Search

In the past few years, point-of-care testing (POCT) technology has crossed the boundaries of laboratory determination and entered the stage of practical applications. Herein, the latest advances and principal issues in the design and fabrication of paper-based bipolar electrode electrochemiluminescence (BPE-ECL) sensors, which are widely used in the POCT field, are highlighted. After introducing the attractive physical and chemical properties of cellulose paper, various approaches aimed at enhancing the functions of the paper, and their underlying principles are described. The materials typically employed for fabricating paper-based BPE are also discussed in detail. Subsequently, the universal method of enhancing BPE-ECL signal and improving detection accuracy is put forward, and the ECL detector widely used is introduced. Furthermore, the application of paper-based BPE-ECL sensors in biomedical, food, environmental and other fields are displayed. Finally, future opportunities and the remaining challenges are analyzed. It is expected that more design concepts and working principles for paper-based BPE-ECL sensors will be developed in the near future, paving the way for the development and application of paper-based BPE-ECL sensors in the POCT field and providing certain guarantee for the development of human health. • Preparation and application prospect of paper-based BPE-ECL sensor are discussed. • Approaches to boost functionalization of paper and existing limitations are described. • Fabricating BPE from classical electrode materials are introduced exhaustively. • Strategies of enhancing ECL signal to improve device sensitivity are displayed. [ABSTRACT FROM AUTHOR]

Among the properties melatonin is claimed to possess, are the immuno-inflammation inductive capacities that would be responsible of some of the paramount of activities melatonin is reported to have in most of the human pathological conditions. In the present paper, we measured the effect of melatonin on established cellular models of immuno-inflammation, and found none. The discrepancies are discussed, especially because those properties are reported at pharmacological concentration (1 μM and beyond) at which the melatonin receptors are desensitized by internalization, leading to putative non-receptor-dependent mechanism of action. • The melatonin enthusiasts are ruining Science reputation, by claiming facts that are often wishful thinking. • Melatonin is not able to boost most of the actors of the immune system, even at pharmacological concentrations. • We hope to be able to show that some of the activities of melatonin are pure fantasies. [ABSTRACT FROM AUTHOR]

Link prediction is significant in the field of network analysis which helps to determine the future or hidden connections between the entities in a network. Traditional link prediction methods typically utilize single algorithms to make predictions, which might not be optimal for diverse and complex networks. In this research paper, a new framework is proposed which utilizes the existing link prediction algorithms with ensemble techniques. We have explored three ensemble strategies: bagging, boosting, and voting classifier and four individual link prediction algorithms: Adamic Adar, Katz, CCPA, Accurate link prediction. Methods considering ensemble techniques combine multiple individual models to improve prediction accuracy and robustness. We have experimentally compared the performance of proposed framework using six real world datasets in terms of AUC and Accuracy. The results show the superiority of the proposed framework over individual link prediction algorithms. [ABSTRACT FROM AUTHOR]

Station-pair passenger flow forecast modeling is crucial for public transportation to address emerging needs. The accurate prediction and estimation will provide backbone support for various features of transport, viz. (a) Demand forecasting for resource allocation during peak travel periods; (b) Service planning to determine transportation frequency on specific routes; (c) Resource allocation for vehicles and capacity adjustments, including planning for new fleet size; (d) Infrastructure planning to identify areas requiring additional development; (e) Enhancing passenger experience with ample seating and amenities; and (f) Emergency planning for crowd control and passenger safety. Recent advancements in transit information station-pair estimation methods can be implemented with Data Science. Over the years, there has been significant progress in developing innovative modeling approaches to estimate travel behaviour, taking into account various factors such as timeslots, holidays, and other relevant features. In this study, we have synthesized ticket data from Thane Municipal Transport (TMT), collected from e-ticket machines, spanning from January 1 to June 23, 2023, covering all routes and comprising more than 2.80 crore tickets. This paper presents a comprehensive station-pair short-term passenger flow forecast by utilizing three boosting models: extreme Gradient Boosting (XGBoost), Light Gradient Boosting model (LightGBM), and Categorical Boosting model (CatBoost). Their implementation is well-suited based on statistical parameters. The study concludes by comparing the results of the models, considering computation time and statistical parameters, to validate their superiority. By looking into day to day requirements, the LightGBM model is most appropriate for implementation with an accurate result. The research findings contribute to providing valuable data support and a robust scientific foundation for managing passenger flow through route planning and dispatching in urban transit systems. [ABSTRACT FROM AUTHOR]

Existing RGB-D tracking algorithms advance the performance by constructing typical appearance models from the RGB-only tracking frameworks. There is no attempt to exploit any complementary visual information from the multi-modal input. This paper addresses this deficit and presents a novel algorithm to boost the performance of RGB-D tracking by taking advantage of collaborative clues. To guarantee input consistency, depth images are encoded into the three-channel HHA representation to create input of a similar structure to the RGB images, so that the deep CNN features can be extracted from both modalities. To highlight the discriminatory information in multi-modal features, a feature enhancement module using a cross-attention strategy is proposed. With the attention map produced by the proposed cross-attention method, the target area of the features can be enhanced and the negative influence of the background is suppressed. Besides, we address the potential tracking failure by introducing a long-term mechanism. The experimental results obtained on the well-known benchmarking datasets, including PTB, STC, and CTDB, demonstrate the superiority of the proposed RGB-D tracker. On PTB, the proposed method achieves the highest AUC scores against compared trackers across scenarios with five distinct challenging attributes. On STC and CDTB, our FECD obtains an overall AUC of 0.630 and an F-score of 0.630, respectively. • The single-channel depth maps were encoded into three-channel HHA images. • A feature enhancement method with a cross-attention module to enhance features. • A long-term tracking mechanism to detect failures and recapture lost targets. • Experiments were conducted on several standard tracking benchmarking datasets. [ABSTRACT FROM AUTHOR]

The immense growth of Android mobile malware threats has pushed cybersecurity researchers to develop efficient systems that can detect new Android malware. In spite of the academic and industrial attempts to establish a robust, reliable, and efficient solution for Android, malware classification is considered an open problem with many challenges. This paper sheds light on the performance of several machine learning algorithms and analyzes their efficiency in detecting android malware. Moreover, it applies Synthetic Minority Oversampling Technique (SMOTE), normalizes the numerical features and PCA to reach the maximum accuracy. Furthermore, the paper develops a Light Gradient Boosting Model to identify Android malware and classify their families into five classes: Adware, Banking Malware, SMS Malware, Mobile Riskware, and Benign. The paper uses a large and recent dataset, which consists of 11,598 APK collected from several sources and provided by the Canadian Institute of Cybersecurity. [ABSTRACT FROM AUTHOR]

Industry 4.0 uses artificial intelligence and machine learning algorithms to optimize processes. The main goal of the manuscript is to analyze the possibilities of applying automated machine learning to predict company bankruptcy. The data sample consists of financial data of 9,771 manufacturing companies for the years 2020 and 2021 collected from the Finstat database. Two methods of automated machine learning, AutoML and H2O, were tested. The results were compared with five other methods - linear discriminant analysis, logistic regression, naive Bayes classifier, CatBoost and XGBoost. The resulting model was cross-validated through the 10-fold approach. The best results were achieved by H2O automated machine learning algorithm with an AUC of 90.13%, followed by the gradient boosting methods CatBoost with AUC of 90.05% and XGBoost (AUC of 88.61%) and another automated learning algorithm AutoML with AUC of 81.17%. The findings of this paper indicate possibilities to apply automated machine learning methods in predicting bankruptcy. However, it is necessary to distinguish between individual automated machine learning algorithms since they provide a different range of results. [ABSTRACT FROM AUTHOR]

Online measurement of particle size distribution (PSD) of rocks on a conveyor belt is of great significance for intelligent control in process industries. Measurement methods based on the instance segmentation model are often used to measure PSD. However, they have high requirements for the quantity and annotation quality of learning samples, which remains a non-negligible challenge in industrial applications. In this paper, an improved lightweight rock object detection method is proposed. By adding the Convolutional Block Attention Module (CBAM) attention mechanism module to the YOLOv7 model and performing steps such as image rotation, bounding box prediction, and hierarchical clustering of centroid points, the convex hull contour of rock fragments is obtained. The results have been validated and tested on three independent datasets, including a manual sieving case study, demonstrating the effective substitution of instance segmentation with object detection, which meets the measurement accuracy requirements of online PSD. Additionally, this paper proposes a lightweight training dataset and a rotation data augmentation method that enhance the recognition rate during rock rotation with reduced image labeling effort, overcoming the challenges posed by extensive annotation workload. [Display omitted] • Proposed: A novel rotating object detection for rock PSD analysis with rectangular detecting. • A new model integrates CBAM with YOLOv7, enhancing rock fragment detection. • Lightweight training & data augmentation reduce labeling effort while boosting recognition metrics. • Rigorous testing with a manual sieving case study validates the effectiveness of the method. [ABSTRACT FROM AUTHOR]

There has been a growing demand for energy consumption statistics in the manufacturing industry to establish national energy and greenhouse gas policies. Despite its importance, the Korean government faces significant challenges in collecting energy data at a facility level in a precise and timely manner. To address the lack of timely data, this paper employs machine-learning models to predict the annual total energy consumptions of each manufacturing facility. We first designed four prediction models that take into account the characteristics and energy consumption behaviors of industry sub-sectors. As input variables, these prediction models mainly included electricity consumption, employee size, energy types, gas consumption and other accessible data. Finally, we conducted numerical experiments on approximately 100,000 facilities and evaluated the prediction performance of various machine-learning algorithms such as linear regression, decision tree regression, random forest regression, gradient boost regression, and extreme gradient boosting regression. The numerical experiments provided insights into which model and algorithm offer the best prediction performance for each industry sub-sector. In addition, we identified the important variables for predicting total energy consumption, revealing that not only electricity but also various other energy sources and variables representing industry-specific characteristics play a crucial role in improving prediction performance. • This paper predicts the annual total energy consumption of individual manufacturing facilities in Korea. • Several prediction models capable of considering industry-specific features are presented. • This paper employs machine-learning models. • The numerical experiments provided insights into which model and algorithm offer the best prediction performance. • Not only electricity but also variables representing industry-specific characteristics play a crucial role. [ABSTRACT FROM AUTHOR]

• GSOEM-SV was first proposed to predict slope stability. • GSOEM-SV uses a soft voting method to integrate five mesh search hyperparameter optimized models. • GSOEM-SV outperforms 15 improved models and 2 integrated models. • A practical slope stability prediction application was developed based on uni-app. Slope stability evaluation is a complex and uncertain system problem, and carrying out slope stability prediction is the prerequisite and foundation for slope disaster prevention. In order to achieve fast and accurate prediction of slope stability, this paper considers height, total slope angle, unit weight, cohesion, internal friction angle, and pore water pressure ratio as input features and proposes an intelligent slope stability prediction method based on grid search optimization ensemble learning model by soft voting (GSOEM-SV). First, 390 sets of on-site data were collected to form a dataset, and analyses including correlation coefficients, density estimates, and box lines were carried out. Then, the grid search optimization algorithm is used to optimize the hyperparameters of five algorithms—Gradient Boosting Decision Trees, Light Gradient Boosting Machine, Categorical Boosting, Support Vector Machine, and Random Forest, and integrates them through soft voting. Furthermore, this paper optimizes the hyperparameters of the above five algorithms based on grid search, particle swarm and simulated annealing algorithms, builds 15 improved models and 2 ensemble models and conducts comparison. The results reveal that the GSOEM-SV has the highest slope stability prediction accuracy, up to 91 %, the area under the curve (AUC) is 0.950, and its F 1 score 0.917, which are better than the 15 improved and 2 integrated models. In addition, a set of slope stability prediction app based on uni-app is developed in the paper. It provides a technical foundation and an open and shareable information service platform for slope hazard prediction in geotechnical engineering. [ABSTRACT FROM AUTHOR]

• Machine learning based energy prediction for a machining process. • Validation based on complex geometries. • Usage of high-frequency data. Nowadays, the reduction of CO 2 emissions by moving from fossil to renewable energy sources is on the policy of many governments. At the same time, these governments are forcing the reduction of energy consumption. Since large industries have been in the focus for the last decade, today also small and medium enterprises with production lot size one are increasingly being obliged to reduce their energy requirements in production. Energy-efficient CNC machine tools contribute to this goal. In machining processes, the machining strategy also has a significant influence on energy demand. For manufacturing of lot size one, the prediction of the energy demand of a machining strategy, before a part is manufactured plays a decisive role. In numerous previous studies, analytical models between the energy demand and the machining strategy have been developed. However, their accuracy depends largely on the parameterization of these models by dedicated experiments. In this paper, different machine learning algorithms, especially variations of the decision tree ('DecisionTree', 'RandomForest', boosted 'RandomForest') are investigated for their ability to predict the energy demand of CNC machining operations based on real production data, without the need for dedicated experiments. As shown in this paper, the most accurate energy demand predictions can be achieved with the 'RandomForest' algorithm. [ABSTRACT FROM AUTHOR]

For the design of stainless steel bolted connections, current design codes firstly calculate the design resistance of each potential failure mode and then take the minimum of the design resistances calculated from all the potential failure modes as the final design failure load. However, this design framework has been found to be tedious and also leads to inaccurate failure load predictions. In this paper, a more accurate and unified predictive framework for stainless steel bolted connections made of different materials with various configurations and bolt hole patterns at both room and elevated temperatures is proposed based on machine learning. This paper starts with a collection of 301 experimental data of stainless steel bolted connections to establish a database. Then, regression models for failure load predictions were developed and trained by six machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, Adaptive Boosting, Extreme Gradient Boosting and Cat Boosting, with the key hyperparameters for each machine learning algorithm tuned. This is followed by the evaluation of the model performance by means of a series of statistical indices, with the results indicating that the regression model trained by Support Vector Machine has the best model performance. On the basis of the collected experimental data, the regression model trained by Support Vector Machine and current design codes were assessed and compared, showing that the current design codes are rather inaccurate, while the machine-learning-assisted design method is a unified method and can provide accurate and consistent failure load predictions for stainless steel bolted connections made of different materials with various configurations and bolt hole patterns at both ambient and elevated temperatures. • A database of stainless steel bolted plate-to-plate connections was established. • Regression models were developed and trained by six machine learning algorithms. • The regression model with the best performance was compared with existing design codes. • The machine-learning-assisted design method resulted in much improved design accuracy and consistency. [ABSTRACT FROM AUTHOR]

Various stages of highway project construction process involve text, image, audio, video and other related data sources involving many participants, forming a huge amount of data. Accurately tracing the source of responsibility, refining and applying the unbalanced data in the highway project archives is of great significance for realizing the intelligent transformation of highway construction project management. This paper firstly sorts out the construction process of highway projects and the main data sources, constructs a data association network between construction entities and construction process, as well as a knowledge map of highway construction data. Then, according to the highway construction stage, an index system based on 12 key data is constructed by using the entropy weight cloud model method, and the importance of the data is evaluated. Thirdly, based on the unbalanced characteristics of highway project data, a method of mining big data in highway project archives using classification evaluation indexes is proposed, and the accuracy of this method is verified by case calculation. Finally, taking the Shizong Qiubei Expressway in China as an example, the intelligent management and control suggestions for key data of transportation projects are proposed. It is found that the key data with special importance rate in highway construction include construction data, supervision data and completion data. Boosting algorithm is more accurate than the traditional SMOTE algorithm for unbalanced data mining, which helps to save the project construction cost and improve the quality of data extraction in the project archives. This study provides a theoretical reference for key data traceability of highway project intelligent management and control platform and the improvement of intelligent management efficiency. [ABSTRACT FROM AUTHOR]

• This paper is dedicated to vehicle-bicycle crash severity modeling. • The class-imbalanced issue in vehicle-bicycle crash severity analysis is handled with the imbalanced data resampling process. • To address the complexity of crash dataset, the learning-based feature extraction process is adopted in an iterative manner, such that the the most significant contributing factors to the severity of vehicle-bicycle crashes are determined and the trade-off between computation time and model performance is catered for. • The vehicle-bicycle crash dataset in this paper contains a large number of discrete variables. The gradient boosting algorithm is applied to handle the large number of categories and does not rely on strict statistical assumptions. • The impact of the most significant contributing factors on the severity of vehiclebicycle crashes are explained with the marginal effect analysis. • The result can provide some implications for policies and counter-measures for fatal and serious vehicle-bicycle crashes. Introduction: Although cycling is increasingly being promoted for transportation, the safety concern of bicyclists is one of the major impediments to their adoption. A thorough investigation on the contributing factors to fatalities and injuries involving bicyclist. Method: This paper designs an integrated data mining framework to determine the significant factors that contribute to the severity of vehicle-bicycle crashes based on the crash dataset of Victorian, Australia (2013–2018). The framework integrates imbalanced data resampling, learning-based feature extraction with gradient boosting algorithm and marginal effect analysis. The top 10 significant predictors of the severity of vehicle-bicycle crashes are extracted, which gives an area under ROC curve (AUC) value of 0.8236 and computing time as 37.8 s. Results: The findings provide insights for understanding and developing countermeasures or policy initiatives to reduce severe vehicle-bicycle crashes. [ABSTRACT FROM AUTHOR]

Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a functional variable. This paper proposes to build upon the proximal point algorithm, when the empirical risk to minimize is not differentiable, in order to introduce a novel boosting approach, called proximal boosting. It comes with a compagnon algorithm inspired by Grubb and Bagnell (2011) and called residual proximal boosting , which is aimed at better controlling the approximation error. Theoretical convergence is proved for these two procedures under different hypotheses on the empirical risk and advantages of leveraging proximal methods for boosting are illustrated by numerical experiments on simulated and real-world data. In particular, we exhibit a favorable comparison over gradient boosting regarding convergence rate and prediction accuracy. [ABSTRACT FROM AUTHOR]

The peak shear strength of clayey soil-geomembrane interfaces is a vital parameter for the design of relevant engineering infrastructure. However, due to the large number of influence factors and the complex action mechanism, accurate prediction of the peak shear strength for clayey soil-geomembrane interfaces is always a challenge. In this paper, a machine learning model was established by combining Mind Evolutionary Algorithm (MEA) and the ensemble algorithm of Adaptive Boosting Algorithm (ADA)-Back Propagation Artificial Neural Network (BPANN) to predict the peak shear strength of clayey soil-geomembrane interfaces based on the results of 623 laboratory interface direct shear experiments. By comparing with the conventional machine learning algorithms, including Particle Swarm Optimisation Algorithm (PSO) and Genetic Algorithm (GA) tuned ADA-BPANN, MEA tuned Support Vector Machine (SVM) and Random Forest (RF), the superior performance of MEA tuned ADA-BPANN has been validated, with higher predicting precision, shorter training time, and the avoidance of local optimum and overfitting. By adopting the proposed novel model, sensitivity analysis was carried out, which indicates that normal pressure has the largest influence on the peak shear strength, followed by geomembrane roughness. Furthermore, an analytical equation was proposed to assess the peak shear strength that allows the usage of machine learning skills for the practitioners with limited machine learning knowledge. The present research highlights the potential of the MEA tuned ADA-BPANN model as a useful tool to assist in preciously estimating the peak shear strength of clayey soil-geomembrane interfaces, which can provide benefits for the design of relevant engineering applications. • The ensemble artificial intelligence algorithms in predicting the peak shear strength of interfaces is compared. • An analytical equation for estimating the peak shear strength is proposed. • Physical experiments are conducted to validate the effectiveness of the proposed analytical equation. [ABSTRACT FROM AUTHOR]

In this paper, we present a machine learning based High-Level Synthesis (HLS) design space explorer (DSE) that significantly reduces the exploration runtime while leading to very accurate results. In order to do so, we leverage the power of low level virtual machine (LLVM) to generate the features used in the machine learning (ML) model. The proposed design space explorer uses a modified version of simulated annealing (SA) algorithm, where initially the search space is sampled to generate the predictive model. In this work we used gradient boost regression algorithm as our preferred ML model and achieve comparable results as a full DSE that performs logic synthesis for each newly generated design. • Proposed a method to converts untimed C/C++ descriptions for HLS into LLVM IR codes. • The IR code and the graphs are used to generate features for predictive models. • A gradient boost model is used to predict post route area and latency of the design. • A fast ML based design space explorer is proposed using the gradient boost model. [ABSTRACT FROM AUTHOR]

This paper proposes an integrated framework of remote sensing and machine-learning techniques to predict municipal wastewater influent biochemical oxygen demand (BOD5) in wastewater treatment plants (WWTPs). The study compares the performance of several supervised machine-learning algorithms, specifically decision tree, random forest, adaptive boosting, gradient boost, and extreme gradient boosting algorithms, against the wastewater received by two WWTPs in South Kingdom of Bahrain. The gradient boost algorithm model obtained the best results, scoring 1.00 coefficient of determination (R2) and 0.08 mean absolute error (MAE) against Askar WWTP dataset. In addition, the developed model showed its applicability and robustness against Al Dur WWTP dataset scoring 0.95 R2 and 3.93 MAE. This study showed that empirically, using a manual sampling method to obtain developed model input feature readings, the duration of the results can be accelerated by 40 times compared to traditional laboratory procedures. As a result, the duration was reduced from five days to only three hours. On the contrary, using real-time sensors to obtain developed model input readings, BOD5 can be predicted in real-time. The proposed approach mitigates environmental risks and ensures an effective treatment process that meets the effluent quality parameters. [Display omitted] [ABSTRACT FROM AUTHOR]

Sentiment analysis has become a state-of-the-art to make products market adaptive and understand the market gaps to launch updates and variants of a product entity. The contributions of this paper are providing prior point of sale based key features to generate rule based algorithms to predict the attitude and opinion implied. Amazon food reviews data has been used in the paper. We have done a comparative analysis of Random Forest and Extreme Gradient Boosting model using Bag of Words(BoW) and Term Frequency-Inverse Document Frequency(TFIDF) featurizations. [ABSTRACT FROM AUTHOR]

• An experimental system for noise recognition based on PIND system is established. • The proposed method improves the recognition effect by fusing the feature extraction capabilities of multiple individual models. • Creatively adding the recognition results of each layer to the original samples as new features. The detection and identification of the noise of the movable parts in a sealed cavity are of great reference significance for the fault analysis of the sealed equipment. However, traditional machine learning algorithms have the problem that it is difficult to distinguish the noise signal generated by the internal movable parts from the collision signal generated by the movable objects in a sealed cavity. Therefore, this paper proposes a fusion machine learning (FML) method based on Boosting algorithm to improve the accuracy of noise signals recognition. First of all, data were collected using the experimental platform, and then the feature selection was performed to establish the noise signal datasets. Finally, the noise identification of the internal movable parts was realized by FML, and its parameters were optimized. FML consists of a three-layer algorithm. The first layer recognition algorithm is used to identify the noise data set D1, and then adds its noise recognition result as a new feature to the original sample to form the data set D2. The second layer algorithm is used to identify D2 and then add the output noise recognition result to the data set D2 as a new feature to form D3. The third layer algorithm is used to identify noise in data set D3. Simulation experiments are carried out in this paper to verify the proposed method's effectiveness. The results show that the recognition accuracy of FML is 7.6 % higher than that of the traditional Stacking algorithm. The training time of the Stacking algorithm is more than 2 times higher than that of FML and more than 4 times higher on UCI datasets. In addition, the algorithm is also significant in innovating fusion methods and expanding the scope of adaptation. [ABSTRACT FROM AUTHOR]

Continued increases in global population and rising living standards in many countries are driving a surge in demand for energy and protein-rich foods. Wheat, barley, and canola are important crops that are grown and traded globally. However, climate change, geopolitical tensions and competition from other crops threaten the ability to satisfy global demand. Accurate predictions of crop production and its spatial variation can play a significant role in their reliable and efficient production, marketing, and distribution. This review examined recently published models and data used to predict wheat, barley, and canola yield to identify which factors produced the best yield predictions. A literature search was conducted across the Scopus, EBSCOhost and Web of Science databases over seven years between 2015 and 2021. Data extracted from the papers identified by the literature search were investigated using graphical and quantitative analytical techniques to determine if the type of algorithm, input data, prediction timing, output scale or extent and climate variability both in isolation and in combination affected the model's predictive ability. The literature search produced 11,908 results which was reduced to 118 papers after applying the review criteria (peer reviewed papers focussed on models predicting yield at greater than plot scale across extensive areas using accessible data). China produced almost one third of all yield prediction models over the study period and 87% of models were used to predict wheat yield. Statistical models were the most common algorithm in most regions and in total. However, there was a surge in machine learning models after 2018. They were the most common model from 2019 to 2021, with one third developed in China. The review concluded that only the choice of modelling technique and the input data had a significant effect on model performance with the machine learning techniques Random Forest, Boosting algorithms and Deep Learning models as well as process-based Light Use Efficiency models that used a combination of remotely sensed and agrometeorological data performing best. The review showed that matching the model to the available data could improve the ability to predict wheat, barley or canola yield. The use of quantitative statistical techniques in this review, should give modellers trying to predict wheat, barley or canola yield more confidence in matching their approach to the available data than previous reviews that relied on visual interpretation of data. [Display omitted] • Recent advances in models and data used to predict crop yield were examined to identify any patterns and trends. • Statistical models were the most common but there was a surge in the use of machine learning models after 2018. • Quantitative analytical techniques were used to identify factors that affected the model's predictive ability. • Machine learning models were more accurate than process-based models but not statistical models. • Combining agro-meteorological with remotely sensed data was more accurate than using agro-meteorological data only. [ABSTRACT FROM AUTHOR]

Hyperparameter Optimization (HPO) aims to tune hyperparameters for a system in order to improve the predictive performance. Typically, only the hyperparameter configuration with the best performance is chosen after performing several trials. However, some works try to take advantage of the effort made when training all the models with every hyperparameter configuration trial and, instead of discarding all but one, they propose performing an ensemble of all the models. However, this ensemble consists of simply averaging the model predictions or weighting the models by a certain probability. Recently, some of the so-called Automated Machine Learning (AutoML) frameworks have included other more sophisticated ensemble strategies, such as the Caruana method or the stacking strategy. On the one hand, the Caruana method has been shown to perform well in HPO ensemble, since it is not affected by the issues caused by multicollinearity, which is prevalent in HPO. It just computes the average over a subset of predictions, previously chosen through a forward stepwise selection with replacement. But it does not benefit from the generalization power of a learning process. On the other hand, stacking approaches include a learning procedure since a meta-learner is required to perform the ensemble. Yet, one hardly finds advice about which meta-learner can be adequate. Besides, some possible meta-learners may suffer from problems caused by multicollinearity or need to be tuned in order to mitigate or reduce this obstacle. In an attempt to reduce this lack of advice, this paper exhaustively explores possible meta-learners for stacking ensemble in HPO, free of hyperparameter tuning and able to mitigate the problems derived from multicollinearity as well as taking advantage of the generalization power that a learning process may include in the ensemble. Particularly, the boosting strategy shows promise in this context as a stacking meta-learner, since it satisfies the required conditions. In addition, boosting is even able to completely remove the effects of multicollinearity. This paper provides advice on how to use boosting as a meta-learner in the stacking ensemble. In any case, its main contribution is to propose an implicit regularization in the classical boosting algorithm and a novel non-parametric stop criterion suitable only for boosting and specifically designed for the HPO context. The existing synergy between these two improvements performed over boosting exhibits competitive and promising predictive power performance as a stacking meta-learner in HPO compared to other existing meta-learners and ensemble approaches for HPO other than the stacking ensemble. [ABSTRACT FROM AUTHOR]

As a metabolic disease, diabetes is a serious threat to human health, in which type 2 diabetes (T2D) constitutes about 90% of diabetic cases. As the disease progresses, T2D often comes with various complications such as kidney disease and retinopathy, which may cause huge threats to patients' health. In recent years, complication prediction of T2D has gained wide research interest as early disease detection and management can effectively reduce the risk of death. In this paper, to break through the limitation of the available data and achieve higher overall prediction accuracy, an improved feature space-based gradient boosting regression tree ensemble (IFS-GBRTE) approach is proposed for the risk prediction of developing T2D complications. Specifically, the original feature space is expanded based on existing feature generation theories. Then the new feature space is refined by comparing the total contribution of each feature during the construction of a classification and regression tree (CART) under a cross-validation scheme. Finally, a gradient boosting ensemble algorithm using CART as base learners is utilized for model training. The prediction model is validated on the T2D data provided by the China National Clinical Medical Science Data Center. The experimental results show that the proposed IFS-GBRTE achieves 82.49% accuracy and realizes better generalization ability than compared single models and ensemble learning models, meanwhile it is helpful to obtain more effective predictive variables for improving the accuracy of risk prediction of T2D complications, which is of great significance for achieving the early prevention, screening and nursing of complications, and further reducing mortality and save medical resources. • This paper develops a risk prediction model for type 2 diabetes complication forecast. • An expanded feature space-based gradient boosting ensemble learning method is proposed. • An efficient feature expansion, evaluation, and selection mechanism is investigated. • Experiments using real-world type 2 diabetes data verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Distance metric learning plays a significant role in improving the generalization of algorithms related to distance metrics. In this paper, we first propose a generalized Mahalanobis metric learning framework (called GLML) to make use of the prior knowledge from the samples including global and local information, the main goal of which is to enlarge the distance of dissimilar sample pairs and shrink the distance of similar sample pairs simultaneously. Specifically, the metric learning problem is guided by a discriminative regularization through incorporating the pair-wise and class-wise information. Moreover, an effective alternating iterative algorithm is developed to optimize the proposed GLML, and the convergence of the algorithm is demonstrated theoretically. Then a boosting algorithm of GLML (BGLML) is proposed, where the low-rank basis learning is jointly optimized with the metric to better uncover the data structure and mitigate the computational burden. Following that, numerical experiments are carried out on binary classification and multi-classification problems. With different assessment criteria, experiment results from different scale datasets confirm that the proposed methods either improve generalization or have comparable results compared with the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

• New tree-based method for ranking tasks in imbalanced settings. • Direct optimization of the average precision during the meta-tree construction. • Comparison to tree-based methods as well as random forests and gradient tree boosting methods. • Inference of interpretable models to support decision making for tax fraud detection. In this paper, we address the challenging problem of learning to rank from highly imbalanced data. This scenario requires to resort to specific metrics able to account the scarcity of the so-called positive examples. We present MetaAP , a tree-based ranking algorithm, which induces meta-trees by optimizing directly during the learning process the Average Precision (AP). This latter has been shown to be more relevant than the area under the ROC curve (AUC – ROC) when the objective is to push the examples of interest at the very top of the list. This effect of the AP in tree-based ranking is particularly wished to address fraud detection tasks where (i) the budget is often constrained (in terms of possible controls) and (ii) the interpretability of the induced models is required to support decision making. After an extensive comparative study on 28 public datasets showing that MetaAP is significantly better than other tree-based ranking methods, we tackle a tax fraud detection task coming from a partnership with the French Ministry of Economy and Finance. The results show that MetaAP is able to make the tax audit process much more efficient. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach that merges a lightweight parallel depth-wise separable convolutional neural network (LPDCNN) with a ridge regression extreme learning machine (Ridge-ELM) for precise classification of three lung cancer types alongside normal lung tissue (adenocarcinoma, large cell carcinoma, normal, and squamous cell carcinoma) using CT images. The proposed methodology combines contrast-limited adaptive histogram equalization (CLAHE) and Gaussian blur to enhance image quality, reduce noise, and improve visual clarity. The LPDCNN extracts discriminant features while minimizing computational complexity (0.53 million parameters and 9 layers). The Ridge-ELM model was developed to enhance classification performance, replacing the traditional pseudoinverse in the ELM approach. Through comprehensive evaluation against state-of-the-art models, the framework achieves remarkable average recall and accuracy values of 98.25 ± 1.031 % and 98.40 ± 0.822 %, respectively, through rigorous five-fold cross-validation for four-class classifications. In binary classifications, outstanding results are obtained with recall and accuracy values of 99.70 ± 0.671 % and 99.70 ± 0.447 %%, respectively. Notably, the framework exhibits exceptional efficiency, with a testing time of only 0.003 s. Additionally, integrating the SHAP (Shapley Additive Explanations) in the proposed framework enhances Explain-ability, providing insights into decision-making and boosting confidence in real-world lung cancer diagnoses. [ABSTRACT FROM AUTHOR]

Tube bending is a widely used process in marine, automotive, construction and other industries. Different methods are available for this process during which various problems and defects are encountered. This paper aims to develop the most relevant model for bending the tubes using a computer numerical controlled (CNC) bending machine on the first attempt without any defects. To achieve this goal, the parameters affecting the tube bending process on the bending machine are defined. Based on these parameters, 150 bending experiments are conducted in an industrial plant to collect data and their results are used as dataset for machine learning (ML) algorithms. Seven different state-of-the-art ML algorithms –logistic regression, decision tree, k-nearest neighbor, random forest, Naïve Bayes, support vector machine and eXtreme gradient boosting (XGBoost)– are implemented using Python's Scikit-Learn library. Their performance is compared using confusion matrix and classification metrics such as accuracy, precision, recall, F1-score, receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) value. Considering all the performance metrics, logistic regression performed best in terms of prediction on our dataset. XGBoost and support vector machine were quiet successful based on F1 score and AUC, respectively. Overall, logistic regression, Naïve Bayes, Support Vector Machine, and XGBoost showed performances above 90% across all metrics. Decision tree, k-nearest neighbor and random forest performed poorly compared to other algorithms for our data. The proposed ML method is expected to save costs by reducing material waste and labor time and to increase the process efficiency and the product quality. [ABSTRACT FROM AUTHOR]

This paper introduces an improved differential evolution algorithm based on cooperative multi-population (CMp-DE for short), which combines diverse population collaboration mechanisms and catalytic factors into an improved differential evolution framework. By harnessing various population collaboration mechanisms, the algorithm enhances the diversity of individuals within populations during initial iterations and reduces it during later iterations, thereby harmonizing the algorithm's exploratory and exploitative capabilities. Furthermore, a novel mutation operator is proposed that divides the iterative process into exploration and exploitation phases, thereby augmenting the algorithm's global exploration prowess. Lastly, a catalytic operator is introduced to generate new individuals near post-crossover individuals based on a specified rule, which enhances the algorithm's ability to escape local optima and increasing stability. The proposed CMp-DE is benchmarked against the CEC2017 benchmark test functions and compared against 13 algorithms, including five differential evolution algorithms and their variants, as well as eight state-of-the-art metaheuristic optimization algorithms. This evaluation assesses the CMp-DE's solution accuracy, convergence, stability, and scalability. Finally, the applicability of CMp-DE is validated by addressing six practical optimization problems. The experimental results show that CMp-DE surpasses other algorithms in terms of both convergence accuracy and robustness. Moreover, integrating a catalytic operator with other optimization algorithms notably boosts performance in convergence accuracy and stability. The inclusion of the catalytic operator has significantly enhanced the performance of algorithms compared to their performance before its addition. This underscores the potential of the catalytic operator in improving the performance of various algorithms, particularly in terms of convergence accuracy and robustness. [ABSTRACT FROM AUTHOR]

Modernizing traditional power grids into smart grids represents a significant advancement in improving efficiency and sustainability within the energy sector. However, integrating renewable energy sources and the intricate network of interconnected devices has presented new challenges, especially in grid stability. Anticipating and maintaining grid stability ensures a continuous energy supply and prevents potential disruptions. This research paper explores the smart grid stability issue through machine learning. Two distinct scenarios are examined. In the first scenario, the problem is approached as a binary classification task, where grid states are categorized as stable or unstable, a well-established method for addressing grid stability. In the second scenario, an effort is made to predict continuous values that reflect the degree of grid stability. These continuous values are subsequently mapped to a conditional function, facilitating stability detection based on a predefined threshold. To address data imbalance, two balancing strategies, specifically the Synthetic Minority Over-sampling Technique (SMOTE) and K-means SMOTE, are employed in each scenario. The analysis covers a range of regressors and classifiers, focusing on tree-based models, boosting algorithms, ensemble learners, and Multilayer Perceptrons (MLP). The investigation results demonstrate that combining the K-means SMOTE strategy with the CatBoost Classifier in the first scenario achieves the highest accuracy, reaching an impressive 99.6%, and an exceptional ability to detect grid instability, achieving 100% accuracy. Furthermore, the results of the second scenario are promising, with accuracy rates reaching 99.4%, thanks to the utilization of a stacking ensemble learner. Notably, this study introduces Explainable AI, a groundbreaking initiative in this field, to delve into the inner workings of the proposed models and enhance their transparency. This pioneering effort marks a significant step forward in understanding and optimizing the predictive capabilities of machine learning models applied to smart grid stability. [Display omitted] • Reframing the smart grid stability problem as a regression task. • Underscoring the significance of predicting the grid stability value. • Assessing the impact of data balancing strategies on the prediction results. • Evaluating several classifiers and regressors for smart grid stability. • Achieving 100% instability detection accuracy using K-means SMOTE and CatBoost. • Pioneering eXplainable AI (XAI) techniques to enhance model transparency. [ABSTRACT FROM AUTHOR]

• A novel post-earthquake, rapid failure mode identification methodology is proposed. • Surface crack and crushing pattern of RC columns are quantified by three indices. • Ten image-based scenarios according to the availability of indices are considered. • Eight ML-based models are trained and validated through 5-fold cross validation. • High accuracy of models for various ML algorithms and scenarios are achieved. The seismic failure mode identification of reinforced concrete columns is crucial for post-earthquake stability and safety assessment of the damaged concrete buildings. In this paper, a multi-feature crack image-based methodology is proposed for non-destructive non-contact failure mode prediction in reinforced concrete columns damaged in an earthquake. A databank of 455 surface crack patterns from quasi-static experiments on 111 reinforced concrete columns with a variety of structural and geometric properties is collected by the authors aimed at the development and validation of the methodology. For the intricacy retrieval of the surface crack maps, multi-feature fractal-based procedures are taken into consideration. Various machine learning algorithms are employed to train the seismic failure mode predictive models using the characteristics of the damaged RC columns. Ten scenarios are defined based on the image-extracted indices, and structural and geometric characteristics of rectangular reinforced concrete columns. Hyperparameter tuning of the machine learning algorithms using GridsearchCV function has optimized the performance of the models. A k-fold cross-validation procedure is also executed to examine the robustness of the results. Results reveal that the predictive model in which the image-extracted indices and structural parameters are jointly used as input features of supervised learning provides 98% accuracy for the testing dataset with Extreme gradient boost algorithm. In addition, among the scenarios that only image-derived parameters are considered as input features, an accuracy of 83% is obtained with Extreme gradient boost algorithm for the testing dataset. [ABSTRACT FROM AUTHOR]

This paper presents data-driven models for photovoltaic module temperature prediction and analyzes the relation and effects of ambient conditions to module temperature. A total of 12 different machine learning and regression algorithms are implemented, with a large experimental dataset of 345,600 × 7. Prior to implementing those algorithms, data preprocessing is performed to prepare the datasets and determine the informative attributes for the models. Using PCA with module temperature as target to predict, the selected features for models' inputs were determined to be ambient temperature, solar radiation, wind speed, and relative humidity, and each algorithm is cross-validated and tuned with optimal performance parameters. Results show that while relative humidity is more likely to introduce less information to the model, other aforementioned features are the important parameters to predict the module temperature. While for linear modeling, LASSO algorithm provided the best performance, the ANN model demonstrated the best overall results as it produced the most accurate predictions with lowest errors. A similar performance is attained by the proposed non-linear model, KRR and Gradient Boosting algorithm, with a slight advantage to the KRR model. Furthermore, in comparison to experimental data, the ANN model and the proposed non-linear model provided an R2 values of 0.986 and 0.981, with a MAE of 0.982 and 1.476, and MSE of 2.181and 3.464, respectively. Moreover, the proposed model supplied accurate results when compared to models from literature in an out-of-sample testing, it also proven to be robust and accurate when used to predict the PV power output. • Prediction of photovoltaic module temperature considering ambient weather conditions. • Predictive models have been developed using twelve different machine learning and regression algorithms. • Ambient temperature and solar radiation are key parameters and important variables to predict the PV module temperature. • The performance of developed models was evaluated and compared with other models in the literature. [ABSTRACT FROM AUTHOR]

• A database on compressive strength of recycled aggregate concrete is built up. • The compressive strength prediction models with high accuracy are constructed. • The multi-objective optimization design of recycled aggregate concrete mixture proportions based on machine learning and NSGA-II algorithm is carried out. • The influence factors on compressive strength of recycled aggregate concrete are analyzed. This paper employs Support Vector Regression (SVR), Random Forest Regression (RF), Gradient Boosting (GB), and Extreme Gradient Boosting (XGB) algorithms to establish the compressive strength prediction models for Recycled Aggregate Concrete (RAC) and analyze the influence of ten inputs on RAC compressive strength. Combined with the best prediction model, the Non-dominated Sorting Genetic Algorithm Ⅱ (NSGA-II) is applied for multi-objective optimization of mixture proportions in RAC addressing cost, carbon emissions, and compressive strength as key objectives. The results demonstrate that the RAC compressive strength prediction model using the GB algorithm exhibits the highest accuracy, with the R2 value of 0.99 for the training set and 0.85 for the testing set. Feature importance and SHAP analysis reveal that cement and water contents are the primary factors affecting the compressive strength of RAC. Among the three mineral admixtures including Silica Fume (SF), Fly Ash (FA), and Ground Granulated Blast Furnace Slag (GGBFS), SF exhibits superior improvement in the compressive strength of RAC compared to FA and GGBFS. Partial dependency plot analysis indicates that concrete strength remains unaffected by recycled coarse aggregate content within the range of 0 to 300 kg/m3. Pareto fronts of a tri-objective mixture optimization problem for RAC are successfully obtained through the GB model combined with the NSGA-II algorithm, which can guide the optimization of RAC preparation. [ABSTRACT FROM AUTHOR]

OWL ontologies are nowadays a quite popular way to describe structured knowledge in terms of classes, relations among classes and class instances. In this paper, given an OWL ontology and a target class T , we address the problem of learning fuzzy concept inclusion axioms that describe sufficient conditions for being an individual instance of T (and to which degree). To do so, we present Fuzzy OWL-Boost that relies on the R eal AdaBoost boosting algorithm adapted to the (fuzzy) OWL case. We illustrate its effectiveness by means of an experimentation with several ontologies. [ABSTRACT FROM AUTHOR]

Efficient utilization of forestry, agriculture, and marine resources in various manufacturing sectors requires optimizing fiber transformation, dewatering, and drying energy consumption. These processes play a crucial role in reducing the carbon footprint and boosting sustainability within the circular bioeconomy framework. Despite efforts made in the paper industry to enhance productivity while conserving resources and energy through lower grammage and higher machine speeds, reducing thermal energy consumption during papermaking remains a significant challenge. A key approach to address this challenge lies in increasing dewatering of the fiber web before entering the dryer section of the paper machine. Similarly, the production of high-value-added products derived from alternative lignocellulosic feedstocks, such as nanocellulose and microalgae, requires advanced dewatering techniques for techno-economic viability. This critical and systematic review aims to comprehensively explore the intricate interactions between water and lignocellulosic surfaces, as well as the leading technologies used to enhance dewatering and drying. Recent developments in technologies to reduce water content during papermaking, and advanced dewatering techniques for nanocellulosic and microalgal feedstocks are addressed. Existing research highlights several fundamental and technical challenges spanning from the nano- to macroscopic scales that must be addressed to make lignocellulosics a suitable feedstock option for industry. By identifying alternative strategies to improve water removal, this review intends to accelerate the widespread adoption of lignocellulosics as feasible manufacturing feedstocks. Moreover, this review aims to provide a fundamental understanding of the interactions, associations, and bonding mechanisms between water and cellulose fibers, nanocellulosic materials, and microalgal feedstocks. The findings of this review shed light on critical research directions necessary for advancing the efficient utilization of lignocellulosic resources and accelerating the transition towards sustainable manufacturing practices. [Display omitted] • One key strategic issue facing the forest products industry is the high energy requirements. • The nature of interactions, association, and bonding of lignocelluloses is essential. • Alternative enzymatic treatments targeting the fiber surface can increase dryness while reducing the need for refining. • An understanding of floc formation and micro and nano-fines migration mechanisms is required. • Nanocellulose and microalgal dewatering is critical to enable braoder applicaitons. [ABSTRACT FROM AUTHOR]

• Eight machine learning models are developed to predict shear capacity of recycled aggregate concrete (RAC) slender and deep beams. • A database of 401 RAC beam shear tests, among them, 264 sorted as the slender beams, and 137 as deep beams is assembled. • Xgboost ensemble learning model demonstrated excellent performance against experimental results. • Four widely used code equations are compared against the machine learning predictions. • The RAC beams with recycled aggregate replacement ratio above the 40% leads to lower shear resistance. Recycled aggregate concrete (RAC) has gradually received attention in recent years for sustainable development. However, the adaptation of RAC for structural elements is becoming less popular due to the lack of proper design guidelines. Thus, to encourage the structural application of RAC, it is essential to develop a framework for predicting the shear capacity of RAC beams. The data-driven prediction has demonstrated excellent accuracy compared to traditional empirical equations. This study proposed a data-driven framework using machine learning. In this paper, 401 samples of different RAC beams are analysed, including 264 slender beams and 137 deep beams. Eight machine learning (ML) algorithms namely Linear Regression, K-nearest neighbour, Random Forest, Adaptive boosting, Gradient Boosting, Extreme gradient boosting (XGBoost), Category Boosting, and Light Gradient Boosting Machine were employed to develop the best ML-based framework. Having the best prediction output (R2 score: 0.95 in slender beam, 0.78 in deep beam), XGBoost is selected to further analyse the feature importance and parametric study with SHapley Additive exPlanations (SHAP). Simultaneously, the experiment values were compared with calculated values according to the codes in different regions, such as ACI-381-19, AS3600-2018, Eurocode 2, and GB50010-2010. The results of SHAP from XGBoost indicate that the replacement ratio of RCA has limited influence on normalized shear strength value, V u / b d , and it is applicable to adopt RAC without shear strength reduction if the replacement ratio of RA is lower than 40%. Nevertheless, the comparison of experiment value from the database and calculated value according to classical analytical methods demonstrates the necessity for adjustment to existing design codes against RAC replacement ratio. Some suggestions which could further improve the accuracy of results are provided at the end of this paper as well. [ABSTRACT FROM AUTHOR]

For a secure multimedia data exchange, watermarking is used. Generally, meta-heuristic optimization is required to optimize scheme parameters in the watermarking embedding. Even though meta-heuristic methods have been widely used because of their enhancing capability, due to their large time consumption nature they are not applicable for time-sensitive applications. This paper proposes a time efficient optimization method based on machine learning algorithms to detect the best embedding parameter for image watermarking with both robustness and imperceptibility. Initially, for providing robustness against watermarking attacks, a method for watermarking embedding is designed in the domain of Discrete Cosine Transform. After that, Ant Colony optimization is used for finding the optimization parameters. Then an observation data is obtained, which includes the feature vector and optimum strength values of the training images. The image features are extracted at different embedded strength values by the calculation of optimum fitness function. Finally Light Gradient Boosting algorithm (LGBA) is applied to predict the optimum embedding parameters of the set of new images which are to be watermarked. When compared with the existing optimization methods, it has been found that the proposed method consumes very less time for the evaluation of optimum solutions. From the results, it has been identified that the proposed algorithm satisfies the image watermarking with the improvement in time enhancement. The effectiveness of the proposed method is analyzed using MATLAB 2018b. [ABSTRACT FROM AUTHOR]

This paper aims to propose a new hybrid Machine Learning (ML) with Egret Swarm Optimization Algorithm (ESOA) and Weighted Relevance-based Combination Strategy (WERCS) methods for predicting the patch loading resistance (PLR) of both longitudinally unstiffened and stiffened plate girders. A dataset of both stiffened and unstiffened plate girders under patch loading are collected and used for training and testing to generate the proposed models. Firstly, the WERCS method is used to resample the training set to improve the performance of training data. After that, four ML models, including Gradient Boosted Tree (GTB), Extreme Gradient Boosting algorithm (XGB), Artificial neural network (ANN), and CATBoost regression (CAT) are employed. The hyperparameter of all above ML models are optimized by using ESOA algorithm to choose the best performance models. It was found that the WERCS influences considerably the performance of hybrid ML models, and the WERCS + ESOA + XGB model presents the best performance compared to others. The accuracy of the WERCS + ESOA + XGB model is validated by comparing its predictive results with the existing design codes and formulae. Additionally, the Local Interpretable Model-Agnostic Explanations (LIME) method is used to assess the importance and contributions of each input variable in the proposed model. This algorithm can explain the global and local effects of features with each range and create favourable foundations for practical designing. A Graphical User Interface (GUI) tool is developed to conveniently estimate both the patch loading resistance of longitudinally unstiffened and stiffened plate girders. A Python library has been developed and uploaded to PyPi for more convenient use without the need for accessing the source code. [ABSTRACT FROM AUTHOR]

To accurately predict the existing tunnel deformation from adjacent foundation pit construction (AFPC), a hybrid prediction framework based on random forest recursive feature elimination and the Bayesian optimization natural gradient boosting algorithm (RF-RFE-BO-NGBoost) is presented in this paper. The key findings from this study include the following: (1) RF-RFE effectively screens out crucial parameters, with the optimal feature subset postscreening encompassing ten influencing factors. (2) The BO-NGBoost-based prediction model for existing tunnel deformation from AFPC achieves high accuracy, with R2 values ranging from 0.914 to 0.935, RMSE values ranging from 0.104 to 0.364, MAE values ranging from 0.089 to 0.335, and MAPE values ranging from 3.08% to 10.71% (3) SHapley Additive ExPlanations (SHAP) determines the contribution of each parameter, identifying important construction parameters influencing existing tunnel deformation. The hybrid prediction framework proposed herein provides guidance for realizing the excavation safety management of existing tunnels. • A method for predicting the adjacent existing tunnel deformation caused by foundation pit construction is proposed. • RF-RFE is used to screen out important parameters and BO-NGBoost is used to predict existing tunnel deformation. • The contribution of each parameter to the model output is analyzed using SHAP. • A tunnel construction example in China is taken as an example for verification. [ABSTRACT FROM AUTHOR]

Modeling solar plants, like Linear Fresnel Reflectors, plays an essential role in analyzing plant characteristics, assessing overall efficiency, designing appropriate controllers, and optimizing system's operation. Although physical modeling approaches are widely used, their accuracy when compared to real operational data is deficient. In this context, this paper conducts a novel and comprehensive investigation for an existing Linear Fresnel Reflector using six distinct machine learning algorithms namely, Multilayer Perceptron and LSTM Neural Networks, Random Forest, Decision Trees, Extreme Gradient Boosting, and K-Nearest Neighbours to forecast the useable output power of a linear Fresnel solar plant. Datasets between May 2018 and September 2019 with a 30-s time interval from a linear Fresnel plant located in Nicosia, Cyprus are used in this research. Seven distinct statistical metrics, in conjunction with the computation time are employed to assess the performance of the different machine learning models. The objective of this study is to further improve the prediction of Linear Fresnel Reflectors performance using machine learning model, in order to increase modeling reliability on an annual basis. Outcomes reveal that, among the various models considered, K-Nearest Neighbours demonstrated the most optimal performance with a coefficient of determination 98.81 % and a mean absolute percentage error of 1.975 %. [ABSTRACT FROM AUTHOR]

This paper presents a novel Iterative Bidirectional Gradient Boosting Model (IBi-GBM) for estimating the baseline of Conservation Voltage Reduction (CVR) programs. In contrast to many existing methods, we treat CVR baseline estimation as a missing data retrieval problem. The approach involves dividing the load and its corresponding temperature profiles into three periods: pre-CVR, CVR, and post-CVR. To restore the missing load profile during the CVR period, the method employs a three-step process. First, a forward-pass GBM is executed using data from the pre-CVR period as inputs. Subsequently, a backward-pass GBM is applied using data from the post-CVR period. The two restored load profiles are reconciled, considering pre-calculated weights derived from forecasting accuracy, and only the leftmost and rightmost points are retained. The newly restored points are then included as inputs for the subsequent iteration. This iterative procedure continues until the original load data in the CVR period is fully restored. We develop IBi-GBM using actual smart meter and Supervisory Control and Data Acquisition (SCADA) data. Our results demonstrate that IBi-GBM exhibits robust performance across various data resolutions and in different seasons and outperforms existing methods by achieving a 1%–2% reduction in normalized Root Mean Square Error (nRMSE). • Propose an Iterative Bidirectional Gradient Boosting Model for CVR baseline estimation. • The methodology includes selecting similar days, training the GB model, and generating the baseline. • Illustrate the impact of diverse data sources on CVR baseline recovery using bottom-up and top-down methods at different resolutions. [ABSTRACT FROM AUTHOR]

• Greedy strategy fused with centroid and elite guidance boosts algorithm exploration. • Adding self-learning to the Levy flight algorithm reduces the risk of local optima. • Per-dimension mirror boundary control assures algorithm search within feasible bounds. • An adaptive survival-of-the-fittest strategy improves the algorithm's robustness. • IARO is compared to 14 algorithms on 52 functions and 7 engineering problems. The Artificial Rabbit Optimization (ARO) algorithm has been proposed as an effective metaheuristic optimization approach in recent years. However, the ARO algorithm exhibits shortcomings in certain cases, including inefficient search, slow convergence, and vulnerability to local optima. To address these issues, this paper introduces a multi-strategy improved Artificial Rabbit Optimization (IARO) algorithm. Firstly, in the enhanced search strategy, we propose integrating the centroid guidance mechanism and elite guidance mechanism with the greedy strategy to update the position during the exploration phase. Additionally, the Levy flight strategy integrated with self-learning, is employed to update the position during the development phase to improve convergence speed and prevent falling into local optima. Secondly, the algorithm incorporates a per-dimension mirror boundary control strategy to map individuals exceeding the boundary back within the boundary back inside the boundary. This boundary control strategy ensures the algorithm operates within bounds and enhances convergence speed. Finally, within the survival of the fittest strategy, an adaptive factor is introduced to gradually enhance the population's overall adaptability. This factor regulates the balance between exploration and exploitation, allowing the algorithm to fully explore the search space and improve its robustness. To substantiate the effectiveness of the proposed IARO algorithm, a rigorous and systematic verification analysis was undertaken. Comparative experiments for qualitative and quantitative analysis were conducted on three benchmark test sets, namely CEC2017, CEC2020, and CEC2022. The analysis results, including the Wilcoxon rank-sum test, consistently demonstrates that this improved algorithm outperforms ARO and other state-of-the-art optimization algorithms comprehensively. Finally, the feasibility of the IARO algorithm has been verified in seven classical constrained engineering problems. [ABSTRACT FROM AUTHOR]

In recent years cryptographic tokens have gained popularity as they can be used as a form of emerging alternative financing and as a means of building platforms. The token markets innovate quickly through technology and decentralization, and they are constantly changing, and they have a high risk. Negotiation strategies must therefore be suited to these new circumstances. The genetic algorithm offers a very appropriate approach to resolving these complex issues. However, very little is known about genetic algorithm methods in cryptographic tokens. Accordingly, this paper presents a case study of the simulation of Fan Tokens trading by implementing selected best trading rule sets by a genetic algorithm that simulates a negotiation system through the Monte Carlo method. We have applied Adaptive Boosting and Genetic Algorithms, Deep Learning Neural Network-Genetic Algorithms, Adaptive Genetic Algorithms with Fuzzy Logic, and Quantum Genetic Algorithm techniques. The period selected is from December 1, 2021 to August 25, 2022, and we have used data from the Fan Tokens of Paris Saint-Germain, Manchester City, and Barcelona , leaders in the market. Our results conclude that the Hybrid and Quantum Genetic algorithm display a good execution during the training and testing period. Our study has a major impact on the current decentralized markets and future business opportunities. [ABSTRACT FROM AUTHOR]

The unceasing evolution of analytical instrumentation determines an exponential increase of data production, which in turn boosts new cutting-edge analytical challenges, requiring a progressive integration of artificial intelligence (AI) algorithms into the instrumental data treatment software. Machine learning, deep learning, and computer vision are the most common techniques adopted to exploit the information potential of advanced analytical chemistry measures. In this paper, our primary focus is on elucidating the remarkable advantages of leveraging AI tools for comprehensive two-dimensional gas chromatography data (pre)processing. We illustrate how AI techniques can efficiently explore the complex datasets derived from multidimensional platforms combining comprehensive two-dimensional separations with mass spectrometry in the challenging application area of food-omics. Pattern recognition based on image processing, computer vision, and AI smelling are discussed by introducing the principles of operation, reviewing available tools and software solutions, and illustrating their potentials and limitations through selected applications. • Artificial Intelligence boost the informative potential of GC × GC. • Computer Vision based on chromatogram images. • AI smelling machine with GC × GC-MS predicts food aroma properties. • Advancing the explorative potential of comprehensive two-dimensional chromatography. • Augmented visualization combines visual features with chemical information. [ABSTRACT FROM AUTHOR]

The proliferation of Internet of Things (IoT) devices within the cyber–physical infrastructure has raised privacy and security concerns. This is because processing large amounts of data and extracting anomalous data cannot be imprecisely identified with the limited storage and processing capabilities of IoT devices. Against this backdrop, edge computing is a networking paradigm to reshape the next generation of IoT-based applications, which brings computation and data storage closer to the data sources. However, since edge servers are difficult to obtain security protections like in centralized data centers, this makes them more vulnerable to security attacks. To address this issue, we propose a novel digital twin system architecture in edge computing-based Internet of Things (IoT) networks, which allows efficient data processing for anomaly detection at the network edge. Digital twin is a replica of the real world in a virtual environment with continuous information exchange. Our digital twin-assisted solution gives a data-driven strategy against the cell outage and simulates the behavior and patterns of the physical assets in the digital world. Powered by data processing capabilities at the network edge, the proposed digital twin-assisted model can help extract features and behaviors, reduce noise from data generated in the network physical model, and filter out redundant data for a better characterization of the network physical model in the anomaly detection service. To this extent, the contributions in this paper are threefold: We first propose a novel digital twin-assisted anomaly detection framework that processes high-dimensional data efficiently and improves the system performance despite the imbalanced classes. Second, we define an autoencoder-based threshold algorithm and evaluate the eXtreme Gradient Boosting (XGBoost) classifier to implement self-learning capability into the digital twin for an accurate prediction. Third, we extract the features, dependencies, and relationships to apply the learned model to the new and unseen dataset for real-time monitoring and optimization and evaluate the performance of the proposed model with both real-time and historical data. Finally, we analyze the performance of different classifiers to validate our model. We use four different datasets and demonstrate that our solution outperforms the state-of-the-art techniques in terms of accuracy performance, AUC score, and ROC curve. [ABSTRACT FROM AUTHOR]

High-resolution residential smart meter data play a pivotal role in numerous applications, ranging from assessing hosting capacity in low-voltage grids to evaluating the economic viability of household-level solutions such as the integration of photovoltaic (PV) installations with battery energy storage systems (BESS). However, privacy concerns often restrict access to large-scale residential smart meter datasets, leaving only synthetic load profiles available to the public, which generally only represent averages of individual data. In response to this challenge, this paper proposes an innovative approach leveraging Generative Adversarial Networks (GANs) to generate synthetic residential load profiles. Our method operates in two distinct phases: First, we employ the DoppelGANger (DGAN) architecture to construct annual time series of daily consumption values. DGAN has been selected due to its demonstrated capacity for capturing interday and seasonal dynamics. Second, a wavelet-based decomposition-recombination technique is employed to create stochastic daily profiles with realistic intraday variations and peak demand behavior. Our DGAN-based approach demonstrates remarkable effectiveness, as evidenced by evaluation against a real-world dataset through a series of qualitative microbenchmarks. Moreover, the practical utility of the two-step methodology is explored in three downstream applications: (i) the integration of PV systems, (ii) PV-BESS systems increasing PV self-consumption, and (iii) PV-BESS systems boosting PV self-consumption while performing peak shaving. Our methodology is shown to accurately capture and model the intricate complexities inherent in real smart meter data. • Modeling high-frequency annual residential load profiles via two-step approach. • DGAN captures interday, weekly and seasonal long-term correlations. • Wavelet-based modeling at daily level assures realistic stochastic peak load behavior. • Benchmark GAN output via autocorrelation, annual consumption and profile variability. • Fidelity of synthetic data was validated for various PV and PV-BESS applications. [ABSTRACT FROM AUTHOR]

• Piecewise nonlinear resistor-capacitor inductor shunted josephson junction is presented. • The rate equations of the model are obtained and the model has two steady states. • Bursting, chaotic, bistable, coexisting and antimonotonicity behaviors are obtained. • The microcontroller and dynamical attractors find qualitative agreement. • Offset boosting control is achieved in the voltage and current variables. This paper evaluates the theoretical and microcontroller execution probing of piecewise nonlinear resistor-capacitor inductor shunted Josephson junction circuit (PNRCISJJC). Kirchhoff's laws establish the equivalent rate equations of the PNRCISJJC where two steady states with one stable and its counterpart unstable for excitation current less than or equal to one with a hat tip to Routh–Hurwitz criterion. No steady state for the applied current greater than one is observed in the PNRCISJJC. The PNRCISJJC exhibits bursting behaviors, varying structures of hidden chaotic characteristics, bistable period-4-oscillations, coexisting behaviors, regular and hidden chaotic bubbles, and antimonotonicity. Furthermore, linear offset boosting based on the current and voltage state variables uncovered that the polarity of the hidden chaotic signal of either state variable can be flexibly altered by varying the offset boosting parameters. The agreement between dynamical analysis and microcontroller realization dynamics finalizes the investigation. [ABSTRACT FROM AUTHOR]

Establishing an accurate quality prediction model is an essential prerequisite for quality management in diesel engine manufacturing factories. However, the large production scale and non-linear relationship between features and the diesel engine power significantly aggravate the complexity of establishing a power prediction model. The identification of key features can not only improve the prediction performance but also facilitate the control of product quality. The mainstream feature selection methods estimate features on a whole static sampling space, which ignores dynamic correlation among candidate features, selected features, and the label variable. This paper focuses on the relevance between the candidate features and diesel engine quality, the complementary and redundancy between the candidate features and selected features, proposing a conditional mutual information-based dynamic feature selection method for the prediction of diesel engine quality. Then, a high-accuracy AdaBoost model is proposed with support vector regression-partial swarm optimization (SVR-PSO) as weak learners, showing a satisfactory non-linear fitting ability and a convenient parameter optimization process. Finally, several cases are performed to evaluate the effectiveness of the proposed methods. The proposed feature selection method shows a better performance than common feature selection methods on UCI datasets. Results on diesel engine power prediction declare that the proposed AdaBoost-SVR-PSO model is an effective quality prediction method compared with adaptive boosting, multilayer perception, and gradient boosting decision tree. [ABSTRACT FROM AUTHOR]