Conventional Machine Learning Models Research Articles

GeneNet: Transfer learning-based hybrid African buffalo optimization with genetic algorithm for gene expression based cancer classification

Gene therapy is one of the advanced medical diagnosis environments, which is used to identify the solutions to various cancers by identifying the perfect gene expressions. The computer aided detection of gene expressions is a research problem, where cancer type is identified by artificial intelligence methods. However, the conventional machine learning models were failed to provide the accurate cancer classification and resulted in poor quantitative performance. Therefore, this work focuses on the implementation of gene expression-based cancer classification (GECC) network, here after referred as GeneNet. Initially, the proposed GeneNet performs the data preprocessing to normalize the gene-expression data by replacing the unknown characters and missing symbols. Then, the visual geometry group developed VGG16 model for extraction of correlated, and structural features from pre-processed dataset. In addition, hybrid African buffalo optimization with genetic algorithm (HABO-GA) is used to select the optimal features through natural inspired hunting (searching) properties. Finally, low complex convolutional neural network (LC-CNN) model is trained with HABO-GA features, which also performs the multi-class cancer classification from test data. The simulations are conducted on publicly available GECC datasets such as lymphography, ovarian, leukemia, lung, and prostate cancers discloses the superiority of proposed GeneNetas compared to state-of-the-art approaches with 86.6 %, 100 %, 76.92 %, 100 %, and 100 % of accuracy, respectively.

A Novel Ensemble Learning Approach for Stock Market Prediction Based on Sentiment Analysis and the Sliding Window Method

Financial news disclosures provide valuable information for traders and investors while making stock market investment decisions. Essential but challenging, the stock market prediction problem has attracted significant attention from both researchers and practitioners. Conventional machine learning models often fail to interpret the content of financial news due to the complexity and ambiguity of natural language used in the news. Inspired by the success of recurrent neural networks (RNNs) in sequential data processing, we propose an ensemble RNN approach (long short-term memory, gated recurrent unit, and SimpleRNN) to predict stock market movements. To avoid extracting tens of thousands of features using traditional natural language processing methods, we apply sentiment analysis and the sliding window method to extract only the most representative features. Our experimental results confirm the effectiveness of these two methods for feature extraction and show that the proposed ensemble approach is able to outperform other models under comparison.

Enhancing understanding of real-world listening experiences: Insights from ecological momentary assessments with assistive listening technologies

Comprehending the daily listening experiences of people who use assistive listening technologies is difficult due to individual differences and the variety of listening environments they encounter. Consequently, a lack of comprehensive insight into real-world experiences often leads to misconstrued interpretations of research outcomes and future technological directions. Addressing this issue, the National Acoustic Laboratories (NAL) in Sydney, Australia, has been actively investigating the applications of ecological momentary assessments (EMA) since 2010. By employing EMA, NAL aims to comprehend the impact of assistive listening technologies in real-world conditions. To achieve this, we invested data from four distinct studies, encompassing more than 3000 survey entries. Utilizing an EMA app specifically developed by NAL, participants reported various challenges they faced in their listening experiences. These challenges include difficulties in understanding conversation when listening to a single speaker or in multitasking scenarios, as well as frustration with the loudness and annoyance of background noise. The analysis of this extensive dataset involved a combination of conventional statistical methods and advanced machine learning models. By employing these techniques, key insights were extracted from the data, offering valuable guidance for the design of future research conducted in real-world settings.

A Comparative Study: Deep Learning Approach to Predict Autism Spectrum Disorder Based on Q-Chat-10 Responses

Autism spectrum disorder (ASD) is a neurodevelopmental condition that has been observed to have an increasing incidence and significant health-related expenses. The timely identification of these burdens can mitigate their impact; however, current diagnostic protocols are protracted and entail significant expenses. The implementation of machine learning and, more recently, deep learning techniques presents promising remedies to improve ASD screening procedures. The present research introduces a deep learning framework for the purpose of forecasting autism spectrum disorder (ASD) utilizing responses obtained from the Q-Chat-10 questionnaire. The dataset employed in this study comprises 1054 records, encompassing ten behavioral traits and additional individual characteristics. The objective of this study is to improve the precision, efficacy, sensitivity, and specificity of autism spectrum disorder (ASD) predictions by contrasting the performance of a deep learning model with that of conventional machine learning models. The implementation of this technology has the potential to significantly optimize the ASD screening procedure, rendering it more affordable and convenient and ultimately assisting healthcare practitioners in their clinical judgment for prompt ASD identification.

Enhancing temple surveillance through human activity recognition: A novel dataset and YOLOv4-ConvLSTM approach

Automated identification of human activities remains a complex endeavor, particularly in unique settings like temple environments. This study focuses on employing machine learning and deep learning techniques to analyze human activities for intelligent temple surveillance. However, due to the scarcity of standardized datasets tailored for temple surveillance, there is a need for specialized data. In response, this research introduces a pioneering dataset featuring Eight distinct classes of human activities, predominantly centered on hand gestures and body postures. To identify the most effective solution for Human Activity Recognition (HAR), a comprehensive ablation study is conducted, involving a variety of conventional machine learning and deep learning models. By integrating YOLOv4’s robust object detection capabilities with ConvLSTM’s ability to model both spatial and temporal dependencies in spatio-temporal data, the approach becomes capable of recognizing and understanding human activities in sequences of images or video frames. Notably, the proposed YOLOv4-ConvLSTM approach emerges as the optimal choice, showcasing a remarkable accuracy of 93.68%. This outcome underscores the suitability of the outlined methodology for diverse HAR applications in temple environments.

AutoML accurately predicts endovascular mechanical thrombectomy in acute large vessel ischemic stroke.

Automated machine learning or autoML has been widely deployed in various industries. However, their adoption in healthcare, especially in clinical settings is constrained due to a lack of clear understanding and explainability. The aim of this study is to utilize autoML for the prediction of functional outcomes in patients who underwent mechanical thrombectomy and compare it with traditional ML models with a focus on the explainability of the trained models. A total of 156 patients of acute ischemic stroke with Large Vessel Occlusion (LVO) who underwent mechanical thrombectomy within 24 h of stroke onset were included in the study. A total of 34 treatment variables including clinical, demographic, imaging, and procedure-related data were extracted. Various conventional machine learning models such as decision tree classifier, logistic regression, random forest, kNN, and SVM as well as various autoML models such as AutoGluon, MLJAR, Auto-Sklearn, TPOT, and H2O were used to predict the modified Rankin score (mRS) at the time of patient discharge and 3 months follow-up. The sensitivity, specificity, accuracy, and AUC for traditional ML and autoML models were compared. The autoML models outperformed the traditional ML models. For the prediction of mRS at discharge, the highest testing accuracy obtained by traditional ML models for the decision tree classifier was 74.11%, whereas for autoML which was obtained through AutoGluon, it showed an accuracy of 88.23%. Similarly, for mRS at 3 months, the highest testing accuracy of traditional ML was that of the SVM classifier at 76.5%, whereas that of autoML was 85.18% obtained through MLJAR. The 24-h ASPECTS score was the most important predictor for mRS at discharge whereas for prediction of mRS at 3 months, the most important factor was mRS at discharge. Automated machine learning models based on multiple treatment variables can predict the functional outcome in patients more accurately than traditional ML models. The ease of clinical coding and deployment can assist clinicians in the critical decision-making process. We have developed a demo application which can be accessed at https://mrs-score-calculator.onrender.com/.

OFVSD: a Python package of optimized forward variable selection decoder for high-dimensional neuroimaging data.

The complexity and high dimensionality of neuroimaging data pose problems for decoding information with machine learning (ML) models because the number of features is often much larger than the number of observations. Feature selection is one of the crucial steps for determining meaningful target features in decoding; however, optimizing the feature selection from such high-dimensional neuroimaging data has been challenging using conventional ML models. Here, we introduce an efficient and high-performance decoding package incorporating a forward variable selection (FVS) algorithm and hyper-parameter optimization that automatically identifies the best feature pairs for both classification and regression models, where a total of 18 ML models are implemented by default. First, the FVS algorithm evaluates the goodness-of-fit across different models using the k-fold cross-validation step that identifies the best subset of features based on a predefined criterion for each model. Next, the hyperparameters of each ML model are optimized at each forward iteration. Final outputs highlight an optimized number of selected features (brain regions of interest) for each model with its accuracy. Furthermore, the toolbox can be executed in a parallel environment for efficient computation on a typical personal computer. With the optimized forward variable selection decoder (oFVSD) pipeline, we verified the effectiveness of decoding sex classification and age range regression on 1,113 structural magnetic resonance imaging (MRI) datasets. Compared to ML models without the FVS algorithm and with the Boruta algorithm as a variable selection counterpart, we demonstrate that the oFVSD significantly outperformed across all of the ML models over the counterpart models without FVS (approximately 0.20 increase in correlation coefficient, r, with regression models and 8% increase in classification models on average) and with Boruta variable selection algorithm (approximately 0.07 improvement in regression and 4% in classification models). Furthermore, we confirmed the use of parallel computation considerably reduced the computational burden for the high-dimensional MRI data. Altogether, the oFVSD toolbox efficiently and effectively improves the performance of both classification and regression ML models, providing a use case example on MRI datasets. With its flexibility, oFVSD has the potential for many other modalities in neuroimaging. This open-source and freely available Python package makes it a valuable toolbox for research communities seeking improved decoding accuracy.

Semi-supervised learning for industrial fault detection and diagnosis: A systemic review

The automation of Fault Detection and Diagnosis (FDD) is a central task for many industries today. A myriad of methods are in use, although the most recent leading contenders are data-driven approaches and especially Machine Learning (ML) methods. ML algorithms fall into two main categories: supervised and unsupervised methods, depending on whether or not the instances are labeled with the expected outputs. However, a new approach called Semi-Supervised Learning (SSL) has recently emerged that uses a few labeled instances together with other unlabeled instances for the training process. This new approach can significantly improve the accuracy of conventional ML models for industrial environments where labeled data are scarce. SSL has been tested as a promising solution over the past few years for several FDD problems, although there have been no systemic reviews of this sort of approach up until the present review. In this study, an attempt to organize the existing literature on SSL for FDD using the taxonomy of van Engelen & Hoos is reported. The most and the least frequently used SSL algorithms are identified and considered in terms of different fault detection tasks and their most common dataset structure. Moreover, a set of best practices are proposed in the conclusions of this work for implementation under real industrial conditions, so as to avoid some of the most common faults.

Deep learning models for assisted decision-making in performance optimization of thin film nanocomposite membranes

The performance of thin film nanocomposite nanofiltration membranes (TFNNMs) is frequently constrained by the trade-off between the permeability and rejection/selectivity of the membrane. In this study, to provide assisted decision-making in performance optimization of TFNNMs, we utilized a dataset comprising four categories of impact parameters, including membrane manufacturing conditions, membrane performance, nanoparticle material performance, and organic solvent nanofiltration conditions, and trained a dual output neural network (D-ANN) to simulate the relative permeability (RP) and relative rejection/selectivity (RR) of TFNNMs. The D-ANN model outperformed conventional machine learning models and single-output neural networks in predicting both RP and RR, indicating its potential in uncovering correlations between output variables. The Shapley additive explanation method was employed to elucidate the contribution and marginal effects of each influencing parameter on RP and RR, among them, NP size, NP loading, water contact angle, and chloride concentration were influential parameters that are important for both RP and RR. Based on the D-ANN model, we extrapolated two sets of unknown data and achieved good predictive performance (RP-error <15%, RS-error <7% for most sample points). Furthermore, we observed that the predicted performance of the data points rarely exceeded the actual performance, indicating a low probability of overestimation. Based on these premises, the influential parameters can be optimized using the D-ANN model, which ultimately led to exceptional performance for a total of 22 datasets in four pairs of organic solvent and solute purifications guided by the D-ANN model. This study demonstrates that the D-ANN model can provide decisions for the performance optimization of TFNNMs while highlighting the enhancement of nanofiltration performance by thin film nanocomposites, significantly facilitating the design of high-performance TFNNMs.

Leaf water content determination of oilseed rape using near-infrared hyperspectral imaging with deep learning regression methods

Water content is crucial for plant growth. Determination of water content can help monitor plant growth status. In this study, spectral data in the range of 900–1700 nm acquired by near-infrared hyperspectral imaging and corrected by black-white calibration were used to detect the water content of fresh oilseed rape leaves. The oilseed leaves were analyzed without particular treatments. Conventional machine learning (support vector regression, partial least squares regression and least absolute shrinkage and selection operator) and deep learning regression models (Convolutional Neural Network and Long Short-Term Memory) were developed to predict oilseed rape leaf water content. The performance of CNN-LSTM-R was highly accurate. The coefficient of determination and root mean square error of the testing set (RMSEP) were 0.814 and 0.005, respectively. The characteristic wavelengths with strong correlation with water content prediction of the regression models were analyzed. The results showed that the deep learning-based regression models showed great potential for water content determination of oilseed rape leaves. Therefore, this study provides an important theoretical basis and practical application for the detection of fresh plant water content.

A Cost-Based Dual ConvNet-Attention Transfer Learning Model for ECG Heartbeat Classification

The heart is a very crucial organ of the body. Concerted efforts are constantly put forward to provide adequate monitoring of the heart. A heart disorder is reported to cause a lot of hidden ailments resulting in numerous deaths. Early heart monitoring using an electrocardiogram (ECG) through the advancement of computer-aided diagnostic (CAD) systems is widely used. Meanwhile, the use of human reading of ECG results are faced with many challenges of inaccurate and unreliable interpretations. Over two decades, studies provided artificial intelligence (AI) technique using machine learning (ML) algorithms as a fast and reliable technique for ECG heartbeat classification. Moreover, in recent times, deep learning (DL) techniques have been focused on providing automatic feature extraction and better classification performance. On the other hand, the challenge with the ECG data is its imbalance nature. Therefore, this paper proposes a cost-based dual convolutional attention transfer DL model for ECG classification. The proposed model uses PhysionNet-MIT-BIH and Physikalisch-Technische Bundesanstalt (PTB) Diagnostics datasets. The first part uses the MIT-BIH for ECG categorization, while representations learned from the first classifier are used for PTB analysis through transfer learning (TL). The proposed model is evaluated and compared with well-performing conventional ML models based on their F1-score and accuracy scores. Our experimental finding show that the proposed model outperformed the well-performing ML models as well as competitive with past studies for both the classification and TL part, having obtained 98.45% for both F1-score and accuracy. The proposed model is applicable to real-life trials and experiments for ECG heartbeat and other similar domains.

Phenotyping agronomic and physiological traits in peanut under mid‐season drought stress using UAV‐based hyperspectral imaging and machine learning

AbstractAgronomic and physiological traits in peanut (Arachis hypogaea) are important to breeders for selecting high‐yielding and resilient genotypes. However, direct measurement of these traits is labor‐intensive and time‐consuming. This study assessed the feasibility of using unmanned aerial vehicles (UAV)‐based hyperspectral imaging and machine learning (ML) techniques to predict three agronomic traits (biomass, pod count, and yield) and two physiological traits (photosynthesis and stomatal conductance) in peanut under drought stress. Two different approaches were evaluated. The first approach employed eighty narrowband vegetation indices as input features for an ensemble model that included K‐nearest neighbors, support vector regression, random forest, and multi‐layer perceptron (MLP). The second approach utilized mean and standard deviation of canopy spectral reflectance per band. The resultant 400 features were used to train a deep learning (DL) model consisting of one‐dimensional convolutional layers followed by an MLP regressor. Predictions of the agronomic traits obtained using feature learning and DL (R2 = 0.45–0.73; symmetric mean absolute percentage error [sMAPE] = 24%–51%) outperformed those obtained using feature engineering and conventional ML models (R2 = 0.44–0.61, sMAPE = 27%–59%). In contrast, the ensemble model had a slightly better performance in predicting physiological traits (R2 = 0.35–0.57; sMAPE = 37%–70%) compared to the results obtained from the DL model (R2 = 0.36–0.52; sMAPE = 47%–64%). The results showed that the combination of UAV‐based hyperspectral imaging and ML techniques have the potential to assist breeders in rapid screening of genotypes for improved yield and drought tolerance in peanut.

An ensemble-based framework for mispronunciation detection of Arabic phonemes

Determination of mispronunciations and ensuring feedback to users are maintained by computer-assisted language learning (CALL) systems. In this work, we introduce an ensemble model that defines the mispronunciation of Arabic phonemes and assists learning of Arabic, effectively. To the best of our knowledge, this is the very first attempt to determine the mispronunciations of Arabic phonemes employing ensemble learning techniques and conventional machine learning models, comprehensively. In order to observe the effect of feature extraction techniques, mel-frequency cepstrum coefficients (MFCC), and Mel-spectrogram are blended with each learning algorithm. To show the success of proposed model, 29 letters in the Arabic phonemes, 8 of which are hafiz, are voiced by a total of 11 different person. The amount of data set has been enhanced employing the methods of adding noise, time shifting, time stretching, pitch shifting. Extensive experiment results demonstrate that the utilization of voting classifier as an ensemble algorithm with Mel-spectrogram feature extraction technique exhibits remarkable classification result with 95.9% of accuracy.

Evaluating the Use of Graph Neural Networks and Transfer Learning for Oral Bioavailability Prediction.

Oral bioavailability is a pharmacokinetic property that plays an important role in drug discovery. Recently developed computational models involve the use of molecular descriptors, fingerprints, and conventional machine-learning models. However, determining the type of molecular descriptors requires domain expert knowledge and time for feature selection. With the emergence of the graph neural network (GNN), models can be trained to automatically extract features that they deem important. In this article, we exploited the automatic feature selection of GNN to predict oral bioavailability. To enhance the prediction performance of GNN, we utilized transfer learning by pre-training a model to predict solubility and obtained a final average accuracy of 0.797, an F1 score of 0.840, and an AUC-ROC of 0.867, which outperformed previous studies on predicting oral bioavailability with the same test data set.

RETRACTED ARTICLE: A Computational Model for Predicting Customer Behaviors Using Transformer Adapted with Tabular Features

The recent decade has seen an explosion in the e-commerce industry with the support of modern technologies (e.g., artificial intelligence) to maximize conversion rates. Many recommendation systems, therefore, have been developed to predict the customer behaviors to take appropriate actions. Customization of promotions or items for distinct groups of online customers considerably contributes to enhancing the sales. The purchasing records are essential information that can be used to investigate the customer behaviors. These kinds of information, however, are mainly expressed in tubular forms. Several computational models were developed using conventional machine learning algorithms to deal with that data type. However, these approaches struggle with large-volume and high-dimensional data, feature engineering, and high computational cost. In our study, we propose a deep learning model based on the Feature Tokenizer Transformer architecture to predict the customer purchasing intention. This novel architecture is a simplified adaptive version of the Transformer tabular data. The results demonstrated that our model showed better performance compared to conventional machine learning models. Furthermore, the model’s stability was also confirmed by the results of multiple repeated experiments.

A review of SARS-CoV-2 drug repurposing: databases and machine learning models.

The emergence of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) posed a serious worldwide threat and emphasized the urgency to find efficient solutions to combat the spread of the virus. Drug repurposing has attracted more attention than traditional approaches due to its potential for a time- and cost-effective discovery of new applications for the existing FDA-approved drugs. Given the reported success of machine learning (ML) in virtual drug screening, it is warranted as a promising approach to identify potential SARS-CoV-2 inhibitors. The implementation of ML in drug repurposing requires the presence of reliable digital databases for the extraction of the data of interest. Numerous databases archive research data from studies so that it can be used for different purposes. This article reviews two aspects: the frequently used databases in ML-based drug repurposing studies for SARS-CoV-2, and the recent ML models that have been developed for the prospective prediction of potential inhibitors against the new virus. Both types of ML models, Deep Learning models and conventional ML models, are reviewed in terms of introduction, methodology, and its recent applications in the prospective predictions of SARS-CoV-2 inhibitors. Furthermore, the features and limitations of the databases are provided to guide researchers in choosing suitable databases according to their research interests.

A Fine-Tuned Hybrid Stacked CNN to Improve Bengali Handwritten Digit Recognition

Recognition of Bengali handwritten digits has several unique challenges, including the variation in writing styles, the different shapes and sizes of digits, the varying levels of noise, and the distortion in the images. Despite significant improvements, there is still room for further improvement in the recognition rate. By building datasets and developing models, researchers can advance state-of-the-art support, which can have important implications for various domains. In this paper, we introduce a new dataset of 5440 handwritten Bengali digit images acquired from a Bangladeshi University that is now publicly available. Both conventional machine learning and CNN models were used to evaluate the task. To begin, we scrutinized the results of the ML model used after integrating three image feature descriptors, namely Binary Pattern (LBP), Complete Local Binary Pattern (CLBP), and Histogram of Oriented Gradients (HOG), using principal component analysis (PCA), which explained 95% of the variation in these descriptors. Then, via a fine-tuning approach, we designed three customized CNN models and their stack to recognize Bengali handwritten digits. On handcrafted image features, the XGBoost classifier achieved the best accuracy at 85.29%, an ROC AUC score of 98.67%, and precision, recall, and F1 scores ranging from 85.08% to 85.18%, indicating that there was still room for improvement. On our own data, the proposed customized CNN models and their stack model surpassed all other models, reaching a 99.66% training accuracy and a 97.57% testing accuracy. In addition, to robustify our proposed CNN model, we used another dataset of Bengali handwritten digits obtained from the Kaggle repository. Our stack CNN model provided remarkable performance. It obtained a training accuracy of 99.26% and an almost equally remarkable testing accuracy of 96.14%. Without any rigorous image preprocessing, fewer epochs, and less computation time, our proposed CNN model performed the best and proved the most resilient throughout all of the datasets, which solidified its position at the forefront of the field.

Acoustic signal based water leakage detection system using hybrid machine learning model

ABSTRACT Water supply pipeline leakage is a major issue around the world. Leak detection and remediation can prevent water scarcity and some other problems. As a result, investigating pipeline leak-detecting technology has a high practical value. This study employs a promising technique for detecting pipeline leaks using Acoustic Emission (AE) signals. A dytran acceleration sensor was used to collect leakage signals in the time domain. The time-domain signal is transformed into a frequency domain by employing Fast Fourier Transform (FFT). The produced frequency signal has many dimensions which can be reduced to 17 by Principal Component Analysis (PCA). Intelligent leakage diagnosis techniques should eliminate time, and human intervention, and increase effectiveness. Machine learning (ML) models come into play at this point. To detect leakage, the hybrid ML model is proposed and it is compared with the conventional ML models. The best model for detecting water leakage is identified using the classification metrics.

Materials fatigue prediction using graph neural networks on microstructure representations

The local prediction of fatigue damage within polycrystals in a high-cycle fatigue setting is a long-lasting and challenging task. It requires identifying grains tending to accumulate plastic deformation under cyclic loading. We address this task by transcribing ferritic steel microtexture and damage maps from experiments into a microstructure graph. Here, grains constitute graph nodes connected by edges whenever grains share a common boundary. Fatigue loading causes some grains to develop slip markings, which can evolve into microcracks and lead to failure. This data set enables applying graph neural network variants on the task of binary grain-wise damage classification. The objective is to identify suitable data representations and models with an appropriate inductive bias to learn the underlying damage formation causes. Here, graph convolutional networks yielded the best performance with a balanced accuracy of 0.72 and a F1-score of 0.34, outperforming phenomenological crystal plasticity (+ 68%) and conventional machine learning (+ 17%) models by large margins. Further, we present an interpretability analysis that highlights the grains along with features that are considered important by the graph model for the prediction of fatigue damage initiation, thus demonstrating the potential of such techniques to reveal underlying mechanisms and microstructural driving forces in critical grain ensembles.

Predicting the Gas Permeability of Sustainable Cement Mortar Containing Internal Cracks by Combining Physical Experiments and Hybrid Ensemble Artificial Intelligence Algorithms.

The presence of internal fissures holds immense sway over the gas permeability of sustainable cement mortar, which in turn dictates the longevity and steadfastness of associated edifices. Nevertheless, predicting the gas permeability of sustainable cement mortar that contains internal cracks poses a significant challenge due to the presence of numerous influential variables and intricate interdependent mechanisms. To solve the deficiency, this research establishes an innovative machine learning algorithm via the integration of the Mind Evolutionary Algorithm (MEA) with the Adaptive Boosting Algorithm-Back Propagation Artificial Neural Network (ABA-BPANN) ensemble algorithm to predict the gas permeability of sustainable cement mortar that contains internal cracks, based on the results of 1452 gas permeability tests. Firstly, the present study employs the MEA-tuned ABA-BPANN model as the primary tool for gas permeability prediction in cement mortar, a comparative analysis is conducted with conventional machine learning models such as Particle Swarm Optimisation Algorithm (PSO) and Genetic Algorithm (GA) optimised ABA-BPANN, MEA optimised Extreme Learning Machine (ELM), and BPANN. The efficacy of the MEA-tuned ABA-BPANN model is verified, thereby demonstrating its proficiency. In addition, the sensitivity analysis conducted with the aid of the innovative model has revealed that the gas permeability of durable cement mortar incorporating internal cracks is more profoundly affected by the dimensions and quantities of such cracks than by the stress conditions to which the mortar is subjected. Thirdly, puts forth a novel machine-learning model, which enables the establishment of an analytical formula for the precise prediction of gas permeability. This formula can be employed by individuals who lack familiarity with machine learning skills. The proposed model, namely the MEA-optimised ABA-BPANN algorithm, exhibits significant potential in accurately estimating the gas permeability of sustainable cement mortar that contains internal cracks in varying stress environments. The study highlights the algorithm's ability to offer essential insights for designing related structures.