Search

Early detection of brain tumors can save precious human life. This work presents a fully automated design to classify brain tumors. The proposed scheme employs optimal deep learning features for the classification of FLAIR, T1, T2, and T1CE tumors. Initially, we normalized the dataset to pass them to the ResNet101 pretrained model to perform transfer learning for our dataset. This approach results in fine-tuning the ResNet101 model for brain tumor classification. The problem with this approach is the generation of redundant features. These redundant features degrade accuracy and cause computational overhead. To tackle this problem, we find optimal features by utilizing differential evaluation and particle swarm optimization algorithms. The obtained optimal feature vectors are then serially fused to get a single-fused feature vector. PCA is applied to this fused vector to get the final optimized feature vector. This optimized feature vector is fed as input to various classifiers to classify tumors. Performance is analyzed at various stages. Performance results show that the proposed technique achieved a speedup of 25.5x in prediction time on the medium neural network with an accuracy of 94.4%. These results show significant improvement over the state-of-the-art techniques in terms of computational overhead by maintaining approximately the same accuracy., Competing Interests: All authors declare that they have no conflicts of interest., (Copyright © 2022 Usman Zahid et al.)

Abstract The gradual decline of production of the major fields of the Indus Basin has influenced the field pressure. Therefore, the prospects need to be assessed by the petro-elastic relationship. This study highlights the value-addition for identifying gas pockets within the E-Sand of the Lower Goru Formation through estimating and populating petro-elastic properties. A probabilistic neural network (PNN) was employed to develop the relationship of pore pressure to the inverted properties. The outcomes will help identify the high-pressure areas in accordance with the petro-elastic relationship for optimizing production strategy. In order to evaluate the petro-elastic relationship, stochastic seismic inversion was employed to holistically capture the reservoir’s variability. Pore pressure volumetric was estimated from inverted attributes using a PNN, a non-linear algorithm that was more suited to heterogeneous reservoirs. The main objective of the research is achieved via enhanced resolution of elastic properties attained through the integration of stochastic inversion and PNN processes. The high-resolution elastic properties including P-impedance, S-impedance, and Vp/Vs ratio can delineate the heterogeneities more profoundly. The petrophysical volumes obtained via enhanced inverted properties combined with pore-pressure through PNN illuminated the potential facies and the correlations in predicting the properties. The procedure provides a linkage of elastic, petrophysical, and geomechanical properties that is helpful for professionals covering a broad field of the petroleum sector. The developed workflow can be followed globally where problems occur regarding heterogeneities and early depletion.

Predicting wind energy production accurately is crucial for enhancing grid management and dispatching capacity. However, the inherent unpredictability of wind speed poses significant challenges to achieving high prediction accuracy.To address this challenge, this study introduces a novel pre-processing framework that leverages thirteen nature-inspired optimization algorithms to extract and combine Intrinsic Mode Functions (IMFs) of atmospheric and wind speed variables. The objective function ensures that the selected IMF combinations exhibit high correlation, enhancing their predictive relevance.The outputs of these algorithms are further refined using the proposed Optimal Search IMF (OAIMF) algorithm, which reduces redundancy and selects a minimal yet highly relevant set of IMF combinations for wind speed prediction.The methodology was validated through a case study conducted at the Climate, Energy, and Water Research Institute (CEWRI), NARC, Islamabad, Pakistan, leveraging real-world atmospheric data.Experimental results demonstrate that the proposed framework significantly outperforms direct prediction methods and state-of-the-art pre-processing techniques. For instance, the framework achieved an RMSE of 2.73 on an LSTM network and 3.86 on a GRU network, compared to RMSE values of 19.78 and 18.89, respectively, for direct prediction. Superior performance was also observed across MAE, MAPE, and R2 metrics.This study highlights the critical role of robust pre-processing in enhancing deep learning-based wind speed prediction. By integrating nature-inspired optimization with a novel IMF selection strategy, the proposed approach advances the state-of-the-art in renewable energy forecasting.

Cybersecurity is gaining a high position in the IT sector. Connecting more devices to the internet smooths the way for hackers. It is hard for signature-based security tools to detect new attacks that emerge and evolve with slight changes. Researchers are trying to build a Network Intrusion Detection System (NIDS) that can accurately detect the zero-day attacks evolved through minor changes. An anomaly-based NIDS has attracted researchers to develop a system to detect malign traffic in a network using Machine Learning (ML) models. Therefore, in recent years, the designs of modern NIDS for higher detection rates and lower false alarms have been refined by utilizing advanced ML and Deep Learning (DL) approaches. However, it is still a problem for the supervised and unsupervised algorithms to achieve high performance, absolute accuracy, and minimal false alarm rate. This work aims to design an effective NIDS that addresses the current limitation using machine learning models trained on reliable flow-based data (CICIDS-2017). The system will improve the detection accuracy and reduce false alarms in high-speed network environments. To achieve results, the dataset has been balanced using the SMOTE-Tomek Links technique. After cleaning and organizing the dataset, the trained algorithms are Decision Tree, Random Forest, XGBoost, K-Nearest Neighbor, Naive Bayes, Logistic Regression, and AdaBoost algorithm. These algorithms are pulled from literature studies because of their exceptional performance on old datasets. This work has achieved a Decision Tree model with 96.37% accuracy and 96.33% F1-score and the AdaBoost model with 96.37% accuracy and 96.33% F1-score for multiclass classification. For binary classification, the Decision Tree (DT) model has exhibited the highest test accuracy of 99.96%, followed by Random Forest (99.84%), Adaboost (99.77%), and Xgboost (99.57), with the highest average precision of 100% and ROC-AUC of 99.96%. We have also found that binary classification performs better when it takes more time to train each classifier than multiclass classification. This research study incorporates proper validation of the models and achieves high accuracy and exact results compared to the literature. The results show that a balanced CICIDS-2017 dataset improves the performance of decision trees and AdaBoost classifiers. The emplacement of NIDS in networks and their underlying technology are equally significant for detecting real-time attacks.

Enhancing model performance in agricultural image analysis faces challenges due to limited datasets, biological variability, and uncontrolled environments. Deep learning models require large, realistic datasets, which are often difficult to obtain. Data augmentation, especially through Generative Adversarial Networks (GANs), has become essential in farming applications, generating synthetic images to improve model training and reduce the need for extensive image collection. This review explores various GAN approaches for image augmentation in farming, investigating their challenges and limitations. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 128 publications were analyzed to identify research trends and gaps in GAN applications within the farming industry. Key applications of GANs include plant classification, weed detection, animal detection and behavior recognition, animal health and disease analysis, plant disease detection, phenotyping, and fruit quality assessment. Persistent issues like limited training datasets, occlusion challenges, and imbalanced data hinder model performance across these applications. Recognizing these challenges is critical for enhancing the efficiency and effectiveness of farming operations. Finally, this review concludes with insights and future directions to foster progress in this field.

Nowadays global market products are readily accessible worldwide, and a vast array of reviews across numerous platforms are posted daily in several categories, making it challenging for customers to stay informed about their product interests. To make informed decisions regarding product quality, users require access to reviews and ratings. Owners and managers must analyze customer ratings and the underlying emotional content of reviews to enhance the product’s quality, cost, customer service, and environmental impact. The primary aim of our proposed research is to accurately predict product helpfulness through customer reviews using the Large Language Model (LLM), thereby assisting customers in saving time and money. We employed a benchmark dataset, the Amazon Fine Food Reviews, to develop numerous advanced machine-learning techniques. We introduced a novel transformer approach BERF (BERT Random Forest) for feature engineering to enhance the value of user evaluations for Amazon’s gourmet food products. The BERF method utilizes BERT embeddings and class probability features derived from product helpfulness online reviews textual data. We have balanced the dataset using the Synthetic Minority Over-sampling TEchnique (SMOTE) approach. Our comprehensive study results demonstrated that the Light Gradient Boosting Machine (LGBM) strategy outperformed existing state-of-the-art approaches, achieving an accuracy of 98%. The performance of each method is confirmed using a k-fold method and further improved through hyperparameter optimization. Our innovative study employing a transformer model has significantly enhanced the utility of customer reviews, substantially reducing online product scams and preventing wasted time and money.

Depression constitutes a significant mental health condition, impacting an individual’s emotional state, thought processes, and ability to carry out everyday tasks. Depression is defined by ongoing feelings of sadness, diminished interest in previously enjoyed activities, alterations in hunger, sleep disturbances, decreased vitality, and challenges with focus. The impact of depression extends beyond the individual, affecting society at large through decreased productivity and higher healthcare costs. In the realm of social media, users often express their thoughts and emotions through posts, which can provide insightful data for identifying patterns of depression. This research aims to detect depression early by analyzing social media user content with machine learning techniques. We have built advanced machine learning models using a benchmark depression database containing 20,000 tagged tweets from user profiles identified as depressed or non-depressed. We are introducing an innovative BERT-RF feature engineering method that extracts Contextualized Embeddings and Probabilistic Features from textual input. The Bidirectional Encoder Representations from Transformers (BERT) model, based on the Transformer architecture, is used to extract Contextualized Embedding features. These features are then fed into a random forest model to generate class probabilistic features. These prominent features aid in enhancing the identification of depression from social media. In order to classify tweets using the features derived from the BERT-RF features selection step, we have used five popular classifiers: Random Forest (RF), Multilayer Perceptron (MLP), K-Neighbors Classifier (KNC), Logistic Regression (LR), and Long Short-Term Memory (LSTM). Evaluation experiments show that our approach, using BERT-RF for feature engineering, enables the Logistic Regression model to outperform state-of-the-art methods with a high accuracy score of 99%. We have validated the results through k-fold cross-validation and statistical T-tests. We achieved 99% k-fold accuracy during the validation of the proposed approach. This research contributes significantly to computational linguistics and mental health analytics by providing a robust approach to the early detection of user depression from social media content.

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 top-tier 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.

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.

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.

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.