Search

An accurate prediction of house prices is a fundamental requirement for various sectors, including real estate and mortgage lending. It is widely recognized that a property’s value is not solely determined by its physical attributes but is significantly influenced by its surrounding neighborhood. Meeting the diverse housing needs of individuals while balancing budget constraints is a primary concern for real estate developers. To this end, we addressed the house price prediction problem as a regression task and thus employed various machine learning (ML) techniques capable of expressing the significance of independent variables. We made use of the housing dataset of Ames City in Iowa, USA to compare XGBoost, support vector regressor, random forest regressor, multilayer perceptron, and multiple linear regression algorithms for house price prediction. Afterwards, we identified the key factors that influence housing costs. Our results show that XGBoost is the best performing model for house price prediction. Our findings present valuable insights and tools for stakeholders, facilitating more accurate property price estimates and, in turn, enabling more informed decision making to meet the housing needs of diverse populations while considering budget constraints.

The overall purpose of this paper is to demonstrate how data preprocessing, training size variation, and subsampling can dynamically change the performance metrics of imbalanced text classification. The methodology encompasses using two different supervised learning classification approaches of feature engineering and data preprocessing with the use of five machine learning classifiers, five imbalanced sampling techniques, specified intervals of training and subsampling sizes, statistical analysis using R and tidyverse on a dataset of 1000 portable document format files divided into five labels from the World Health Organization Coronavirus Research Downloadable Articles of COVID-19 papers and PubMed Central databases of non-COVID-19 papers for binary classification that affects the performance metrics of precision, recall, receiver operating characteristic area under the curve, and accuracy. One approach that involves labeling rows of sentences based on regular expressions significantly improved the performance of imbalanced sampling techniques verified by performing statistical analysis using a t-test documenting performance metrics of iterations versus another approach that automatically labels the sentences based on how the documents are organized into positive and negative classes. The study demonstrates the effectiveness of ML classifiers and sampling techniques in text classification datasets, with different performance levels and class imbalance issues observed in manual and automatic methods of data processing.

High-quality short-term forecasts of electrical energy generation in solar power plants are crucial in the dynamically developing sector of renewable power generation. This article addresses the issue of selecting appropriate (preferred) methods for forecasting energy generation from a solar power plant within a 15 min time horizon. The effectiveness of various machine learning methods was verified. Additionally, the effectiveness of proprietary ensemble and hybrid methods was proposed and examined. The research also aimed to determine the appropriate sets of input variables for the predictive models. To enhance the performance of the predictive models, proprietary additional input variables (feature engineering) were constructed. The significance of individual input variables was examined depending on the predictive model used. This article concludes with findings and recommendations regarding the preferred predictive methods.

With the proliferation of the Internet, network complexities for both commercial and state organizations have significantly increased, leading to more sophisticated and harder-to-detect network attacks. This evolution poses substantial challenges for intrusion detection systems, threatening the cybersecurity of organizations and national infrastructure alike. Although numerous deep learning techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph neural networks (GNNs) have been applied to detect various network attacks, they face limitations due to the lack of standardized input data, affecting model accuracy and performance. This paper proposes a novel preprocessing method for flow data from network intrusion detection systems (NIDSs), enhancing the efficacy of a graph neural network model in malicious flow detection. Our approach initializes graph nodes with data derived from flow features and constructs graph edges through the analysis of IP relationships within the system. Additionally, we propose a new graph model based on the combination of the graph neural network (GCN) model and SAGEConv, a variant of the GraphSAGE model. The proposed model leverages the strengths while addressing the limitations encountered by the previous models. Evaluations on two IDS datasets, CICIDS-2017 and UNSW-NB15, demonstrate that our model outperforms existing methods, offering a significant advancement in the detection of network threats. This work not only addresses a critical gap in the standardization of input data for deep learning models in cybersecurity but also proposes a scalable solution for improving the intrusion detection accuracy.

In today’s dynamic business world, organizations are increasingly relying on innovative technologies to improve the efficiency and effectiveness of their human resource (HR) management. Our study uses historical time and attendance data collected with the MojeUre time and attendance system to predict employee absenteeism, including sick and vacation leave, using machine learning methods. We integrate employee demographic data and the absence profiles on timesheets showing daily attendance patterns as fundamental elements for our analysis. We also convert the absence data into a feature-based format suitable for the machine learning methods used. Our primary goal in this paper is to evaluate how well we can predict sick leave and vacation leave over short- and long-term intervals using tree-based machine learning methods based on the predictive clustering paradigm. This paper compares the effectiveness of these methods in different learning settings and discusses their impact on improving HR decision-making processes.

This work describes a mathematical model for handwriting devices without a specific reference surface (SRS). The research was carried out on two hypotheses: the first considers possible circular segments that could be made during execution for the reconstruction of the trace, and the second is the combination of lines and circles. The proposed system has no flat reference surface, since the sensor is inside the pencil that describes the trace, not on the surface as in tablets or cell phones. An inertial sensor was used for the measurements, in this case, a commercial Micro-Electro Mechanical sensor of linear acceleration. The tracking device is an IMU sensor and a processing card that allows inertial measurements of the pen during on-the-fly tracing. It is essential to highlight that the system has a non-inertial reference frame. Comparing the two proposed models shows that it is possible to construct shapes from curved lines and that the patterns obtained are similar to what is recognized; this method provides an alternative to quaternion calculus for poorly specified orientation problems.

This study compares the calculation of snow water equivalent (SWE) using machine learning algorithms with the conventional degree-day method. The study uses machine learning techniques such as LASSO, Random Forest, Support Vector Machines, and CatBoost. It proposes an innovative use of feature engineering (FE) to improve the accuracy and robustness of SWE predictions by machine learning intended for interpolation, extrapolation, or imputation of missing data. The performance of machine learning approaches is evaluated against the traditional degree-day method for predicting SWE. The study emphasizes and demonstrates gains when modeling is enhanced by transforming basic, raw data through feature engineering. The results, verified in a case study from the mountainous region of Slovakia, suggest that machine learning, particularly CatBoost with feature engineering, shows better results in SWE estimation in comparison with the degree-day method, although the authors present a refined application of the degree-day method by utilizing genetic algorithms. Nevertheless, the study finds that the degree-day method achieved accuracy with a Nash–Sutcliffe coefficient of efficiency NSE = 0.59, while the CatBoost technique enhanced with the proposed FE achieved an accuracy NSE = 0.86. The results of this research contribute to refining snow hydrology modeling and optimizing SWE prediction for improved decision-making in snow-dominated regions.

Thyroid disease is among the most prevalent endocrinopathies worldwide. As the thyroid gland controls human metabolism, thyroid illness is a matter of concern for human health. To save time and reduce error rates, an automatic, reliable, and accurate thyroid identification machine-learning (ML) system is essential. The proposed model aims to address existing work limitations such as the lack of detailed feature analysis, visualization, improvement in prediction accuracy, and reliability. Here, a public thyroid illness dataset containing 29 clinical features from the University of California, Irvine ML repository was used. The clinical features helped us to build an ML model that can predict thyroid illness by analyzing early symptoms and replacing the manual analysis of these attributes. Feature analysis and visualization facilitate an understanding of the role of features in thyroid prediction tasks. In addition, the overfitting problem was eliminated by 5-fold cross-validation and data balancing using the synthetic minority oversampling technique (SMOTE). Ensemble learning ensures prediction model reliability owing to the involvement of multiple classifiers in the prediction decisions. The proposed model achieved 99.5% accuracy, 99.39% sensitivity, and 99.59% specificity with the boosting method which is applicable to real-time computer-aided diagnosis (CAD) systems to ease diagnosis and promote early treatment.

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method’s performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning.

The opportunities of impedance-based condition monitoring for rolling bearings have been shown earlier by the authors: Changes in the impedance signal and the derived features enable the detection of pitting damages. Localizing and measuring the pitting length in the raceway direction is possible. Furthermore, the changes in features behavior are physically explainable. These investigations were focused on a single bearing type and only one load condition. Different bearing types and load angles were not considered yet. Thus, the impedance signals and their features of different bearing types under different load angles are investigated and compared. The signals are generated in fatigue tests on a rolling bearing test rig with conventional integrated vibration analysis based on structural borne sound. The rolling bearing impedance is gauged using an alternating current measurement bridge. Significant changes in the vibration signals mark the end of the fatigue tests. Therefore, comparing the response time of the impedance can be compared to the vibration signal response time. It can be shown that the rolling bearing impedance is an instrument for condition monitoring, independently from the bearing type. In case of pure radial loads, explicit changes in the impedance signal are detectable, which indicate a pitting damage. Under combined loads, the signal changes are detectable as well, but not as significant as under radial load. Damage-indicating signal changes occur later compared to pure radial loads, but nevertheless enable an early detection. Therefore, the rolling bearing impedance is an instrument for pitting damage detection, independently from bearing type and load angle.

Hyperspectral imaging holds significant promise in remote sensing applications, particularly for land cover and land-use classification, thanks to its ability to capture rich spectral information. However, leveraging hyperspectral data for accurate segmentation poses critical challenges, including the curse of dimensionality and the scarcity of ground truth data, that hinder the accuracy and efficiency of machine learning approaches. This paper presents a holistic approach for adaptive optimized hyperspectral-based land cover and land-use segmentation using automated machine learning (AutoML). We address the challenges of high-dimensional hyperspectral data through a revamped machine learning pipeline, thus emphasizing feature engineering tailored to hyperspectral classification tasks. We propose a framework that dissects feature engineering into distinct steps, thus allowing for comprehensive model generation and optimization. This framework incorporates AutoML techniques to streamline model selection, hyperparameter tuning, and data versioning, thus ensuring robust and reliable segmentation results. Our empirical investigation demonstrates the efficacy of our approach in automating feature engineering and optimizing model performance, even without extensive ground truth data. By integrating automatic optimization strategies into the segmentation workflow, our approach offers a systematic, efficient, and scalable solution for hyperspectral-based land cover and land-use classification.

Online platforms have become the primary means for travellers to search, compare, and book accommodations for their trips. Consequently, online platforms and revenue managers must acquire a comprehensive comprehension of these dynamics to formulate a competitive and appealing offerings. Recent advancements in natural language processing, specifically through the development of large language models, have demonstrated significant progress in capturing the intricate nuances of human language. On the other hand, knowledge graphs have emerged as potent instruments for representing and organizing structured information. Nevertheless, effectively integrating these two powerful technologies remains an ongoing challenge. This paper presents an innovative deep learning methodology that combines large language models with domain-specific knowledge graphs for classification of tourism offers. The main objective of our system is to assist revenue managers in the following two fundamental dimensions: (i) comprehending the market positioning of their accommodation offerings, taking into consideration factors such as accommodation price and availability, together with user reviews and demand, and (ii) optimizing presentations and characteristics of the offerings themselves, with the intention of improving their overall appeal. For this purpose, we developed a domain knowledge graph covering a variety of information about accommodations and implemented targeted feature engineering techniques to enhance the information representation within a large language model. To evaluate the effectiveness of our approach, we conducted a comparative analysis against alternative methods on four datasets about accommodation offers in London. The proposed solution obtained excellent results, significantly outperforming alternative methods.

Deformation effectively represents the structural integrity of concrete dams and acts as a clear indicator of their operational performance. Predicting deformation is critical for monitoring the safety of hydraulic structures. To this end, this paper proposes an artificial intelligence-based process for predicting concrete dam deformation. Initially, using the principles of feature engineering, the preprocessing of deformation safety monitoring data is conducted. Subsequently, employing a stacking model fusion method, a novel prediction process embedded with multiple artificial intelligence algorithms is developed. Moreover, three new performance indicators—a superiority evaluation indicator, an accuracy evaluation indicator, and a generalization evaluation indicator—are introduced to provide a comprehensive assessment of the model’s effectiveness. Finally, an engineering example demonstrates that the ensemble artificial intelligence method proposed herein outperforms traditional statistical models and single machine learning models in both fitting and predictive accuracy, thereby providing a scientific and effective foundation for concrete dam deformation prediction and safety monitoring.

The dropout rate in underdeveloped and emerging countries is a pressing social issue, as highlighted by studies conducted by The Organization for Economic Co-operation and Development. This study compares five feature selection techniques to address this challenge and improve the automatic detection of dropout risk. The methodological design involves three distinct phases: data preparation, feature selection, and model evaluation utilizing machine learning algorithms. The results demonstrate that (1) the top features identified by feature selection techniques, i.e., those constructed through feature engineering, proved to be among the most effective in classifying student dropout; (2) the F-score of the best model increased by 5% with feature selection techniques; and (3) depending on the type of feature selection, the performance of the machine learning algorithm can vary, potentially increasing or decreasing based on the sensitivity of features with higher noise. At the same time, metaheuristic algorithms demonstrated significant precision improvements, but there was a risk of increasing errors and reducing recall.

Personalized recommender systems play a crucial role in assisting users in discovering items of interest from vast amounts of information across various domains. However, developing accurate personalized recommender systems remains challenging due to the need to balance model architectures, input feature combinations, and fusion of heterogeneous data sources. This study investigates the impacts of these factors on recommendation performance using the MovieLens and Book Recommendation datasets. Six models, including single-task neural networks, multi-task learning, and baselines, were evaluated with various input feature combinations using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The multi-task learning approach achieved significantly lower RMSE and MAE by effectively leveraging heterogeneous data sources for personalized recommendations through a shared neural network architecture. Furthermore, incorporating user data and content data progressively enhanced performance compared to using only item identifiers. The findings highlight the importance of advanced model architectures and fusing heterogeneous data sources for high-quality recommendations, providing valuable insights for designing effective recommender systems across diverse domains.

Nocturnal enuresis (NE) is involuntary bedwetting during sleep, typically appearing in young children. Despite the potential benefits of the long-term home monitoring of NE patients for research and treatment enhancement, this area remains underexplored. To address this, we propose NEcare, an in-home monitoring system that utilizes wearable devices and machine learning techniques. NEcare collects sensor data from an electrocardiogram, body impedance (BI), a three-axis accelerometer, and a three-axis gyroscope to examine bladder volume (BV), heart rate (HR), and periodic limb movements in sleep (PLMS). Additionally, it analyzes the collected NE patient data and supports NE moment estimation using heuristic rules and deep learning techniques. To demonstrate the feasibility of in-home monitoring for NE patients using our wearable system, we used our datasets from 30 in-hospital patients and 4 in-home patients. The results show that NEcare captures expected trends associated with NE occurrences, including BV increase, HR increase, and PLMS appearance. In addition, we studied the machine learning-based NE moment estimation, which could help relieve the burdens of NE patients and their families. Finally, we address the limitations and outline future research directions for the development of wearable systems for NE patients

Clinical text often includes numbers of various types and formats. However, most current text classification approaches do not take advantage of these numbers. This study aims to demonstrate that using numbers as features can significantly improve the performance of text classification models. This study also demonstrates the feasibility of extracting such features from clinical text. Unsupervised learning was used to identify patterns of number usage in clinical text. These patterns were analyzed manually and converted into pattern-matching rules. Information extraction was used to incorporate numbers as features into a document representation model. We evaluated text classification models trained on such representation. Our experiments were performed with two document representation models (vector space model and word embedding model) and two classification models (support vector machines and neural networks). The results showed that even a handful of numerical features can significantly improve text classification performance. We conclude that commonly used document representations do not represent numbers in a way that machine learning algorithms can effectively utilize them as features. Although we demonstrated that traditional information extraction can be effective in converting numbers into features, further community-wide research is required to systematically incorporate number representation into the word embedding process.

In recent years, one of the most promising areas in modern concrete science and the technology of reinforced concrete structures is the technology of vibro-centrifugation of concrete, which makes it possible to obtain reinforced concrete elements with a variatropic structure. However, this area is poorly studied and there is a serious deficiency in both scientific and practical terms, expressed in the absence of a systematic knowledge of the life cycle management processes of vibro-centrifuged variatropic concrete. Artificial intelligence methods are seen as one of the most promising methods for improving the process of managing the life cycle of such concrete in reinforced concrete structures. The purpose of the study is to develop and compare machine learning algorithms based on ridge regression, decision tree and extreme gradient boosting (XGBoost) for predicting the compressive strength of vibro-centrifuged variatropic concrete using a database of experimental values obtained under laboratory conditions. As a result of laboratory tests, a dataset of 664 samples was generated, describing the influence of aggressive environmental factors (freezing–thawing, chloride content, sulfate content and number of wetting–drying cycles) on the final strength characteristics of concrete. The use of analytical techniques to extract additional knowledge from data contributed to improving the resulting predictive properties of machine learning models. As a result, the average absolute percentage error (MAPE) for the best XGBoost algorithm was 2.72%, mean absolute error (MAE) = 1.134627, mean squared error (MSE) = 4.801390, root-mean-square error (RMSE) = 2.191208 and R2 = 0.93, which allows to conclude that it is possible to use “smart” algorithms to improve the life cycle management process of vibro-centrifuged variatropic concrete, by reducing the time required for the compressive strength assessment of new structures.

Accurate estimation of lithium-ion battery state of health (SOH) can effectively improve the operational safety of electric vehicles and optimize the battery operation strategy. However, previous SOH estimation algorithms developed based on high-precision laboratory data have ignored the discrepancies between field and laboratory data, leading to difficulties in field application. Therefore, aiming to bridge the gap between the lab-developed models and the field operational data, this paper presents a feature engineering-based SOH estimation method with downgraded laboratory battery data, applicable to real vehicles under different operating conditions. Firstly, a data processing pipeline is proposed to downgrade laboratory data to operational fleet-level data. The six key features are extracted on the partial ranges to capture the battery’s aging state. Finally, three machine learning (ML) algorithms for easy online deployment are employed for SOH assessment. The results show that the hybrid feature set performs well and has high accuracy in SOH estimation for downgraded data, with a minimum root mean square error (RMSE) of 0.36%. Only three mechanism features derived from the incremental capacity curve can still provide a proper assessment, with a minimum RMSE of 0.44%. Voltage-based features can assist in evaluating battery state, improving accuracy by up to 20%.

Anonymous networks, which aim primarily to protect user identities, have gained prominence as tools for enhancing network security and anonymity. Nonetheless, these networks have become a platform for adversarial affairs and sources of suspicious attack traffic. To defend against unpredictable adversaries on the Internet, detecting anonymous network traffic has emerged as a necessity. Many supervised approaches to identify anonymous traffic have harnessed machine learning strategies. However, many require access to engineered datasets and complex architectures to extract the desired information. Due to the resistance of anonymous network traffic to traffic analysis and the scarcity of publicly available datasets, those approaches may need to improve their training efficiency and achieve a higher performance when it comes to anonymous traffic detection. This study utilizes feature engineering techniques to extract pattern information and rank the feature importance of the static traces of anonymous traffic. To leverage these pattern attributes effectively, we developed a reinforcement learning framework that encompasses four key components: states, actions, rewards, and state transitions. A lightweight system is devised to classify anonymous and non-anonymous network traffic. Subsequently, two fine-tuned thresholds are proposed to substitute the traditional labels in a binary classification system. The system will identify anonymous network traffic without reliance on labeled data. The experimental results underscore that the system can identify anonymous traffic with an accuracy rate exceeding 80% (when based on pattern information).

Accurate building energy consumption prediction is a crucial condition for the sustainable development of building energy management systems. However, the highly nonlinear nature of data and complex influencing factors in the energy consumption of large public buildings often pose challenges in improving prediction accuracy. In this study, we propose a combined prediction model that combines signal decomposition, feature screening, and deep learning. First, we employ the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose energy consumption data. Next, we propose the Maximum Mutual Information Coefficient (MIC)-Fast Correlation Based Filter (FCBF) combined feature screening method for feature selection on the decomposed components. Finally, the selected input features and corresponding components are fed into the Bi-directional Long Short-Term Memory Attention Mechanism (BiLSTMAM) model for prediction, and the aggregated results yield the energy consumption forecast. The proposed approach is validated using energy consumption data from a large public building in Shaanxi Province, China. Compared with the other five comparison methods, the RMSE reduction of the CEEMDAN-MIC-FCBF-BiLSTMAM model proposed in this study ranged from 57.23% to 82.49%. Experimental results demonstrate that the combination of CEEMDAN, MIC-FCBF, and BiLSTMAM modeling markedly improves the accuracy of energy consumption predictions in buildings, offering a potent method for optimizing energy management and promoting sustainability in large-scale facilities.

This paper introduces an innovative framework for wind power prediction that focuses on the future of energy forecasting utilizing intelligent deep learning and strategic feature engineering. This research investigates the application of a state-of-the-art deep learning model for wind energy prediction to make extremely short-term forecasts using real-time data on wind generation from New South Wales, Australia. In contrast with typical approaches to wind energy forecasting, this model relies entirely on historical data and strategic feature engineering to make predictions, rather than relying on meteorological parameters. A hybrid feature engineering strategy that integrates features from several feature generation techniques to obtain the optimal input parameters is a significant contribution to this work. The model’s performance is assessed using key metrics, yielding optimal results with a Mean Absolute Error (MAE) of 8.76, Mean Squared Error (MSE) of 139.49, Root Mean Squared Error (RMSE) of 11.81, R-squared score of 0.997, and Mean Absolute Percentage Error (MAPE) of 4.85%. Additionally, the proposed framework outperforms six other deep learning and hybrid deep learning models in terms of wind energy prediction accuracy. These findings highlight the importance of advanced data analysis for feature generation in data processing, pointing to its key role in boosting the precision of forecasting applications.

Research in field sports often involves analysis of running performance profiles of players during competitive games with individual, per-position, and time-related descriptive statistics. Data are acquired through wearable technologies, which generally capture simple data points, which in the case of many team-based sports are times, latitudes, and longitudes. While the data capture is simple and in relatively high volumes, the raw data are unsuited to any form of analysis or machine learning functions. The main goal of this research is to develop a multistep feature engineering framework that delivers the transformation of sequential data into feature sets more suited to machine learning applications.

Momentum has been a consistently studied aspect of sports science for decades. Among the established literature, there has, at times, been a discrepancy between conclusions. However, if momentum is indeed an actual phenomenon, it would affect all aspects of sports, from player evaluation to pre-game prediction and betting. Therefore, using momentum-based features that quantify a team’s linear trend of play, we develop a data pipeline that uses a small sample of recent games to assess teams’ quality of play and measure the predictive power of momentum-based features versus the predictive power of more traditional frequency-based features across several leagues using several machine learning techniques. More precisely, we use our pipeline to determine the differences in the predictive power of momentum-based features and standard statistical features for the National Hockey League (NHL), National Basketball Association (NBA), and five major first-division European football leagues. Our findings show little evidence that momentum has superior predictive power in the NBA. Still, we found some instances of the effects of momentum on the NHL that produced better pre-game predictors, whereas we view a similar trend in European football/soccer. Our results indicate that momentum-based features combined with frequency-based features could improve pre-game prediction models and that, in the future, momentum should be studied more from a feature/performance indicator point-of-view and less from the view of the dependence of sequential outcomes, thus attempting to distance momentum from the binary view of winning and losing.

Addressing the problems of misclassification and omissions in urban vegetation fine classification from current remote sensing classification methods, this research proposes an intelligent urban vegetation classification method that combines feature engineering and improved DeepLabV3+ based on unmanned aerial vehicle visible spectrum images. The method constructs feature engineering under the ReliefF algorithm to increase the number of features in the samples, enabling the deep learning model to learn more detailed information about the vegetation. Moreover, the method improves the classical DeepLabV3+ network structure based on (1) replacing the backbone network using MoblieNetV2; (2) adjusting the atrous spatial pyramid pooling null rate; and (3) adding the attention mechanism and the convolutional block attention module. Experiments were conducted with self-constructed sample datasets, where the method was compared and analyzed with a fully convolutional network (FCN) and U-Net and ShuffleNetV2 networks; the migration of the method was tested as well. The results show that the method in this paper is better than FCN, U-Net, and ShuffleNetV2, and reaches 92.27%, 91.48%, and 85.63% on the accuracy evaluation indices of overall accuracy, MarcoF1, and mean intersection over union, respectively. Furthermore, the segmentation results are accurate and complete, which effectively alleviates misclassifications and omissions of urban vegetation; moreover, it has a certain migration ability that can quickly and accurately classify the vegetation.

This research addresses a critical need in the ongoing battle against malware, particularly in the form of obfuscated malware, which presents a formidable challenge in the realm of cybersecurity. Developing effective antivirus (AV) solutions capable of combating packed malware remains a crucial endeavor. Packed malicious programs employ encryption and advanced techniques to obfuscate their payloads, rendering them elusive to AV scanners and security analysts. The introduced research presents an innovative malware packer classifier specifically designed to adeptly identify packer families and detect unknown packers in real-world scenarios. To fortify packer identification performance, we have curated a meticulously crafted dataset comprising precisely packed samples, enabling comprehensive training and validation. Our approach employs a sophisticated feature engineering methodology, encompassing multiple layers of analysis to extract salient features used as input to the classifier. The proposed packer identifier demonstrates remarkable accuracy in distinguishing between known and unknown packers, while also ensuring operational efficiency. The results reveal an impressive accuracy rate of 99.60% in identifying known packers and 91% accuracy in detecting unknown packers. This novel research not only significantly advances the field of malware detection but also equips both cybersecurity practitioners and AV engines with a robust tool to effectively counter the persistent threat of packed malware.

Condition monitoring (CM) is essential for maintaining operational reliability and safety in complex machinery, particularly in robotic systems. Despite the potential of deep learning (DL) in CM, its ‘black box’ nature restricts its broader adoption, especially in mission-critical applications. Addressing this challenge, our research introduces a robust, four-phase framework explicitly designed for DL-based CM in robotic systems. (1) Feature extraction utilizes advanced Fourier and wavelet transformations to enhance both the model’s accuracy and explainability. (2) Fault diagnosis employs a specialized Convolutional Long Short-Term Memory (CLSTM) model, trained on the features to classify signals effectively. (3) Model refinement uses SHAP (SHapley Additive exPlanation) values for pruning nonessential features, thereby simplifying the model and reducing data dimensionality. (4) CM interpretation develops a system offering insightful explanations of the model’s decision-making process for operators. This framework is rigorously evaluated against five existing fault diagnosis architectures, utilizing two distinct datasets: one involving torque measurements from a robotic arm for safety assessment and another capturing vibration signals from an electric motor with multiple fault types. The results affirm our framework’s superior optimization, reduced training and inference times, and effectiveness in transparently visualizing fault patterns.

Coronary artery disease (CAD) is the most prevalent form of cardiovascular disease that may result in myocardial infarction. Annually, it leads to millions of fatalities and causes billions of dollars in global economic losses. Limited resources and complexities in interpreting results pose challenges to healthcare centers in implementing deep learning (DL)-based CAD detection models. Ensemble learning (EL) allows developers to build an effective CAD detection model by integrating the outcomes of multiple medical imaging models. In this study, the authors build an EL-based CAD detection model to identify CAD from coronary computer tomography angiography (CCTA) images. They employ a feature engineering technique, including MobileNet V3, CatBoost, and LightGBM models. A random forest (RF) classifier is used to ensemble the outcomes of the CatBoost and LightGBM models. The authors generalize the model using two benchmark datasets. The proposed model achieved an accuracy of 99.7% and 99.6% with limited computational resources. The generalization results highlight the importance of the proposed model’s efficiency in identifying CAD from the CCTA images. Healthcare centers and cardiologists can benefit from the proposed model to identify CAD in the initial stages. The proposed feature engineering can be extended using a liquid neural network model to reduce computational resources.

Cocoa is the economic backbone of Côte d’Ivoire and Ghana, making them the leading cocoa-producing countries in the world. However, cocoa farming has been a major driver of deforestation and landscape degradation in West Africa. Various stakeholders are striving for a zero-deforestation cocoa sector by implementing sustainable farming strategies and a more transparent supply chain. In the context of tracking cocoa sources and contributing to cocoa-driven deforestation monitoring, the demand for accurate and up-to-date maps of cocoa plantations is increasing. Yet, access to limited reference data and imperfect data quality can impose challenges in producing reliable maps. This study classified full-sun-cocoa-growing areas using limited reference data relative to the large and heterogeneous study areas in Côte d’Ivoire and Ghana. A Sentinel-2 composite image of 2021 was generated to train a random forest model. We undertook reference data refinement, selection of the most important handcrafted features and data sampling to ensure spatial independence. After refining the quality of the reference data and despite their size reduction, the random forest performance was improved, achieving an overall accuracy of 85.1 ± 2.0% and an F1 score of 84.6 ± 2.4% (mean ± one standard deviation from ten bootstrapping iterations). Emphasis was given to the qualitative visual assessment of the map using very high-resolution images, which revealed cases of strong and weak generalisation capacity of the random forest. Further insight was gained from the comparative analysis of our map with two previous cocoa classification studies. Implications of the use of cocoa maps for reporting were discussed.

Neural networks require a large quantity of training spectra and detector responses in order to learn to solve the inverse problem of neutron spectrum unfolding. In addition, due to the under-determined nature of unfolding, non-physical spectra which would not be encountered in usage should not be included in the training set. While physically realistic training spectra are commonly determined experimentally or generated through Monte Carlo simulation, this can become prohibitively expensive when considering the quantity of spectra needed to effectively train an unfolding network. In this paper, we present three algorithms for the generation of large quantities of realistic and physically motivated neutron energy spectra. Using an IAEA compendium of 251 spectra, we compare the unfolding performance of neural networks trained on spectra from these algorithms, when unfolding real-world spectra, to two baselines. We also investigate general methods for evaluating the performance of and optimizing feature engineering algorithms.

Driving style classification does not only depend on objective measures such as vehicle speed or acceleration, but is also highly subjective as drivers come with their own definition. From our perspective, the successful implementation of driving style classification in real-world applications requires an adaptive approach that is tuned to each driver individually. Within this work, we propose a transfer learning framework for driving style classification in which we use a previously developed rule-based algorithm for the initialization of the neural network weights and train on limited data. Therefore, we applied various state-of-the-art machine learning methods to ensure robust training. First, we performed heuristic-based feature engineering to enhance generalized feature building in the first layer. We then calibrated our network to be able to use its output as a probabilistic metric and to only give predictions above a predefined neural network confidence. To increase the robustness of the transfer learning in early increments, we used a synthetic oversampling technique. We then performed a holistic hyperparameter optimization in the form of a random grid search, which incorporated the entire learning framework from pretraining to incremental adaption. The final algorithm was then evaluated based on the data of predefined synthetic drivers. Our results showed that, by integrating these various methods, high system-level performance and robustness were met with as little as three new training and validation data samples in each increment.

Breast cancer (BC) is the leading cause of mortality among women across the world. Earlier screening of BC can significantly reduce the mortality rate and assist the diagnostic process to increase the survival rate. Researchers employ deep learning (DL) techniques to detect BC using mammogram images. However, these techniques are resource-intensive, leading to implementation complexities in real-life environments. The performance of convolutional neural network (CNN) models depends on the quality of mammogram images. Thus, this study aimed to build a model to detect BC using a DL technique. Image preprocessing techniques were used to enhance image quality. The authors developed a CNN model using the EfficientNet B7 model’s weights to extract the image features. Multi-class classification of BC images was performed using the LightGBM model. The Optuna algorithm was used to fine-tune LightGBM for image classification. In addition, a quantization-aware training (QAT) strategy was followed to implement the proposed model in a resource-constrained environment. The authors generalized the proposed model using the CBIS-DDSM and CMMD datasets. Additionally, they combined these two datasets to ensure the model’s generalizability to diverse images. The experimental findings revealed that the suggested BC detection model produced a promising result. The proposed BC detection model obtained an accuracy of 99.4%, 99.9%, and 97.0%, and Kappa (K) values of 96.9%, 96.9%, and 94.1% in the CBIS-DDSM, CMMD, and combined datasets. The recommended model streamlined the BC detection process in order to achieve an exceptional outcome. It can be deployed in a real-life environment to support physicians in making effective decisions. Graph convolutional networks can be used to improve the performance of the proposed model.

Digital forensic investigations are becoming increasingly crucial in criminal investigations and civil litigations, especially in cases of corporate espionage and intellectual property theft as more communication occurs online via e-mail and social media. Deceptive opinion spam analysis is an emerging field of research that aims to detect and identify fraudulent reviews, comments, and other forms of deceptive online content. In this paper, we explore how the findings from this field may be relevant to forensic investigation, particularly the features that capture stylistic patterns and sentiments, which are psychologically relevant aspects of truthful and deceptive language. To assess these features’ utility, we demonstrate the potential of our proposed approach using the real-world dataset from the Enron Email Corpus. Our findings suggest that deceptive opinion spam analysis may be a valuable tool for forensic investigators and legal professionals looking to identify and analyze deceptive behavior in online communication. By incorporating these techniques into their investigative and legal strategies, professionals can improve the accuracy and reliability of their findings, leading to more effective and just outcomes.

Patients in Intensive Care Units (ICU) face the threat of decompensation, a rapid decline in health associated with a high risk of death. This study focuses on creating and evaluating machine learning (ML) models to predict decompensation risk in ICU patients. It proposes a novel approach using patient vitals and clinical data within a specified timeframe to forecast decompensation risk sequences. The study implemented and assessed long short-term memory (LSTM) and hybrid convolutional neural network (CNN)-LSTM architectures, along with traditional ML algorithms as baselines. Additionally, it introduced a novel decompensation score based on the predicted risk, validated through principal component analysis (PCA) and k-means analysis for risk stratification. The results showed that, with PPV = 0.80, NPV = 0.96 and AUC-ROC = 0.90, CNN-LSTM had the best performance when predicting decompensation risk sequences. The decompensation score’s effectiveness was also confirmed (PPV = 0.83 and NPV = 0.96). SHAP plots were generated for the overall model and two risk strata, illustrating variations in feature importance and their associations with the predicted risk. Notably, this study represents the first attempt to predict a sequence of decompensation risks rather than single events, a critical advancement given the challenge of early decompensation detection. Predicting a sequence facilitates early detection of increased decompensation risk and pace, potentially leading to saving more lives.

The comprehensive use of high-resolution remote sensing (HRS) images and deep learning (DL) methods can be used to further accurate urban green space (UGS) mapping. However, in the process of UGS segmentation, most of the current DL methods focus on the improvement of the model structure and ignore the spectral information of HRS images. In this paper, a multiscale attention feature aggregation network (MAFANet) incorporating feature engineering was proposed to achieve segmentation of UGS from HRS images (GaoFen-2, GF-2). By constructing a new decoder block, a bilateral feature extraction module, and a multiscale pooling attention module, MAFANet enhanced the edge feature extraction of UGS and improved segmentation accuracy. By incorporating feature engineering, including false color image and the Normalized Difference Vegetation Index (NDVI), MAFANet further distinguished UGS boundaries. The UGS labeled datasets, i.e., UGS-1 and UGS-2, were built using GF-2. Meanwhile, comparison experiments with other DL methods are conducted on UGS-1 and UGS-2 to test the robustness of the MAFANet network. We found the mean Intersection over Union (MIOU) of the MAFANet network on the UGS-1 and UGS-2 datasets was 72.15% and 74.64%, respectively; outperforming other existing DL methods. In addition, by incorporating false color image in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.64%; by incorporating vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.09%; and by incorporating false color image and the vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.73%. Our experimental results demonstrated that the proposed MAFANet incorporating feature engineering (false color image and NDVI) outperforms the state-of-the-art (SOTA) methods in UGS segmentation, and the false color image feature is better than the vegetation index (NDVI) for enhancing green space information representation. This study provided a practical solution for UGS segmentation and promoted UGS mapping.

Although the accuracy of short-term prediction of building-integrated photovoltaics is essential to making an optimal decision on the management of the generated electricity, the weather forecasting service in many countries provides insufficient features for improving the prediction accuracy of the photovoltaics power output. This study suggests a machine learning model incorporated with feature engineering to improve the prediction performance of day-ahead hourly power outputs using a simple weather forecast service. A new synthetic feature, the modified sky condition, is derived to infer onsite sky condition and solar irradiation, which is not supported by the typical weather forecasting services. It evaluated the prediction performance with different training and hyper-parameter conditions for 60 days. By using the derived modified sky condition, the model outperformed other predictor configurations in most daily sky conditions; particularly, the accuracy improved by more than 50% on overcast days compared to when it used the original weather forecasting service data. The result demonstrates the feasibility and ability of the model to enable more efficient energy management of building-integrated photovoltaic power output in buildings without an onsite weather station, thus contributing toward the optimized dispatch of the integrated electricity energy storage system and other distributed energy resources.

Due to the transition toward the Internet of Everything (IOE), the prediction of energy consumed by household appliances has become a progressively more difficult topic to model. Even with advancements in data analytics and machine learning, several challenges remain to be addressed. Therefore, providing highly accurate and optimized models has become the primary research goal of many studies. This paper analyzes appliance energy consumption through a variety of machine learning-based strategies. Utilizing data recorded from a single-family home, input variables comprised internal temperatures and humidities, lighting consumption, and outdoor conditions including wind speed, visibility, and pressure. Various models were trained and evaluated: (a) multiple linear regression, (b) support vector regression, (c) random forest, (d) gradient boosting, (e) xgboost, and (f) the extra trees regressor. Both feature engineering and hyperparameter tuning methodologies were applied to not only extend existing features but also create new ones that provided improved model performance across all metrics: root mean square error (RMSE), coefficient of determination (R2), mean absolute error (MAE), and mean absolute percentage error (MAPE). The best model (extra trees) was able to explain 99% of the variance in the training set and 66% in the testing set when using all the predictors. The results were compared with those obtained using a similar methodology. The objective of performing these actions was to show a unique perspective in simulating building performance through data-driven models, identifying how to maximize predictive performance through the use of machine learning-based strategies, as well as understanding the potential benefits of utilizing different models.

Accurate remaining useful life (RUL) prediction is one of the most challenging problems in the prognostics of turbofan engines. Recently, RUL prediction methods for turbofan engines mainly involve data-driven models. Preprocessing the sensor data is essential for the performance of the prognostic models. Most studies on turbofan engines use piecewise linear (PwL) labeling, which starts with a constant initial RUL value in normal/healthy operating time. In this study, we designed a prognostic procedure that includes difference-based feature construction, change-point-detection-based PwL labeling, and a 1D-CNN-LSTM (one-dimensional–convolutional neural network–long short-term memory) hybrid neural network model for RUL prediction. The procedure was evaluated on the subset FD001 of the C-MAPSS dataset. The proposed procedure was compared with machine learning and deep learning models with and without the new difference feature. Also, the results were compared with the studies that used similar labeling approaches. Our analysis of the numerical results underscores the clear superiority of the proposed 1D-CNN-LSTM model with the difference feature in RUL prediction, with a score of 437.2 and an RMSE value of 16.1. This result illustrates the superior predictive capability of the 1D-CNN-LSTM model, which outperformed traditional machine learning methods and one of the earliest deep learning methods. These findings emphasize the superior predictive capability of the 1D-CNN-LSTM model and underline the potential of the feature engineering process for more accurate and robust RUL prediction in the context of turbofan engine prognostics.

In this study, 220 AA7075-T6 B-pillars were fabricated using a thoroughly instrumented hot-stamping press under varied conditions. Feature engineering work identified nineteen attributes of the hot-stamping process as impacting four characteristics of the obtained B-pillars: electrical conductivity (%IACS), mechanical strength, distortion, and the presence of visible defects. Pearson correlation suggests an important correlation between the heating phase and the mechanical strength, as well as the %IACS values. As for distortion, the influence of the stamping phase is more obvious. Finally, no correlation was obtained between the hot stamping attributes and the presence of visible cracks. This is mainly due to the pre-assembly phase, i.e., Friction Stir Welding, which will be considered in future works.

Utilized extensively in a myriad of industries, solid-solution copper alloys are prized for their superior electrical conductivity and mechanical properties. However, optimizing these often mutually exclusive properties poses a challenge, especially considering the complex interplay of alloy composition and processing techniques. To address this, we introduce a novel computational framework that employs advanced feature engineering within machine learning algorithms to accurately predict the alloy’s microhardness and electrical conductivity. Our methodology demonstrates a substantial enhancement over traditional data-driven models, achieving remarkable increases in R2 scores—from 0.939 to 0.971 for microhardness predictions and from −1.05 to 0.934 for electrical conductivity. Through machine learning, we also spotlight key determinants that significantly influence overall performance of solid-solution copper alloys, providing actionable insights for future alloy design and material optimization.

Wind factors significantly influence air travel, and extreme conditions can cause operational disruptions. Machine learning approaches are emerging as a valuable tool for predicting wind patterns. This research, using Madeira International Airport as a case study, delves into the effectiveness of feature creation and selection for wind nowcasting, focusing on predicting wind speed, direction, and gusts. Data from four sensors provided 56 features to forecast wind conditions over intervals of 2, 10, and 20 min. Five feature selection techniques were analyzed, namely mRMR, PCA, RFECV, GA, and XGBoost. The results indicate that combining new wind features with optimized feature selection can boost prediction accuracy and computational efficiency. A strong spatial correlation was observed among sensors at different locations, suggesting that the spatial-temporal context enhances predictions. The best accuracy for wind speed forecasts yielded a mean absolute percentage error of 0.35%, 0.53%, and 0.63% for the three time intervals, respectively. Wind gust errors were 0.24%, 0.33%, and 0.38%, respectively, while wind direction predictions remained challenging with errors above 100% for all intervals.

The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning methods are becoming increasingly popular, aiming for accurate predictions of bearing faults without requiring bearing-specific domain knowledge. Opposing this trend in popularity, the present paper takes a more traditional approach, incorporating domain knowledge by evaluating a variety of feature engineering methods in combination with a random forest classifier. For a comprehensive feature engineering study, a total of 42 mathematical feature formulas are combined with the preprocessing methods of envelope analysis, empirical mode decomposition, wavelet transforms, and frequency band separations. While each single processing method and feature formula is known from the literature, the presented paper contributes to the body of knowledge by investigating novel series connections of processing methods and feature formulas. Using the CWRU bearing fault data for performance evaluation, feature calculation based on the processing method of frequency band separation leads to particularly high prediction accuracies, while at the same time being very efficient in terms of low computational effort. Additionally, in comparison with deep learning approaches, the proposed feature engineering method provides excellent accuracies and enables explainability.

Building type prediction is a critical task for urban planning and population estimation. The growing availability of multi-source data presents rich semantic information for building type prediction. However, existing residential building prediction methods have problems with feature extraction and fusion from multi-type data and multi-level interactions between features. To overcome these limitations, we propose a deep learning approach that takes both the internal and external characteristics of buildings into consideration for residential building prediction. The internal features are the shape characteristics of buildings, and the external features include location features and semantic features. The location features include the proximity of the buildings to the nearest road and areas of interest (AOI), and the semantic features are mainly threefold: spatial co-location patterns of points of interest (POI), nighttime light, and land use information of the buildings. A deep learning model, DeepFM, with multi-type features embedded, was deployed to train and predict building types. Comparative and ablation experiments using OpenStreetMap and the nighttime light dataset were carried out. The results showed that our model had significantly higher classification performance compared with other models, and the F1 score of our model was 0.9444. It testified that the external semantic features of the building significantly enhanced the predicted performance. Moreover, our model showed good performance in the transfer learning between different regions. This research not only significantly enhances the accuracy of residential building identification but also offers valuable insights and ideas for related studies.

Natural language understanding technologies play an essential role in automatically solving math word problems. In the process of machine understanding Chinese math word problems, comma disambiguation, which is associated with a class imbalance binary learning problem, is addressed as a valuable instrument to transform the problem statement of math word problems into structured representation. Aiming to resolve this problem, we employed the synthetic minority oversampling technique (SMOTE) and random forests to comma classification after their hyperparameters were jointly optimized. We propose a strict measure to evaluate the performance of deployed comma classification models on comma disambiguation in math word problems. To verify the effectiveness of random forest classifiers with SMOTE on comma disambiguation, we conducted two-stage experiments on two datasets with a collection of evaluation measures. Experimental results showed that random forest classifiers were significantly superior to baseline methods in Chinese comma disambiguation. The SMOTE algorithm with optimized hyperparameter settings based on the categorical distribution of different datasets is preferable, instead of with its default values. For practitioners, we suggest that hyperparameters of a classification models be optimized again after parameter settings of SMOTE have been changed.

Electroencephalogram (EEG) signals contain information about the brain's state as they reflect the brain's functioning. However, the manual interpretation of EEG signals is tedious and time-consuming. Therefore, automatic EEG translation models need to be proposed using machine learning methods. In this study, we proposed an innovative method to achieve high classification performance with explainable results. We introduce channel-based transformation, a channel pattern (ChannelPat), the t algorithm, and Lobish (a symbolic language). By using channel-based transformation, EEG signals were encoded using the index of the channels. The proposed ChannelPat feature extractor encoded the transition between two channels and served as a histogram-based feature extractor. An iterative neighborhood component analysis (INCA) feature selector was employed to select the most informative features, and the selected features were fed into a new ensemble k-nearest neighbor (tkNN) classifier. To evaluate the classification capability of the proposed channel-based EEG language detection model, a new EEG language dataset comprising Arabic and Turkish was collected. Additionally, Lobish was introduced to obtain explainable outcomes from the proposed EEG language detection model. The proposed channel-based feature engineering model was applied to the collected EEG language dataset, achieving a classification accuracy of 98.59%. Lobish extracted meaningful information from the cortex of the brain for language detection.

Good feature engineering is a prerequisite for accurate classification, especially in challenging scenarios such as detecting the breathing of living persons trapped under building rubble using bioradar. Unlike monitoring patients’ breathing through the air, the measuring conditions of a rescue bioradar are very complex. The ultimate goal of search and rescue is to determine the presence of a living person, which requires extracting representative features that can distinguish measurements with the presence of a person and without. To address this challenge, we conducted a bioradar test scenario under laboratory conditions and decomposed the radar signal into different range intervals to derive multiple virtual scenes from the real one. We then extracted physical and statistical quantitative features that represent a measurement, aiming to find those features that are robust to the complexity of rescue-radar measuring conditions, including different rubble sites, breathing rates, signal strengths, and short-duration disturbances. To this end, we utilized two methods, Analysis of Variance (ANOVA), and Minimum Redundancy Maximum Relevance (MRMR), to analyze the significance of the extracted features. We then trained the classification model using a linear kernel support vector machine (SVM). As the main result of this work, we identified an optimal feature set of four features based on the feature ranking and the improvement in the classification accuracy of the SVM model. These four features are related to four different physical quantities and independent from different rubble sites.

Condition monitoring of technical systems has increasing importance for the reduction of downtimes based on unplanned breakdowns. Rolling bearings are a central component of machines because they often support energy-transmitting elements like shafts and spur gears. Bearing damages lead to a high number of machine breakdowns; thus, observing these has the potential to reduce unplanned downtimes. The observation of bearings is challenging since their behavior in operation cannot be investigated directly. A common solution for this task is the measurement of vibration or component temperature, which is able to show an already occurred bearing damage. Measuring the electrical bearing impedance in situ has the ability to gather information about bearing revolution speed and bearing loads. Additionally, measuring the impedance allows for the detection and localization of damages in the bearing, as early research has shown. In this paper, the impedance signal of five fatigue tests is investigated using individual feature selection. Additionally, the feature behavior is analyzed and explained. It is shown that the three different bearing operational time phases can be distinguished via the analysis of impedance signal features. Furthermore, some of the features show a significant change in behavior prior to the occurrence of initial damages before the vibration signals of the test rig vary from a normal state.

Machining is a crucial constituent of the manufacturing industry, which has begun to transition from precision machinery to smart machinery. Particularly, the introduction of artificial intelligence into computer numerically controlled (CNC) machine tools will enable machine tools to self-diagnose during operation, improving the quality of finished products. In this study, feature engineering and principal component analysis were combined with the online and real-time Gaussian mixture model (GMM) based on the Kullback–Leibler divergence’s measure to achieve the real-time monitoring of changes in manufacturing parameters. Based on the attached accelerometer device’s vibration signals and current sensing of the spindle, the developed GMM unsupervised learning was successfully used to diagnose the spindle speed changes of a CNC machine tool during milling. The F1-scores with improved experimental results for X, Y, and Z axes were 0.95, 0.88, and 0.93, respectively. The established FE-PCA-GMM/KLD method can be applied to issue warnings when it predicts a change in the manufacturing process parameter. A smart sensing device for diagnosing the machining status can be fabricated for implementation. The effectiveness of the developed method for determining the manufacturing parameter changes was successfully verified by experiments.

Distributed denial-of-service (DDoS) attacks pose a significant cybersecurity threat to software-defined networks (SDNs). This paper proposes a feature-engineering- and machine-learning-based approach to detect DDoS attacks in SDNs. First, the CSE-CIC-IDS2018 dataset was cleaned and normalized, and the optimal feature subset was found using an improved binary grey wolf optimization algorithm. Next, the optimal feature subset was trained and tested in Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (k-NN), Decision Tree, and XGBoost machine learning algorithms, from which the best classifier was selected for DDoS attack detection and deployed in the SDN controller. The results show that RF performs best when compared across several performance metrics (e.g., accuracy, precision, recall, F1 and AUC values). We also explore the comparison between different models and algorithms. The results show that our proposed method performed the best and can effectively detect and identify DDoS attacks in SDNs, providing a new idea and solution for the security of SDNs.

Network traffic anomaly detection is a key step in identifying and preventing network security threats. This study aims to construct a new deep-learning-based traffic anomaly detection model through in-depth research on new feature-engineering methods, significantly improving the efficiency and accuracy of network traffic anomaly detection. The specific research work mainly includes the following two aspects: 1. In order to construct a more comprehensive dataset, this article first starts from the raw data of the classic traffic anomaly detection dataset UNSW-NB15 and combines the feature extraction standards and feature calculation methods of other classic detection datasets to re-extract and design a feature description set for the original traffic data in order to accurately and completely describe the network traffic status. We reconstructed the dataset DNTAD using the feature-processing method designed in this article and conducted evaluation experiments on it. Experiments have shown that by verifying classic machine learning algorithms, such as XGBoost, this method not only does not reduce the training performance of the algorithm but also improves its operational efficiency. 2. This article proposes a detection algorithm model based on LSTM and the recurrent neural network self-attention mechanism for important time-series information contained in the abnormal traffic datasets. With this model, through the memory mechanism of the LSTM, the time dependence of traffic features can be learned. On the basis of LSTM, a self-attention mechanism is introduced, which can weight the features at different positions in the sequence, enabling the model to better learn the direct relationship between traffic features. A series of ablation experiments were also used to demonstrate the effectiveness of each component of the model. The experimental results show that, compared to other comparative models, the model proposed in this article achieves better experimental results on the constructed dataset.