Feature Selection Techniques Research Articles

Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement

ObjectivesThis study aimed to assess the accuracy of machine learning (ML) models with feature selection technique in classifying cervical vertebral maturation stages (CVMS). Consensus-based datasets were used for models training and evaluation for their model generalization capabilities on unseen datasets.MethodsThree clinicians independently rated CVMS on 1380 lateral cephalograms, resulting in the creation of five datasets: two consensus-based datasets (Complete Agreement and Majority Voting), and three datasets based on a single rater’s evaluations. Additionally, landmarks annotation of the second to fourth cervical vertebrae and patients’ information underwent a feature selection process. These datasets were used to train various ML models and identify the top-performing model for each dataset. These models were subsequently tested on their generalization capabilities.ResultsFeatures that considered significant in the consensus-based datasets were consistent with a CVMS guideline. The Support Vector Machine model on the Complete Agreement dataset achieved the highest accuracy (77.4%), followed by the Multi-Layer Perceptron model on the Majority Voting dataset (69.6%). Models from individual ratings showed lower accuracies (60.4–67.9%). The consensus-based training models also exhibited lower coefficient of variation (CV), indicating superior generalization capability compared to models from single raters.ConclusionML models trained on consensus-based datasets for CVMS classification exhibited the highest accuracy, with significant features consistent with the original CVMS guidelines. These models also showed robust generalization capabilities, underscoring the importance of dataset quality.

Interactive visual formula composition of multidimensional data classifiers

Understanding how a classification result is generated and what role individual features play in the classification is crucial in many applications and, in particular, in medical contexts such as the translation of diagnosis biomarkers into clinical practice. The goal is to find (ideally simple) relationships between the features in multi-dimensional data and the classification for an explanation of the underlying phenomenon. Mathematical formulas allow for the expression of these relationships and can serve as classifiers. However, there are infinitely many mathematical formulas for the given features and they bear an inherent trade-off between complexity and accuracy. We present an interactive visual approach that supports domain experts to mitigate the trade-off issue. Core to our approach is a novel feature selection method, from which formulas are composed using symbolic regression and where state-of-the-art classifiers serve as a reference. To evaluate our approach and compare the achieved classification performance to the performance achieved by other state-of-the-art feature selection techniques, we test our methods with well-known machine learning data sets. Our evaluation shows that our feature selection method performs better than randomly selecting features for data sets with many features or when a low number of generations in the symbolic regression is required. Moreover, it consistently matches or outperforms state-of-the-art methods. Moreover, we apply our approach in a case study to a hemodynamic cohort data set, where we report our findings and domain expert feedback. Our approach was able to find formulas containing features that are in agreement with literature. Also, we could find formulas that performed better in the micro-averaged F1 score when compared to established histological indices.

From dim to glow: dynamic illuminance adjustment for simultaneous exposure correction and low-light image enhancement

Acquiring high-quality images in diverse lighting conditions is challenging, particularly in the constantly evolving driving landscape. From the harsh brilliance of daylight to the subtle shadows of nighttime scenarios, the complexity of capturing accurate images intensifies. Therefore, addressing exposure issues across various lighting conditions is imperative. This study introduces a novel multi-task end-to-end dynamic illumination adjustment approach termed CPGA-DIA. By incorporating feature selection and gamma factor correction techniques, our method effectively handles extreme variations in light conditions for both low-light image enhancement and exposure correction. Comprehensive experimental evaluations demonstrate superior performance to existing processes, showcasing our method’s adaptability and robustness in real-world driving scenarios. Furthermore, our approach extends its capabilities to include the control and estimation of explainable factors related to changing lightness, enabling our model to understand better the environmental conditions that influence image perception and clarity. This research contributes to advancing image capture methodologies, particularly in dynamic lighting conditions, with promising implications for applications ranging from photography to various other fields.

Attack Detection in IoT Network Using Support Vector Machine and Improved Feature Selection Technique

Attack Detection in IoT Network Using Support Vector Machine and Improved Feature Selection Technique

The Effect of Multicollinearity on Feature Selection

Objectives: To provide a new LASSO-based feature selection technique that aids in selecting important variables for predicting the response variables in case of multicollinearity. Methods: LASSO is a type of regression method employed to select important covariates for predicting a dependent variable. The traditional LASSO method uses the conventional Ordinary Least Square (OLS) method for this purpose. The Use of the OLS based LASSO approach gives unreliable results if the data deviates from normality. Thus, this study recommends using, a Redescending M-estimator-based LASSO approach. The efficacy of this new method is checked against the ordinary LASSO method using a real dataset and also a simulation study with various levels of sample size (N=100,200,1000), different numbers of predictors (p=10,15,20), and varying degrees of correlation (ρ = 0.96, 0.98, 0.999). Findings: The usual OLS-based LASSO finds it difficult to select important variables when the independent variables are correlated. The Redescending M-estimator-based LASSO addresses at tackling the pitfalls faced by Conventional LASSO methodology. Among other things, the proposed method is far better than the old-fashioned LASSO since it helps to pick out significant factors more effectively, particularly in the presence of multicollinearity. Novelty: The conventional OLS-based LASSO approach selects a greater number of non-significant variables in the presence of multicollinearity. The proposed Redescending M-estimator-based LASSO approach selects the important variables in the presence of multicollinearity. Keywords: Feature Selection, LASSO, MDAE, VIF, Variable Selection

Pilot Study on Enhanced Detection of Cues over Malicious Sites Using Data Balancing on the Random Forest Ensemble

The digital revolution frontiers have rippled across society today – with various web content shared online for users as they seek to promote monetization and asset exchange, with clients constantly seeking improved alternatives at lowered costs to meet their value demands. From item upgrades to their replacement, businesses are poised with retention strategies to help curb the challenge of customer attrition. The birth of smartphones has proliferated feats such as mobility, ease of accessibility, and portability – which, in turn, have continued to ease their rise in adoption, exposing user device vulnerability as they are quite susceptible to phishing. With users classified as more susceptible than others due to online presence and personality traits, studies have sought to reveal lures/cues as exploited by adversaries to enhance phishing success and classify web content as genuine and malicious. Our study explores the tree-based Random Forest to effectively identify phishing cues via sentiment analysis on phishing website datasets as scrapped from user accounts on social network sites. The dataset is scrapped via Python Google Scrapper and divided into train/test subsets to effectively classify contents as genuine or malicious with data balancing and feature selection techniques. With Random Forest as the machine learning of choice, the result shows the ensemble yields a prediction accuracy of 97 percent with an F1-score of 98.19% that effectively correctly classified 2089 instances with 85 incorrectly classified instances for the test-dataset.

Optimizing Prognostic Predictions in Liver Cancer with Machine Learning and Survival Analysis.

This study harnesses RNA sequencing data from the Cancer Genome Atlas to unearth pivotal genetic markers linked to the progression of liver hepatocellular carcinoma (LIHC), a major contributor to cancer-related deaths worldwide, characterized by a dire prognosis and limited treatment avenues. We employ advanced feature selection techniques, including sure independence screening (SIS) combined with the least absolute shrinkage and selection operator (Lasso), smoothly clipped absolute deviation (SCAD), information gain (IG), and permutation variable importance (VIMP) methods, to effectively navigate the challenges posed by ultra-high-dimensional data. Through these methods, we identify critical genes like MED8 as significant markers for LIHC. These markers are further analyzed using advanced survival analysis models, including the Cox proportional hazards model, survival tree, and random survival forests. Our findings reveal that SIS-Lasso demonstrates strong predictive accuracy, particularly in combination with the Cox proportional hazards model. However, when coupled with the random survival forests method, the SIS-VIMP approach achieves the highest overall performance. This comprehensive approach not only enhances the prediction of LIHC outcomes but also provides valuable insights into the genetic mechanisms underlying the disease, thereby paving the way for personalized treatment strategies and advancing the field of cancer genomics.

Local-structure-preservation and redundancy-removal-based feature selection method and its application to the identification of biomarkers for schizophrenia

Accurate diagnosis of mental disorders is expected to be achieved through the identification of reliable neuroimaging biomarkers with the help of cutting-edge feature selection techniques. However, existing feature selection methods often fall short in capturing the local structural characteristics among samples and effectively eliminating redundant features, resulting in inadequate performance in disorder prediction. To address this gap, we propose a novel supervised method named local-structure-preservation and redundancy-removal-based feature selection (LRFS), and then apply it to the identification of meaningful biomarkers for schizophrenia (SZ). LRFS method leverages graph-based regularization to preserve original sample similarity relationships during data transformation, thus retaining crucial local structure information. Additionally, it introduces redundancy-removal regularization based on interrelationships among features to exclude similar and redundant features from high-dimensional data. Moreover, LRFS method incorporates l2,1 sparse regularization that enables selecting a sparse and noise-robust feature subset. Experimental evaluations on eight public datasets with diverse properties demonstrate the superior performance of our method over nine popular feature selection methods in identifying discriminative features, with average classification accuracy gains ranging from 1.30 % to 9.11 %. Furthermore, the LRFS method demonstrates superior discriminability in four functional magnetic resonance imaging (fMRI) datasets from 708 healthy controls (HCs) and 537 SZ patients, with an average increase in classification accuracy ranging from 1.89 % to 9.24 % compared to other nine methods. Notably, our method reveals reproducible and significant changes in SZ patients relative to HCs across the four datasets, predominantly in the thalamus-related functional network connectivity, which exhibit a significant correlation with clinical symptoms. Convergence analysis, parameter sensitivity analysis, and ablation studies further demonstrate the effectiveness and robustness of our method. In short, our proposed feature selection method effectively identifies discriminative and reliable features that hold the potential to be biomarkers, paving the way for the elucidation of brain abnormalities and the advancement of precise diagnosis of mental disorders.

AScirRNA: A novel computational approach to discover abiotic stress-responsive circular RNAs in plant genome

In the realm of plant biology, understanding the intricate regulatory mechanisms governing stress responses stands as a pivotal pursuit. Circular RNAs (circRNAs), emerging as critical players in gene regulation, have garnered attention in recent days for their potential roles in abiotic stress adaptation. A comprehensive grasp of circRNAs' functions in stress response offers avenues for breeders to manipulating plants to develop abiotic stress resistant crop cultivars to thrive in challenging climates. This study pioneers a machine learning-based model for predicting abiotic stress-responsive circRNAs. The K-tuple nucleotide composition (KNC) and Pseudo KNC (PKNC) features were utilized to numerically represent circRNAs. Three different feature selection strategies were employed to select relevant and non-redundant features. Eight shallow and four deep learning algorithms were evaluated to build the final predictive model. Following five-fold cross-validation process, XGBoost learning algorithm demonstrated superior performance with LightGBM-chosen 260 KNC features (Accuracy: 74.55 %, auROC: 81.23 %, auPRC: 76.52 %) and 160 PKNC features (Accuracy: 74.32 %, auROC: 81.04 %, auPRC: 76.43 %), over other combinations of learning algorithms and feature selection techniques. Further, the robustness of the developed models were evaluated using an independent test dataset, where the overall accuracy, auROC and auPRC were found to be 73.13 %, 72.34 % and 72.68 % for KNC feature set and 73.52 %, 79.53 % and 73.09 % for PKNC feature set, respectively. This computational approach was also integrated into an online prediction tool, AScirRNA (https://iasri-sg.icar.gov.in/ascirna/) for easy prediction by the users. Both the proposed model and the developed tool are poised to augment ongoing efforts in identifying stress-responsive circRNAs in plants.

A modified CNN-IDS model for enhancing the efficacy of intrusion detection system

As the security of computer networks in enterprises worldwide is dependent on the proper functioning of intrusion detection systems (IDSs) and intrusion prevention systems (IPSs), this effectiveness of both of them is of utmost priority. Leveraging diverse techniques, these network security systems are created to keep the reliability, the availability, and the integrity of the organizational networks safe. One plus point of using ML in intrusion detection system (IDS) is that it has successfully weeded out all the IDS attacks with a high degree of accuracy. In contrast, such systems may be believed to operate to their least competent levels when supersized data spaces have to be dealt with. In the process to solve this, application of feature selection techniques will play the crucial role to ignore non-relevant features which do not impact the issue of classification much. One more thing to keep in mind is that the ML-based IDSs often have problems with high false alarms and percentage accuracy because of the imbalanced training sets. The undertaking of this paper involves a through the analysis of the UNSW-NB15 intrusion detection data set as upon which our models will be tested and trained. We utilize two feature selection approaches: the PCA method, which is denoted as PCA, and the SVD method, called SVD. Furthermore, we categorize the datasets using these methods— Ridge Regression (RR), Stochastic Gradient Descent, and Convolutional Neural Network (CNN)-- on the transformed feature space. What is the most widely used for, is that it deals with both, binary and multiclass classification. The result measure that PCA and SVD are succeeded in getting better performance of IDS than others with enhancing the accuracy of classification models. More specifically, the RR classifier's precise was outstanding for the binary classification problem experiencing a rise in the accuracy from 98.13 % to 99.85 %. This shows the critical role of feature selection approaches and is also demonstrates the modeling capabilities of RR, SGD, and CNN classifiers and stands out as a solution to intrusion detection.

Optimized Intrusion Detection for IoMT Networks with Tree-Based Machine Learning and Filter-Based Feature Selection.

The Internet of Medical Things (IoMTs) is a network of connected medical equipment such as pacemakers, prosthetics, and smartwatches. Utilizing the IoMT-based system, a huge amount of data is generated, offering experts a valuable resource for tasks such as prediction, real-time monitoring, and diagnosis. To do so, the patient's health data must be transferred to database storage for processing because of the limitations of the storage and computation capabilities of IoMT devices. Consequently, concerns regarding security and privacy can arise due to the limited control over the transmitted information and reliance on wireless transmission, which leaves the network vulnerable to several kinds of attacks. Motivated by this, in this study, we aim to build and improve an efficient intrusion detection system (IDS) for IoMT networks. The proposed IDS leverages tree-based machine learning classifiers combined with filter-based feature selection techniques to enhance detection accuracy and efficiency. The proposed model is used for monitoring and identifying unauthorized or malicious activities within medical devices and networks. To optimize performance and minimize computation costs, we utilize Mutual Information (MI) and XGBoost as filter-based feature selection methods. Then, to reduce the number of the chosen features selected, we apply a mathematical set (intersection) to extract the common features. The proposed method can detect intruders while data are being transferred, allowing for the accurate and efficient analysis of healthcare data at the network's edge. The system's performance is assessed using the CICIDS2017 dataset. We evaluate the proposed model in terms of accuracy, F1 score, recall, precision, true positive rate, and false positive rate. The proposed model achieves 98.79% accuracy and a low false alarm rate 0.007 FAR on the CICIDS2017 dataset according to the experimental results. While this study focuses on binary classification for intrusion detection, we are planning to build a multi-classification approach for future work which will be able to not only detect the attacks but also categorize them. Additionally, we will consider using our proposed feature selection technique for different ML classifiers and evaluate the model's performance empirically in real-world IoMT scenarios.

Magnetic Resonance-Guided Cancer Therapy Radiomics and Machine Learning Models for Response Prediction.

Magnetic resonance imaging (MRI) is known for its accurate soft tissue delineation of tumors and normal tissues. This development has significantly impacted the imaging and treatment of cancers. Radiomics is the process of extracting high-dimensional features from medical images. Several studies have shown that these extracted features may be used to build machine-learning models for the prediction of treatment outcomes of cancer patients. Various feature selection techniques and machine models interrogate the relevant radiomics features for predicting cancer treatment outcomes. This study aims to provide an overview of MRI radiomics features used in predicting clinical treatment outcomes with machine learning techniques. The review includes examples from different disease sites. It will also discuss the impact of magnetic field strength, sample size, and other characteristics on outcome prediction performance.

Enhancing metastatic colorectal cancer prediction through advanced feature selection and machine learning techniques

Background and aimsColorectal cancer (CRC) is the third most prevalent cancer globally, posing a significant challenge due to its high rate of metastasis. Approximately 20% of patients with CRC present with distant metastases at diagnosis, and over 50% develop metastases within five years. Accurate prediction of metastasis is crucial for improving survival outcomes in patients with CRC. MethodsThis study introduces an innovative cost-sensitive fast correlation-based filter (CS-FCBF) algorithm for feature selection, integrated with machine learning techniques to predict metastatic CRC. The CS-FCBF algorithm effectively reduced the number of genomic features from 184 to 9 critical genes: CXCL9, C2CD4B, RGCC, GFI1, BEX2, CXCL3, FOXQ1, PBK, and PLAG1. The methodology combined in vitro, in vivo, and analysis of publicly available single-cell RNA-seq datasets to validate the findings. ResultsThe application of the CS-FCBF algorithm led to a significant improvement in prediction model performance, with an average 21.16% increase in the area under the precision-recall curve. The nine identified genes hold potential as diagnostic biomarkers and therapeutic targets for metastatic CRC. ConclusionsThis study highlights the critical role of advanced feature selection methods, combined with machine learning, in addressing the challenge of class imbalance in medical diagnosis, particularly for CRC. Early detection of metastasis is vital, and the identified genes underscore their importance in the metastatic process of CRC. The methodology applied here offers valuable insights and paves the way for future research in other cancers or diseases that face similar diagnostic challenges.

Feature selection technique on convolutional neural network – multilabel classification task

Automated text-based recommendation, an artificial intelligence development, finds application in document analysis like job resumes. The classification of job resumes poses challenges due to the ambiguity in categorizing multiple potential jobs in a single application file, termed multi-label classification, deep learning, particularly convolutional neural networks (CNN), offers flexibility in enhancing feature representations. Despite its robust learning capabilities, the black-box design of deep learning lacks interpretability and demands a substantial number of parameters, requiring significant computational resources. The primary challenge in multilabel learning is the ambiguity of labels not fully explained by traditional equivalence relations. To address this, the research employs feature selection techniques, specifically the Chi-square method. The goal is to reduce features in deep learning models while considering label relevance in multi-label text classification, easing computational workload while preserving model performance. Experimental tests, both with and without the Chi-square feature selection technique on the dataset, underscore its substantial impact on the classification model's ability. The conclusion emphasizes the influence of the Chi-square feature selection technique on performance and computational time. In summary, the research underscores the importance of balancing computational efficiency and model interpretability, especially in complex multi-label classification tasks like job applications.

Epilepsy detection using wavelet transform, genetic algorithm, and decision tree classifier

<p><span lang="EN-US">This work presents a unique detection approach for classifying epilepsy using the CHB_MIT dataset. The suggested system utilizes the discrete wavelet transform (DWT) technique, genetic algorithm (GA), and decision tree (DT). This model consists of three distinct steps. In the first one, we present a feature extraction method that uses a DWT of four levels on electroencephalogram (EEG) and electrocardiogram (ECG) signals. The second step is the process of feature selection, which entails the elimination of irrelevant features in order to produce datasets of superior quality. This is achieved via the use of correlation and GA techniques. The reduction in dimensionality of the dataset serves to decrease the complexity of the training process and effectively addresses the problem of overfitting. The third step utilizes a DT algorithm to make predictions based on the data of epileptic patients. The performance evaluation layer encompasses the implementation of our prediction model on the CHB-MIT dataset. The results achieved from this implementation show that using feature selection techniques and an ECG signal as additional information increases the detection model's performance. The averaging accuracy is 98.3%, the sensitivity is 96%, and the specificity is 99%.</span></p>

Automatic Intrusion Detection Model with Secure Data Storage on Cloud Using Adaptive Cyclic Shift Transposition with Enhanced ANFIS Classifier

Cloud computing has emerged as a pivotal technology in the computer electronics industry, offering users significant computing power and ample storage space. Security threats pose significant challenges to the progression of cloud computing, hindering its growth in the industry. Detecting intrusions is crucial for protecting cloud environments from harmful attacks. However, due to the complexity and vast amount of network data, building effective intrusion detection systems (IDS) for cloud setups is difficult. Traditional IDS have struggled to effectively mitigate these risks. To overcome these problems, we propose a novel feature selection technique with deep learning classifier-based intrusion detection and avoidance in a cloud environment. The suggested model is divided into four phases: feature selection, pre-processing, classification, and encryption. The initial step involves gathering the data from the dataset and pre-processing it. The Adaptive Walrus Optimization Algorithm (AWO) is then used to choose select optimal features, aiming to mitigate computational complexity and reduce time consumption. These selected features are then fed into an enhanced Adaptive Neuro-Fuzzy Inference System (EANFIS) classifier for accurate classification of normal and intruded data. Following classification, normal data undergoes encryption using the Adaptive Cyclic Shift Transposition (ACST) Algorithm to bolster security.For experimental evaluation two datasets used namely, KDDCup-99 and NSL-KDD. The proposed method notably achieves impressive accuracy rates of 98.47% for the NSL KDD dataset and 98.97% for the KDD-CUP99 dataset.

Hyperspectral image classification with spectral-spatial feature integration and ensemble learning

<p>Hyperspectral imaging (HSI) has emerged as a robust remote sensing and medical imaging tool. However, HSI classification remains a challenging problem due to the high-dimensional data and the need for efficient feature selection and enhancement techniques. The proposed work addresses the problem of spatial feature extraction in spectral-spatial HSI classification tasks. This paper introduces an innovative model addressing the intricacies of spatial feature extraction in spectral-spatial HSI classification tasks, employing a fusion of spectral and spatial features through an adaptive kernel-based Gaussian filtering mechanism to elevate the quality of HSI data and augment classification performance. The classification is executed using three distinct classifiers, whose decisions are harmoniously integrated within an ensemble learning framework to optimize outcomes. The effectiveness of the proposed system is meticulously evaluated across three diverse datasets, Indian Pine, Pavia, and Salinas. This study also compares the model's efficiency against the existing similar work presented in the literature. The results show that the proposed work outperforms existing methods with constantly showing 99% accuracy and kappa score for each dataset, demonstrating its potential applications in various domains such as remote sensing and medical imaging.</p>

A hybrid Feature Selection Method Based on Binary PSO Algorithm for Microarray Data Classification

Microarray technology produces data with a large number of dimensions. The abundance of dimensions in the data makes it challenging for machine learning algorithms to extract meaningful information from it. To overcome this limitation, feature selection (FS) techniques can be applied to reduce the dimensionality of the data. FS is a crucial preprocessing step that allows for the handling of high-dimensional data and facilitates more effective and efficient processing. The primary objective of this paper is to develop an efficient FS method that can effectively reduce the dimensionality of microarray data. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is utilized in the first filtering stage to extract informative features. The best feature subset is then determined by using a Particle Swarm Optimization (PSO) algorithm as a wrapper feature selector to identify ideal features. The proposed approach is evaluated using microarray datasets from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and compared with other algorithms. The experimental findings indicate that the proposed approach outperforms the benchmark methods in terms of classification accuracy.

Securing the Internet of Health Things: Embedded Federated Learning-Driven Long Short-Term Memory for Cyberattack Detection

The proliferation of the Internet of Health Things (IoHT) introduces significant benefits for healthcare through enhanced connectivity and data-driven insights, but it also presents substantial cybersecurity challenges. Protecting sensitive health data from cyberattacks is critical. This paper proposes a novel approach for detecting cyberattacks in IoHT environments using a Federated Learning (FL) framework integrated with Long Short-Term Memory (LSTM) networks. The FL paradigm ensures data privacy by allowing individual IoHT devices to collaboratively train a global model without sharing local data, thereby maintaining patient confidentiality. LSTM networks, known for their effectiveness in handling time-series data, are employed to capture and analyze temporal patterns indicative of cyberthreats. Our proposed system uses an embedded feature selection technique that minimizes the computational complexity of the cyberattack detection model and leverages the decentralized nature of FL to create a robust and scalable cyberattack detection mechanism. We refer to the proposed approach as Embedded Federated Learning-Driven Long Short-Term Memory (EFL-LSTM). Extensive experiments using real-world ECU-IoHT data demonstrate that our proposed model outperforms traditional models regarding accuracy (97.16%) and data privacy. The outcomes highlight the feasibility and advantages of integrating Federated Learning with LSTM networks to enhance the cybersecurity posture of IoHT infrastructures. This research paves the way for future developments in secure and privacy-preserving IoHT systems, ensuring reliable protection against evolving cyberthreats.

Predictors of the willingness to accept a free COVID-19 vaccine among households in Nigeria

BackgroundTo inform vaccination policy and programmatic strategies to increase COVID-19 vaccine uptake, an understanding of the factors associated with the willingness to vaccinate is needed. MethodsWe analyzed data collected from the sixth and tenth round of the Nigerian COVID-19 National Longitudinal Phone Survey conducted by the National Bureau of Statistics and the World Bank in 2020 and 2021, respectively. Exploratory data analysis and feature selection techniques were used to identify important variables. Multivariable logistic regression models were fitted to assess the association between socio-demographic and economic factors and the willingness to receive a free COVID-19 vaccine among Nigerian households at two different time points before vaccines became widely available. ResultsData from 1,733 and 1,651 Nigerian households who completed the sixth and tenth round of the survey, respectively, were included. Most respondents (>85% of households) were willing to receive a free COVID-19 vaccine from both survey rounds. The median household size was 6 (IQR: [4, 8]) with females heading about 18% of the households. Approximately 22% of the household heads had not received any formal education. Compared to households whose head had no education, households whose heads had completed tertiary education or higher had significantly lower odds of willingness to be vaccinated (ORround 6: 0.46, 95% CI: [0.31, 0.68], ORround 10: 0.49, 95% CI: [0.34, 0.71]). An increasing proportion of male household members was associated with greater willingness to receive a free COVID-19 vaccine (ORround 6: 1.84, 95% CI: [1.01, 3.33], ORround 10: 5.25, 95% CI: [2.86, 9.65]). Significant associations with vaccine willingness were also observed across geopolitical zones of residence with households in South-East Nigeria (ORround 6: 0.16, 95% CI: [0.10, 0.24]; ORround 10: 0.29, 95% CI: [0.19, 0.43]) and South-South Nigeria (ORround 6: 0.57, 95% CI: [0.36, 0.90], ORround 10: 0.32, 95% CI: [0.22, 0.48]) less likely to be willing to receive a free vaccine compared to households in North-Central Nigeria. ConclusionThese findings from two different time points before vaccine roll-out suggest that the educational level of household head, proportion of male household members, and the geopolitical zone of residence are important baseline predictors of the willingness to receive a free COVID-19 vaccine in Nigeria. These factors should be carefully considered and specifically targeted when designing public health programs to inform early-stage strategies that address underlying vaccine hesitancy, improve vaccine uptake, promote ongoing COVID-19 vaccination efforts, and potentially enhance other immunization programs in Nigeria.