, available at the district level for the year 2017, was the area of focus, with this analysis utilizing a dataset of 689 rows, each representing a district, and 16 columns describing the various groundwater extraction and recharge metrics. The study involves five regression models adapting RandomForestRegressor, DecisionTreeRegressor, MLPRegressor, KNeighborsRegressor, and SupportVectorRegression for water resource evaluation and prediction. Every model is appraised by using a thorough metrics set where we incorporate Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Explained Variance Score (EVS), Max Error, Median Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), R-squared (R2), among others. Our results put the spotlight on RandomForestRegressor, making MSE measures the same as 0.000206624, endorsing its better performance versus the criteria considered. The approach used in this model provides us with an ensemble effect that makes it more robust in the sense that we can capture the interrelationships within the dataset in a comprehensive way. DecisionTreeRegressor also provides nice options for precision and transparency. The use of such models depicts the potential value of predictive analytics, which has the role of improving resource management and planning because we can all agree that the impending water crisis is also a fact. These research outcomes provide us with important data for well-informed decision-making and strategic management of water reserves through all avenues and most affected areas to air most of the impact of water scarcity.

COVID-19, one of the most highly transmissible diseases in the twenty-first century, has had a profound impact on global lifestyles. Recently, the medical industry has increasingly relied on machine learning, which shows promise in anticipating the presence of COVID-19. By using machine learning techniques, test result turnaround time can be accelerated, and medical personnel can promptly attend to patients’ needs. These algorithms analyze various attributes to classify COVID patients and predict their likelihood of contracting the disease. This study aims to utilize X-ray images processed by machine learning algorithms to predict the occurrence of COVID-19 and enhance its detection rate. The paper outlines two strategies employing machine learning techniques: one for predicting the likelihood of infection and the other for identifying positive cases. Different machine learning algorithms, such as decision trees, logistic regression, support vector machines, naive Bayes, and artificial neural networks, were employed. The simulation results reveal that the artificial neural networks model outperforms other methods in terms of accuracy rate.