Machine Learning Classification Algorithms Research Articles

Mapping land cover in the low Arctic using multiple sources of earth observation data

Land cover maps in high latitude regions are important for permafrost modeling and mapping and other climate change related studies. National and global land cover products cannot meet the requirements for regional permafrost mapping due to their broad land cover types. This study produced a land cover map in a low Arctic region using multi-source earth observation data, including different modes of RADARSAT-2 (RS2), Sentinel 2 (S2), and the high resolution ArcticDEM. We assessed the performances of two machine learning classification algorithms (Random Forest (RF) and Support Vector Machine (SVM)) with different combinations of input data, including evaluating the effects of incidence angle from different RS2 modes on classification results. This study concludes that the combination of two imaging modes of RS2, S2 composites and the high resolution ArcticDEM achieves a more accurate land cover map (the overall accuracy is 93.6%) than other combinations with the overall accuracies ranging from 38% to 87%; the performance of RF is better than that of SVM, the overall accuracy difference ranges from 21% to 1%; and the shallow SAR incidence angles outperform steep ones in classification results of different combinations for both classifiers.

Development of a Machine Learning Tool to Predict Deep Inspiration Breath Hold Requirement for Locoregional Right-Sided Breast Radiation Therapy Patients.

&#xD;This study presents machine learning (ML) models that predict if deep inspiration breath hold (DIBH) is needed based on lung dose in right-sided breast cancer patients during the initial computed tomography (CT) appointment. &#xD;Materials and methods. &#xD;Anatomic distances were extracted from a single-institution dataset of free breathing (FB) CT scans from locoregional right-sided breast cancer patients. Models were developed using combinations of anatomic distances and ML classification algorithms (gradient boosting, k-nearest neighbors, logistic regression, random forest, and support vector machine) and optimized over 100 iterations using stratified 5-fold cross-validation. Models were grouped by the number of anatomic distances used during development; those with the highest validation accuracy were selected as final models. Final models were compared based on their predictive ability, measurement collection efficiency, and robustness to simulated user error during measurement collection. &#xD;Results. &#xD;This retrospective study included 238 patients treated between 2016 and 2021. Model development ended once eight anatomic distances were included, and the validation accuracy plateaued. The best performing model used logistic regression with four anatomic distances achieving 80.5% average testing accuracy, with minimal false negatives and positives (< 27%). The anatomic distances required for prediction were collected within 3 minutes and were robust to simulated user error during measurement collection, changing accuracy by < 5%. &#xD;Conclusion. &#xD;Our logistic regression model using four anatomic distances provided the best balance between efficiency, robustness, and ability to predict if DIBH was needed for locoregional right-sided breast cancer patients.&#xD.

基于堆叠学习的番茄器官尺度的生物量预测模型的构建与验证

In this study, a stacked machine learning algorithm was constructed with tomato organ biomass as the research object, taking the geometric morphology data of tomato organs as the variables, utilizing eight classical machine learning algorithms as the base-model, and applying the linear regression algorithm as the stacked meta-model. This algorithm was then utilized to establish a prediction model for tomato biomass at the organ scale, and the biomass models of tomato plant leaves and fruits at the organ scale were constructed. The model has R2=0.86, MAE=0.49, and RMSE=0.81 in predicting leaves, and R2=0.94, MAE=0.33, and RMSE=0.57 in predicting fruits. The model has practical applications in predicting tomato yield and supply, providing market information, and supporting agricultural investment decisions. It also helps to optimize agricultural production and management, guide industrial development and planning, and improve the efficiency and competitiveness of the agricultural sector.

MODELING OF HUMAN BEHAVIOR FOR SMARTPHONE WITH USING MACHINE LEARNING ALGORITHM

The article focuses on exploring human behavior recognition as an alternative means of identifying and authenticating smartphone users. The process involves obtaining raw data, extracting features, and making classifications. In this study, a single accelerometer-equipped smartphone is utilized to sense users' walking patterns for experimental data. Unlike traditional machine learning algorithms, a deep learning approach is employed. The paper introduces a novel Convolutional Neural Network (CNN) model for user identification based on activity patterns. The experiment uses a publicly available walking activity dataset for user identification. The CNN model achieves an impressive 99.88% accuracy in recognizing users from their walking patterns. Additionally, the article conducts a comparative analysis with classical machine learning algorithms such as Ada-Boost, Decision Tree, GaussianNB, Linear Discriminant, Logistic Regression, Quadratic Discriminant, and Random Forest. While Random Forest reaches a commendable accuracy of 95.78%, the CNN model surpasses it in terms of both recognition time and accuracy.

Development of machine learning algorithms in student performance classification based on online learning activities

Development of machine learning algorithms in student performance classification based on online learning activities

Evaluative comparison of machine learning algorithms for stutter detection and classification

Evaluative comparison of machine learning algorithms for stutter detection and classification

A novel automated labelling algorithm for deep learning-based built-up areas extraction using nighttime lighting data

The use of remote sensing imagery and cutting-edge deep learning techniques can produce impressive results when it comes to built-up areas extraction (BUAE). However, reducing the manual labelling set production process while ensuring high accuracy is currently the main research topic. This study pioneers the exploitation of nighttime lighting data (NLD) for automatically generating deep learning label sets, assessing the feasibility, and identifying limitations of using varied intensity ranges of lighting data directly for this purpose. We provide a novel method for generating fine-grained labels through an optimisation technique that eliminates the necessity for human involvement. This approach employs deep learning segmentation algorithms and has been tested in eight cities across seven countries. The results indicate that segmentation performs well in most cities, with the combination of iso clustering and NLD allowing for more precise extraction of urban building districts. The overall accuracy exceeds 90% in most cities. The results based on manual and historical data (around 0.7) as labels are significantly lower than those based on NLD. At the same time, the segmentation effect of deep learning has a more significant advantage over traditional machine learning classification algorithms (around 0.8). DeeplabV3 and U-Net exhibit different strengths in segmentation and extraction: DeeplabV3 has a stronger ability to eliminate errors, while U-Net retains the capability to handle less labelled information, making them mutually advantageous depending on the specific requirements of the task. It proposes a Strategy to automatically extract built-up areas with minimal human involvement.

Finger Vein Detection using Deep Learning

The deep learning is a part of machine learning that uses neural networks with many layers (deep architecture) to fit the intricate patterns. Deep learning has shown remarkable performance in image classification mainly due to its ability in learning and extracting features from the raw inputs. In this research study, some techniques of image preprocessing were described and utilized to machine learning algorithm for image classification. The purpose was to promote the specific preprocessing techniques on the impact, which are commonly used in classification model of images, relating to time and precision improvement. The techniques that are applied in this documentation include; image enhancement, binarization, transformation, edge detection and scaling. The present research study therefore comes handy in trying to establish the significance of enhancing statistic and the impact on the performance of the model. The following preprocessing methods have been used because the image datasets need preprocessing to be input for the machine learning models for better image classification

Implementation and Performance Evaluation of Quantum Machine Learning Algorithms for Binary Classification

Implementation and Performance Evaluation of Quantum Machine Learning Algorithms for Binary Classification

A mindset toward greening the blue economy: Analyzing social environmental awareness of aquatic ecosystem protection

To help address global water pollution challenges, this article explores the interconnections between public awareness, education, social engagement, and knowledge transfer in promoting sustainable water resource management. The socialization, externalization, combination, and internalization (SECI) model and the transtheoretical model of change (TMC) are used to examine how education and awareness can influence citizens' behavior. The article also assesses the contribution of the entrepreneurial sector to aquatic biodiversity conservation and pollution reduction. The analysis is based on Kruskal-Wallis and Mann-Whitney U tests, as well as several machine learning regression and classification algorithms. This analysis sheds light on the complex relationships between awareness, education, engagement, and knowledge transfer. A key aspect of this study is the analysis of demographic data. This analysis reveals varying perceptions and levels of engagement with aquatic ecosystem protection across different demographic groups. The results indicate variations by age, gender, occupation, and education level, highlighting the importance of tailored educational and social engagement strategies. Additionally, the results underscore the pivotal role of entrepreneurs in developing and implementing innovative, sustainable solutions. This research reveals the need for integrated strategies that combine educational and entrepreneurial efforts to ensure more efficient and responsible management and thus protect aquatic ecosystems while reducing pollution.

The Click-Based MNL Model: A Framework for Modeling Click Data in Assortment Optimization

We introduce the click-based MNL choice model, a framework for capturing customer purchasing decisions in e-commerce settings. Specifically, we augment the classical Multinomial Logit choice model by assuming that customers only consider the items they have clicked on before they proceed to compare their random utilities. In this context, we study the resulting assortment optimization problem, where the objective is to select a subset of products, made available for purchase, to maximize the expected revenue. Our main algorithmic contribution comes in the form of a polynomial-time approximation scheme (PTAS) for this problem, showing that the optimal expected revenue can be efficiently approached within any degree of accuracy. To establish this result, we develop several technical ideas, including enumeration schemes and stochastic inequalities, which may be of broader interest. Using data from Alibaba’s online marketplace, we fit click-based MNL and latent class MNL models to historical sales and click data in a setting where the online platform recommends a personalized six-product display to each user. We propose an estimation methodology for the click-based MNL model that leverages clickstream data and machine learning classification algorithms. Our numerical results suggest that clickstream data are valuable for predicting choices and that the click-based MNL model can outperform standard logit-based models in certain settings. This paper was accepted by Chung Piaw Teo, optimization. Funding: D. Segev was supported by the Israel Science Foundation [Grant 1407/20]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2021.00281 .

Studying the Impact of Changing Consumer Behavior During Crisis Periods Through Store Classification

Since customer behavior changes unpredictably during crisis periods such as pandemics, many sectors have been affected differently. The retail sector in particular has been one of the most affected sectors. Retail companies that could not determine the right strategies against customer behavior change were in a difficult situation, and some even had to close down. The inability of consumers to do physical shopping for reasons such as socializing, experiencing products and interacting during the pandemic process required an understanding of changing consumer needs. In this study, to determine the changes in customer purchasing behaviors during the pandemic period, using the sales data of a company operating in the women’s clothing sector and whose sales loss approached 50% during the pandemic period, separate stores were divided into clusters using machine learning methods for the pre-pandemic and pandemic period. The clusters formed were examined and the stores in different clusters were determined depending on customer purchasing behavior. The aim of the study is to ensure that the company segments its stores correctly to gain competitive advantage. Firms will be able to determine the right strategies against changing consumer behavior through a correct store segmentation. First, stores that do not belong to any classification group are clustered using unsupervised machine learning methods. No significant change was observed in the clusters formed before and during the pandemic. This indicated that the pandemic had a similar effect on all stores. Then, pre-pandemic, pandemic period and both periods data were analyzed using 7 different machine learning classification algorithms. The results obtained were compared. For all three analyses, the random forest algorithm gave the highest accuracy rate. The random forest algorithm with the highest accuracy was hybridized with 3 different classification algorithms. The hybrid model consisting of random forest and support vector machine gave the highest accuracy rate (90%) for the period including all data for store classification. Thanks to the hybrid model created with random forest and support vector machines, companies can be advantageous against other companies in the competitive environment by creating separate strategies for each store class.

AI powered detection and assessment of onychomycosis: A spotlight on yellow and deep learning

AI powered detection and assessment of onychomycosis: A spotlight on yellow and deep learning

A comparative study of machine learning algorithms for sediment classification in debris flow fans using UAV imagery: a case study in the Ohya landslide scar, Japan

A comparative study of machine learning algorithms for sediment classification in debris flow fans using UAV imagery: a case study in the Ohya landslide scar, Japan

ANALYSIS STUDENT EMOTIONS AND MENTAL HEALTH ON CUMULATIVE GPA USING MACHINE LEARNING AND SMOTE

This research investigates the impact of emotions and mental health on students' cumulative grade point average (CGPA) using machine learning classification algorithms while addressing data imbalances with the Synthetic Minority Oversampling Technique (SMOTE). Emotional well-being and mental health are acknowledged as vital determinants of academic achievement. Data imbalance, particularly in mental health metrics such as anxiety and depression, frequently compromises forecast accuracy. This study improves the accuracy of CGPA prediction based on emotional and mental health factors by utilizing SMOTE in machine learning models such as logistic regression and random forest. A dataset including 226 university students, including academic records and self-reported mental health evaluations, was evaluated. The random forest model attained an accuracy of 87.63%, exceeding the logistic regression model's accuracy of 86.56%. These findings emphasize the significant role of emotions and mental health in academic outcomes and validate SMOTE’s efficacy in addressing class imbalance. This work offers a fresh technique in educational data mining by revealing the possibility for improved academic achievement forecasts based on psychological characteristics, helping to the development of targeted therapies for students experiencing emotional issues. Implications for educational policy emphasize the significance of mental health support systems in promoting academic achievement. Subsequent research should investigate supplementary psychological variables and comprehensible models to improve predictive accuracy and facilitate evidence-based policymaking.

Wear Resistance Design of Laser Cladding Ni-Based Self-Fluxing Alloy Coating Using Machine Learning.

To improve the collaborative design of laser cladding Ni-based self-fluxing alloy (SFA) wear-resistant coatings, machine learning methods were applied. A comprehensive database was constructed from the literature, linking alloy composition, processing parameters, testing conditions, and the wear properties of Ni-based SFA coatings. Feature correlation analysis using Pearson's correlation coefficient and feature importance assessment via the random forest (RF) model highlighted the significant impact of C and B elements. The predictive performance of five classical machine learning algorithms was evaluated using metrics such as the squared correlation coefficient (R²) and mean absolute error (MAE). The RF model, which exhibited the best overall performance, was further combined with a genetic algorithm (GA) to optimize both composition and processing parameters collaboratively. This integrated RF-GA optimization system significantly enhanced efficiency and successfully designed multiple composition and process plans. The optimized alloy demonstrated superior wear resistance with an average friction coefficient of only 0.34, attributed to an enhanced solid solution strengthening effect (110 MPa) and increased hard phase content (52%), such as Ni₃Si, CrB, and NbC. These results provide valuable methodological insights and theoretical support for the preparation of laser cladding coatings and enable efficient process optimization for other laser processing applications.

Roman urdu hate speech detection using hybrid machine learning models and hyperparameter optimization.

With the rapid increase of users over social media, cyberbullying, and hate speech problems have arisen over the past years. Automatic hate speech detection (HSD) from text is an emerging research problem in natural language processing (NLP). Researchers developed various approaches to solve the automatic hate speech detection problem using different corpora in various languages, however, research on the Urdu language is rather scarce. This study aims to address the HSD task on Twitter using Roman Urdu text. The contribution of this research is the development of a hybrid model for Roman Urdu HSD, which has not been previously explored. The novel hybrid model integrates deep learning (DL) and transformer models for automatic feature extraction, combined with machine learning algorithms (MLAs) for classification. To further enhance model performance, we employ several hyperparameter optimization (HPO) techniques, including Grid Search (GS), Randomized Search (RS), and Bayesian Optimization with Gaussian Processes (BOGP). Evaluation is carried out on two publicly available benchmarks Roman Urdu corpora comprising HS-RU-20 corpus and RUHSOLD hate speech corpus. Results demonstrate that the Multilingual BERT (MBERT) feature learner, paired with a Support Vector Machine (SVM) classifier and optimized using RS, achieves state-of-the-art performance. On the HS-RU-20 corpus, this model attained an accuracy of 0.93 and an F1 score of 0.95 for the Neutral-Hostile classification task, and an accuracy of 0.89 with an F1 score of 0.88 for the Hate Speech-Offensive task. On the RUHSOLD corpus, the same model achieved an accuracy of 0.95 and an F1 score of 0.94 for the Coarse-grained task, alongside an accuracy of 0.87 and an F1 score of 0.84 for the Fine-grained task. These results demonstrate the effectiveness of our hybrid approach for Roman Urdu hate speech detection.

A Mixed Neuro Graph Approach with Gradient Boosting to Hybrid Job-Shop Scheduling to Minimize a Regular Function of Job Completion Times and Numbers of Used Machines

The paper considers a multi-stage processing system including sets of identical (parallel) machines and a set of dedicated machines processing different operations of the given jobs in any sectors of economy. Based on the weighted Mixed Neuro graph model, the paper proposes adaptive algorithms for solving this problem via appropriate Mixed Neuro graph transformations. The main novelty is (1) low demands on the source data-unlike classical machine learning algorithms, the approach can offer stable interpretable results even with a short dataset size; (2) the number of new matrix multiplication operations that make up the main load when training models increases linearly with the number of new data from 0 to 999 time periods; (3) the results of the model are repeatable due to the stability of the coefficients of the model. These algorithms are able to solve (exactly or heuristically) the tested instances with N jobs and W types of parallel identical machines within on the personal computer. The gradient boosting result is in interval 5.9677410-3.4982093.

Comparison of the performance of classical and quantum machine‐learning methods on the detection of sugar beet Cercospora leaf disease

AbstractImage processing and machine‐learning (ML) techniques are essential for the detection of diseases and pests in plants. This study explored the application of quantum ML (QML) algorithms for the early detection of Cercospora beticola leaf disease in sugar beet, which causes significant impact on global sugar production. Using a dataset of 1065 images (739 diseased and 326 healthy), we extracted 70 ML statistical features, including 10 from the grey‐level co‐occurrence matrix (GLCM) and 60 colour‐related features. Performance evaluations of classical ML algorithms, such as random forest (RF; 91.95% accuracy) and extreme gradient boosting (91.95% accuracy), demonstrated strong results compared to quantum approaches. Notably, the quantum support vector classifier (QSVC) achieved an accuracy of 85% with perfect recall of 1.00, while the variational quantum classifier (VQC) recorded an accuracy of 88.73%. Dimensionality reduction via principal component analysis reduced features from 70 to 5, enabling effective classification with competitive results: ML (RF) 91.41%, VQC with limited‐memory Broyden–Fletcher–Goldfarb–Shanno with box constraints (L_BFGS_B) 88.73% and QSVC 85%. These findings highlight the potential of QML algorithms in improving agricultural disease identification and aiding in the advancement of more efficient, sustainable farming techniques.

A Novel Information Complexity Approach to Score Receiver Operating Characteristic (ROC) Curve Modeling

Performance metrics are measures of success or performance that can be used to evaluate how well a model makes accurate predictions or classifications. However, there is no single measure since each performance metric emphasizes a different classification aspect. Model selection procedures based on information criteria offer a quantitative measure that balances model complexity with goodness of fit, providing a better alternative to classical approaches. In this paper, we introduce and develop a novel Information Complexity–Receiver Operating Characteristic, abbreviated as ICOMP-ROC, criterion approach to fit and study the performance of ROC curve models. We construct and derive the Universal ROC (UROC) for a combination of sixteen Bi-distributional ROC models to choose the best Bi-distributional ROC by minimizing the ICOMP-ROC criterion. We conduct large-scale Monte Carlo simulations using the sixteen Bi-distributional ROC models with the Normal–Normal and Weibull–Gamma pairs as the pseudo-true ROC models. We report the frequency of hits of the ICOMP-ROC criterion, showing its remarkable recovery rate. In addition to Bi-distributional fitting, we consider a high-dimensional real Magnetic Resonance Imaging (MRI) of the Brain dataset and Wisconsin Breast Cancer (WBC) dataset to study the performance of the common performance metrics and the ICOMP-ROC criterion using several machine learning (ML) classification algorithms. We use the genetic algorithm (GA) to reduce the dimensions of these two datasets to choose the best subset of the features to study and compare the performance of the newly proposed ICOMP-ROC criterion along with the traditional performance metrics. The choice of a suitable metric is not just contingent upon the ML model used, but it also depends upon the complexity and high dimensionality of the input datasets, since the traditional performance metrics give different results and have inherent limitations. Our numerical results show the consistency and reliability of the ICOMP-ROC criterion over the traditional performance metrics as a clever model selection criterion to choose the best fitting Bi-distributional ROC model and the best classification algorithm among the ones considered. This shows the utility and the versatility of our newly proposed approach in ROC curve modeling that integrates and robustifies currently used procedures.