Explore the vast range of titles available.

Background Pigmented skin lesions (PSLs) pose medical and esthetic challenges for those affected. PSLs can cause skin cancers, particularly melanoma, which can be life‐threatening. Detecting and treating melanoma early can reduce mortality rates. Dermoscopic imaging offers a noninvasive and cost‐effective technique for examining PSLs. However, the lack of standardized colors, image capture settings, and artifacts makes accurate analysis challenging. Computer‐aided diagnosis (CAD) using deep learning models, such as convolutional neural networks (CNNs), has shown promise by automatically extracting features from medical images. Nevertheless, enhancing the CNN models' performance remains challenging, notably concerning sensitivity. Materials and methods In this study, we aim to enhance the classification performance of selected pretrained CNNs. We use the 2019 ISIC dataset, which presents eight disease classes. To achieve this goal, two methods are applied: resolution of the dataset imbalance challenge through augmentation and optimization of the training hyperparameters via Bayesian tuning. Results The performance improvement was observed for all tested pretrained CNNs. The Inception‐V3 model achieved the best performance compared to similar results, with an accuracy of 96.40% and an AUC of 0.98. Conclusion According to the study, classification performance was significantly enhanced by augmentation and Bayesian hyperparameter tuning.

Severe space weather produced by disturbed conditions on the Sun results in harmful effects both for humans in space and in high‐latitude flights, and for technological systems such as spacecraft or communications. Also, geomagnetically induced currents (GICs) flowing on long ground‐based conductors, such as power networks, potentially threaten critical infrastructures on Earth. The first step in developing an alarm system against GICs is to forecast them. This is a challenging task given the highly non‐linear dependencies of the response of the magnetosphere to these perturbations. In the last few years, modern machine‐learning models have shown to be very good at predicting magnetic activity indices. However, such complex models are on the one hand difficult to tune, and on the other hand they are known to bring along potentially large prediction uncertainties which are generally difficult to estimate. In this work we aim at predicting the SYM‐H index characterizing geomagnetic storms multiple‐hour ahead, using public interplanetary magnetic field (IMF) data from the Sun‐Earth L1 Lagrange point and SYM‐H data. We implement a type of machine‐learning model called long short‐term memory (LSTM) network. Our scope is to estimate the prediction uncertainties coming from a deep‐learning model in the context of forecasting the SYM‐H index. These uncertainties will be essential to set reliable alarm thresholds. The resulting uncertainties turn out to be sizable at the critical stages of the geomagnetic storms. Our methodology includes as well an efficient optimization of important hyper‐parameters of the LSTM network and robustness tests.

Stock market prediction has long attracted the attention of academia and industry due to its potential for substantial financial returns. Despite the availability of various forecasting methods, such as CNN, LSTM, BiLSTM, GRU, and Transformer, the hyperparameter optimization of these models often faces limitations, particularly in single-objective optimization, where they can easily fall into local optima. To address this issue, this paper proposes an innovative multi-objective optimization algorithm—the Multi-Objective Escape Bird Algorithm (MOEBS)—and introduces the MOEBS-Transformer architecture to enhance the efficiency and effectiveness of hyper-parameter optimization for Transformer models. This study first validates the performance of MOEBS through a series of multi-objective benchmark tests on standard problem sets such as ZDT, DTLZ, and WFG, comparing it with other multi-objective optimization algorithms (e.g., MOMVO, MSSA, and MOEAD) using evaluation metrics such as GD, Spacing, IGD, and HV for comprehensive analysis. In the context of stock price prediction, we select the closing price datasets of Amazon, Google, and Uniqlo, using MOEBS to optimize the core hyper parameters of the Transformer while considering multiple objectives, including training set RMSE, testing set RMSE, and testing set error variance. In the experiments, this paper first compares CNN, LSTM, BiLSTM, GRU, and traditional Transformer models to establish the Transformer as the optimal model for stock market prediction. Subsequently, the study compares the MOEBS-Transformer with Transformer models optimized using various hyperparameter optimization methods, including MOMVO-Transformer, MSSA-Transformer, and MOEAD-Transformer. Additionally, it evaluates Transformer models optimized through conventional methods: Random Search (RS-Transformer), Grid Search (GS-Transformer), and Bayesian Optimization (BO-Transformer). By assessing the performance of these models using R 2 , RMSE, and RPD metrics on both training and testing sets, the results demonstrate that the Transformer model optimized by MOEBS significantly outperforms the other methods in terms of prediction accuracy and prediction stability. This research offers a new solution for complex optimization scenarios and lays a foundation for advancements in stock market prediction technologies.

It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end, the realization of feature selection for fault detection is firstly achieved by utilizing the maximum information coefficient to analyze the correlation among features in supervisory control and data acquisition (SCADA) of wind turbines. After that, a performance evaluation criterion is proposed for the improved LightGBM model to support fault detections. In this scheme, by embedding the confusion matrix as a performance indicator, an improved LightGBM fault detection approach is then developed. Based on the adaptive LightGBM fault detection model, a fault detection strategy for wind turbine gearboxes is investigated. To demonstrate the applications of the proposed algorithms and methods, a case study with a three-year SCADA dataset obtained from a wind farm sited in Southern China is conducted. Results indicate that the proposed approaches established a fault detection framework of wind turbine systems with either lower false alarm rate or lower missing detection rate.

Deep neural networks (DNNs), which are extensions of artificial neural networks, can learn higher levels of feature hierarchy established by lower level features by transforming the raw feature space to another complex feature space. Although deep networks are successful in a wide range of problems in different fields, there are some issues affecting their overall performance such as selecting appropriate values for model parameters, deciding the optimal architecture and feature representation and determining optimal weight and bias values. Recently, metaheuristic algorithms have been proposed to automate these tasks. This survey gives brief information about common basic DNN architectures including convolutional neural networks, unsupervised pre-trained models, recurrent neural networks and recursive neural networks. We formulate the optimization problems in DNN design such as architecture optimization, hyper-parameter optimization, training and feature representation level optimization. The encoding schemes used in metaheuristics to represent the network architectures are categorized. The evolutionary and selection operators, and also speed-up methods are summarized, and the main approaches to validate the results of networks designed by metaheuristics are provided. Moreover, we group the studies on the metaheuristics for deep neural networks based on the problem type considered and present the datasets mostly used in the studies for the readers. We discuss about the pros and cons of utilizing metaheuristics in deep learning field and give some future directions for connecting the metaheuristics and deep learning. To the best of our knowledge, this is the most comprehensive survey about metaheuristics used in deep learning field.

Brain tumor diagnosis and classification still rely on histopathological analysis of biopsy specimens today. The current method is invasive, time-consuming and prone to manual errors. These disadvantages show how essential it is to perform a fully automated method for multi-classification of brain tumors based on deep learning. This paper aims to make multi-classification of brain tumors for the early diagnosis purposes using convolutional neural network (CNN). Three different CNN models are proposed for three different classification tasks. Brain tumor detection is achieved with 99.33% accuracy using the first CNN model. The second CNN model can classify the brain tumor into five brain tumor types as normal, glioma, meningioma, pituitary and metastatic with an accuracy of 92.66%. The third CNN model can classify the brain tumors into three grades as Grade II, Grade III and Grade IV with an accuracy of 98.14%. All the important hyper-parameters of CNN models are automatically designated using the grid search optimization algorithm. To the best of author’s knowledge, this is the first study for multi-classification of brain tumor MRI images using CNN whose almost all hyper-parameters are tuned by the grid search optimizer. The proposed CNN models are compared with other popular state-of-the-art CNN models such as AlexNet, Inceptionv3, ResNet-50, VGG-16 and GoogleNet. Satisfactory classification results are obtained using large and publicly available clinical datasets. The proposed CNN models can be employed to assist physicians and radiologists in validating their initial screening for brain tumor multi-classification purposes.

Cross-Validation (CV), and out-of-sample performance-estimation protocols in general, are often employed both for (a) selecting the optimal combination of algorithms and values of hyper-parameters (called a configuration) for producing the final predictive model, and (b) estimating the predictive performance of the final model. However, the cross-validated performance of the best configuration is optimistically biased. We present an efficient bootstrap method that corrects for the bias, called Bootstrap Bias Corrected CV (BBC-CV). BBC-CV’s main idea is to bootstrap the whole process of selecting the best-performing configuration on the out-of-sample predictions of each configuration, without additional training of models. In comparison to the alternatives, namely the nested cross-validation (Varma and Simon in BMC Bioinform 7(1):91, 2006) and a method by Tibshirani and Tibshirani (Ann Appl Stat 822–829, 2009), BBC-CV is computationally more efficient, has smaller variance and bias, and is applicable to any metric of performance (accuracy, AUC, concordance index, mean squared error). Subsequently, we employ again the idea of bootstrapping the out-of-sample predictions to speed up the CV process. Specifically, using a bootstrap-based statistical criterion we stop training of models on new folds of inferior (with high probability) configurations. We name the method Bootstrap Bias Corrected with Dropping CV (BBCD-CV) that is both efficient and provides accurate performance estimates.

Colorectal cancer (CRC) is one of the most common and malignant types of cancer worldwide. Colonoscopy, considered the gold standard for CRC screening, allows immediate removal of polyps, which are precursors to CRC. Many computer-aided diagnosis systems (CADs) have been proposed for automatic polyp detection. Most of these systems are based on traditional machine learning algorithms and their generalization ability, sensitivity and specificity are limited. On the other hand, with the widespread use of deep learning algorithms in medical image analysis and the successful results in the analysis of colonoscopy images, especially in the early and accurate detection of polyps, these problems are eliminated in recent years. In short, deep learning algorithms and applications have gained a critical role in CAD systems for real-time autonomous polyp detection. Here, we make significant improvements to object detection algorithms to improve the performance of CAD-based real-time polyp detection systems. We integrate the artificial bee colony algorithm (ABC) into the YOLO algorithm to optimize the hyper-parameters of YOLO-based algorithms. The proposed method can be easily integrated into all YOLO algorithms such as YOLOv3, YOLOv4, Scaled-YOLOv4, YOLOv5, YOLOR and YOLOv7. The proposed method improves the performance of the Scaled-YOLOv4 algorithm with an average of more than 3% increase in mAP and a more than 2% improvement in F1 value. In addition, the most comprehensive study is conducted by evaluating the performance of all existing models in the Scaled-YOLOv4 algorithm (YOLOv4s, YOLOv4m, YOLOV4-CSP, YOLOv4-P5, YOLOV4-P6 and YOLOv4-P7) on the novel SUN and PICCOLO polyp datasets. The proposed method is the first study for the optimization of YOLO-based algorithms in the literature and makes a significant contribution to the detection accuracy.

We present a stochastic deep collocation method (DCM) based on neural architecture search (NAS) and transfer learning for heterogeneous porous media. We first carry out a sensitivity analysis to determine the key hyper-parameters of the network to reduce the search space and subsequently employ hyper-parameter optimization to finally obtain the parameter values. The presented NAS based DCM also saves the weights and biases of the most favorable architectures, which is then used in the fine-tuning process. We also employ transfer learning techniques to drastically reduce the computational cost. The presented DCM is then applied to the stochastic analysis of heterogeneous porous material. Therefore, a three dimensional stochastic flow model is built providing a benchmark to the simulation of groundwater flow in highly heterogeneous aquifers. The performance of the presented NAS based DCM is verified in different dimensions using the method of manufactured solutions. We show that it significantly outperforms finite difference methods in both accuracy and computational cost.

The glass transition temperature of polymers is a key parameter in meeting the application requirements for energy absorption. Previous studies have provided some data from slow, expensive trial-and-error procedures. By recognizing these data, machine learning algorithms are able to extract valuable knowledge and disclose essential insights. In this study, a dataset of 7174 samples was utilized. The polymers were numerically represented using two methods: Morgan fingerprint and molecular descriptor. During preprocessing, the dataset was scaled using a standard scaler technique. We removed the features with small variance from the dataset and used the Pearson correlation technique to exclude the features that were highly connected. Then, the most significant features were selected using the recursive feature elimination method. Nine machine learning techniques were employed to predict the glass transition temperature and tune their hyperparameters. The models were compared using the performance metrics of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). We observed that the extra tree regressor provided the best results. Significant features were also identified using statistical machine learning methods. The SHAP method was also employed to demonstrate the influence of each feature on the model’s output. This framework can be adaptable to other properties at a low computational expense.