Search

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]

Diabetic retinopathy (DR) is a diabetes complication that can cause vision loss among patients due to damage to blood vessels in the retina. Early retinal screening can avoid the severe consequences of DR and enable timely treatment. Nowadays, researchers are trying to develop automated deep learning-based DR segmentation tools using retinal fundus images to help Ophthalmologists with DR screening and early diagnosis. However, recent studies are unable to design accurate models due to the unavailability of larger training data with consistent and fine-grained annotations. To address this problem, we propose a semi-supervised multitask learning approach that exploits widely available unlabelled data (i.e., Kaggle-EyePACS) to improve DR segmentation performance. The proposed model consists of novel multi-decoder architecture and involves both unsupervised and supervised learning phases. The model is trained for the unsupervised auxiliary task to effectively learn from additional unlabelled data and improve the performance of the primary task of DR segmentation. The proposed technique is rigorously evaluated on two publicly available datasets (i.e., FGADR and IDRiD) and results show that the proposed technique not only outperforms existing state-of-the-art techniques but also exhibits improved generalisation and robustness for cross-data evaluation. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a chronic and common form of dementia that mainly affects elderly individuals. The disease is dangerous because it causes damage to brain cells and tissues before the symptoms appear, and there is nomedicinal or surgical treatment available yet forAD.ADcauses loss of memory and functionality control in multiple degrees according to AD's progression level. However, early diagnosis of AD can hinder its progression. Brain imaging tools such as magnetic resonance imaging (MRI), computed tomography (CT) scans, positron emission tomography (PET), etc. can help in medical diagnosis of AD. Recently, computer-aided diagnosis (CAD) such as deep learning applied to brain images obtained with these tools, has been an established strategic methodology that is widely used for clinical assistance in prognosis of AD. In this study, we proposed an intelligent methodology for building a convolutional neural network (CNN) from scratch to detect AD stages from the brain MRI images dataset and to improve patient care. It is worth mentioning that training a deep-learning model requires a large amount of data to produce accurate results and prevent the model from overfitting problems. Therefore, for better understanding of classifiers and to overcome the model overfitting problem, we applied data augmentation to the minority classes in order to increase the number of MRI images in the dataset. All experiments were conducted using Alzheimer's MRI dataset consisting of brain MRI scanned images. The performance of the proposed model determines detection of the four stages of AD. Experimental results show high performance of the proposed model in that the model achieved a 99.38% accuracy rate, which is the highest so far. Moreover, the proposed model performance in terms of accuracy, precision, sensitivity, specificity, and f-measures is promising when compared to the very recent state-of-the-art domain-specific models existing in the literature. [ABSTRACT FROM AUTHOR]

As tomatoes are the most consumed vegetable in the world, production should be increased to fulfill the vast demand for this vegetable. Global warming, climate changes, and other significant factors, including pests, badly affect tomato plants and cause various diseases that ultimately affect the production of this vegetable. Several strategies and techniques have been adopted for detecting and averting such diseases to ensure the survival of tomato plants. Recently, the application of artificial intelligence (AI) has significantly contributed to agronomy in the detection of tomato plant diseases through leaf images. Deep learning (DL)-based techniques have been largely utilized for detecting tomato leaf diseases. This paper proposes a hybrid DL-based approach for detecting tomato plant diseases through leaf images. To accomplish the task, this study presents the fusion of two pretrained models, namely, EfficientNetB3 and MobileNet (referred to as the EffiMob-Net model) to detect tomato leaf diseases accurately. In addition, model overfitting was handled using various techniques, such as regularization, dropout, and batch normalization (BN). Hyperparameter tuning was performed to choose the optimal parameters for building the best-fitting model. The proposed hybrid EffiMob-Net model was tested on a plant village dataset containing tomato leaf disease and healthy images. This hybrid model was evaluated based on the best classifier with respect to accuracy metrics selected for detecting the diseases. The success rate of the proposed hybrid model for accurately detecting tomato leaf diseases reached 99.92%, demonstrating the model's ability to extract features accurately. This finding shows the reliability of the proposed hybrid model as an automatic detector for tomato plant diseases that can significantly contribute to providing better solutions for detecting other crop diseases in the field of agriculture. [ABSTRACT FROM AUTHOR]

The Kingdom of Saudi Arabia is considered to be one of the world leaders in olive production accounting for about 6% of the global olive production. Given the fact that 94% of the olive groves are mainly rain-fed using traditional methods of production, the annual olive production is witnessing a noticeable fluctuation which is worse due to infectious diseases and climate change. Thus, early and effective detection of plant diseases is both required and urgent. Most farmers use traditional methods, for example, visual inspection or laboratory examination, to identify plant diseases. Currently, deep learning (DL) techniques have been shown to be useful methods for diagnosing olive leaf diseases and many other fields. In this work, we use a deep feature concatenation (DFC) mechanism to combine features extracted from input images using the two modern pretrained CNN models, i.e., ResNet50 and MobileNet. Hence, we propose MobiRes-Net: A neural network that is a concatenation of the ResNet50 and MobileNet models for overall improvement of prediction capability. To build the dataset used in the study, 5400 olive leaf images were collected from an olive grove using a remote-controlled agricultural unmanned aerial vehicle (UAV) equipped with a camera. The overall performance of the MobiRes-Net model achieved a classification accuracy of 97.08% which showed its superiority over ResNet50 and MobileNet that achieved classification accuracies of 94.86% and 95.63%, respectively. [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]

Capacitive deionization (CDI) is an emerging technique for water treatment and electroadsorption processes (i.e., brackish water desalination). Various numerical modeling methods have been developed to predict and optimize the performance of CDI, and artificial intelligence techniques have recently been applied to overcome the limitations of numerical modelings, such as the difficulty in handling all complexities in the environment. However, such a complex neural network (i.e., deep learning (DL)) has limitations in that it is difficult to design a structure, takes a long time to train, and requires massive computer resources. Therefore, in this study, a tree-based model that is more effective than a neural network model for processing tabular data was developed to predict effluent pH and concentration in the CDI process. The tree-based ensemble models had a remarkably lower computational cost (100 times less than the DL model) with almost the same prediction accuracy (R2 = 0.998 for the steady random forest model and R2 = 0.986 for the DL model) using a binary feature concept. These findings will contribute to further examining the use of tree-based models for predicting and optimizing the CDI process to reduce computing capacity and minimize modeling complexity. [Display omitted] • Artificial intelligence models were compared for capacitive deionization. • The effluent pH and concentration were predicted. • Tree-based and deep learning models showed almost the same prediction accuracy. • Tree-based ensemble models required a remarkably lower computational cost. [ABSTRACT FROM AUTHOR]

Efficient diagnosis of COVID-19 plays an important role in preventing the spread of the disease. There are three major modalities to diagnose COVID-19 which include polymerase chain reaction tests, computed tomography scans, and chest X-rays (CXRs). Among these, diagnosis using CXRs is the most economical approach; however, it requires extensive human expertise to diagnose COVID-19 in CXRs, which may deprive it of cost-effectiveness. The computer-aided diagnosis with deep learning has the potential to perform accurate detection of COVID-19 in CXRs without human intervention while preserving its cost-effectiveness. Many efforts have been made to develop a highly accurate and robust solution. However, due to the limited amount of labeled data, existing solutions are evaluated on a small set of test dataset. In this work, we proposed a solution to this problem by using a multi-task semi-supervised learning (MTSSL) framework that utilized auxiliary tasks for which adequate data is publicly available. Specifically, we utilized Pneumonia, Lung Opacity, and Pleural Effusion as additional tasks using the ChesXpert dataset. We illustrated that the primary task of COVID-19 detection, for which only limited labeled data is available, can be improved by using this additional data. We further employed an adversarial autoencoder (AAE), which has a strong capability to learn powerful and discriminative features, within our MTSSL framework to maximize the benefit of multi-task learning. In addition, the supervised classification networks in combination with the unsupervised AAE empower semi-supervised learning, which includes a discriminative part in the unsupervised AAE training pipeline. The generalization of our framework is improved due to this semi-supervised learning and thus it leads to enhancement in COVID-19 detection performance. The proposed model is rigorously evaluated on the largest publicly available COVID-19 dataset and experimental results show that the proposed model attained state-of-the-art performance. • The automated detection of COVID-19 using chest X-rays. • A novel MTL-based adversarial semi-supervised framework to address the smaller size of data. • We focus to utilize the unlabeled data to improve the performance as well as the generalization of the system. • Model was developed using publicly available datasets i.e., CheXpert and COVIDx. • The proposed method outperforms the standard state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

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. [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]