Search

Breast cancer is the second leading cause of mortality among women. Early and accurate detection plays a crucial role in lowering its mortality rate. Timely detection and classification of breast cancer enable the most effective treatment. Convolutional neural networks (CNNs) have significantly improved the accuracy of tumor detection and classification in medical imaging compared to traditional methods. This study proposes a comprehensive classification technique for identifying breast cancer, utilizing a synthesized CNN, an enhanced optimization algorithm, and transfer learning. The primary goal is to assist radiologists in rapidly identifying anomalies. To overcome inherent limitations, we modified the Ant Colony Optimization (ACO) technique with opposition-based learning (OBL). The Enhanced Ant Colony Optimization (EACO) methodology was then employed to determine the optimal hyperparameter values for the CNN architecture. Our proposed framework combines the Residual Network-101 (ResNet101) CNN architecture with the EACO algorithm, resulting in a new model dubbed EACO–ResNet101. Experimental analysis was conducted on the MIAS and DDSM (CBIS-DDSM) mammographic datasets. Compared to conventional methods, our proposed model achieved an impressive accuracy of 98.63%, sensitivity of 98.76%, and specificity of 98.89% on the CBIS-DDSM dataset. On the MIAS dataset, the proposed model achieved a classification accuracy of 99.15%, a sensitivity of 97.86%, and a specificity of 98.88%. These results demonstrate the superiority of the proposed EACO–ResNet101 over current methodologies. [ABSTRACT FROM AUTHOR]

The most frequent and noticeable natural calamity in the Karakoram region is landslides. Extreme landslides have occurred frequently along Karakoram Highway, particularly during monsoons, causing a major loss of life and property. Therefore, it is necessary to look for a solution to increase growth and vigilance in order to lessen losses related to landslides caused by natural disasters. By utilizing contemporary technologies, an early warning system might be developed. Artificial neural networks (ANNs) are widely used nowadays across many industries. This paper's major goal is to provide new integrative models for assessing landslide susceptibility in a prone area in the north of Pakistan. To achieve this, the training of an artificial neural network (ANN) was supervised using metaheuristic and Bayesian techniques: Particle Swarm Optimization (PSO) algorithm, Genetic algorithm (GA), Bayesian Optimization Gaussian Process (BO_GP), and Bayesian Optimization Tree-structured Parzen Estimator (BO_TPE). In total, 304 previous landslides and the eight most prevalent conditioning elements were combined to form a geospatial database. The models were hyperparameter optimized, and the best ones were employed to generate susceptibility maps. The obtained area under the curve (AUC) accuracy index demonstrated that the maps produced by both Bayesian and metaheuristic algorithms are highly accurate. The effectiveness and efficiency of applying ANNs for landslide mapping, susceptibility analysis, and forecasting were studied in this research, and it was observed from experimentation that the performance differences for GA, BO_GP, and PSO compared to BO_TPE were relatively small, ranging from 0.32% to 1.84%. This suggests that these techniques achieved comparable performance to BO_TPE in terms of AUC. However, it is important to note that the significance of these differences can vary depending on the specific context and requirements of the ML task. Additionally, in this study, we explore eight feature selection algorithms to determine the geospatial variable importance for landslide susceptibility mapping along the Karakoram Highway (KKH). The algorithms considered include Information Gain, Variance Inflation Factor, OneR Classifier, Subset Evaluators, principal components, Relief Attribute Evaluator, correlation, and Symmetrical Uncertainty. These algorithms enable us to evaluate the relevance and significance of different geospatial variables in predicting landslide susceptibility. By applying these feature selection algorithms, we aim to identify the most influential geospatial variables that contribute to landslide occurrences along the KKH. The algorithms encompass a diverse range of techniques, such as measuring entropy reduction, accounting for attribute bias, generating single rules, evaluating feature subsets, reducing dimensionality, and assessing correlation and information sharing. The findings of this study will provide valuable insights into the critical geospatial variables associated with landslide susceptibility along the KKH. These insights can aid in the development of effective landslide mitigation strategies, infrastructure planning, and targeted hazard management efforts. Additionally, the study contributes to the field of geospatial analysis by showcasing the applicability and effectiveness of various feature selection algorithms in the context of landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

For the regulation and operation of electrical systems, a reliable and precise prediction of solar irradiation is extremely beneficial. Therefore, this paper deals with the issue of accurate and reliable estimation of solar irradiance by developing and investigating the different standalone and hybrid forecasting models. Eleven different models: Feedforward neural network (FFNN), long short term memory (LSTM), gated recurrent unit (GRU), Bidirectional long short term memory (BDLSTM), BDLSTM with empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), wavelet transform (WT) and wavelet packet decomposition (WPD) are developed for point and interval forecasting of solar global horizontal irradiance (GHI) on hour ahead basis for two Indian locations. The autocorrelation function ((ACF) and partial autocorrelation function (PACF) are used as statistical measurement to select the optimal lags of the input lags of deep learning (DL) predictors. Likewise, the grid search algorithm is used to select the optimum value of hyperparameters of the predictor. To evaluate the model's performance, root mean square error (RMSE) and mean absolute error (MAE) for point forecast whereas; prediction interval nominal confidence (PINC), average coverage error (ACE) and prediction interval average width (PIAW) for the interval forecast are calculate for annual and seasonal datasets. From the study, the WPD based model achieved the minimum annual RMSE (11.35 W/m2 & 10.49 W/m2) and MAE (6.04 W/m2 & 6.41W/m2). Likewise, at confidence interval (CI) = 99%, the PICP, ACE and PIAW achieved by WPD are ranges from 80.66–81.27, 19.92–21.03, 17.71–18.33 respectively. [ABSTRACT FROM AUTHOR]

Copyright of Revista Cubana de Ciencias Informáticas is the property of Universidad de las Ciencias Informaticas (UCI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Natural Gas & Oil is the property of Editorial Department of Natural Gas & Oil and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Modern active distribution networks (ADNs) witness increasing complexities that require efforts in control practices, including optimal reactive power dispatch (ORPD). Deep reinforcement learning (DRL) is proposed to manage the network's reactive power by coordinating different resources, including distributed energy resources, to enhance performance. However, there is a lack of studies examining DRL elements' performance sensitivity. To this end, in this paper we examine the impact of various DRL reward representations and hyperparameters on the agent's learning performance when solving the ORPD problem for ADNs. We assess the agent's performance regarding accuracy and training time metrics, as well as critic estimate measures. Furthermore, different environmental changes are examined to study the DRL model's scalability by including other resources. Results show that compared to other representations, the complementary reward function exhibits improved performance in terms of power loss minimization and convergence time by 10–15% and 14–18%, respectively. Also, adequate agent performance is observed to be neighboring the best-suited value of each hyperparameter for the studied problem. In addition, scalability analysis depicts that increasing the number of possible action combinations in the action space by approximately nine times results in 1.7 times increase in the training time. [ABSTRACT FROM AUTHOR]

Induction motor fault diagnosis and condition monitoring are on the anvil of researchers, who have reported many studies and developments in the literature. However, the reported technique requires intervention to interpret the frequency and time–frequency domain analysis results. Intelligent systems have been reported to overcome these limitations; however, time delays and additional costs are incurred owing to the need for expert interpretation. Hence, this work proposes a methodology based on motor current signal processing in image format to automatically diagnose and classify the inter-turn fault of the three-phase induction motor. The motor current sampled in the time domain by shortening the inter turns in the winding for different load conditions is expressed as three-color monotonous images for each phase. These obtained images are applied for training and testing of convolution neural network, which can classify the faults according to their severity and identify the phase in which the fault prevails. Furthermore, efforts have been made to design the convolution neural network architecture, i.e., selecting hyperparameters such as learning rate, batch size, number of epochs, and momentum rate, and average classification accuracy of 99.38% is obtained. The proposed technique with monotonous coloured images of current signal as an input to CNN is found to be effective in terms of computational time, robustness to identify the faults even in the presence of noise and fault classification accuracy when compared to other published literature. [ABSTRACT FROM AUTHOR]

Traditional survival analysis methods have been widely used in medicine and various fields, but they must satisfy some statistical assumptions. Machine learning methods can overcome this weakness. Three support vector-based machine learning-survival analysis models are proposed with an actual cancer dataset. Experiments show that some machine learning models outperform the Cox statistical model. Accurate kernel complexity experiments are designed for different models, and the selected kernel functions are Poly, neural tangent kernel (NTK) and so on. The NTK kernel model with the highest accuracy is investigated in more depth, including computational complexity and robustness. Some interesting properties are found in these aspects that may provide new ideas for researchers. [ABSTRACT FROM AUTHOR]

This work proposes a metaheuristic-based approach to hyperparameter selection in a multilayer perceptron to classify EMG signals. The main goal of the study is to improve the performance of the model by optimizing four important hyperparameters: the number of neurons, the learning rate, the epochs, and the training batches. The approach proposed in this work shows that hyperparameter optimization using particle swarm optimization and the gray wolf optimizer significantly improves the performance of a multilayer perceptron in classifying EMG motion signals. The final model achieves an average classification rate of 93% for the validation phase. The results obtained are promising and suggest that the proposed approach may be helpful for the optimization of deep learning models in other signal processing applications. [ABSTRACT FROM AUTHOR]

In this study, an Artificial Neural Network (ANN) model to predict the moment capacity of Fiber Reinforced Plastic (FRP) strengthened Reinforced Concrete (RC) beams exposed to fire is developed. The software ABAQUS heat transfer analysis is verified by comparison with the fire resistance test results. Through this heat transfer analysis, the temperature distribution of the beam section is determined, and 400 datasets are obtained using the moment capacity calculation method combined with the section equilibrium method. The data consist of eight input parameters: the beam width, beam height, FRP area, rebar area, concrete compressive strength, insulation thickness, concrete cover depth, and fire exposure time. The output parameter is the moment capacity. The ANN model is developed through a sensitivity study using the algorithm type and the number of hidden-layer neurons as variables. The average error between the predicted data of the developed ANN model and the target data obtained from the moment capacity calculation method was 0.35 kN·m, and the average relative error was 0.2512%, showing high accuracy. Therefore, the ANN model developed here can determine the moment capacity without complex calculations. The effects of the input parameters on the moment capacity of the FRP-strengthened RC beams exposed to fire are investigated using the ANN model. [ABSTRACT FROM AUTHOR]

An accurate forecasting of solar global horizontal irradiance (GHI) provides the estimation of future output from photovoltaic (PV) cells, resulting in guaranteed sustainable functioning of solar integrated smart grids. Traditional forecasting algorithms find it relatively hard to obtain the intrinsic non-linearity of solar GHI, leading to poor forecasting accuracy. This work offers a deep learning (DL)-based hybrid model called RLMD BILSTM that combines robust local mean decomposition (RLMD) algorithm with bidirectional long short-term memory (BILSTM) predictor. The proposed RLMD BILSTM model has been developed and evaluated for two separate Indian locations: Hisar and Jaipur, by comparing with benchmark models: persistence, long short-term memory (LSTM), gated recurrent unit (GRU), BILSTM, and their RLMD-based hybrid variations (RLMD LSTM and RLMD GRU). The performance of the proposed model has been verified by the statistical and visual results of short-term annual and seasonal forecast of solar GHI. From the results, it has been observed that the proposed model achieved lower root mean square error (RMSE) (16.34 W/m2-35.07 W/m2) compared to contrast mforecastsodels. The higher annual R2 yielding a value of 0.977–0.995 for the proposed model compared to the contrast model proved its better fitness. Moreover, the study showed that the RLMD with BILSTM improved the RMSE (59.16%–88.88%) and mean absolute error (MAE) (66.45%–92.22%) over various contrast models. The study also conducted the sensitivity analysis using the forecasting efficacy and forecast skill to prove the significance of the proposed model. [ABSTRACT FROM AUTHOR]

Cryptocurrencies are rapidly growing and are increasingly accepted by major commercial vendors. However, along with their rising popularity, they have also become the go-to currency for illicit activities driven by the anonymity they provide. Cryptocurrencies such as the one on the Ethereum blockchain provide a way for entities to hide their real-world identities behind pseudonyms, also known as addresses. Hence, the purpose of this work is to uncover the level of anonymity in Ethereum by investigating multiclass classification models for Externally Owned Accounts (EOAs) of Ethereum. The researchers aim to achieve this by examining patterns of transaction activity associated with these addresses. Using a labelled Ethereum address dataset from Kaggle and the Ethereum crypto dataset by Google BigQuery, an address profiles dataset was compiled based on the transaction history of the addresses. The compiled dataset, consisting of 4371 samples, was used to tune and evaluate the Random Forest, Gradient Boosting and XGBoost classifier for predicting the category of the addresses. The best-performing model found for the problem was the XGBoost classifier, achieving an accuracy of 75.3% with a macro-averaged F1-Score of 0.689. Following closely was the Random Forest classifier, with an accuracy of 73.7% and a macro-averaged F1-Score of 0.641. Gradient Boosting came in last with 73% accuracy and a macro-averaged F1-Score of 0.659. Owing to the data limitations in this study, the overall scores of the best model were weaker in comparison to similar research, with the exception of precision, which scored slightly higher. Nevertheless, the results proved that it is possible to predict the category of an Ethereum wallet address such as Phish/Hack, Scamming, Exchange and ICO wallets based on its transaction behaviour. [ABSTRACT FROM AUTHOR]

Heart disease, globally recognized as a leading cause of death, has seen its impact magnified by the emergence of COVID-19. The heightened demand for early detection and diagnosis of heart disease has forced the development of innovative, intelligent systems. This research offers a novel approach by leveraging extended short-term memory networks (LSTM) and including COVID-19 as a significant parameter in cardiac arrest analysis. A comparative study is conducted between LSTM and other prevalent techniques, such as support vector machines (SVM), linear regression (LR), and artificial neural networks (ANN), focusing on accuracy and other prognostic criteria for heart disease. We aim to develop an intelligent system powered by LSTM to predict heart disease, thereby assisting healthcare professionals in making well-informed decisions about heart disease management, stroke prevention, and patient monitoring. Additionally, hyperparameter tuning has been performed to optimize the LSTM model's performance in cardiac arrest prediction. The results underscore that LSTM, especially when trained with COVID-19 as an input parameter, surpasses other established techniques in prediction accuracy. The proposed model underwent experimental testing, showcasing its proficiency in predicting cardiovascular disease. [ABSTRACT FROM AUTHOR]

Face recognition (FR) is one of the most active research areas in the field of computer vision. Convolutional neural networks (CNNs) have been extensively used in this field due to their good efficiency. Thus, it is important to find the best CNN parameters for its best performance. Hyperparameter optimization is one of the various techniques for increasing the performance of CNN models. Since manual tuning of hyperparameters is a tedious and time-consuming task, population based metaheuristic techniques can be used for the automatic hyperparameter optimization of CNNs. Automatic tuning of parameters reduces manual efforts and improves the efficiency of the CNN model. In the proposed work, genetic algorithm (GA) based hyperparameter optimization of CNNs is applied for face recognition. GAs are used for the optimization of various hyperparameters like filter size as well as the number of filters and of hidden layers. For analysis, a benchmark dataset for FR with ninety subjects is used. The experimental results indicate that the proposed GA-CNN model generates an improved model accuracy in comparison with existing CNN models. In each iteration, the GA minimizes the objective function by selecting the best combination set of CNN hyperparameters. An improved accuracy of 94.5 % is obtained for FR.

Non-traumatic grief can be defined as, a complex process that includes emotional, physical, spiritual, social, and intellectual behaviors and responses through which individuals, families, and communities incorporate actual, anticipated, or perceived loss into their daily lives. In the age of widespread social media usage, individuals frequently share their emotions online for various reasons. This was particularly evident during the peak of the COVID-19 pandemic and its aftermath, where many social media interactions replaced or supplemented traditional farewell and mourning practices, including communications related to deaths. Recognizing messages expressing non-traumatic grief is a crucial challenge for nursing, medicine, and socio-health interventions. This awareness could assist specialists in improving early prevention and healthcare measures. In this work we present an approach to automatically detect messages (tweets) containing non-traumatic grief by means of deep learning techniques. To this end, a corpus of Spanish-language tweets has been built using a binary label to indicate the presence or absence of non-traumatic grief and has been released for use in future research. To address this challenge, multiple monolingual and multilingual language models based on pre-trained Transformer models have been fine-tuned, performing an exhaustive search to obtain the best hyperparameter values. Through this approach and employing various oversampling and undersampling techniques to mitigate the dataset’s imbalance issue, the trained models reached very good results on different evaluation metrics, achieving an accuracy, AUC-ROC, and F-measure of 0.850, 0.836, and 0.827, respectively. Our results show the significance of hyperparameter selection during the learning process and demonstrate the potential of deep learning approaches for detecting non-traumatic grief messages.

Prediction of work Travel mode choice is one of the most important parts of travel demand forecasting. Planners can achieve sustainability goals by accurately forecasting how people will get to and from work. In the prediction of travel mode selection, machine learning methods are commonly employed. To fit a machine-learning model to various challenges, the hyperparameters must be tweaked. Choosing the optimal hyperparameter configuration for machine learning models has an immediate effect on the performance of the model. In this paper, optimizing the hyperparameters of common machine learning models, including support vector machines, k-nearest neighbor, single decision trees, ensemble decision trees, and Naive Bayes, is studied using the Bayesian Optimization algorithm. These models were developed and optimized using two datasets from the 2017 National Household Travel Survey. Using several criteria, including average accuracy (%), average area under the receiver operating characteristics, and a simple ranking system, the performance of the optimized models was investigated. The findings of this study show that the BO is an effective model for improving the performance of the k-nearest neighbor model more than other models. This research lays the groundwork for using optimized machine learning methods to mitigate the negative consequences of automobile use.

This study was motivated by the difficulty in determining the resilient modulus of soils using the repeated load triaxial test (RLTT) recommended by the mechanistic-empirical pavement design guide (MEPDG). An alternative means to estimate the resilient modulus of fine-grained soils has been established in the form of three models that were developed using three supervised machine-learning techniques. This includes k-nearest neighbor (KNN), multivariate adaptive regression splines (MARS), and random forest. The data utilized for the development of the models were sourced from the long-term pavement performance (LTPP) database domiciled in the Infopave database in the USA. A total of twelve routine soil properties that have significant influence on the resilient modulus of fine-grained soils were considered in this study. Results obtained from this study revealed that the three developed models (KNN, MARS, and random forest) had high prediction accuracy and high generalization ability. However, the random forest model, based on the statistical indices used to evaluate the models, gave the best prediction accuracy (R2 = 0.9312 for the testing dataset) of the three developed model. It was followed closely by the MARS model with an R2 value of 0.9057. The last model in terms of prediction accuracy was the KNN model with an R2 value of 0.8748. Furthermore, based on parameter significance assessment using the random forest model, it was revealed that the nominal maximum axial stress and confining pressure are the best predictor variables for the estimation of the resilient modulus of fine-grained soils. [ABSTRACT FROM AUTHOR]

There has been a fast deployment of wireless networks in recent years, which has been accompanied by significant impacts on the environment. Among the solutions that have been proven to be effective in reducing the energy consumption of wireless networks is the use of machine learning algorithms in cell traffic management. However, despite promising results, it should be noted that the computations required by machine learning algorithms have increased at an exponential rate. Massive computing has a surprisingly large carbon footprint, which could affect its real-world deployment. Thus, additional attention needs to be paid to the design and parameterization of these algorithms applied in order to reduce the energy consumption of wireless networks. In this article, we analyze the impact of hyperparameters on the energy consumption and performance of machine learning algorithms used for cell traffic prediction. For each hyperparameter (number of layers, number of neurons per layer, optimizer algorithm, batch size, and dropout) we identified a set of feasible values. Then, for each combination of hyperparameters, we trained our model and analyzed energy consumption and the resulting performance. The results from this study reveal a great correlation between hyperparameters and energy consumption, confirming the paramount importance of selecting optimal hyperparameters. A tradeoff between the minimization of energy consumption and the maximization of machine learning performance is suggested. [ABSTRACT FROM AUTHOR]

Compared with ground-based light detection and ranging (LiDAR) data, the differential distribution of the quantity and quality of point cloud data from airborne LiDAR poses difficulties for tree species classification. To verify the feasibility of using the PointNet++ algorithm for point cloud tree species classification with airborne LiDAR data, we selected 11 tree species from the Minjiang River Estuary Wetland Park in Fuzhou City and Sanjiangkou Ecological Park. Training and testing sets were constructed through pre-processing and segmentation, and direct and enhanced down-sampling methods were used for tree species classification. Experiments were conducted to adjust the hyperparameters of the proposed algorithm. The optimal hyperparameter settings used the multi-scale sampling and grouping (MSG) method, down-sampling of the point cloud to 2048 points after enhancement, and a batch size of 16, which resulted in 91.82% classification accuracy. PointNet++ could be used for tree species classification using airborne LiDAR data with an insignificant impact on point cloud quality. Considering the differential distribution of the point cloud quantity, enhanced down-sampling yields improved the classification results compared to direct down-sampling. The MSG classification method outperformed the simplified sampling and grouping classification method, and the number of epochs and batch size did not impact the results. [ABSTRACT FROM AUTHOR]

Every academic institution's goal is to identify students who require additional assistance and to take appropriate actions to improve their performance. As such, various research studies have focused on developing prediction models that can detect correlated patterns influencing students' performance, dropout, collaboration, and engagement. Among the influential predictive models available, the bagging ensemble has captured the interest of researchers seeking to improve prediction accuracy over single classifiers. However, prior work in this area has focused mainly on selecting single classifiers as the base classifier of the bagging ensemble, with little to no further optimization of the proposed framework. This study aimed to fill this gap by providing a bagging ensemble framework to optimize its hyperparameters and achieve improved prediction accuracy. The proposed model used the Weka BESTrees data mining tool and Math language course student dataset from UCI Machine Learning Repository. Based on the experiments performed, the proposed bagging optimization technique can effectively increase the accuracy of a traditional bagging ensemble method. It reveals further that the proposed BESTrees framework can achieve an optimized performance when trained with the appropriate hyperparameters and hill climb metrics. [ABSTRACT FROM AUTHOR]

This scientific research paper presents the development of a neural network for a computer model that will be applied in the development of a chatbot web application based on a proprietary dataset. The aim of the chatbot is to provide virtual consulting support in the implementation of the Public Procurement Law in the Republic of Serbia. This AI tool is of crucial importance for both procurers and bidders, given the need for understanding and compliance with the law. By using the complete content of texts related to the law's implementation available on the internet, the model will train its neural networks based on an algorithm to provide answers to various questions. The chatbot will be capable of answering questions related to the definitions of the Public Procurement Law ("What is...?"), procedural questions ("What to do in the following case...?"), and ways to overcome obstacles in implementing the law ("How to overcome the problem...?"). By tracking the conversation context and searching through texts, the model will provide meaningful responses. This project has the potential to revolutionize the implementation of the Public Procurement Law in Serbia, considering the large number of officials and the lack of consultants who could provide accurate real-time answers and solutions. Currently, there are numerous decisions of the Republic Commission for the Protection of Rights that represent the practice of law implementation, and the chatbot would enable access to this information to ensure the correctness and transparency of public procurement procedures. Therefore, the model can be expanded and adapted for application with other laws, provided that there is appropriate textual material for model training and tokenization, which would further enhance the accuracy of responses to questions regarding the implementation of the Public Procurement Law. It is important to note that as the conceptual creator of this concept, I have personally submitted a request to the Institute for Artificial Intelligence - AI Institute Novi Sad, Serbia, to collaborate on realizing this idea. [ABSTRACT FROM AUTHOR]

Pervasive computing, human–computer interaction, human behavior analysis, and human activity recognition (HAR) fields have grown significantly. Deep learning (DL)-based techniques have recently been effectively used to predict various human actions using time series data from wearable sensors and mobile devices. The management of time series data remains difficult for DL-based techniques, despite their excellent performance in activity detection. Time series data still has several problems, such as difficulties in heavily biased data and feature extraction. For HAR, an ensemble of Deep SqueezeNet (SE) and bidirectional long short-term memory (BiLSTM) with improved flower pollination optimization algorithm (IFPOA) is designed to construct a reliable classification model utilizing wearable sensor data in this research. The significant features are extracted automatically from the raw sensor data by multi-branch SE-BiLSTM. The model can learn both short-term dependencies and long-term features in sequential data due to SqueezeNet and BiLSTM. The different temporal local dependencies are captured effectively by the proposed model, enhancing the feature extraction process. The hyperparameters of the BiLSTM network are optimized by the IFPOA. The model performance is analyzed using three benchmark datasets: MHEALTH, KU-HAR, and PAMPA2. The proposed model has achieved 99.98%, 99.76%, and 99.54% accuracies on MHEALTH, KU-HAR, and PAMPA2 datasets, respectively. The proposed model performs better than other approaches from the obtained experimental results. The suggested model delivers competitive results compared to state-of-the-art techniques, according to experimental results on four publicly accessible datasets. [ABSTRACT FROM AUTHOR]

The human eye's anatomical features and defects can be captured by using the retinal image modality known as fundus imaging. The effective method for observing and detecting a variety of ophthalmological diseases is fundus imaging. Diseases including diabetic retinopathy, diabetic macular edema (DME), glaucoma, and cataracts are indicated by changes in and around the structural abnormalities like macula, optic disc, blood vessels, and fovea. More than one retinal disease may be present in one or both of the patient's eyes. For multi-class fundus image classification, the new deep learning (DL) model is proposed for ophthalmological diseases using a transfer learning (TL) based deep identification network (DeepID3) network. The flower pollination optimization algorithm (FPOA) is used to optimize the hyperparameters of the network. The model is tested using many large public datasets. The best pre-trained convolutional neural network (CNN) models from ImageNet were used in the experiment. Different performance optimization strategies were also used. Multi-class multi-label fundus image classification is more effective while using the DeepID3 net pre-trained architecture with FPOA optimizer. Maximum accuracy of 99.23%, sensitivity of 98%, precision of 98.13%, recall of 98%, F1-score of 98.3%, and specificity of 98.28% were attained by the proposed model for multi-class classification. The implementation is done by using the Python platform. The performance of the proposed approach is demonstrated by extensive experiments and comparison with baseline methods. [ABSTRACT FROM AUTHOR]

The diagnosis of different pathologies and stages of cancer using whole histopathology slide images (WSI) is the gold standard for determining the degree of tissue metastasis. The use of deep learning systems in the field of medical images, especially histopathology images, is becoming increasingly important. The training and optimization of deep neural network models involve fine-tuning parameters and hyperparameters such as learning rate, batch size (BS), and boost to improve the performance of the model in task-specific applications. Tuning hyperparameters is a major challenge in designing deep neural network models, having a large impact on the performance. This paper analyzes how the parameters and hyperparameters of a deep learning architecture affect the classification of colorectal cancer (CRC) histopathology images using the well-known VGG19 model. This paper also discusses the pre-processing of these images, such as the use of color normalization and stretching transformations on the data set. Among these hyperparameters, the most important neural network hyperparameter is the learning rate (LR). In this paper, different strategies for the optimization of LR are analyzed (both static and dynamic) and a new experiment based on the variation of LR is proposed (the relevance of dynamic strategies over fixed LR is highlighted), after each layer of the neural network together with decreasing variations according to the epochs. The results obtained are very remarkable, obtaining in the simulation an accurate system that achieves 96.4% accuracy on test images (for nine different tissue classes) using the triangular-cyclic learning rate. [ABSTRACT FROM AUTHOR]

We propose a conditional variational auto-encoder within Gibbs sampling (CVAE-within-Gibbs) for Bayesian linear inverse problems where the prior or the likelihood function depends on ambiguous hyperparameters. The method builds on ideas from classical sampling theory and recent advances in deep generative models to approximate complicated probability distributions. Specifically, we use a CVAE model which is trained with a large amount of data to learn the conditional density of hyperparameters in the original Gibbs sampler. The learned property of the conditional posterior provides more flexibility than classical Gibbs sampling because it avoids manually or experimentally determining the hyperpriors and their hyperparameters. We demonstrate the performance of the proposed method for three linear inverse problems, i.e., image deblurring, signal denoising, and boundary heat flux identification in a heat conduction problem. [ABSTRACT FROM AUTHOR]

Network intrusion detection is a relevant cybersecurity research field. The growing number of intrusions requires more sophisticated methods to protect computer networks. Various machine learning algorithms are used to detect network intrusions and anomalies, but their accuracy is limited. In this research, we address the problem of improving network-level intrusion detection by applying hybrid machine-learning algorithms. The paper proposes three new hybrid machine learning methods and investigates their accuracy using two publicly available datasets CSE-CIC-IDS2018 and NSW-NB-15. In order to increase the accuracy of the classification models, hyperparameter optimization was performed. The iteration method and the Chi-square χ2 test were used to identify significant features of the data set. Analyzing the research results, it was found that the highest network anomaly recognition accuracy of 99.34% was achieved by applying a hybrid algorithm consisting of a decision tree, naive Bayesian, and multilayer perceptron algorithms. Achieved result is 3.13% higher than the best accuracy achieved by individual machine learning algorithms. In order to comprehensively evaluate the studied machine learning algorithms and their suitability for detecting intrusions in a computer network, the algorithms were ranked using the SCR, DR, FR ranking methods. Article in Lithuanian. Įsilaužimų aptikimas kompiuterių tinkluose taikant hibridinius mašininio mokymosi metodus Santrauka Viena iš aktualių kibernetinės saugos tyrimų krypčių – tai įsilaužimų arba anomalijų aptikimas kompiuterių tinkle. Įsilaužimų skaičius nuolat didėja, o taikomos įsilaužimo technikos ir metodai sudėtingėja, todėl siekiant apsaugoti kompiuterių tinklą, reikia taikyti vis sudėtingesnius apsaugos metodus. Tinklo įsilaužimams ir anomalijoms nustatyti taikomi įvairūs mašininio mokymosi algoritmai, tačiau jų tikslumas yra ribotas. Siekiama pagerinti tinklo anomalijų aptikimą, taikomi hibridiniai mašininio mokymosi algoritmai. Straipsnyje pasiūlyti trys nauji hibridiniai mašininio mokymosi algoritmai, ištirtas jų tikslumas naudojant du viešai prieinamus duomenų rinkinius, t. y. CSE-CIC-IDS2018 ir NSW-NB-15. Siekiant padidinti klasifikavimo modelių tikslumą, buvo atliktas hiperparametrų optimizavimas. Reikšmingiems duomenų rinkinio požymiams nustatyti taikytas iteracijų metodas ir Chi kvadrato χ2 testas. Analizuojant tyrimo rezultatus, nustatyta, kad aukščiausias tinklo anomalijų atpažinimo tikslumas 99,34 % buvo pasiektas taikant hibridinį algoritmą, sudarytą iš sprendimų medžio, naivaus Bajeso ir daugiasluoksnio perceptrono algoritmų rinkinio. Šis rezultatas yra 3,13 % geresnis, lyginant su geriausiu tikslumu, gautu taikant atskirus mašininio mokymosi algoritmus. Siekiant kompleksiškai įvertinti tirtus mašininio mokymosi algoritmus ir jų tinkamumą įsilaužimams kompiuterių tinkle aptikti, algoritmai buvo sureitinguoti taikant SCR, DR, FR reitingavimo metodus. Reikšminiai žodžiai: tinklo anomalijos, mašininis mokymasis, χ2 Chi kvadratu testas, hiperparametrai, hibridiniai algoritmai.

The growth of deep learning technologies allows us to achieve higher accuracy in the classification of plant diseases, as well as in other domains. This research reveals the performance of several DL approaches, including custom convolutional neural networks (CNNs) and models which are pre-trained namely VGG16 and ResNet34, which were used for the recognition of diseases in plants that are depicted through the images. These models may obtain the necessary growing environment for training and assessing the models by using a publicly accessible dataset that includes pictures of both healthy and diseased plants, in total there are 14 unique plants used. The results of the experiment suggest that all the models combinedly gave 98.46% accuracy in the classification of diverse plant diseases. In addition to this, the paper discusses the hyperparameters like learning rate and optimizer choice that affect the model furthermore, the project discusses the methods involved in training deep learning models on GPU devices computationally speaking. Thereby, this project can be added to the field of agriculture vision by showing that deep learning methods are good for plant disease classification.

Backpropagation Neural Network (BPNN) is a suitable method for predicting the future. It has weaknesses, namely poor convergence speed and instability, requiring parameter tuning to overcome speed problems, and having a high bias. This research uses the Random Search hyperparameter technique to optimize BPNN to automatically select the number of hidden layers, learning rate, and momentum. The added accuracy of momentum will speed up the training process, produce predictions with better accuracy, and determine the best architectural model from a series of faster training processes with low bias. This research will predict the local Indonesian cattle population, which is widely developed by people in the eastern part, especially Madura, in 4 types of cattle: sono cattle, karapan cattle, mixed cattle, and breeder cattle. The results of BPNN hyperparameter measurements with the best model show that hyperparameter optimization did not experience overfitting and experienced an increase in accuracy of 2.5% compared to the Neural Network model without hyperparameter optimization. Based on the test results, the BPNN algorithm parameters with a data ratio of 70:30, the best architecture for backpropagation momentum is 6-6-1, with a learning rate of 0.002, momentum 0.3, which has an MSE during testing of 0.1176 on Karapan type Madurese cattle. Tests based on computing time measurements show that the BPNN hyperparameter algorithm stops at 490 iterations compared to regular BPNN. The research results show that the hidden layers, learning rate, and momentum if optimized simultaneously, have a significant influence in preventing overfitting, increasing accuracy, and having better execution times than without optimization.

Determining the classification of motor competence is an essential aspect of physical activity that must be carried out during school years. The objective is to evaluate motor competence in schoolchildren using smart bands, generate percentiles of the evaluation metrics, and classify motor performance through machine learning with hyperparameter optimization. A cross-sectional descriptive study was carried out on 764 schoolchildren (451 males and 313 females) aged 6 to 17 years. Five state schools in the city of Arequipa, Peru were evaluated. Weight, height, and waist circumference were assessed, and body mass index (BMI) was calculated. The tests evaluated in the schoolchildren measured walking and running for 6 minutes. These tests were carried out using smart bands, capturing cadence, number of steps, calories consumed, speed, stride, and heart rate. As a result, the percentiles were created through the LMS method [L (asymmetry: lambda), M (median: mu), and S (coefficient of variation: sigma)]. The cut-off points considered were p75 (above average). For classification, the machine-learning algorithms random forest, decision tree, support vector machine, naive Bayes, logistic regression, k-nearest neighbor, neural network, gradient boosting, XGBboost, LightGBM, and CatBoost were used, and the hyperparameters of the models were optimized using the RandomizedSearchCV technique. In conclusion, it was possible to classify motor competence with the tests carried out on schoolchildren, significantly improving the accuracy of the machine-learning algorithms through the selected hyperparameters, with the gradient boosting classifier being the best result at 0.95 accuracy and in the ROC-AUC curves with a 0.98. The reference values proposed in this study can be used to classify the walking motor competence of schoolchildren. Finally, the mobile software product built based on the proposed model was validated using the prototype of the Software Quality Systemic Model (SQSM) based on three specific categories: functionality, reliability, and usability, obtaining 77.09%. The results obtained can be used in educational centers to achieve the suggested recommendations for physical activity in schoolchildren.

The quality characteristic(s) are assumed to follow the normal distribution in many control chart constructions, although this assumption may not hold in some instances. This study proposes the Bayesian-I and Bayesian-II Shewhart-type control charts for monitoring the Maxwell scale parameter in the phase II study. The posterior and predictive distributions are used to construct the control limits for the proposed Bayesian-I and Bayesian-II Shewhart-type control charts, respectively. Various performance indicators, including average run length, quadratic loss, relative average run length, and performance comparison index, are utilized to evaluate the performance of the proposed control charts. The Bayesian-I and Bayesian-II Shewhart-type control charts are compared to their competitive CUSUMV, EWMAV and V control charts. Sensitivity analysis is also performed to study the effect of hyperparameter values on the performance behavior of the proposed control charts. Finally, real-life data is analyzed for the implementation of the proposed control charts. [ABSTRACT FROM AUTHOR]

Compressive sensing is a sub-Nyquist sampling technique for efficient signal acquisition and reconstruction of sparse or compressible signals. In order to account for the sparsity of the underlying signal of interest, it is common to use sparsifying priors such as Bernoulli–Gaussian-inverse Gamma (BGiG) and Gaussian-inverse Gamma (GiG) priors on the components of the signal. With the introduction of variational Bayesian inference, the sparse Bayesian learning (SBL) methods for solving the inverse problem of compressive sensing have received significant interest as the SBL methods become more efficient in terms of execution time. In this paper, we consider the sparse signal recovery problem using compressive sensing and the variational Bayesian (VB) inference framework. More specifically, we consider two widely used Bayesian models of BGiG and GiG for modeling the underlying sparse signal for this problem. Although these two models have been widely used for sparse recovery problems under various signal structures, the question of which model can outperform the other for sparse signal recovery under no specific structure has yet to be fully addressed under the VB inference setting. Here, we study these two models specifically under VB inference in detail, provide some motivating examples regarding the issues in signal reconstruction that may occur under each model, perform comparisons and provide suggestions on how to improve the performance of each model. [ABSTRACT FROM AUTHOR]

Improved irradiance forecasting ensures precise solar power generation forecasts, resulting in smoother operation of the distribution grid. Empirical models are used to estimate irradiation using a wide range of data and specific national or regional parameters. In contrast, algorithms based on Artificial Intelligence (AI) are becoming increasingly popular and effective for estimating solar irradiance. Although there has been significant development in this area elsewhere, employing an AI model to investigate irradiance in Bangladesh is limited. This research forecasts solar radiation in Bangladesh using ensemble machine-learning models. The meteorological data collected from 32 stations contain maximum temperature, minimum temperature, total rain, humidity, sunshine, wind speed, cloud coverage, and irradiance. Ensemble machine-learning algorithms including Adaboost regression (ABR), gradient-boosting regression (GBR), random forest regression (RFR), and bagging regression (BR) are developed to predict solar irradiance. With the default parameters, the GBR provides the best performance as it has the lowest standard deviation of errors. Then, the important hyperparameters of the GRB are tuned with the grid-search algorithms to further improve the prediction accuracy. On the testing dataset, the optimized GBR has the highest coefficient of determination ( R 2 ) performance, with a value of 0.9995. The same approach also has the lowest root mean squared error (0.0007), mean absolute percentage error (0.0052), and mean squared logarithmic error (0.0001), implying superior performance. The absolute error of the prediction lies within a narrow range, indicating good performance. Overall, ensemble machine-learning models are an effective method for forecasting irradiance in Bangladesh. They can attain high accuracy and robustness and give significant information for the assessment of solar energy resources. [ABSTRACT FROM AUTHOR]

One of the most difficult challenges in medicine is predicting heart disease at an early stage. In this study, six machine learning (ML) algorithms, viz., logistic regression, K-nearest neighbor, support vector machine, decision tree, random forest classifier, and extreme gradient boosting, were used to analyze two heart disease datasets. One dataset was UCI Kaggle Cleveland and the other was the comprehensive UCI Kaggle Cleveland, Hungary, Switzerland, and Long Beach V. The performance results of the machine learning techniques were obtained. The support vector machine with tuned hyperparameters achieved the highest testing accuracy of 87.91% for dataset-I and the extreme gradient boosting classifier with tuned hyperparameters achieved the highest testing accuracy of 99.03% for the comprehensive dataset-II. The novelty of this work was the use of grid search cross-validation to enhance the performance in the form of training and testing. The ideal parameters for predicting heart disease were identified through experimental results. Comparative studies were also carried out with the existing studies focusing on the prediction of heart disease, where the approach used in this work significantly outperformed their results. [ABSTRACT FROM AUTHOR]

Concrete can be recycled after certain processing technologies for use in pavement engineering but the flexural strength (FS) is difficult to predict accurately in the design process. This study proposes a novel systematic and evolved approach to estimate the FS of recycled concrete. The proposed methods are conducted based on the random forest (RF) model as well as the firefly algorithm (FA), where the latter is employed to tune the hyperparameters of the RF model. For this purpose, data sets were collected from previously published literature for the training and verification of the model, and the accuracy of the model was verified by the fitting effect of the predicted and actual values. The results showed that the proposed hybrid machine learning model has a good fitting effect on the predicted and actual values; the calculation and evaluation process demonstrated fast convergence and significantly lower values of RMSE for the proposed model to determine the FS of the recycling concrete. In addition, the study analyzed the sensitivity of the FS of recycled concrete to input variables, and the results showed that effective water-cement ratio (WC), water absorption of recycling concrete (WAR), and water absorption of natural aggregate (WAN) show more obvious influences on FS, so these factors should be paid more attention in future pavement design using the recycling of concrete. [ABSTRACT FROM AUTHOR]

Diagnosing a brain tumor takes a long time and relies heavily on the radiologist's abilities and experience. The amount of data that must be handled has increased dramatically as the number of patients has increased, making old procedures both costly and ineffective. Many researchers investigated a variety of algorithms for detecting and classifying brain tumors that were both accurate and fast. Deep Learning (DL) approaches have recently been popular in developing automated systems capable of accurately diagnosing or segmenting brain tumors in less time. DL enables a pre-trained Convolutional Neural Network (CNN) model for medical images, specifically for classifying brain cancers. The proposed Brain Tumor Classification Model based on CNN (BCM-CNN) is a CNN hyperparameters optimization using an adaptive dynamic sine-cosine fitness grey wolf optimizer (ADSCFGWO) algorithm. There is an optimization of hyperparameters followed by a training model built with Inception-ResnetV2. The model employs commonly used pre-trained models (Inception-ResnetV2) to improve brain tumor diagnosis, and its output is a binary 0 or 1 (0: Normal, 1: Tumor). There are primarily two types of hyperparameters: (i) hyperparameters that determine the underlying network structure; (ii) a hyperparameter that is responsible for training the network. The ADSCFGWO algorithm draws from both the sine cosine and grey wolf algorithms in an adaptable framework that uses both algorithms' strengths. The experimental results show that the BCM-CNN as a classifier achieved the best results due to the enhancement of the CNN's performance by the CNN optimization's hyperparameters. The BCM-CNN has achieved 99.98% accuracy with the BRaTS 2021 Task 1 dataset. [ABSTRACT FROM AUTHOR]

Network intrusion detection is a relevant cybersecurity research field. The growing number of intrusions requires more sophisticated methods to protect computer networks. Various machine learning algorithms are used to detect network intrusions and anomalies, but their accuracy is limited. In this research, we address the problem of improving network-level intrusion detection by applying hybrid machine-learning algorithms. The paper proposes three new hybrid machine learning methods and investigates their accuracy using two publicly available datasets CSE-CIC-IDS2018 and NSW-NB-15. In order to increase the accuracy of the classification models, hyperparameter optimization was performed. The iteration method and the Chi-square χ² test were used to identify significant features of the data set. Analyzing the research results, it was found that the highest network anomaly recognition accuracy of 99.34% was achieved by applying a hybrid algorithm consisting of a decision tree, naive Bayesian, and multilayer perceptron algorithms. Achieved result is 3.13% higher than the best accuracy achieved by individual machine learning algorithms. In order to comprehensively evaluate the studied machine learning algorithms and their suitability for detecting intrusions in a computer network, the algorithms were ranked using the SCR, DR, FR ranking methods. [ABSTRACT FROM AUTHOR]

As a new type of riser connecting offshore platforms and submarine pipelines, steel catenary risers (SCRs) are generally subject to waves and currents for a long time, thus it is significant to fully evaluate the SCR structure's safety. Aiming at the damage identification of the SCR, the acceleration time series signals at multiple locations are taken as the damage characteristics. The damage characteristics include spatial information of the measurement point location and time information of the acquisition signal. Therefore, a convolutional neural network (CNN) is employed to obtain spatial information. Considering the variable period characteristics of the acceleration time series of the SCR, a gated recurrent unit (GRU) neural network is utilized to study these characteristics. However, neither a single CNN nor GRU model can simultaneously obtain temporal and spatial data information. Therefore, by combining a CNN with a GRU, the CNN-GRU model is established. Moreover, the hyperparameters of deep learning models have a significant influence on their performance. Therefore, particle swarm optimization (PSO) is applied to solve the hyperparameter optimization problem of the CNN-GRU. Thus, the PSO-CNN-GRU (PCG) model is established. Subsequently, an SCR damage identification method based on the PCG model is presented to predict the damage location and degree by SCR acceleration time series. By analyzing the SCR acceleration data, the prediction performances of the PCG model and the PSO optimization capacity are verified. The experimental results indicate that the identification result of the proposed PCG model is better than that of several existing models (CNN, GRU, and CNN-GRU). [ABSTRACT FROM AUTHOR]

This research focuses on employing Recurrent Neural Networks (RNN) to prognosis a wind turbine operation’s health from collected vibration time series data, by using several memory cell variations, including Long Short Time Memory (LSTM), Bilateral LSTM (BiLSTM), and Gated Recurrent Unit (GRU), which are integrated into various architectures. We tune the training hyperparameters as well as the adapted depth and recurrent cell number of the proposed networks to obtain the most accurate predictions. Tuning those parameters is a hard task and depends widely on the experience of the designer. This can be resolved by integrating the training process in a Bayesian optimization loop where the loss is considered as the objective function to minimize. The obtained results show the effectiveness of the proposed method, which generates more accurate recurrent models with a more accurate prognosis of the operating state of the wind turbine than those generated using trivial training parameters.

In view of the low calculation accuracy of physical analytical model of harmonic loss,a support vector regression (SVR) model based on crisscross optimization (CSO) algorithm is proposed to evaluate the harmonic loss of overhead lines. Firstly,the SVR model designed to minimize structural risk is used to fit the relationship between line characteristics and harmonic losses. Then,the SVR hyperparameters are globally searched by the CSO algorithm. The optimal hyperparameter group is obtained by dynamic optimization,and the CSO-SVR harmonic loss evaluation model is established. Based on a large power quality test platform,the harmonic test of low voltage overhead lines is carried out. And the proposed model is verified by the measured data of this test. The results show that using CSO algorithm to optimize hyperparameters of SVR can effectively improve the line loss evaluation performance of SVR model. Compared with other models,the proposed model presents higher accuracy.

The human activity recognition (HAR) field has recently become one of the trendiest research topics due to ready-made sensors such as accelerometers and gyroscopes equipped with smartphones and smartwatches as an embedded devices, decreasing the cost and power consumption. As a result, human activity is considered a time series classification problem. Now a day, deep learning approaches such as Convolutional Neural Network (CNN) have been successful when implemented with HAR to learn automatically higher-order features and, at the same time, work as a classifier. Recently, a one-dimensional Convolutional Neural Network (1D CNN) has been suggested and carried out at the best performance levels in numerous applications, such as the classification of personalized biomedical data and time series classification. This paper studies how to leverage a 1D single CNN model to produce an excellent performance on the human activity raw data. This is done by empirically tuning the values of hyperparameters, such as kernel size, filter maps, number of epochs, batch size, and promoting an advanced multi-headed 1D CNN by employing each convolutional layer with a different kernel size to gain an ensemble–like results. The selected hyper parameter's impact is evaluated on a publicly available dataset named UCI HAR collected from smartphone sensors to perform six activities. A significant determinant of better results depends on the hyperparameter that has been chosen. The results demonstrated that tuning the hyperparameter of 1D CNN increased activity recognition accuracy.