Swarm intelligence (SI) has emerged as a transformative approach in solving complex optimization problems by drawing inspiration from collective behaviors observed in nature, particularly among social animals and insects. Ant Colony Optimization (ACO), a prominent subclass of SI algorithms, models the foraging behavior of ant colonies to address a range of challenging combinatorial problems. Originally introduced in 1992 for the Traveling Salesman Problem (TSP), ACO employs artificial pheromone trails and heuristic information to probabilistically guide solution construction. The artificial ants within ACO algorithms engage in a stochastic search process, iteratively refining solutions through the deposition and evaporation of pheromone levels based on previous search experiences. This review synthesizes the extensive body of research that has since advanced ACO from its initial ant system (AS) model to sophisticated algorithmic variants. These advances have both significantly enhanced ACO's practical performance across various application domains and contributed to a deeper theoretical understanding of its mechanics. The focus of this study is placed on the behavioral foundations of ACO, as well as on the metaheuristic frameworks that enable its versatility and robustness in handling large-scale, computationally intensive tasks. Additionally, this study highlights current limitations and potential areas for future exploration within ACO, aiming to facilitate a comprehensive understanding of this dynamic field of swarm-based optimization.

Radar warning receivers (RWRs) are critical for swiftly and accurately identifying potential threats in complex electromagnetic environments. Numerous methods have been developed over the years, with recent advances in artificial intelligence (AI) significantly enhancing RWR capabilities. This study presents a machine learning-based approach for emitter identification within RWR systems, leveraging a comprehensive radar signal library. Key parameters such as signal frequency, pulse width, pulse repetition frequency (PRF), and beam width were extracted from pulsed radar signals and utilized in various machine learning algorithms. The preprogramming phase of RWRs was optimized through the application of multiple classification algorithms, including k-Nearest Neighbors (KNN), Decision Tree (DT), the ensemble learning method, support vector machine (SVM), and Artificial Neural Network (ANN). These algorithms were compared against conventional methods to evaluate their performance. The machine learning models demonstrated a high degree of accuracy, achieving over 95% in training phases and exceeding 99% in test simulations. The findings highlight the superiority of machine learning algorithms in terms of speed and precision when compared to traditional approaches. Furthermore, the flexibility of machine learning techniques to adapt to diverse problem sets underscores their potential as a preferred solution for future RWR applications. This study suggests that the integration of machine learning into RWR emitter identification not only enhances the operational efficiency of electronic warfare (EW) systems but also represents a significant advancement in the field. The increasing relevance of machine learning in recent years positions it as a promising tool for addressing complex signal processing challenges in EW.

Maintaining wheat moisture content within a safe range is of critical importance for ensuring the quality and safety of wheat. High-precision, rapid detection of wheat moisture content is a key factor in enabling effective control processes. A microwave detection system based on metasurface lens antennas was proposed in this study, which facilitates accurate, non-invasive, and contactless measurement of wheat moisture content. The system measures the attenuation characteristics of wheat with varying moisture content from 23.5 GHz to 24.5 GHz in the frequency range. A linear regression equation (coefficient of determination R²=0.9946) was established by using the measured actual moisture content obtained through the standard drying method, and was used as the prediction model for wheat moisture. Totally, 72 wheat samples were selected for moisture content prediction, yielding a root mean square error (RMSE) of 0.193%, mean absolute error (MAE) of 0.16%, and maximum relative error (MRE) of 5.25%. The results indicate that the proposed microwave detection system, based on metasurface lens antennas, provides an effective method for detecting wheat moisture content.

Leaf diseases pose a significant threat to global agricultural productivity, impacting both crop yields and quality. Traditional detection methods often rely on expert knowledge, are labor-intensive, and can be time-consuming. To address these limitations, a novel framework was developed for the segmentation and detection of leaf diseases, incorporating complex fuzzy set (CFS) theory and advanced spatial averaging and difference techniques. This approach leverages the Hue, Saturation, and Value (HSV) color model, which offers superior contrast and visual clarity, to effectively distinguish between healthy and diseased regions in leaf images. The HSV space was utilized due to its ability to enhance the visibility of subtle disease patterns. CFSs were introduced to manage the inherent uncertainty and imprecision associated with disease characteristics, enabling a more accurate delineation of affected areas. Spatial techniques further refine the segmentation, improving detection precision and robustness. Experimental validation on diverse datasets demonstrates the proposed method’s high accuracy across a variety of plant diseases, highlighting its reliability and adaptability to real-world agricultural conditions. Moreover, the framework enhances interpretability by offering insights into the progression of disease, thus supporting informed decision-making for crop protection and management. The proposed model shows considerable potential in practical agricultural applications, where it can assist farmers and agronomists in timely and accurate disease identification, ultimately improving crop management practices.

Accurately predicting whether bank users will opt for time deposit products is critical for optimizing marketing strategies and enhancing user engagement, ultimately improving a bank’s profitability. Traditional predictive models, such as linear regression and Logistic Regression (LR), are often limited in their ability to capture the complex, time-dependent patterns in user behavior. In this study, a hybrid approach that combines Long Short-Term Memory (LSTM) neural networks and a stacked ensemble learning framework is proposed to address these limitations. Initially, LSTM models were employed to extract temporal features from two distinct bank marketing datasets, thereby capturing the sequential nature of user interactions. These extracted features were subsequently input into several base classifiers, including Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbour (KNN), to conduct initial classifications. The outputs of these classifiers were then integrated using a LR model for final decision-making through a stacking ensemble method. The experimental evaluation demonstrates that the proposed LSTM-stacked model outperforms traditional models in predicting user time deposits on both datasets, providing robust predictive performance. The results suggest that leveraging temporal feature extraction with LSTM and combining it with ensemble techniques yields superior prediction accuracy, thereby offering a more sophisticated solution for banks aiming to enhance their marketing efficiency.

Rice is a staple food for a significant portion of the global population, particularly in countries where it constitutes the primary source of sustenance. Accurate classification of rice varieties is critical for enhancing both agricultural yield and economic outcomes. Traditional classification methods are often inefficient, leading to increased costs, higher misclassification rates, and time loss. To address these limitations, automated classification systems employing machine learning (ML) algorithms have gained attention. However, when raw data is inadequately organized or scattered, classification accuracy can decline. To improve data organization, normalization processes are often employed. Despite its widespread use, the specific contribution of normalization to classification performance requires further validation. In this study, a dataset comprising two rice varieties Osmancik and Cammeo produced in Turkey was utilized to evaluate the impact of normalization on classification outcomes. The k-Nearest Neighbor (KNN) algorithm was applied to both normalized and non-normalized datasets, and their respective performances were compared across various training and testing ratios. The normalized dataset achieved a classification accuracy of 0.950, compared to 0.921 for the non-normalized dataset. This approximately 3% improvement demonstrates the positive effect of data normalization on classification accuracy. These findings underscore the importance of incorporating normalization in ML models for rice classification to optimize performance and accuracy.

In the realm of urban public affairs management, the necessity for accurate and intelligent distribution of resources has become increasingly imperative for effective social governance. This study, drawing on crime data from Chicago in 2022, introduces a novel approach to public affairs distribution by employing Long Short-Term Memory (LSTM), Multilayer Perceptron (MLP), and their integration. By extensively preprocessing textual, numerical, boolean, temporal, and geographical data, the proposed models were engineered to discern complex interrelations among multidimensional features, thereby enhancing their capability to classify and predict public affairs events. Comparative analysis reveals that the hybrid LSTM-MLP model exhibits superior prediction accuracy over the individual LSTM or MLP models, evidencing enhanced proficiency in capturing intricate event patterns and trends. The effectiveness of the model was further corroborated through a detailed examination of training and validation accuracies, loss trajectories, and confusion matrices. This study contributes a robust methodology to the field of intelligent public affairs prediction and resource allocation, demonstrating significant practical applicability and potential for widespread implementation.

Sentiment analysis, a crucial component of natural language processing (NLP), involves the classification of subjective information by extracting emotional content from textual data. This technique plays a significant role in the movie industry by analyzing public opinions about films. The present research addresses a gap in the literature by conducting a comparative analysis of various machine learning algorithms for sentiment analysis in film reviews, utilizing a dataset from Kaggle comprising 50,000 reviews. Classifiers such as Logistic Regression, Multinomial Naive Bayes, Linear Support Vector Classification (LinearSVC), and Gradient Boosting were employed to categorize the reviews into positive and negative sentiments. The emphasis was placed on specifying and comparing these classifiers in the context of film review sentiment analysis, highlighting their respective advantages and disadvantages. The dataset underwent thorough preprocessing, including data cleaning and the application of stemming techniques to enhance processing efficiency. The performance of the classifiers was rigorously evaluated using metrics such as accuracy, precision, recall, and F1-score. Among the classifiers, LinearSVC demonstrated the highest accuracy at 90.98%. This comprehensive evaluation not only identified the most effective classifier but also elucidated the contextual efficiencies of various algorithms. The findings indicate that LinearSVC excels at accurately classifying sentiments in film reviews, thereby offering new insights into public opinions on films. Furthermore, the extended comparison provides a step-by-step guide for selecting the most suitable classifier based on dataset characteristics and context, contributing valuable knowledge to the existing literature on the impact of different machine learning approaches on sentiment analysis outcomes in the movie industry.

Advancements in information technology have significantly enhanced productivity and efficiency through the adoption of cloud computing, yet this adoption has also introduced a spectrum of security threats. Effective cybersecurity mitigation strategies are imperative to minimize the impact on cloud infrastructure and ensure reliability. This study seeks to categorize and assess the risk levels of cybersecurity threats in cloud computing environments, providing a comprehensive characterization based on eleven major causes, including natural disasters, loss of encryption keys, unauthorized login access, and others. Using fuzzy set theory to analyze uncertainties and model threats, threats were identified, prioritized, and categorized according to their impact on cloud infrastructure. A high level of data loss was revealed in five key features, such as encryption key compromise and unauthorized login access, while a lower impact was observed in unknown cloud storage and exposure to sensitive data. Seven threat features, including encryption key loss and operating system failure, were found to significantly contribute to data breaches. In contrast, others like virtual machine sharing and impersonation, exhibited lower risk levels. A comparative analysis of threat mitigation techniques determined Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service and Elevation of Privilege (STRIDE) as the most effective methodology with a score of 59, followed by Quality Threat Modeling Methodology (QTMM) (57), Common Vulnerability Scoring System (CVSS) (51), Process for Attack Simulation and Threat Analysis (PASTA) (50), and Persona non-Grata (PnG) (47). Attack Tree and Hierarchical Threat Modeling Methodology (HTMM) each achieved 46, while Linkability, Identifiablility, Nonrepudiation, Detectability, Disclosure of Information, Unawareness and Noncompliance (LINDDUN) scored 45. These findings underscore the value of fuzzy set theory in tandem with threat modeling to categorize and assess cybersecurity risks in cloud computing. STRIDE is recommended as an effective modeling technique for cloud environments. This comprehensive analysis provides critical insights for organizations and security experts, empowering them to proactively address recurring threats and minimize disruptions to daily operations.

Dental implants (DIs) are prone to failure due to uncommon mechanical complications and fractures. Precise identification of implant fixture systems from periapical radiographs is imperative for accurate diagnosis and treatment, particularly in the absence of comprehensive medical records. Existing methods predominantly leverage spatial features derived from implant images using convolutional neural networks (CNNs). However, texture images exhibit distinctive patterns detectable as strong energy at specific frequencies in the frequency domain, a characteristic that motivates this study to employ frequency-domain analysis through a novel multi-branch spectral channel attention network (MBSCAN). High-frequency data obtained via a two-dimensional (2D) discrete cosine transform (DCT) are exploited to retain phase information and broaden the application of frequency-domain attention mechanisms. Fine-tuning of the multi-branch spectral channel attention (MBSCA) parameters is achieved through the modified aquila optimizer (MAO) algorithm, optimizing classification accuracy. Furthermore, pre-trained CNN architectures such as Visual Geometry Group (VGG) 16 and VGG19 are harnessed to extract features for classifying intact and fractured DIs from panoramic and periapical radiographs. The dataset comprises 251 radiographic images of intact DIs and 194 images of fractured DIs, meticulously selected from a pool of 21,398 DIs examined across two dental facilities. The proposed model has exhibited robust accuracy in detecting and classifying fractured DIs, particularly when relying exclusively on periapical images. The MBSCA-MAO scheme has demonstrated exceptional performance, achieving a classification accuracy of 95.7% with precision, recall, and F1-score values of 95.2%, 94.3%, and 95.6%, respectively. Comparative analysis indicates that the proposed model significantly surpasses existing methods, showcasing its superior efficacy in DI classification.

Named Entity Recognition (NER), a pivotal task in information extraction, is aimed at identifying named entities of various types within text. Traditional NER methods, however, often fall short in providing sufficient semantic representation of text and preserving word order information. Addressing these challenges, a novel approach is proposed, leveraging dual Graph Neural Networks (GNNs) based on multi-feature fusion. This approach constructs a co-occurrence graph and a dependency syntax graph from text sequences, capturing textual features from a dual-graph perspective to overcome the oversight of word interdependencies. Furthermore, Bidirectional Long Short-Term Memory Networks (BiLSTMs) are utilized to encode text, addressing the issues of neglecting word order features and the difficulty in capturing contextual semantic information. Additionally, to enable the model to learn features across different subspaces and the varying degrees of information significance, a multi-head self-attention mechanism is introduced for calculating internal dependency weights within feature vectors. The proposed model achieves F1-scores of 84.85% and 96.34% on the CCKS-2019 and Resume datasets, respectively, marking improvements of 1.13 and 0.67 percentage points over baseline models. The results affirm the effectiveness of the presented method in enhancing performance on the NER task.