Individual Classifiers Research Articles

Crop Recommendation System Using Machine Learning: A Comparative Study

Agriculture, as a fundamental aspect of human existence, faces challenges in crop selection, impacting resource allocation and productivity. This project addresses these challenges by proposing a stable system employing a soft voting classifier ensemble method. The ensemble comprises Naive Bayes, Support Vector Machine (SVM), Decision Tree, and Random Forest classifiers, offering personalized crop recommendations. Feasibility analysis encompasses technical, operational, economic, and scheduling aspects, ensuring practicality and efficacy. Development follows an incremental model, emphasizing continuous enhancement through feedback. Results indicate accuracies for individual classifiers (’Decision Tree’: 98.38%, ’Random Forest’: 98.90%, ’Naive Bayes’: 98.14%, ’SVM’: 98.50%), with an ensemble accuracy of 98.99%. Cross-validation confirms robustness. Evaluation metrics such as recall, precision, and F1 score demonstrate that the soft voting ensemble outperforms individual classifiers, highlighting its effectiveness in optimizing crop selection processes in agriculture and facilitating improved resource management and productivity.

A Novel Dataset and Approach for Adversarial Attack Detection in Connected and Automated Vehicles

Adversarial attacks have received much attention as communication network applications rise in popularity. Connected and Automated Vehicles (CAVs) must be protected against adversarial attacks to ensure passenger and vehicle safety on the road. Nevertheless, CAVs are susceptible to several types of attacks, such as those that target intra- and inter-vehicle networks. These harmful attacks not only cause user privacy and confidentiality to be lost, but they also have more grave repercussions, such as physical harm and death. It is critical to precisely and quickly identify adversarial attacks to protect CAVs. This research proposes (1) a new dataset comprising three adversarial attacks in the CAV network traffic and normal traffic, (2) a two-phased adversarial attack detection technique named TAAD-CAV, where in the first phase, an ensemble voting classifier having three machine learning classifiers and one separate deep learning classifier is trained, and the output is used in the next phase. In the second phase, a meta classifier (i.e., Decision Tree is used as a meta classifier) is trained on the combined predictions from the previous phase to detect adversarial attacks. We preprocess the dataset by cleaning data, removing missing values, and adjusting the Z-score normalization. Evaluation metrics such as accuracy, recall, precision, F1-score, and confusion matrix are employed to evaluate and compare the performance of the proposed model. Results reveal that TAAD-CAV achieves the highest accuracy with a value of 70% compared with individual ML and DL classifiers.

Contact sex offenders with adult and minor victims: Psychopathological and criminological differences

BackgroundEffective classification of individuals who commit sexual offences is important for their assessment, treatment, and risk management. Victim age has often been used as a distinguishing factor between perpetrators. ObjectiveThis study aimed to analyse the distinctive psychopathological and criminological characteristics of contact sexual offenders with adult and minor victims. Participants and settingThe study involved 97 adult males who were serving a prison sentence in Spain for at least one contact sexual offence against an adult or a minor. MethodsResearchers gathered data on criminological variables concerning the offender, victim, and modus operandi from prison records and interviews. Participants completed the Millon Clinical Multiaxial Inventory-III (MCMI-III) in a second session, and between-group differences were analysed. ResultsSex offenders with minor victims (SOMV) had significantly lower scores than sex offenders with adult victims (SOAV) on the Antisocial (r = −0.283, p = .005) and Sadistic (r = −0.209, p = .04) personality subscales, and on the Alcohol (r = −0.426, p < .001) and Drug dependence (r = −0.332, p = .001) syndrome subscales. SOAV were also more likely to use violence and/or intimidation, use a weapon, offend against female victims, offend against an intimate partner, commit their offences in public places, serve other ongoing prison sentences, and report a history of alcohol and substance abuse. SOMV were older and more likely to offend against family members. ConclusionsThese results suggest that there are key differences between SOAV and SOMV that should be considered in tailored prevention programmes for each subgroup of offenders.

Predictive breast cancer diagnosis using ensemble fuzzy model

Breast cancer continues to be a major global health challenge, necessitating reliable diagnostic methods for early detection and improved patient outcomes. This study introduces a novel ensemble fuzzy model for predictive breast cancer diagnosis, integrating multiple deep-learning classifiers with fuzzy logic to enhance decision-making. Traditional diagnostic approaches often struggle with the complexity and heterogeneity of breast cancer data, which this new model addresses through an innovative ensemble technique. The ensemble model combines the strengths of Inception-V4, Inception-ResNet, and Inception V3/V4 + BN, with fuzzy logic for adaptive priority assignment based on confidence scores. The method employs a re-parameterized Gompertz function to assign fuzzy ranks to constituent classifiers, allowing flexible fusion strategies. The proposed model is evaluated on two benchmark breast cancer datasets: the Digital Database for Screening Mammography (DDSM) and the Breast Cancer Histopathological Image Classification (BACH) dataset. It achieves high performance across key metrics, including accuracy, precision, recall, and F1 score, consistently outperforming individual classifiers. On the DDSM dataset, the ensemble fuzzy model attains an accuracy of 0.97, a recall of 0.93, a precision of 0.95, and an F1 score of 0.96. Similarly, on the BACH dataset, the proposed method records an accuracy of 97.05%, a recall of 99.31%, a precision of 95.44%, and an F1 score of 97.37%, demonstrating its robust capability to identify positive instances and maintain a balanced performance. These results highlight the potential of the ensemble fuzzy model to improve breast cancer diagnosis, offering a reliable solution to the inherent challenges in this field.

A practical classification scale for the dermatology management of individuals with skin of color: the colorimetric scale for skin of color.

A simple and rapid method that is not based on race and ethnicity for classifying people with skin of color is of paramount importance in dermatology. The currently used Fitzpatrick classification of sun-reactive skin types is inadequate. Newer scales that have been used in immigration surveys and sociology studies are not applicable in the office setting. A new, non-racial and non-ethnic, colorimetric scale for skin of color has recently been proposed that is simple to perform. The scale has five colors: very light beige (skin color type 1), light brown (skin color type 2), medium brown (skin color type 3), dark brown (skin color type 4) and very dark brown (skin color type 5); an individual with white skin, such as in albinism, would have a skin color type 0 in this classification. In conclusion, the colorimetric scale enables the rapid classification of individuals with skin of color and allows for accurate assessment of skin cancer risk, more appropriate management of cosmetic dermatologic procedures and aesthetic devices, and enhanced ability for focused counseling regarding hair products, skin care interventions, and color-targeted makeup based on the person's skin tone.

A novel ensemble artificial intelligence approach for coronary artery disease prediction

PurposeCoronary artery disease is one of the most common cardiovascular disorders in the world, and it can be deadly. Traditional diagnostic approaches are based on angiography, which is an interventional procedure having side effects such as contrast nephropathy or radio exposure as well as significant expenses. The purpose of this paper is to propose a novel artificial intelligence (AI) approach for the diagnosis of coronary artery disease as an effective alternative to traditional diagnostic methods.Design/methodology/approachIn this study, a novel ensemble AI approach based on optimization and classification is proposed. The proposed ensemble structure consists of three stages: feature selection, classification and combining. In the first stage, important features for each classification method are identified using the binary particle swarm optimization algorithm (BPSO). In the second stage, individual classification methods are used. In the final stage, the prediction results obtained from the individual methods are combined in an optimized way using the particle swarm optimization (PSO) algorithm to achieve better predictions.FindingsThe proposed method has been tested using an up-to-date real dataset collected at Basaksehir Çam and Sakura City Hospital. The data of disease prediction are unbalanced. Hence, the proposed ensemble approach improves majorly the F-measure and ROC area which are more prominent measures in case of unbalanced classification. The comparison shows that the proposed approach improves the F-measure and ROC area results of the individual classification methods around 14.5% in average and diagnoses with an accuracy rate of 96%.Originality/valueThis study presents a low-cost and low-risk AI-based approach for diagnosing heart disease compared to traditional diagnostic methods. Most of the existing research studies focus on base classification methods. In this study, we mainly investigate an effective ensemble method that uses optimization approaches for feature selection and combining stages for the medical diagnostic domain. Furthermore, the approaches in the literature are commonly tested on open-access dataset in heart disease diagnoses, whereas we apply our approach on a real and up-to-date dataset.

IoT Enabled Mushroom Farm Automation with Machine Learning

Mushroom farming has gained prominence due to its significant contribution to the global market. One major challenge for mushroom cultivation is maintaining optimal environmental conditions, specifically temperature and humidity. Traditional farming methods, prevalent in many parts of the world, lack precise control over these parameters, often leading to poor yield. This paper presents an innovative approach combining the Internet of Things (IoT) and Machine Learning (ML) for mushroom farm automation. The proposed system employs the ESP8266 microcontroller with specific agricultural sensors for smart monitoring. To regulate the farm's environmental conditions, ML algorithms predict mushroom farm weather states: mild, normal, and hot. The ensemble ML model, comprising five classifiers – Decision Tree, Logistic Regression, K-nearest neighbor, Support Vector Machine, and Random Forest – delivers a commendable accuracy of 100% when combining predictions, surpassing the performance of individual classifiers. This integrated IoT and ML approach promises to revolutionize real-time automation and cultivation practices in the mushroom industry.

Cross-project software defect prediction through multiple learning

Cross-project defect prediction is a method that predicts defects in one software project by using the historical record of another software project. Due to distribution differences and the weak classifier used to build the prediction model, this method has poor prediction performance. Cross-project defect prediction may perform better if distribution differences are reduced, and an appropriate individual classifier is chosen. However, the prediction performance of individual classifiers may be affected in some way by their weaknesses. As a result, in order to boost the accuracy of cross-project defect prediction predictions, this study proposed a strategy that makes use of multiple classifiers and selects attributes that are similar to one another. The proposed method's efficacy was tested using the Relink and AEEEM datasets in an experiment. The findings of the experiments demonstrated that the proposed method produces superior outcomes. To further validate the method, we employed the Wilcoxon sum rank test at 95% significance level. The approach was found to perform significantly better than the baseline methods.

Alterations in dynamic regional homogeneity within default mode network in patients with thyroid-associated ophthalmopathy.

Thyroid-associated ophthalmopathy (TAO) is a significant autoimmune eye disease known for causing exophthalmos and substantial optic nerve damage. Prior investigations have solely focused on static functional MRI (fMRI) scans of the brain in TAO patients, neglecting the assessment of temporal variations in local brain activity. This study aimed to characterize alterations in dynamic regional homogeneity (dReHo) in TAO patients and differentiate between TAO patients and healthy controls using support vector machine (SVM) classification. Thirty-two patients with TAO and 32 healthy controls underwent resting-state fMRI scans. We calculated dReHo using sliding-window methods to evaluate changes in regional brain activity and compared these findings between the two groups. Subsequently, we employed SVM, a machine learning algorithm, to investigate the potential use of dReHo maps as diagnostic markers for TAO. Compared to healthy controls, individuals with active TAO demonstrated significantly higher dReHo values in the right angular gyrus, left precuneus, right inferior parietal as well as the left superior parietal gyrus. The SVM model demonstrated an accuracy ranging from 65.62 to 68.75% in distinguishing between TAO patients and healthy controls based on dReHo variability in these identified brain regions, with an area under the curve of 0.70 to 0.76. TAO patients showed increased dReHo in default mode network-related brain regions. The accuracy of classifying TAO patients and healthy controls based on dReHo was notably high. These results offer new insights for investigating the pathogenesis and clinical diagnostic classification of individuals with TAO.

질적 메타분석을 통해 살펴본 교사-부모 관계에 관한 영유아교사의 경험

Objectives This study aims to identify factors that influence the formation of teacher-parent relationships as early childhood educators experience interactions with parents, and to explore how these variables affect changes in early childhood educators. Methods To achieve this, a qualitative meta-analysis was conducted on qualitative research materials regarding early childhood teacher-parent relationship experiences. The analysis included 18 qualitative research papers published in domestic journals (KCI listed) from 2000 to 2023. Through processes of data coding between in-dividual studies, case categorization and classification across studies, comparative analysis between studies, and deriving and interpreting results, the changes in teachers during the early childhood teacher-parent relationship process were identified. Results First, the factors of negative experience in the teacher-parent relationship were parental disposition, ex-cessive demands of parents, imbalance in the relationship, teachers' own factors, problems in the teacher training process, and emotional dissonance. Second, the teacher-parent relationship was shown to be a change stage in three stages: teacher-parent relationship experience, coping, and growth into a professional early childhood teacher. Conclusions This study attempted to clarify in depth by comprehensively comparing and interpreting individual qualitative studies on the experience of teacher-parent relationships. We identified relevant factors linked to the teacher-parent relationship and derived comprehensive results.

Secure Your Network: Building a Hybrid Intrusion Detection System in Java

Abstract: To protect the system from different types of intrusions, an intrusion detection system ID is required. It is essential to analyse the communication in order to classify the material as malicious or helpful. The usage of intrusion detection systems for cyber security shouldn't add to the processing time required for classification. These days, classification algorithms are utilized in conjunction with machine learning approaches to identify harmful data or intrusions. KDD cup 99 is the data set that was used in the experiment. Hybrid classification models can be used to adjust the performance of individual classification methods. This model blends rule-based algorithms with categorization techniques. An additional degree of security is provided by the combination of machine and human intelligence in classification. Precision, recall, F-Measure, and Mean Age Precision are used to validate an algorithm. The algorithm has a 92.35 percent accuracy rate. Even after merging our human-written criteria with traditional machine learning classification techniques, the model's accuracy is still considered satisfactory. However, there is still room for improvement and a more specific classification of the attack

Plasmonic nano-aperture label-free imaging of single small extracellular vesicles for cancer detection

BackgroundSmall extracellular vesicle (sEV) analysis can potentially improve cancer detection and diagnostics. However, this potential has been constrained by insufficient sensitivity, dynamic range, and the need for complex labeling.MethodsIn this study, we demonstrate the combination of PANORAMA and fluorescence imaging for single sEV analysis. The co-acquisition of PANORAMA and fluorescence images enables label-free visualization, enumeration, size determination, and enables detection of cargo microRNAs (miRs).ResultsAn increased sEV count is observed in human plasma samples from patients with cancer, regardless of cancer type. The cargo miR-21 provides molecular specificity within the same sEV population at the single unit level, which pinpoints the sEVs subset of cancer origin. Using cancer cells-implanted animals, cancer-specific sEVs from 20 µl of plasma can be detected before tumors were palpable. The level plateaus between 5–15 absolute sEV count (ASC) per µl with tumors ≥8 mm3. In healthy human individuals (N = 106), the levels are on average 1.5 ASC/µl (+/− 0.95) without miR-21 expression. However, for stage I–III cancer patients (N = 205), nearly all (204 out of 205) have levels exceeding 3.5 ASC/µl with an average of 12.2 ASC/µl (±9.6), and a variable proportion of miR-21 labeling among different tumor types with 100% cancer specificity. Using a threshold of 3.5 ASC/µl to test a separate sample set in a blinded fashion yields accurate classification of healthy individuals from cancer patients.ConclusionsOur techniques and findings can impact the understanding of cancer biology and the development of new cancer detection and diagnostic technologies.

DDoS Attack Detection in Edge-IIoT Network Using Ensemble Learning

Abstract As the number of IoT devices increases daily due to the rapid growth in technology, every device and network is vulnerable to attacks because it is exposed to the internet. Denial of Service (DoS) is a prevalent type of intrusion on the Internet of Things (IoT) network in which the server becomes down due to flooding requests. Distributed Denial of Service (DDoS) is a special type of DoS attack where the network of malicious computers called botnet consumes the target’s system resources by flooding the requests. Edge computing is closely related to Industrial Internet of Things (IIoT), and industry 4.0. Both of them are relatively emerging technologies so security is a crucial part of them. By incorporating our contributions to the current and innovative dataset Edge-IIoT, the proposed study presents a novel approach to detect DDoS attacks in an IIoT network in the domain of edge computing, whether the traffic is normal or malicious (DDoS traffic). This study explores various Ensemble Learning (EL) techniques to predict normal and malicious DDoS traffic along with the type of DDoS attack. The study applies various preprocessing techniques like Synthetic Minority Over Sampling Technique (SMOTE), label encoding, etc. to enhance the model’s performance and reveals how EL techniques performs better in terms of accuracy than the individual classifiers. Further, the performance of all EL techniques has been investigated in terms of all evaluation measures, including the elapsed time. This important addition not only broadens the focus of study in this area but also offers insightful comparisons of the efficiency and precision of various ensemble approaches as well as individual classifiers. The study achieved a maximum of 99.99% in all evaluation measures.

An Improved Ensemble-Based Cardiovascular Disease Detection System with Chi-Square Feature Selection

Cardiovascular disease (CVD) is a leading cause of death globally; therefore, early detection of CVD is crucial. Many intelligent technologies, including deep learning and machine learning (ML), are being integrated into healthcare systems for disease prediction. This paper uses a voting ensemble ML with chi-square feature selection to detect CVD early. Our approach involved applying multiple ML classifiers, including naïve Bayes, random forest, logistic regression (LR), and k-nearest neighbor. These classifiers were evaluated through metrics including accuracy, specificity, sensitivity, F1-score, confusion matrix, and area under the curve (AUC). We created an ensemble model by combining predictions from the different ML classifiers through a voting mechanism, whose performance was then measured against individual classifiers. Furthermore, we applied chi-square feature selection method to the 303 records across 13 clinical features in the Cleveland cardiac disease dataset to identify the 5 most important features. This approach improved the overall accuracy of our ensemble model and reduced the computational load considerably by more than 50%. Demonstrating superior effectiveness, our voting ensemble model achieved a remarkable accuracy of 92.11%, representing an average improvement of 2.95% over the single highest classifier (LR). These results indicate the ensemble method as a viable and practical approach to improve the accuracy of CVD prediction.

Improving Artificial-Intelligence-Based Individual Tree Species Classification Using Pseudo Tree Crown Derived from Unmanned Aerial Vehicle Imagery

Improving Artificial-Intelligence-Based Individual Tree Species Classification Using Pseudo Tree Crown Derived from Unmanned Aerial Vehicle Imagery

Effectiveness of an ensemble technique based on the distributivity equation in detecting suspicious network activity

With the growing complexity and frequency of cyber threats, there is a pressing need for more effective defense mechanisms. Machine learning offers the potential to analyze vast amounts of data and identify patterns indicative of malicious activity, enabling faster and more accurate threat detection. Ensemble methods, by incorporating diverse models with varying vulnerabilities, can increase resilience against adversarial attacks. This study covers the usage and evaluation of the relevance of an innovative approach of ensemble classification for identifying intrusion threats on a large CICIDS2017 dataset. The approach is based on the distributivity equation that appropriately aggregates the underlying classifiers. It combines various standard supervised classification algorithms, including Multilayer Perceptron Network, k-Nearest Neighbors, and Naive Bayes, to create an ensemble. Experiments were conducted to evaluate the effectiveness of the proposed hybrid ensemble method. The performance of the ensemble approach was compared with individual classifiers using measures such as accuracy, precision, recall, F-score, and area under the ROC curve. Additionally, comparisons were made with widely used state-of-the-art ensemble models, including the soft voting method (Weighted Average Probabilities), Adaptive Boosting (AdaBoost), and Histogram-based Gradient Boosting Classification Tree (HGBC) and with existing methods in the literature using the same dataset, such as Deep Belief Networks (DBN), Deep Feature Learning via Graph (Deep GFL). Based on these experiments, it was found that some ensemble methods, such as AdaBoost and Histogram-based Gradient Classification Tree, do not perform reliably for the specific task of identifying network attacks. This highlights the importance of understanding the context and requirements of the data and problem domain. The results indicate that the proposed hybrid ensemble method outperforms traditional algorithms in terms of classification precision and accuracy, and offers insights for improving the effectiveness of intrusion detection systems.

Estimation of population affinity using proximal femoral measurements based on computed tomographic images in the Japanese and western Australian populations

The present study analyzes morphological differences femora of contemporary Japanese and Western Australian individuals and investigates the feasibility of population affinity estimation based on computed tomographic (CT) data. The latter is deemed to be of practical importance because most anthropological methods rely on the assessment of aspects of skull morphology, which when damaged and/or unavailable, often hampers attempts to estimate population affinity. The study sample comprised CT scans of 297 (146 females; 151 males) Japanese and 330 (145 females; 185 males) Western Australian adult individuals. A total of 10 measurements were acquired in two-dimensional CT images of the left and right femora; two machine learning methods (random forest modeling [RFM]) and support vector machine [SVM]) were then applied for population affinity classification. The accuracy of the two-way (sex-specific and sex-mixed) model was between 71.38 and 82.07% and 76.09–86.09% for RFM and SVM, respectively. Sex-specific (female and male) models were slightly more accurate compared to the sex-mixed models; there were no considerable differences in the correct classification rates between the female- and male-specific models. All the classification accuracies were higher in the Western Australian population, except for the male model using SVM. The four-way sex and population affinity model had an overall classification accuracy of 74.96% and 79.11% for RFM and SVM, respectively. The Western Australian females had the lowest correct classification rate followed by the Japanese males. Our data indicate that femoral measurements may be particularly useful for classification of Japanese and Western Australian individuals.

Development of a Model to Classify Skin Diseases using Stacking Ensemble Machine Learning Techniques

Skin diseases are highly prevalent and transmissible. It has been one of the major health problems that most people face. The diseases are dangerous to the skin and tend to spread over time. A patient can be cured of these skin diseases if they are detected on time and treated early. However, it is difficult to identify these diseases and provide the right medications. This study's research objectives involve developing an ensemble machine learning based model for classifying Erythemato-Squamous Diseases (ESD). The ensemble techniques combine five different classifiers, Naïve Bayes, Support Vector Classifier, Decision Tree, Random Forest, and Gradient Boosting, by merging their predictions and utilizing them as input features for a meta-classifier during training. We tested and validated the ensemble model using the dataset from the University of California, Irvine (UCI) repository to assess its effectiveness. The Individual classifiers achieved different accuracies: Naïve Bayes (85.41%), Support Vector Machine (98.61%), Random Forest (97.91%), Decision Tree (95.13%), Gradient Boosting (95.83%). The stacking method yielded a higher accuracy of 99.30% and a precision of 1.00, recall of 0.96, F1 score of 0.97, and specificity of 1.00 compared to the base models. The study confirms the effectiveness of ensemble learning techniques in classifying ESD.

Decoding the scientific creative-ability of subjects using dual attention induced graph convolutional-capsule network

There is an increasing demand of creative individuals in scientific research, innovation sectors of software industries and industrial research/development sectors. On the other hand, there are requirements of analytical minded people in investigation departments, academia and management sectors. Unfortunately, classification of individuals into creative and analytical categories based on their behavioral response is not easy. This paper makes an attempt to classify people into 4 categories: Analytical, High Creative, Medium Creative and Low Creative from their brain response during their participation in a creativity-test based on convergent problems. The proposed classification problem involves two main phases. In the first phase, a brain connectivity map is constructed from the electroencephalogram (EEG) response of the brain using Pearson’s correlation technique. In the second phase, a set of three centrality features, namely degree, closeness and betweenness are extracted from the connectivity map and fed to a classifier model for categorizing the afore-said class labels. The classifier model here synergistically combines one Graph Convolution Network (to abstract the brain connectivity-based centrality features) and one Capsule Network (to undertake the classification task) to develop the proposed Dual Attention Induced Graph Convolutional-Capsule network (DAIGC-CapsNet). The novelty of the proposed classifier model lies in the dual attention module and a new routing algorithm. The dual attention modules includes a) a Mish Induced Attention Module (MI-AM) to guide the graph convolution layers to focus on the most significant node attributes, and b) a Fused Attention Module (F-AM) to ensure the transmission of the most relevant predictions from the primary capsule to the class capsule layers. The latter attention module combines the effects of two sub-modules (channel and spatial) that concentrate on determining "what" and "where" to prioritize within the channel and spatial dimensions of the primary capsules. Lastly, the coupling between the primary and class capsule layers is strengthened by a Sparsemax based routing algorithm. Experiments conducted yield fruitful and definitive outcomes that substantiate the effectiveness of the proposed framework with respect to its conventional counterparts. Moreover, statistical validation of the proposed classifier using Friedman’s test also proves its efficacy compared to its competitors.

Ensemble Machine Learning Classification Models for Predicting Pavement Condition

Forecasting pavement performance condition is essential within the pavement management system to optimize decisions with regard to planning maintenance and rehabilitation projects. Accurate forecasts facilitate timely interventions and assist in formulating cost-effective asset management plans. Data-driven machine learning models that utilize historical data to improve forecasting precision have gained attention in the field of asset management. Although numerous studies have employed regression-based models to forecast pavement condition, transportation asset management often operates according to condition index ranges rather than exact values. Therefore, classification models are suitable for predicting pavement condition grades and determining the appropriate maintenance type for pavement assets. This research focuses on developing five machine learning classification models to predict pavement condition: random forest; gradient boost; support vector machine; k-nearest neighbors; and artificial neural network. To enhance prediction performance, these models are integrated using ensemble methods, including voting and stacking. The classification models are developed using a dataset from the Georgia Department of Transportation that documented the condition of asphalt pavements for predefined maintenance sections between 2017 and 2021. A voting ensemble model constructed with the two best-performing individual classification models reached the highest accuracy rate at 83%. Although the performance of individual models fluctuates, ensemble models consistently produce a top-tier performance regardless of the variations in data sampling. Therefore, ensemble methods are recommended for developing pavement condition prediction models to improve accuracy and achieve a more consistent quality of predictions. The findings of this research will provide transportation agencies with information to help them strengthen their forecasting practices in relation to pavement condition, thereby improving their maintenance planning and cost savings.