Search

Context: Artificial Intelligence (AI) has rapidly developed over the past several decades. Several related AI approaches, such as Machine Learning (ML), have been applied to research on landscape patterns and ecological processes. Objectives: Our goal was to review the methods of AI, particularly ML, used in studies related to landscape ecology and the main topics addressed. We aimed to assess the trend in the number of ML papers and the methods used therein, and provide a synopsis and prospectus of current use and future applications of ML in landscape ecology. Methods: We conducted a systematic literature search and selected 125 papers for review. These were examined and scored according to multiple criteria regarding methods and topic. We applied quantitative statistical methods, including cluster analysis based on titles, abstracts, and keywords and a non-metric multidimensional scaling based on attributes assigned during the review. We used Random Forests machine learning to describe the differences between identified clusters in terms of the topics and methods they included. Results: The most frequent method found was Random Forests, but it is noteworthy to mention the increasing popularity of tools related to Deep Learning. The topics cover both ecologically oriented issues and the landscape-human interface. There has been a rapid increase in ML and AI methods in landscape ecology research, with Deep Learning and complex multi-step pipeline AI methods emerging in the last several years. Conclusions: The rapid increase in the number of ML papers in landscape ecology research, and the range of methods employed in them, suggest explosive growth in application of these methods in landscape ecology. The increase of Deep Learning approaches in the most recent years suggest a major change in analytical paradigms and methodologies that we feel may transform the field and enable analyses of more complex pattern process relationships across vaster data sets than has been possible previously. [ABSTRACT FROM AUTHOR]

In most biomedical research paper corpus, document classification is a crucial task. Even due to the global epidemic, it is a crucial task for researchers across a variety of fields to figure out the relevant scientific research papers accurately and quickly from a flood of biomedical research papers. It can also assist learners or researchers in assigning a research paper to an appropriate category and also help to find the relevant research paper within a very short time. A biomedical document classifier needs to be designed differently to go beyond a "general" text classifier because it's not dependent only on the text itself (i.e. on titles and abstracts) but can also utilize other information like entities extracted using some medical taxonomies or bibliometric data. The main objective of this research was to find out the type of information or features and representation method creates influence the biomedical document classification task. For this reason, we run several experiments on conventional text classification methods with different kinds of features extracted from the titles, abstracts, and bibliometric data. These procedures include data cleaning, feature engineering, and multi-class classification. Eleven different variants of input data tables were created and analyzed using ten machine learning algorithms. We also evaluate the data efficiency and interpretability of these models as essential features of any biomedical research paper classification system for handling specifically the COVID-19 related health crisis. Our major findings are that TF-IDF representations outperform the entity extraction methods and the abstract itself provides sufficient information for correct classification. Out of the used machine learning algorithms, the best performance over various forms of document representation was achieved by Random Forest and Neural Network (BERT). Our results lead to a concrete guideline for practitioners on biomedical document classification. [ABSTRACT FROM AUTHOR]

We briefly review the state-of-the-art machine learning (ML) algorithms for mineral exploration, which mainly include random forest (RF), convolutional neural network (CNN), and graph convolutional network (GCN). In recent years, RF, a representative shallow machine learning algorithm, and CNN, a representative deep learning approach, have been proved to be powerful tools for ML-based mapping for mineral exploration. In the future, GCN deserves more attention for ML-based mapping for mineral exploration because of its ability to capture the spatial anisotropy of mineralization and its applicability within irregular study areas. Finally, we summarize the original contributions of the six papers comprising this special issue. [ABSTRACT FROM AUTHOR]

Since the traditional ship stability failure probability assessment method has many input parameters and cumbersome intermediate calculation process, this paper proposes a joint multi-model machine learning prediction method based on confidence. The method calculates the confidence of each machine learning model for the current prediction result, selects the top n models among them, and takes the average of their prediction results as the output. The confidence is calculated by a method inspired by semi-supervised learning. To reduce the number of ship features that need to be input for assessment, a sensitivity analysis is used to reject irrelevant features. Eight machine learning models that have good performance and are widely used in other fields, including Radial Basis Function Neural Network, Random Forest, eXtreme Gradient Boosting, and so on, are used as component learners in this study. The hyperparameters of each model are obtained by cross-validation and grid search. The advancedness of the proposed method is verified by comparing it with other models on a small self-built ship stability failure probability dataset. By conducting experiments that simply average the results of the component learners, it is confirmed that simple superposition different models does not necessarily improve the accuracy. At the same time, after pre-processing the input features in different ways, the comparison of the prediction performance was conducted, and the experimental results showed that the proposed method is not affected by the way the input features are preprocessed and therefore has some robustness. [ABSTRACT FROM AUTHOR]

China, India, and the USA are the countries with the highest energy consumption and CO2 emissions globally. As per the report of datacommons.org, CO2 emission in India is 1.80 metric tons per capita, which is harmful to living beings, so this paper presents India's detrimental CO2 emission effect with the prediction of CO2 emission for the next 10 years based on univariate time-series data from 1980 to 2019. We have used three statistical models; autoregressive-integrated moving average (ARIMA) model, seasonal autoregressive-integrated moving average with exogenous factors (SARIMAX) model, and the Holt-Winters model, two machine learning models, i.e., linear regression and random forest model and a deep learning-based long short-term memory (LSTM) model. This paper brings together a variety of models and allows us to work on data prediction. The performance analysis shows that LSTM, SARIMAX, and Holt-Winters are the three most accurate models among the six models based on nine performance metrics. Results conclude that LSTM is the best model for CO2 emission prediction with the 3.101% MAPE value, 60.635 RMSE value, 28.898 MedAE value, and along with other performance metrics. A comparative study also concludes the same. Therefore, the deep learning-based LSTM model is suggested as one of the most appropriate models for CO2 emission prediction. [ABSTRACT FROM AUTHOR]

Lithofacies identification is critical to energy exploration and reservoir evaluation. Machine learning provides a way to use logging data for lithofacies intelligence identification. However, labeled logging data are usually scarce, which makes the currently used supervised algorithms less effective, so semi-supervised methods have received attention from researchers. In this paper, we propose to apply Tri-Training to the field of lithofacies recognition. The framework used Random Forest (RF), Gradient-Boosted Decision Trees (GBDT), and Support Vector Machine (SVM), as the baseline supervised classifiers, and based on the idea of inductive semi-supervised methods and ensemble learning. Baseline classifiers are trained and iterated using unlabeled data to obtain effect improvement. The final results are output in an ensemble paradigm. We used seven logging parameters from two wells as input and divide the data randomly 10 times for training and testing. With only five samples of each lithology, the prediction accuracy improved by the average of 2.1% and 14.5% in both wells compared to the baseline methods. In addition, we also compared two commonly used semi-supervised methods, label propagation algorithm (LPA) and Co-Training. The experimental results also confirm that Tri-training has the better and more stable performance. The Tri-training method in this paper can be effectively applied to lithofacies identification under scarce labeled logging data. [ABSTRACT FROM AUTHOR]

The air quality index has a severe effect on the determination of health conditions of a city. The prediction of air quality index can aid in determining the optimum route in case of traffic and it can also aid in determining the pollutants which have severe impact on human health conditions. The paper presents an air quality prediction system using various machine learning based models. The air quality index is determined by measuring the different gases present in the atmosphere. In this paper we have considered seven such parameters as concentration levels of Particulate Matter 2.5 (PM2.5), Particulate Matter 10 (PM10), Carbon Mono oxide (CO), Nitrogen Dioxide (NO2), Ammonia (NH3), Sulphur Dioxide (SO2) and Ozone (O3) levels for the duration between the year January 2019 to October 2023 for a crowded area of Varanasi city. The various pre processing techniques have been used in the dataset for the implementation of machine learning models. The performance of the models have been compared for the prediction of the air quality. The results show that the Random Forest and Decision Tree based model achieves the maximum accuracy of approximately 100% as compared to 98%, 95% and 93% and 79% for the SVM, Multi layer Perceptron network, KNN classification and Linear Regression. [ABSTRACT FROM AUTHOR]

Air quality is a fundamental component of a healthy environment for human beings. Monitoring networks for air pollution have been established in numerous industrial zones. The data collected by the pervasive monitoring devices can be utilized not only for determining the current environmental condition, but also for forecasting it in the near future. This paper considers the applications of different machine learning methods for the prediction of the two most widely used quantities. Particulate matter (PM) with a diameter of 2.5 and 10 µm, respectively. The data are collected via a proprietary monitoring station, designated as the Ecolumn. The Ecolumn monitors a number of key parameters, including temperature, pressure, humidity, PM 1.0, PM 2.5, and PM 10, in a timely manner. The data were employed in the development of multiple models based on selected machine learning methods. The decision tree, random forest, recurrent neural network, and long short-term memory models were employed. Experiments were conducted with varying hyperparameters and network architectures. Different time scales (10 min, 1 h, and 24 h) were examined. The most optimal results were observed for the Long Short-Term Memory algorithm when utilizing the shortest available time spans (shortest averaging times). The decision tree and random forest algorithms demonstrated unexpectedly high performance for long averaging times, exhibiting only a slight decline in accuracy compared to neural networks for shorter averaging times. Recommendations for the potential applicability of the tested methods were formulated. [ABSTRACT FROM AUTHOR]

As artificial intelligence (AI) becomes widespread, there is increasing attention on investigating bias in machine learning (ML) models. Previous research concentrated on classification problems, with little emphasis on regression models. This paper presents an easy-to-apply and effective methodology for mitigating bias in bagging and boosting regression models, that is also applicable to any model trained through minimizing a differentiable loss function. Our methodology measures bias rigorously and extends the ML model's loss function with a regularization term to penalize high correlations between model errors and protected attributes. We applied our approach to three popular tree-based ensemble models: a random forest model (RF), a gradient-boosted model (GBT), and an extreme gradient boosting model (XGBoost). We implemented our methodology on a case study for predicting road-level traffic volume, where RF, GBT, and XGBoost models were shown to have high accuracy. Despite high accuracy, the ML models were shown to perform poorly on roads in minority-populated areas. Our bias mitigation approach reduced minority-related bias by over 50%. [ABSTRACT FROM AUTHOR]

Sea surface gage height (SSGH) data are commonly measured at sparsely deployed tidal stations while coastal resources management requires spatially distributed SSGH data. This paper presents three different machine learning models, including a Random Forest (RF) model, an Extreme Gradient Boosting (XGBoost) model, and an Artificial Neural Network (ANN) model, for retrieving and mapping spatially distributed SSGH. The models were originally developed and independently validated using 10 years of VIIRS satellite remote sensing data and corresponding in-situ gage height (GH) data within the MATLAB ANN toolbox and RStudio. The paper made two major new contributions to the determination of SSGH, including a scientific contribution and a technical contribution. Scientifically, this paper has provided new insights into important factors affecting SSGH. The SSGH varies significantly with the location (GPS coordinates) and Julian Day with both factors affecting the tide and thus SSGH. SSGH is also affected by sea surface waves that affect the reflectance of light from different wavelengths of satellite sensors, which are described with the VIIRS remote sensing reflectance (Rrs) bands including Rrs 410, 443, 486, 551, and 671. Technically, the machine learning models, particularly the ANN model, are capable of providing the most accurate and spatially distributed SSGH data particularly for coastal waters, as characterized by the model performance metrics including the correlation coefficient R value of 0.94 for training, 0.94 for validation, and 0.93 for testing and the low root mean square error (RMSE) value of 0.113 m for training, 0.113 m for validation, and 0.118 m for testing. [ABSTRACT FROM AUTHOR]

In recent years, healthcare monitoring systems (HMS) have increasingly integrated the Internet of Medical Things (IoMT) with cloud computing, leading to challenges related to data latency and efficient processing. This paper addresses these issues by introducing a Machine Learning-based Medical Data Segmentation (ML-MDS) approach that employs a k-fold random forest technique for efficient health data classification and latency reduction in a fog-cloud environment. Our method significantly improves latency issues, enhancing the Quality of Service (QoS) in healthcare systems and demonstrating its adaptability in heterogeneous network scenarios. We specifically employ the Random Forest algorithm to mitigate the common problem of overfitting in machine learning models, ensuring broader applicability across various healthcare contexts. Additionally, by optimizing data processing in fog computing layers, we achieve a substantial reduction in overall latency between healthcare sensors and cloud servers. This improvement is evidenced through a comparative performance analysis with existing models. The proposed framework not only ensures secure and scalable management of IoMT health data but also incorporates a stochastic approach to mathematically formulate performance indicators for the HMS queuing model. This model effectively predicts system response times and assesses the computing resources required under varying workload conditions. Our simulation results show a classification accuracy of 92%, a 56% reduction in latency compared to existing models, and an overall enhancement in e-healthcare service quality. [ABSTRACT FROM AUTHOR]

Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches that improve the chance of success in practical situations. Our search simultaneously optimizes for network accuracy, energy efficiency and memory usage. We benchmark the performance of our search on real hardware, but since running thousands of tests with real hardware is difficult, we use a random forest model to roughly predict the energy usage of a candidate network. We present a search strategy that uses both Bayesian and regularized evolutionary search with particle swarms, and employs early stopping to reduce the computational burden. Our search, evaluated on a sound event classification dataset based upon AudioSet, results in an order of magnitude less energy per inference and a much smaller memory footprint than our baseline MobileNetV1/V2 implementations while slightly improving task accuracy. We also demonstrate how combining a 2D spectrogram with a convolution with many filters causes a computational bottleneck for audio classification and that alternative approaches reduce the computational burden but sacrifice task accuracy. [ABSTRACT FROM AUTHOR]

Knowledge discovery from various perspectives has become a crucial asset in almost all fields. Sentimental analysis is a classification task used to classify the sentence based on the meaning of their context. This paper addresses class imbalance problem which is one of the important issues in sentimental analysis. Not much works focused on sentimental analysis with imbalanced class label distribution. The paper also focusses on another aspect of the problem which involves a concept called "Code Mixing". Code mixed data consists of text alternating between two or more languages. Class imbalance distribution is a commonly noted phenomenon in a code-mixed data. The existing works have focused more on analyzing the sentiments in a monolingual data but not in a code-mixed data. This paper addresses all these issues and comes up with a solution to analyze sentiments for a class imbalanced code-mixed data using sampling technique combined with levenshtein distance metrics. Furthermore, this paper compares the performances of various machine learning approaches namely, Random Forest Classifier, Logistic Regression, XGBoost classifier, Support Vector Machine and Naïve Bayes Classifier using F1- Score. [ABSTRACT FROM AUTHOR]

Brønnøy Kalk AS operates an open pit mine in Norway producing marble, mainly used by the paper industry. The final product is used as filler and pigment for paper production. Therefore, the quality of the product has utmost importance. In the mine, the primary quality indicator, called TAPPI, is quantified through a laborious sampling process and laboratory experiments. As a part of digital transformation, measurement while drilling (MWD) data have been collected in the mine. The purpose of this paper is to use the recorded MWD data for the prediction of marble quality to facilitate quality blending in the pit. For this purpose, two supervised classification modelling algorithms such as conventional logistic regression and random forest have been employed. The results show that the random forest classification model presents significantly higher statistical performance, and it can be used as a tool for fast and efficient marble quality assessment. [ABSTRACT FROM AUTHOR]

Underground wastewater collection systems degrade with time, necessitating utility owners to engage in ongoing evaluations and enhancements of their asset management frameworks to preserve the performance of their assets. The inspection and condition assessment of sewer pipes are crucial for the effective operation and maintenance of sewer systems. The closed-circuit television (CCTV) is frequently employed to examine sewer pipes in the United States. This procedure is both costly and laborious because of the extensive number of pipes in a metropolis. Prioritisation of inspection for sanitary sewage pipe segments requiring repair or maintenance can be done in advance depending on their past performance. Hence, the aim of this study is to construct a predictive model for the state of sanitary sewer pipes, utilising data collected from a city located in the southcentral region of the United States. The main contribution is that this study used multiclass classification and predicted PACP scores of the pipes. Condition prediction models were developed using extensively utilised supervised machine learning algorithms including logistic regression (LR), k-nearest neighbors (k-NN), and random forest (RF). However, the bulk of the constructed models were assessed using a limited number of assessment measures, such as the receiver operator characteristic (ROC) curve and the area under the curve (AUC) value. This paper asserts that the assessment of the predictive capacity of these models cannot be determined only by relying on ROC and AUC values. Out of the three models evaluated in this study, the LR model had an AUC value of 0.76. However, this model had a higher number of misclassifications or inaccurate predictions compared to the other models. Consequently, these models were assessed using additional assessment measures, including precision, recall, and F-1 scores (which represent the harmonic mean of precision and recall). Curiously, the LR model achieved an F1-score of 0.28 on a scale ranging from 0 to 1. The RF model yielded an F1-score of 0.45 and an AUC value of 0.86. The existing model can be enhanced before it is employed by asset managers during the inspection phase to assess the state of their sanitary sewers and identify essential sewers that require immediate care. [ABSTRACT FROM AUTHOR]

Historical architecture has different special styles attributed to each era, dynasty, or region. These styles are common features such as geometric properties, ratios, scales, colors, and artistic techniques. Historical geometric ornaments have an enormous capability for classification based on their geometric characteristics. Smart pattern recognition allows researchers to classify huge databases of heritage for useful internet searches. So, our main goal in this paper is to implement the detection of categories in geometric patterns for classification and documentation in which by the photography of ornaments in every monument, the type of patterns and the number of every type of pattern would be estimated quickly. Furthermore, due to occurring deterioration in these patterns, our method also contributes to recognizing the deteriorated patterns. When we encounter numerous pieces of deteriorated patterns, manual recognition in order to reassemble and reconstruct is usually impossible or time-consuming. With the aid of artificial intelligence, in this paper, our aim is to seek to solve the automatic recognition of historical geometric patterns, even patterns having deterioration as an occlusion via image processing and machine learning methods. A challenging issue that researchers would tackle in detecting historical geometric pattern's types is the variety in geometric textures, especially when they have occlusion such as deterioration. This issue leads to limited success in classifying via extracting only one feature. The other issue is that the extracted feature must be invariant to the transformation, such as scale, rotation, and noise variation. To cope with the challenges mentioned above and accurately classify, we plan to use the fusion method based on extracting global and local features. So, the features extracted from images in this research are based on local and global. In other words, the proposed fusion strategy lies both in feature and decision level, but the core is the proposed three combination methods in fusion decision methods. In this method, the dataset is composed of four main Persian geometric pattern types: Tond dah, Kond tablghenas, Hashtva 4 lengeh, and HashtvatablKond. So, the model will be trained by extracting global and local features of the images separately. Random forest, as the prevalent machine learning algorithm, is proposed for training data and predicting the class of input images. Finally, the probability of prediction for random forest classifiers is fused by the Decision Templates (DT) combiner, Naïve Bayes (NB) combiner, and Dempster–Shafer combination methods. In comparison with the individual classifier accuracy results of 80% and 85% for global and local features respectively, our proposed approach achieves an improved accuracy of 90%, 88%, and 90% in three fusion decision methods including DT combiner, NB combiner, and Dempster–Shafer combination methods. [ABSTRACT FROM AUTHOR]

Project risk management which has been rarely considered, especially in software projects, is a crucial process to complete projects successfully. This paper aims to propose a novel project risk management framework both to evaluate the project risks and to predict the success or failure of software projects based on their risk. This new framework uses Machine Learning (ML) and Multi-Attribute Decision-Making under a cloud model to effectively manage uncertainty. Based on the proposed framework, in the first stage, the important risks of the software projects are identified by an organized approach. Then, the risks are evaluated based on their probability and impacts on time, cost, and quality. In the second stage, the obtained results of the previous stage are entered into a new COPRAS method under the cloud model to rank the risks. Then, the risks are classified into various groups according to their rank. It helps project managers to gain a profound awareness of their high-priority project risks. In this paper, data on risks for fifty software projects has been collected. All the steps of the second stage are implemented on these projects in order to assess their risks. As a result, a data set whose features are nine types of software project risks and the label of success or failure of the projects is created. To recognize the pattern between risks' values and the success or failure of the projects, various efficient ML algorithms such as Naive Bayes, Logistic regression, Decision Tree, Bagging, Random Forest, and AdaBoost are applied. This framework can predict the success or failure of software projects based on their risks with good accuracy. The results depict that the Naive Bayes algorithm has the best results compared to others. [ABSTRACT FROM AUTHOR]

Leptospirosis is a global disease that impacts people worldwide, particularly in humid and tropical regions, and is associated with significant socio-economic deficiencies. Its symptoms are often confused with other syndromes, which can compromise clinical diagnosis and the failure to carry out specific laboratory tests. In this respect, this paper presents a study of three algorithms (Decision Tree, Random Forest and Adaboost) for predicting the outcome (cure or death) of individuals with leptospirosis. Using the records contained in the government National System of Aggressions and Notification (SINAN, in portuguese) from 2007 to 2017, for the state of Pará, Brazil, where the temporal attributes of health care, symptoms (headache, vomiting, jaundice, calf pain) and clinical evolution (renal failure and respiratory changes) were used. In the performance evaluation of the selected models, it was observed that the Random Forest exhibited an accuracy of 90.81% for the training dataset, considering the attributes of experiment 8, and the Decision Tree presented an accuracy of 74.29 for the validation database. So, this result considers the best attributes pointed out by experiment 10: time first symptoms medical attention, time first symptoms ELISA sample collection, medical attention hospital admission time, headache, calf pain, vomiting, jaundice, renal insufficiency, and respiratory alterations. The contribution of this article is the confirmation that artificial intelligence, using the Decision Tree model algorithm, depicting the best choice as the final model to be used in future data for the prediction of human leptospirosis cases, helping in the diagnosis and course of the disease, aiming to avoid the evolution to death. [ABSTRACT FROM AUTHOR]

Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods can be used for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (MRep-DeepInsight), a novel extension of the DeepInsight method designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach is able to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimer's data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest, XGBoost, LightGBM, FT-Transformer and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By leveraging the power of diverse representations, MRep-DeepInsight offers a promising new avenue for advancing decision-making and scientific discovery across a wide range of fields. [ABSTRACT FROM AUTHOR]

This paper provides a framework based on machine learning approach in I4.0 environment to predict the remaining useful life of an aviation engine. For illustration purpose, an industrial case study is presented which applies machine learning algorithms to analyze the data collected using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) simulation which includes run-to-degradation data for a turbofan engine. The results obtained from the study validate the proposed framework to identify prominent features and perform sequential analysis on unstructured data for predicting the remaining useful life of an aviation engine. Six machine learning models are applied to the dataset containing four subsets: FD001, FD002, FD003 and FD004 in C-MAPSS dataset each working on different degradation conditions for turbofan engine. For FD001, random forest had the lowest RMSE (11.59), and for FD002, FD003 and FD004, the lowest RMSE was given by LGBM classifier (12.78, 7.95 and 11.04), respectively. From the findings, it is observed that LGBM performs better with higher AUC 89% and lowest RMSE. The proposed framework can be applied to a wide range of failure prediction applications. Regardless of the underlying physics, ML-based data-driven methodologies can be used to analyze a wide range of systems. [ABSTRACT FROM AUTHOR]

Bonica's (Am J Polit Sci 58(2):367–386, 2014) campaign finance-based ideology scores, or CFscores, create an ideological common space that allows researchers to compare a wide variety of actors. Because relatively few citizens donate to candidates, however, the public is not well represented in this common space. This paper addresses that gap. It uses random forest machine learning on data from the 2012 Cooperative Congressional Election Study to impute CFscores for respondents who did not donate to candidates, based on how their policy views compared to those who did. These new scores are robust to differences in issue importance between donors and non-donors, and they outperform other ideological measures in predicting vote choice. The scores are then applied to a substantive exercise. Past research shows that extreme candidates for governor are penalized more by voters than those in lower-profile races. The implied mechanism—that vote choice for governor is more ideologically-driven—can be directly tested with imputed CFscores, since they uniquely allow comparisons between voters and candidates across races. An analysis of voting behavior in 2012 confounds expectations. Ideology appears to factor no more into vote choice for governor than for US House. These novel findings underscore the value of extending CFscores to non-donating survey respondents, and while current efforts are limited by data availability, this study offers encouragement and a roadmap to that end. [ABSTRACT FROM AUTHOR]

The esports industry is one of the prominent business sectors in the digital era, particularly, Multiplayer Online Battle Arena (MOBA) games which gain much attention from gamers and streaming audiences. Among such games, Defense of the Ancient 2 or Dota 2 is the record holder for the highest prize esports tournament. Therefore, various companies and investors start their esports teams to compete in the Dota 2 tournaments, the Internationals. To success in the competition, player recruitment is a crucial process as it usually takes considerable effort to find a skillful player. Watching the game replay to evaluate the player's skill is one of the approaches. However, it can be too exhaustive, also some player's ranking, which represent the player's skill, are often not available. In this paper, we propose an effective machine learning pipeline to evaluate the player's skill. Our designed pipeline includes data collection, feature engineering, and machine learning modeling. We show the data collection process using open-source API. An effective method for feature engineering is proposed. Features, e.g., end-game, or tactical decision related statistics, are incorporated along with the resource in the game distribution, harassment tactic, or spatiotemporal features, in order to provide effective models. Subsequently, we apply major machine learning models based on a single game data, i.e., logistic regression and random forest, to the processed data. The most effective model can achieve up to 0.7091 precision, 0.5850 recall, 0.6411 F1-score, and 0.8123 ROC AUC score. [ABSTRACT FROM AUTHOR]

Purpose: Structural damage can significantly alter a system's local flexibility, leading to undesirable displacements and vibrations. Analysing the dynamic structure feature through statistical analysis enables us to discriminate the current structural condition and predict its short- or long-term lifespan. By directly affecting the system's vibration, cracks and discontinuities can be detected, and their severity quantified using the DI. Two damage indexes (DI) are used to build a dataset from the beam's natural frequency and frequency response function (FRF) under both undamaged and damaged conditions, and numerical and experimental tests provided the data-driven. Methods: In this paper, we present the methodology based on machine learning (ML) to monitor the structural integrity of a beam-like structure. The performance of six ML algorithms, including k-nearest neighbors (kNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Naive Bayes (NB) are investigated. Results: The paper discusses the challenges of implementing each technique and assesses their performance in accurately classifying the dataset and indicating the beam's integrity. Conclusion: The structural monitoring performed with the ML algorithm achieved excellent metrics when inputting the simulation-generated dataset, up to 100%, and up to 95% having as input dataset provided from experimental tests. Demonstrating that the ML algorithm could correctly classify the health condition of the structure. [ABSTRACT FROM AUTHOR]

This paper addresses the issue of the prediction of slope stability with machine learning (ML) applications. Five well-known and popular ML algorithms, namely neural network (NNet), decision tree (DT), support vector machine (SVM), k-nearest neighbor (kNN), and random forest (RF), are used to demonstrate the effectiveness of the ML algorithms for predicting binary classification of slope stability based on a case history dataset containing outliers. This study also evaluates the winsorization method used to treat outliers in the dataset by outlining the effect of outliers on the prediction performances of models. To this end, the performance of all the generated ML models is assessed and compared both for unwinsorized (e.g., raw) and winsorized datasets based on performance metrics (i.e., Recall, Precision, Accuracy, and F1-Score) obtained from the confusion matrix. The experimental outputs showed that the application of winsorization enhanced the prediction performance of the models, and thus, all ML models built with winsorized datasets outperformed the unwinsorized ones. In this paper, the RF model achieves the best prediction performance, especially in the case of the winsorized dataset used. Moreover, it is found that SVM is the most sensitive algorithm to outliers as against the other ML algorithms, while the kNN algorithm is the least among the applied algorithms. Results showed that the increment percentage of accuracy nearly reaches 20% for the SVM model and the following 18% for DT, 11% for NNet, 10% for RF, and 4% for kNN, respectively. Furthermore, the results of the study reveal not only the performance of ML algorithms for the slope stability problem but also show how the handling of outliers of a dataset affects the models' prediction performance. [ABSTRACT FROM AUTHOR]

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power consumption. However, most wearable health data is distributed across different organizations, such as hospitals, research institutes, and companies, and can only be accessed by the owners of the data in compliance with data privacy regulations. The first challenge addressed in this paper is communicating in a privacy-preserving manner among different organizations. The second technical challenge is handling the dynamic expansion of the federation without model retraining. To address the first challenge, we propose a horizontal federated learning method called Federated Extremely Random Forest (FedERF). Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model performance. Based on FedERF, we present a federated incremental learning method called Federated Incremental Extremely Random Forest (FedIERF) to address the second technical challenge. FedIERF introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model incrementally. The experiments show that FedERF achieves comparable performance with non-federated methods, and FedIERF effectively addresses the dynamic expansion of the federation. This opens up opportunities for cooperation between different organizations in wearable health monitoring. [ABSTRACT FROM AUTHOR]

Parkinson disease (PD) is a neurodegenerative disease that occurs due to insufficient level of dopamine in the human brain. This disease may occur predominantly in elder people. There exists no definite procedure to diagnose PD. It is diagnosed based on the symptoms, clinical trials, and number of laboratory tests. In this research paper, machine learning techniques are used to predict PD and help the medical practitioner to recommend personalized drugs for the patients. In this research paper, appropriate features are selected through rough set theory, and principal component analysis is used for dimensionality reduction. The performance is experimented using deep neural network, random forest, and SVM classifiers. The efficiency of the proposed approach is measured through confusion matrix, accuracy, precision, and recall. [ABSTRACT FROM AUTHOR]

This paper proposes a robust model for domain recognition of acoustic communication by using Bidirectional LSTM and deep neural network. The proposed model consists of five layers namely: speech recognition, word embedding, a layer of Bidirectional LSTM (BiLSTM) followed by two fully connected layers (FC). Initially, speech is recognized and resultant text is preprocessed before passing to the proposed model to obtain the domain of communication. Word embedding takes the padded sentence as the input sequence and outputs the encoded sentence. LSTM layer is used to capture the temporal features while fully connected layers (FC) are responsible to capture the linear and nonlinear combination of those features. We compared the performance of our proposed model to the conventional machine learning algorithms such as SVM, KNN, Random forest, and Gradient boosting and found that proposed model outperforms with high accuracy, i.e., 90.09%. [ABSTRACT FROM AUTHOR]

There have been considerable advancements in multimedia technologies over the past 5 years. It has been observed that state-of-the-art multimedia systems face three broad categories of challenges: (1) Dependency on continuous network connections, (2) Data-sharing applications & collaboration, and (3) Security issues. Among these, security vulnerability poses a major threat to modern multimedia systems. Therefore, it is imperative to carefully investigate the security issues that can endanger wireless and mobile communications. At present, multimedia security research mainly focuses on wireless traffic monitoring, wireless system attacks, and wireless and mobile security. In this paper, we have used the network attack-type, "Reconnaissance", which contains two types of malicious activities: (1) OS scanning, and (2) Fuzzing. The goal of this paper is to quantify multimedia security risks due to Fuzzing by using various types of machine learning models. The highest accuracy i.e., 96.8%, is obtained using the XGBoost classifier, which is good compared to the existing models present in the literature. This is the first paper, to the best of our knowledge, that uses machine learning methods to differentiate between benign and malignant Fuzzing attacks. [ABSTRACT FROM AUTHOR]

Disruptive innovations caused by FinTech (i.e., technology-assisted customized financial services) have brought digital peer-to-peer (P2P) payments to the fore. In this challenging environment and based on theories about customer behavior in response to technological innovations, this paper identifies the drivers of consumer adoption of mobile P2P payments and develops a machine learning model to predict the use of this thriving payment option. To do so, we use a unique data set with information from 701 participants (observations) who completed a questionnaire about the adoption of Bizum, a leading mobile P2P platform worldwide. The respondent profile was the average Spanish citizen within the framework of European culture and lifestyle. We document (in this order of priority) the usefulness of mobile P2P payments, influence of peers and other social groups such as friends, family, and colleagues on individual behavior (that is, subjective norms), perceived trust, and enjoyment of the user experience within the digital context and how those attributes better classify (potential) users of mobile P2P payments. We also find that nonparametric approaches based on machine learning algorithms outperform traditional parametric methods. Finally, our results show that feature selection based on random forest, such as the Boruta procedure, as a preprocessing technique substantially increases prediction performance while reducing noise, redundancy of the resulting model, and computational costs. The main limitation of this research is that it only has a place within the sociocultural and institutional framework of the Spanish population. It is therefore desirable to replicate this study by surveying people from other countries to analyze the effects of the institutional environment on the adoption of mobile P2P payments. [ABSTRACT FROM AUTHOR]

The classification of Short Message Service (SMS) is a crucial task that requires distinguishing undesirable and harmful messages from legitimate ones. These spam messages may include malicious links that reveal users' personal data to some sharp practices. Many Machine Learning (ML) and deep learning algorithms prevail for spam detection. However, a large number of features present in the message drop the classifier's performance, which can be untangled through feature engineering. This paper proposes an ensemble feature selection algorithm assessed over a high-dimensional imbalanced dataset that resembles the actual data prevailing in the surroundings. The proposed work employs wrapper-based Stratified K-fold Cross-Validated (SKCV) Recursive Feature Elimination with Cross-Validation (RFECV) over hyperparameters tuned Support Vector Classifier (SVC) and random forest algorithms. This study contributes an efficient feature selection algorithm that produces a pruned feature subset substituting the whole dataset. To establish the potential of the proposed approach, its performance is evaluated against five feature selection techniques, including Mutual Information (MI), Low Variance (LV), Particle Swarm Optimization (PSO), Chi-square, and Recursive Feature Elimination (RFE). All obtained feature subsets are analyzed with three ML models Logistic Regression (LR), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB). This research also compares the proposed framework results with Long Short Term Memory (LSTM) neural network to validate its competence. [ABSTRACT FROM AUTHOR]

In this paper, we modify the proof methods of some previously weakly consistent variants of random forest into strongly consistent proof methods, and improve the data utilization of these variants in order to obtain better theoretical properties and experimental performance. In addition, we propose the Data-driven Multinomial Random Forest (DMRF) algorithm, which has the same complexity with BreimanRF (proposed by Breiman) while satisfying strong consistency with probability 1. It has better performance in classification and regression tasks than previous RF variants that only satisfy weak consistency, and in most cases even surpasses BreimanRF in classification tasks. To the best of our knowledge, DMRF is currently a low-complexity and high-performing variation of random forest that achieves strong consistency with probability 1. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) has gained an increased interest during the last decades as part of enriched affective computing. As a consequence, a variety of engineering approaches have been developed addressing the challenge of the SER problem, exploiting different features, learning algorithms, and datasets. In this paper, we propose the application of the graph theory for classifying emotionally-colored speech signals. Graph theory provides tools for extracting statistical as well as structural information from any time series. We propose to use the mentioned information as a novel feature set. Furthermore, we suggest setting a unique feature-based identity for each emotion belonging to each speaker. The emotion classification is performed by a Random Forest classifier in a Leave-One-Speaker-Out Cross Validation (LOSO-CV) scheme. The proposed method is compared with two state-of-the-art approaches involving well known hand-crafted features as well as deep learning architectures operating on mel-spectrograms. Experimental results on three datasets, EMODB (German, acted) and AESDD (Greek, acted), and DEMoS (Italian, in-the-wild), reveal that our proposed method outperforms the comparative methods in these datasets. Specifically, we observe an average UAR increase of almost 18 % , 8 % and 13 % , respectively. [ABSTRACT FROM AUTHOR]

Decentralized Finance (DeFi) is a system of financial products and services built and delivered through smart contracts on various blockchains. In recent years, DeFi has gained popularity and market capitalization. However, it has also been connected to crime, particularly various types of securities violations. The lack of Know Your Customer requirements in DeFi poses challenges for governments trying to mitigate potential offenses. This study aims to determine whether this problem is suited to a machine learning approach, namely, whether we can identify DeFi projects potentially engaging in securities violations based on their tokens' smart contract code. We adapted prior works on detecting specific types of securities violations across Ethereum by building classifiers based on features extracted from DeFi projects' tokens' smart contract code (specifically, opcode-based features). Our final model was a random forest model that achieved an 80% F-1 score against a baseline of 50%. Notably, we further explored the code-based features that are the most important to our model's performance in more detail by analyzing tokens' Solidity code and conducting cosine similarity analyses. We found that one element of the code that our opcode-based features can capture is the implementation of the SafeMath library, although this does not account for the entirety of our features. Another contribution of our study is a new dataset, comprising (a) a verified ground truth dataset for tokens involved in securities violations and (b) a set of legitimate tokens from a reputable DeFi aggregator. This paper further discusses the potential use of a model like ours by prosecutors in enforcement efforts and connects it to a wider legal context. [ABSTRACT FROM AUTHOR]

Pre-existing public debt vulnerabilities have been exacerbated by the effects of the pandemic, raising the risk of fiscal crises in emerging and low-income countries. This underscores the importance of models aimed at capturing the main determinants of fiscal distress episodes and forecasting the occurrence of sovereign debt crises. In this regard, our paper shows that ensemble tree methods, in particular random forests, are able to outperform standard econometric approaches, such as the probit model. This over-performance is not limited to short-term forecasting horizons, as documented by the previous literature, but holds also at longer horizons. The analysis also identifies the variables that are the most relevant predictors of fiscal crises at different forecasting horizons and provides an assessment of their impact on the probability of observing a crisis episode. Finally, the forecasts of the best performing machine learning algorithm are used to derive aggregate fiscal distress indexes that are able to signal effectively the build-up of debt-related vulnerabilities in emerging and low-income countries. [ABSTRACT FROM AUTHOR]

This paper analyzes the efficiency of various machine learning models (artificial neural networks, random forest, decision tree, AdaBoost and XGBoost) against the evolution of VBA-based (Visual Basic for Applications) malware over a large period of time (1995–2021). The file set used in our research is comprehensive—approximately 1.9 million files (out of which 944,595 are malicious and the rest are benign)—which allowed to gain insights on the resilience of various machine learning models against the diversity and the evolution of file features that reflect obfuscation techniques in VBA-based malware. In studying detection of VBA-based malware, we focus on characteristics of both the classifiers—proactivity (short-term detection efficiency against future malware), endurance (long-term detection robustness)—and of the detection-wise relevant file features—feature perishability (dynamics of feature relevance). We also describe in some detail—as a prerequisite of the study—various obfuscation techniques used by the malware under investigation during the last decade. [ABSTRACT FROM AUTHOR]

With the increase interest and number of the users in Social media, the file handling has also increased. To manage the load, cloud servers are being used by the service providers. To identify and cluster file is a difficult task that is important in the domain of computer science. Various traditional approaches for identification exists that uses design features. The problem with these methods is get that they can be easily spoofed. To resolve the issue, in this paper, a hybrid algorithm combining the features of Random Forest with AdaBoost is proposed. The algorithm Internet of Thing (IoT) data file formatting (IDFF) classifies data as (text, image, audio and video) and gives better accuracy. Our proposed research obtains better Accuracy (93%), Precision (95%), Recall (95%), F-Measure (95%), and G-Mean (96%). [ABSTRACT FROM AUTHOR]

Intensity modulation/direct detection (IM/DD) optical interconnect systems are susceptible to waveform distortion caused by complex nonlinearities. To reduce the effect of waveform distortion on signal transmission accuracy, in this paper, a random forest (RF) equalization algorithm based on decision tree (DT) integration is proposed for cost-sensitive IM/DD systems, which has the characteristics of nonlinear classification and regression. The performance of the RF equalizer is verified by simulation experiments on a 120 Gbps 8-level pulse amplitude modulation (PAM8) transmission system using an electro-absorption-modulated laser (EML). Simulation studies show that whether it is a back-to-back (B2B) transmission system or a 10 km optical fiber transmission system, the RF equalization scheme can achieve much better bit error rate (BER) performance than the traditional equalization scheme. In addition, in both transmission cases, the RF equalization scheme enables efficient classification of signals and is much less simpler than the artificial neural network (ANN) equalization scheme. [ABSTRACT FROM AUTHOR]

An electrocardiogram (ECG) is an electrical signal produced by ECG sensors to examine and visualize the heart's functionality, quick identification of arrhythmia aids in proper care and reduction of the risk factor. This paper uses machine learning algorithms to detect and identify arrhythmia types by extracting simple dynamic features from the ECG signals. The workflow will undergo three stages: pre-processing, feature extraction, and classification. A Low Pass Filter (LPF) and a two-stage median filter are proposed to eliminate all the signaling artifacts for successful feature extraction. The pre-processed signal is then fed into extracts of dynamic ECG features. With the aid of extracted features, the proposed Sampling Vector Random Forest Classifier (SVRF) predicts the form of arrhythmia. The novelty of the proposed SVRF is the ensemble-based approach for multi-class classification has overcome the noise resistance and gained inaccuracy when compared to another state-of-the-art classifier. The proposed method was tested with all the possible eleven types of arrhythmia from the MIT-BIH arrhythmia database, as stated in the association for the advancement of medical instrumentations recommendations. With the help of the proposed (SVRF), 98.22% of accuracy is achieved, which is better than other existing techniques. These aid medical professionals in the early detection of arrhythmia stages. The performance and comparative analysis are presented in this paper to prove the efficiency of the proposed method with the performance metrics of the confusion matrix and receiver operating characteristics. [ABSTRACT FROM AUTHOR]

The financial distress detection of listed companies is very important because it can prevent investors, managers and regulators from suffering huge losses and adverse effects. In this paper, 'special treatment(ST)' is regard as the financial distress due to the special circumstance of Chinese stock market. In the research of financial distress detection, there is not only a very large imbalance ratio between 'ST' companies and 'non-ST' companies, but there is also the problem of overlap, which is a more important factor affecting classification performance. However, for the financial distress detection method based on machine learning, most attention is focused on class imbalance rather than overlap. In order to take the overlap problem into account, firstly, this paper proposes the ESMOTE(Extreme SMOTE) method to select the minority classes close to the classification boundary for oversampling, which is more conducive to discover better and more correct decision boundary. Then a new Synchronous Sampling Learning Method (SSLM) is proposed in this paper. The point is to simultaneously delete the majority class and minority class instances that exceed the learned boundary, where this boundary (the margin's threshold) is obtained by optimizing the F 1 - S c o r e of the final classifier. A large number of experiments on 14 real data sets and the financial data set show that our method is significantly better than the most advanced methods in terms of F 1 - S c o r e and AUC, whether using Random Forest (RF), Naive Bayes (NB) or Support Vector Machine (SVM) as the final classifier. [ABSTRACT FROM AUTHOR]

One of the significant challenges in the sports industry is identifying the factors influencing match results and their respective weightage. For appropriate recommendations to the team management and the team players, there is a need to predict the match and quantify the important factors for which prediction models need to be developed. The second thing required is identifying talented and emerging players and performing an associative analysis of the important factors to the match-winning outcome. This paper formulates a hybrid machine learning-clustering-associative rules model. This paper also implements the framework for cricket matches, one of the most popular sports globally watched by billions around the world. We predict the match outcome for One day Internationals (ODIs) and Twenty 20 s (T20s) (two formats of Cricket representing fifty over and twenty over versions respectively) adopting state-of-the-art machine learning algorithms, Random Forest, Gradient Boosting, and Deep neural networks. The variable importance is computed using machine-learning techniques and further statistically validated through the regression model. The emerging talented players are identified by clustering. Association rules are generated for determining the best possible winning outcome. The results show that environmental conditions are equally crucial for determining a match result, as are internal quantitative factors. The model is thus helpful for both team management and for players to improve their winning strategy and also for discovering emerging players to form an unbeatable team. [ABSTRACT FROM AUTHOR]

With the advent of the Internet, the activities of individuals and businesses have expanded into the online realm. As a result, vulnerabilities that result in actual breaches can lead to data loss and program failure. The number of breaches is increasing every year, as is the number of vulnerabilities. To address this problem, current research focuses on the detection of vulnerabilities using static analysis techniques. To prevent the propagation of vulnerabilities, a new paradigm is needed to quickly detect vulnerabilities, analyze them, and take actions such as blocking or removing them. Recently, artificial intelligence algorithms such as deep learning have been introduced for vulnerability detection. In this paper, we propose a vulnerability detection model, V-CNN, which aims to detect CWE/CVE (Common Weakness Enumeration/Common Vulnerabilities and Exposures) using CNN (convolutional neural network). We trained CWE for deep learning and redefined vulnerabilities based on CWE. We propose an experimental algorithm to improve vulnerability detection. The accuracy of the proposed V-CNN model is 98%, which exceeds the 95% of the random forest model. Therefore, our V-CNN has excellent correctness detection performance in the field of vulnerability detection. The V-CNN vulnerability detection algorithm can be used instead of static analysis to detect various security vulnerabilities. [ABSTRACT FROM AUTHOR]

Malware attacks on the Android platform are rapidly increasing due to the high consumer adoption of Android smartphones. Advanced technologies have motivated cyber-criminals to actively create and disseminate a wide range of malware on Android smartphones. The researchers have conducted numerous studies on the detection of Android malware, but the majority of the works are based on the detection of generic Android malware. The detection based on malware categories will provide more insights about the malicious patterns of the malware. Therefore, this paper presents a detection solution for different Android malware categories, including adware, banking, SMS malware, and riskware. In this paper, a novel Huffman encoding-based feature vector generation technique is proposed. The experiments have proved that this novel approach significantly improves the efficiency of the detection model. This method makes use of system call frequencies as features to extract malware's dynamic behavior patterns. The proposed model was evaluated using machine learning and deep learning methods. The results show that the proposed model with the Random Forest classifier outperforms some existing methodologies with a detection accuracy of 98.70%. [ABSTRACT FROM AUTHOR]

Android operating system is known as one of the most popular mobile operating systems. The malware intrusion increases in the same pace as the production of applicable software. Propagation of new and transformed malware in seconds is a critical challenge in malware detection. Android software supplies thousands of features, providing assistance to identify malware applications. In this paper, a novel method based on a random forest algorithm, which applied three different feature selection techniques is proposed. This paper assesses the consequence of applying three different feature selection types including effective, high weight and effective group feature selection. Experiments conducted on Drebin dataset indicate applying the feature selection methods ameliorate the accuracy in terms of metrics and required time. In addition, comparison between the candidate feature selection model and a variety of algorithms as baselines proves the merit of applying feature selection on Random Forest, which outperforms other models based on several metrics. [ABSTRACT FROM AUTHOR]

Now-a-days fake news have become part and parcel of our everyday life due to its quick spreading in different social media. Fake news identification has been emerging as an important research subject due to the widespread dissemination of fake news on social and news media. Current fake news identification techniques primarily rely on the analysis of natural languages and machine learning models to assess the validity of news information in order to detect whether it is real or fake. Many traditional approaches including machine learning applications have been observed yet to detect fake news but the evolutionary based algorithms have gained lot of popularity because of their ability to converge to near optima and have low computational complexity. This motivated us to adopt a new approach with genetic algorithm to solve the fake news detection problem. In this paper, a comparative analysis is presented among SVM, Naïve Bayes, Random Forest and Logistic Regression classifiers to detect fake news applying on different datasets. SVM classifier has achieved the highest accuracy with 61%, 97% and 96% in Liar, Fake Job Posting and Fake News datasets respectively. Again, SVM, Naïve Bayes, Random Forest and Logistic Regression are considered as the fitness function in our novel GA based fake news detection algorithm. In our proposed algorithm, SVM and LR classifiers both achieved 61% accuracy in LIAR dataset and SVM and RF attained the highest accuracy as 97% in the fake job posting dataset. [ABSTRACT FROM AUTHOR]

Insufficient data is always a challenge for developing an accurate machine learning or deep learning model in manufacturing processes, especially in tool wear monitoring under varied cutting conditions. This paper presents a Random Forest model for predicting tool wear under varied cutting conditions as well as studies extracted signal features. The Random Forest algorithm was chosen as the machine learning model, rather than the novel deep learning model. This was due to the feature importance investigation, which was embedded in the Random Forest algorithm, thereby making it easier to study the physical meanings of signal features. The frequency domain signals were rearranged as features related to spindle speeds and machine tool structure based on domain knowledge. This is the first paper to rearrange the frequency domain signals for observing the physical meanings of selected features. When data normalization was adopted, frequency domain signals related to spindle speeds were excluded from important features. Only spectrum energy related to structure vibration and time domain signals were important features. Data normalization enhanced the weighting of structure vibration features in a machine learning model. This study showed that feature normalization made the machine learning model more adaptable to different cutting conditions. Furthermore, prediction accuracy for cutting condition of spindle speed = 42,000 rpm and feed = 1.5 μm/rev (lowest prediction accuracy among cutting tests in this study) showed an increase from 68.0 to 84.1%. In addition, spindle speed had a more significant effect than feed on classification accuracy in tool wear monitoring based on experimental results. As a result, at least two data sets of the same spindle speed as in tool wear prediction were recommended to be used for model training. When there were at least two data sets in training data with the same spindle speed as in testing data, the study showed prediction accuracies were greater than 75% without data normalization and 81% with data normalization. [ABSTRACT FROM AUTHOR]

It is hard to come up with a strong learning algorithm with high cross-media retrieval accuracy, but finding a weak learning algorithm with slightly higher accuracy than random prediction is simple. This paper proposes an innovative Bagging-based cross-media retrieval algorithm (called BCMR) based on this concept. First, we use bootstrap sampling to take a random sample from the original set. The amount of sample abstracted by bootstrapping is set to be the same as the amount of sample abstracted by the original dataset. Secondly, 50 bootstrap replicates are used to train 50 weak classifiers. In our experiments, we used homogeneous individual classifiers and eight different baseline methods. Last but not least, we generate the final strong classifier from 50 weak classifiers using the sample voting integration strategy. Using collective wisdom, we can get rid of bad decisions, giving the integrated model a much better generalization ability. Extensive experiments on three datasets show that BCMR can significantly improve cross-media retrieval accuracy. [ABSTRACT FROM AUTHOR]

Predictive sports data analytics can be revolutionary for sports performance. Existing literature discusses players' or teams' performance, independently or in tandem. Using Machine Learning (ML), this paper aims to holistically evaluate player-, team-, and conference (season)-level performances in Division-1 Women's basketball. The players were monitored and tested through a full competitive year. The performance was quantified at the player level using the reactive strength index modified (RSImod), at the team level by the game score (GS) metric, and finally at the conference level through Player Efficiency Rating (PER). The data includes parameters from training, subjective stress, sleep, and recovery (WHOOP straps), in-game statistics (Polar monitors), and countermovement jumps. We used data balancing techniques and an Extreme Gradient Boosting (XGB) classifier to predict RSI and GS with greater than 90% accuracy and a 0.9 F1 score. The XGB regressor predicted PER with an MSE of 0.026 and an R2 of 0.680. Ensemble of Random Forest, XGB, and correlation finds feature importance at all levels. We used Partial Dependence Plots to understand the impact of each feature on the target variable. Quantifying and predicting performance at all levels will allow coaches to monitor athlete readiness and help improve training. [ABSTRACT FROM AUTHOR]

Knowing human papillomavirus (HPV) status has important consequences for treatment selection in oropharyngeal cancer. The gold standard is to perform a biopsy. The objective of this paper is to develop a new computed tomography (CT) radiomics-based non-invasive solution to HPV status determination and investigate if and how it can be a viable and accurate complementary technique. Two hundred thirty-eight patients' CT scans were normalized and resampled. One thousand one hundred forty-two radiomics features were obtained from the segmented CT scans. The number of radiomic attributes was decreased by applying correlation coefficient analysis, backward elimination, and random forest feature importance analysis. Random over-sampling (ROSE) resampling algorithm was performed on the training set for data balancing, and as a result, 161 samples were obtained for each of the HPV classes of the training set. A random forest (RF) classification algorithm was used as a prediction model using five-fold cross-validation (CV). Model effectiveness was evaluated on the unused 20% of the imbalanced data. The applicability of the model was investigated based on previous research and error rates reported for biopsy procedures. The HPV status was determined with an accuracy of 91% (95% CI 83–99) and an area under the curve (AUC) of 0.77 (95% CI 65–89) on the test data. The error rates were comparable to those encountered in biopsy. As a conclusion, radiomics has the potential to predict HPV status with accuracy levels that are comparable to biopsy. Future work is needed to improve standardization, interpretability, robustness, and reproducibility before clinical translation. [ABSTRACT FROM AUTHOR]

Optimization of sinter ore allocation is a key step in the steel production process, which has become the most important measure for steel enterprises to effectively reduce cost, improve quality, save energy and reduce emissions. In this paper, the first intelligent recommendation model for the sintering dosing scheme considering cost, quality and carbon emission in the sintering process is developed using the SA2PSO optimization algorithm combined with machine learning. To improve the optimization accuracy and speed of the PSO algorithm, the SA2PSO algorithm is based on the adaptive and simulated annealing operations to achieve different stages of particle optimization, and the convergence speed is reduced by about 5 s compared with PSO while ensuring the optimization accuracy. Based on the optimal solution, the random forest algorithm was used to achieve a high-accuracy prediction of quality. For carbon emission, this paper for the first time to our knowledge converts carbon tax into iron ore sintering cost, establishes a dosing scheme considering cost carbon emission and quality and finally establishes an intelligent recommendation model for sintering dosing based on VIKOR. The model can be used for optimal ore allocation in sintering to achieve low cost, high quality and low CO2 emission in iron ore sintering. [ABSTRACT FROM AUTHOR]

This paper presents a study on developing a chemical vapor deposition film thickness prediction model for semiconductor IC manufacturing. Traditional methods for measuring layer thickness are time-consuming and labor-intensive, prompting the exploration of machine-learning techniques for virtual measurement. These techniques estimate layer thickness directly from production process data, enabling real-time monitoring of product quality and maintaining process efficiency. This study used the Harris Hawks optimization algorithm (HHO) to perform feature selection on deposition process data and constructed a predictive model using the selected feature parameters. Four machine learning models, namely Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost), are evaluated using metrics such as mean squared error (MSE), mean absolute percentage error (MAPE), and R-squared ( R 2 ) on a test set. Results demonstrate that the CatBoost model outperforms the others with an MSE of 353.55, MAPE of 0.246% and R 2 of 0.796, highlighting its superior prediction accuracy in estimating film thickness. However, the integrated tree model used in this study is complex, and its prediction results cannot be directly interpreted, making the model less credible. To address this issue, the SHAP method was introduced for interpretable analysis of the model. Overall, this study shows that the use of machine learning models, such as the CatBoost model, combined with SHAP analysis, significantly improves the credibility of prediction results on deposited film thickness in IC fabrication. Moreover, the timely adjustment of production equipment parameters can be achieved to reduce process deviations and improve IC yield. [ABSTRACT FROM AUTHOR]