Search

Diabetes is a chronic disease that can cause several forms of chronic damage to the human body, including heart problems, kidney failure, depression, eye damage, and nerve damage. There are several risk factors involved in causing this disease, with some of the most common being obesity, age, insulin resistance, and hypertension. Therefore, early detection of these risk factors is vital in helping patients reverse diabetes from the early stage to live healthy lives. Machine learning (ML) is a useful tool that can easily detect diabetes from several risk factors and, based on the findings, provide a decision-based model that can help in diagnosing the disease. This study aims to detect the risk factors of diabetes using ML methods and to provide a decision support system for medical practitioners that can help them in diagnosing diabetes. Moreover, besides various other preprocessing steps, this study has used the synthetic minority over-sampling technique integrated with the edited nearest neighbor (SMOTE-ENN) method for balancing the BRFSS dataset. The SMOTE-ENN is a more powerful method than the individual SMOTE method. Several ML methods were applied to the processed BRFSS dataset and built prediction models for detecting the risk factors that can help in diagnosing diabetes patients in the early stage. The prediction models were evaluated using various measures that show the high performance of the models. The experimental results show the reliability of the proposed models, demonstrating that k-nearest neighbor (KNN) outperformed other methods with an accuracy of 98.38%, sensitivity, specificity, and ROC/AUC score of 98%. Moreover, compared with the existing state-of-the-art methods, the results confirm the efficacy of the proposed models in terms of accuracy and other evaluation measures. The use of SMOTE-ENN is more beneficial for balancing the dataset to build more accurate prediction models. This was the main reason it was possible to achieve models more accurate than the existing ones., Competing Interests: There are no conflicts of interest., (Copyright © 2022 Zahid Ullah et al.)

Brain tumor classification plays an important role in clinical diagnosis and effective treatment. In this work, we propose a method for brain tumor classification using an ensemble of deep features and machine learning classifiers. In our proposed framework, we adopt the concept of transfer learning and uses several pre-trained deep convolutional neural networks to extract deep features from brain magnetic resonance (MR) images. The extracted deep features are then evaluated by several machine learning classifiers. The top three deep features which perform well on several machine learning classifiers are selected and concatenated as an ensemble of deep features which is then fed into several machine learning classifiers to predict the final output. To evaluate the different kinds of pre-trained models as a deep feature extractor, machine learning classifiers, and the effectiveness of an ensemble of deep feature for brain tumor classification, we use three different brain magnetic resonance imaging (MRI) datasets that are openly accessible from the web. Experimental results demonstrate that an ensemble of deep features can help improving performance significantly, and in most cases, support vector machine (SVM) with radial basis function (RBF) kernel outperforms other machine learning classifiers, especially for large datasets.

Electricity theft damages power grid infrastructure and is also responsible for huge revenue losses for electric utilities. Integrating smart meters in traditional power grids enables real-time monitoring and collection of consumers' electricity consumption (EC) data. Based on the collected data, it is possible to identify the normal and malicious behavior of consumers by analyzing the data using machine learning (ML) and deep learning methods. This paper proposes a deep learning-based meta-learner model to distinguish between normal and malicious patterns in EC data. The proposed model consists of two stages. In Fold-0, the ML classifiers extract diverse knowledge and learns based on EC data. In Fold-1, a multilayer perceptron is used as a meta-learner, which takes the prediction results of Fold-0 classifiers as input, automatically learns non-linear relationships among them, and extracts hidden complicated features to classify normal and malicious behaviors. Therefore, the proposed model controls the overfitting problem and achieves high accuracy. Moreover, extensive experiments are conducted to compare its performance with boosting, bagging, standalone conventional ML classifiers, and baseline models published in toptier outlets. The proposed model is evaluated using a real EC dataset, which is provided by the Energy Informatics Group in Pakistan. The model achieves 0.910 ROC-AUC and 0.988 PR-AUC values on the test dataset, which are higher than those of the compared models. [ABSTRACT FROM AUTHOR]

Automatic COVID-19 detection using chest X-ray (CXR) can play a vital part in large-scale screening and epidemic control. However, the radiographic features of CXR have different composite appearances, for instance, diffuse reticular-nodular opacities and widespread ground-glass opacities. This makes the automatic recognition of COVID-19 using CXR imaging a challenging task. To overcome this issue, we propose a densely attention mechanism-based network (DAM-Net) for COVID-19 detection in CXR. DAM-Net adaptively extracts spatial features of COVID-19 from the infected regions with various appearances and scales. Our proposed DAM-Net is composed of dense layers, channel attention layers, adaptive downsampling layer, and label smoothing regularization loss function. Dense layers extract the spatial features and the channel attention approach adaptively builds up the weights of major feature channels and suppresses the redundant feature representations. We use the cross-entropy loss function based on label smoothing to limit the effect of interclass similarity upon feature representations. The network is trained and tested on the largest publicly available dataset, i.e., COVIDx, consisting of 17,342 CXRs. Experimental results demonstrate that the proposed approach obtains state-of-the-art results for COVID-19 classification with an accuracy of 97.22%, a sensitivity of 96.87%, a specificity of 99.12%, and a precision of 95.54%. [ABSTRACT FROM AUTHOR]

This study presents an integrated hybrid framework of data-driven (cascade forward neural network (CFNN)), metaheuristic (artificial bee colony (ABC)), and a mechanistic modeling (Aspen simulation) approach for the biomass pyrolysis process for bio-oil production. We applied CFNN and an ABC to predict and optimize bio-oil yield. The CFNN model achieved high prediction performance with a correlation coefficient value of 0.95 and a root mean squared error value of 0.39. Furthermore, the CFNN-ABC derived optimum parameters were then validated using a mechanistic model of the pyrolysis process. The CFNN and Aspen simulation results were following the experimental results, with an average deviation of 5%. The feature importance showed that the internal information about biomass was more relevant than external factors for bio-oil yield. The partial dependence plots were developed to know the insights into the biomass pyrolysis process. This study presents a modeling and simulation platform for bio-oil production that can increase the waste-to-energy process and can be helpful for academia. [Display omitted] [ABSTRACT FROM AUTHOR]

Cricket databases contain rich and useful information to examine and forecasting patterns and trends. This paper predicts Star Cricketers (SCs) from batting and bowling domains by employing supervised machine learning models. With this aim, each player's performance evolution is retrieved by using effective features that incorporate the standard performance measures of each player and their peers. Prediction is performed by applying Bayesianrule, function and decision-tree-based models. Experimental evaluations are performed to validate the applicability of the proposed approach. In particular, the impact of the individual features on the prediction of SCs are analyzed. Moreover, the category and model-wise feature evaluations are also conducted. A cross-validation mechanism is applied to validate the performance of our proposed approach which further confirms that the incorporated features are statistically significant. Finally, leading SCs are extracted based on their performance evolution scores and their standings are cross-checked with those provided by the International Cricket Council. [ABSTRACT FROM AUTHOR]

This document is a corrigendum for an article titled "Deep learning-based meta-learner strategy for electricity theft detection." The correction addresses an error in the spelling of one of the author's names, which should be "Musaed Alhussein" instead of "Musaed Alhussain." The authors apologize for the mistake and clarify that it does not affect the scientific conclusions of the article. The corrigendum also includes information about the publication date and citation details. The document concludes with a note stating that the views expressed in the article are solely those of the authors and do not necessarily represent the publisher or affiliated organizations. [Extracted from the article]

[Display omitted] • ANN coupled with metaheuristic algorithms were used to predict biochar yield. • ANN integrated with Rao-2 algorithm outperformed all other models (R2 ∼ 0.93). • Pyrolysis temperature and residence time were the most important features. • Partial dependence analysis revealed inside details for the pyrolysis process. • An easy-to-use graphical user interface was developed for biochar yield prediction. In this study, an integrated framework of artificial neural networks (ANNs) and metaheuristic algorithms have been developed for the prediction of biochar yield using biomass characteristics and pyrolysis process conditions. Comparative analysis of six different metaheuristic algorithms was performed to optimize the ANN architecture and select important features. The results suggested that the ANN model coupled with the Rao-2 algorithm outperformed (R2 ∼ 0.93, RMSE ∼ 1.74%) all other models. Furthermore, the detailed information behind the models was acquired, identifying the most influencing factors as follows: pyrolysis temperature (56%), residence time (23%), and heating rate (8%). The partial dependence plot analysis revealed how each influencing factor affected the target variable. Finally, an easy-to-use software tool for predicting biochar yield was built using the ANN-Rao-2 model. This study demonstrates huge potential that machine learning presents in predictive modelling of complex pyrolysis processes, and reduces the time-consuming and expensive experimental work for estimating the biochar yield. [ABSTRACT FROM AUTHOR]

Electronic learning management systems provide live environments for students and faculty members to connect with their institutional online portals and perform educational activities virtually. Although modern technologies proactively support these online sessions, students' active participation remains a challenge that has been discussed in previous research. Additionally, one concern for both parents and teachers is how to accurately measure student performance using different attributes collected during online sessions. Therefore, the research idea undertaken in this study is to understand and predict the performance of the students based on features extracted from electronic learning management systems. The dataset chosen in this study belongs to one of the learning management systems providing a number of features predicting student's performance. The integrated machine learning model proposed in this research can be useful to make proactive and intelligent decisions according to student performance evaluated through the electronic system's data. The proposed model consists of five traditional machine learning algorithms, which are further enhanced by applying four ensemble techniques: bagging, boosting, stacking, and voting. The overall F1 scores of the single models are as follows: DT (0.675), RF (0.777), GBT (0.714), NB (0.654), and KNN (0.664). The model performance has shown remarkable improvement using ensemble approaches. The stacking model by combining all five classifiers has outperformed and recorded the highest F1 score (0.8195) among other ensemble methods. The integration of the ML models has improved the prediction ratio and performed better than all other ensemble approaches. The proposed model can be useful for predicting student performance and helping educators to make informed decisions by proactively notifying the students. [ABSTRACT FROM AUTHOR]

[Display omitted] • A genetic algorithm-based approach was used for feature selection. • Random forest outperformed all other ML models in predicting bio-oil yield. • Analysis of Partial Dependence Plot showed inside details for pyrolysis process. • A Graphical User Interface for predicting bio-oil yield was developed. A novel genetic algorithm-based feature selection approach is incorporated and based on these features, four different ML methods were investigated. According to the findings, ML models could reliably predict bio-oil yield. The results showed that Random forest (RF) is preferred for bio-oil yield prediction (R2 ~ 0.98) and highly recommended when dealing with the complex correlation between variables and target. Multi-Linear regression model showed relatively poor generalization performance (R2 ~ 0.75). The partial dependence analysis was done for ML models to show the influence of each input variable on the target variable. Lastly, an easy-to-use software package was developed based on the RF model for the prediction of bio-oil yield. The current study offered new insights into the pyrolysis process of biomass and to improve bio-oil yield. It is an attempt to reduce the time-consuming and expensive experimental work for estimating the bio-oil yield of biomass during pyrolysis. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) is one of the major driving forces behind the fourth industrial revolution. This study reviews the ML applications in the life cycle stages of biofuels, i.e., soil, feedstock, production, consumption, and emissions. ML applications in the soil stage were mostly used for satellite images of land to estimate the yield of biofuels or a suitability analysis of agricultural land. The existing literature have reported on the assessment of rheological properties of the feedstocks and their effect on the quality of biofuels. The ML applications in the production stage include estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage include analysis of engine performance and estimation of emissions temperature and composition. This study identifies the following trends: the most dominant ML method, the stage of life cycle getting the most usage of ML, the type of data used for the development of the ML-based models, and the frequently used input and output variables for each stage. The findings of this article would be beneficial for academia and industry-related professionals involved in model development in different stages of biofuel's life cycle. [ABSTRACT FROM AUTHOR]

Background: The use of artificial intelligence has revolutionized every area of life such as business and trade, social and electronic media, education and learning, manufacturing industries, medicine and sciences, and every other sector. The new reforms and advanced technologies of artificial intelligence have enabled data analysts to transmute raw data generated by these sectors into meaningful insights for an effective decision-making process. Health care is one of the integral sectors where a large amount of data is generated daily, and making effective decisions based on these data is therefore a challenge. In this study, cases related to childbirth either by the traditional method of vaginal delivery or cesarean delivery were investigated. Cesarean delivery is performed to save both the mother and the fetus when complications related to vaginal birth arise.Objective: The aim of this study was to develop reliable prediction models for a maternity care decision support system to predict the mode of delivery before childbirth.Methods: This study was conducted in 2 parts for identifying the mode of childbirth: first, the existing data set was enriched and second, previous medical records about the mode of delivery were investigated using machine learning algorithms and by extracting meaningful insights from unseen cases. Several prediction models were trained to achieve this objective, such as decision tree, random forest, AdaBoostM1, bagging, and k-nearest neighbor, based on original and enriched data sets.Results: The prediction models based on enriched data performed well in terms of accuracy, sensitivity, specificity, F-measure, and receiver operating characteristic curves in the outcomes. Specifically, the accuracy of k-nearest neighbor was 84.38%, that of bagging was 83.75%, that of random forest was 83.13%, that of decision tree was 81.25%, and that of AdaBoostM1 was 80.63%. Enrichment of the data set had a good impact on improving the accuracy of the prediction process, which supports maternity care practitioners in making decisions in critical cases.Conclusions: Our study shows that enriching the data set improves the accuracy of the prediction process, thereby supporting maternity care practitioners in making informed decisions in critical cases. The enriched data set used in this study yields good results, but this data set can become even better if the records are increased with real clinical data. [ABSTRACT FROM AUTHOR]

The use of renewable energy for power generation is increasing rapidly. However, residual electricity supplied in excess of demand is a global concern. To effectively utilize excess power, storing surplus renewable energy in energy storage systems (ESSs) is important. In this study, a seawater battery (SWB) is proposed as an ESS for intermittent power resources, and its energy storage capability is evaluated. Four charging scenarios that imitate different forms of renewable energy (constant current, solar, tidal, and wind) reveal that SWB is an efficient ESS for intermittent renewable energy sources. Scenario-dependent energy efficiency follows the order: ideal constant current (83.6%) > solar power (80.4%) > tidal power (79.6%) > wind power (79.4%). The ability of two artificial intelligence models is also tested to estimate the potential of SWBs. A novel long short-term memory model outperforms an artificial neural network model, predicting the potential of SWB with a high precision (R2 > 0.99) and an extremely low error rate (<0.18%). Therefore, the conceptualization and modeling of an SWB as an ESS may pave the way for energy storage from and management of intermittent energy sources. The scenario-based research on the energy storage capability of seawater batteries for intermittent power generation systems is experimentally demonstrated and modeled by machine learning algorithms. [Display omitted] • The capability of SWB for renewable energy storage was investigated. • Charging scenarios using solar power had the highest energy storage efficiency. • A deep learning model (LSTM) was trialed to estimate the performance of SWB. • The LSTM model outperformed a neural network in prediction accuracy (R2 > 0.99). [ABSTRACT FROM AUTHOR]

[Display omitted] • Machine learning models can accurately model thermal conversion methods. • Classification, regression, and optimization are involved in thermal conversion. • Artificial neural networks have been the most commonly employed algorithm. • Optimization methods were used for ANN network selection and hyper-parameters. • Hybrid and novel ML algorithms (deep learning) with large databases are expected. Thermochemical conversion of biomass has been considered a promising technique to produce alternative renewable fuel sources for future energy supply. However, these processes are often complex, labor-intensive, and time-consuming. Significant efforts have been made in developing strategies for modeling thermochemical conversion processes to maximize their performance and productivity. Among these strategies, machine learning (ML) has attracted substantial interest in recent years in thermochemical conversion process optimization, yield prediction, real-time monitoring, and process control. This study presents a comprehensive review of the research and development in state-of-the-art ML applications in pyrolysis, torrefaction, hydrothermal treatment, gasification, and combustion. Artificial neural networks have been widely employed due to their ability to learn extremely non-linear input–output correlations. Furthermore, the hybrid ML models outperformed the traditional ML models in modeling and optimization tasks. The comparison between various ML methods for different applications, and insights about where the current research is heading, is highlighted. Finally, based on the critical analysis, existing research knowledge gaps are identified, and future recommendations are presented. [ABSTRACT FROM AUTHOR]

• Applications of Artificial Intelligence in combating COVID-19 pandemic are reviewed. • Comparision of Machine Learning and Deep Learning-based studies are presented. • Focused on COVID-19 screening, diagnosis, prediction, and drug repurposing. • Various challenges and limitations are discussed. During the current global public health emergency caused by novel coronavirus disease 19 (COVID-19), researchers and medical experts started working day and night to search for new technologies to mitigate the COVID-19 pandemic. Recent studies have shown that artificial intelligence (AI) has been successfully employed in the health sector for various healthcare procedures. This study comprehensively reviewed the research and development on state-of-the-art applications of artificial intelligence for combating the COVID-19 pandemic. In the process of literature retrieval, the relevant literature from citation databases including ScienceDirect, Google Scholar, and Preprints from arXiv, medRxiv, and bioRxiv was selected. Recent advances in the field of AI-based technologies are critically reviewed and summarized. Various challenges associated with the use of these technologies are highlighted and based on updated studies and critical analysis, research gaps and future recommendations are identified and discussed. The comparison between various machine learning (ML) and deep learning (DL) methods, the dominant AI-based technique, mostly used ML and DL methods for COVID-19 detection, diagnosis, screening, classification, drug repurposing, prediction, and forecasting, and insights about where the current research is heading are highlighted. Recent research and development in the field of artificial intelligence has greatly improved the COVID-19 screening, diagnostics, and prediction and results in better scale-up, timely response, most reliable, and efficient outcomes, and sometimes outperforms humans in certain healthcare tasks. This review article will help researchers, healthcare institutes and organizations, government officials, and policymakers with new insights into how AI can control the COVID-19 pandemic and drive more research and studies for mitigating the COVID-19 outbreak. [ABSTRACT FROM AUTHOR]