Machine Learning Classification Algorithms Research Articles

Abstract 4137423: Can Machine Learning Help Prioritise Who to Screen for Elevated Lipoprotein(a) (Lp[a]) in the General Population vs a Screen all Approach? An Analysis from UK Biobank

Background: Elevated lipoprotein(a) [Lp(a)] is an inherited, currently non-modifiable risk marker that increases lifetime ASCVD risk. Guidance vary on Lp(a) levels at which risk increases; hence prevalence of “elevated” Lp(a) depends on putative thresholds e.g. >1.3 billion people globally have Lp(a)≥125 nmol/L. Lp(a) levels are >90% genetically determined and stable throughout life; hence measurement once in adulthood is recommended. Awareness of Lp(a) levels may change patient management with more intensive control of traditional risk factors. However, testing all adults is costly and the test is not universally available. Research Question: Can Machine Learning (ML) models reduce the number needed to screen (NNS) compared to population universal screening for identifying individuals with elevated Lp(a)? Aims&Objectives: To derive a model from ML to help prioritise individuals likely to have high levels for Lp(a) testing and compare its yield to universal screening at different Lp(a) cut-points. This approach could enable automatic screening of large databases like EHRs for Lp(a) testing. Method: We conducted a cross-sectional predictive analysis using UK Biobank, including individuals ≥40 years old with Lp(a) measurements, split into feature importance, derivation, and validation datasets. Eight ML classification algorithms were used for feature importance analysis and model derivation. Models' performance was evaluated in the validation set using sensitivity and NNS in comparison with the discrimination ability of the following guidelines across different populations: The 2019’s Heart UK and European Atherosclerosis Society (EAS) and Society of Cardiology guidelines, the 2022 EAS Consensus Statement, and threshold used in clinical trial —respective cut-offs: 90,430,125,200nmol/L. Results: 438,579 patients were included. The best ML models were neural networks with different weights. Regardless of the Lp(a) threshold used, ML models resulted in higher rates of high Lp(a) cases identified per million tests with lower NNS compared to universal screening (Table 1). Using higher Lp(a) thresholds (200-430nmol/L) increased models sensitivity with far fewer tests required to identify those with high Lp(a). Conclusion: ML models could reduce the number of tests needed to identify individuals with high Lp(a), increasing efficiency and potentially helping to prioritize Lp(a) testing, with a potentially scalable cost-effective option for health systems. Work supported by Novartis

Development of a Hybrid Medical Softbot for Enhanced Decision Making using AI-tools

Health is wealth. The maintenance of health is of paramount importance. Due to increasing environmental decay, human health is threatened and therefore requires maintenance. Healthcare providers are few in number and therefore may not be able to cater for everyone. They tend to get fatigued because of the volume of work required on daily basis. This terribly affects their decision making and may lead to death as a result of wrong diagnosis or recommendations. This is the motivation behind this work; design and implementation of a hybrid medical softbot for enhanced decision making. This work was designed with the aid of machine learning algorithms for image analysis and classification and a rule based system that accepts input in the form of symptoms from user to make expert diagnosis and recommendation. Object oriented analysis and design methodology was employed in the analysis and design phase. The result is a hybrid softbot capable of analyzing and classifying X-ray images and giving expert diagnosis for patients.

Advancing user classification models: A comparative analysis of machine learning approaches to enhance faculty password policies at the University of Buraimi

In this paper, we assess the results of experiment with different machine learning algorithms for the data classification on the basis of accuracy, precision, recall and F1-Score metrics. We collected metrics like Accuracy, F1-Score, Precision, and Recall: From the Neural Network model, it produced the highest Accuracy of 0.129526 also highest F1-Score of 0.118785, showing that it has the correct balance of precision and recall ratio that can pick up important patterns from the dataset. Random Forest was not much behind with an accuracy of 0.128119 and highest precision score of 0.118553 knit a great ability for handling relations in large dataset but with slightly lower recall in comparison with Neural Network. This ranked the Decision Tree model at number three with a 0.111792, Accuracy Score while its Recall score showed it can predict true positives better than Support Vector Machine (SVM), although it predicts more of the positives than it actually is a majority of the times. SVM ranked fourth, with accuracy of 0.095465 and F1-Score of 0.067861, the figure showing difficulty in classification of associated classes. Finally, the K-Neighbors model took the 6th place, with the predetermined accuracy of 0.065531 and the unsatisfactory results with the precision and recall indicating the problems of this algorithm in classification. We found out that Neural Networks and Random Forests are the best algorithms for this classification task, while K-Neighbors is far much inferior than the other classifiers.

Hybrid deep learning model for vegetable price forecasting based on principal component analysis and attention mechanism

Abstract With the aim of enhancing the accuracy of current models for forecasting vegetable prices and improving market structures, this study focuses on the prices of bell peppers at the Nanhuanqiao Market in Suzhou. In this paper, we propose a hybrid Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) model for vegetable price forecasting based on Principal Component Analysis (PCA) and Attention Mechanism (ATT). Initially, we utilized the Pearson correlation coefficient to filter out the factors impacting prices. Then, we applied PCA to reduce dimensionality, extracting key price features. Next, we captured local sequence patterns with CNN, while handling time-series features with GRU. Finally, these outputs were integrated via ATT to generate the final prediction. Our results indicate that the hybrid CNN-GRU model, enhanced by PCA and ATT, achieved a Root Mean Square Error (RMSE) as low as 0.16. This performance is 11.11%, 11.11%, and 15.79% better than that of the PCA-CNN, PCA-GRU, and CNN-GRU-ATT models, respectively. Furthermore, in order to prove the effectiveness of our proposed model, the proposed model is compared with the state-of-the-art models and classical machine learning algorithms under the same dataset, the results indicate that our proposed hybrid deep learning model based on PCA and ATT shows the best performance. Consequently, our model offers a valuable reference for vegetable price prediction.

Genome-wide association studies of ischemic stroke based on interpretable machine learning

Despite the identification of several dozen genetic loci associated with ischemic stroke (IS), the genetic bases of this disease remain largely unexplored. In this research we present the results of genome-wide association studies (GWAS) based on classical statistical testing and machine learning algorithms (logistic regression, gradient boosting on decision trees, and tabular deep learning model TabNet). To build a consensus on the results obtained by different techniques, the Pareto-Optimal solution was proposed and applied. These methods were applied to real genotypic data of sick and healthy individuals of European ancestry obtained from the Database of Genotypes and Phenotypes (5,581 individuals, 883,749 single nucleotide polymorphisms). Finally, 131 genes were identified as candidates for association with the onset of IS. UBQLN1, TRPS1, and MUSK were previously described as associated with the course of IS in model animals. ACOT11 taking part in metabolism of fatty acids was shown for the first time to be associated with IS. The identified genes were compared with genes from the Illuminating Druggable Genome project. The product of GPR26 representing the G-coupled protein receptor can be considered as a therapeutic target for stroke prevention. The approaches presented in this research can be used to reprocess GWAS datasets from other diseases.

New Directions and Development Models for College Student Education based on Machine Learning Classification Algorithms

For the contemporary student teaching system, the information-based education management system has played a positive role in the rapid promotion of teaching. In order to get the teaching exploration data of modern information management from the data increment on the Internet, this paper updates the technology of data mining. This paper constructs a quantitative table for teacher positions and conducts ideological and political job evaluations in the database. This paper mainly focuses on the management and construction of ideological informatization based on the [Formula: see text]-means algorithm. By using the [Formula: see text]-means algorithm to analyze the daily behavior data of students, we can discover their behavior patterns and trends, providing decision support for student management. For example, by analyzing data such as students’ internet time, social activities, and library borrowing records, we can understand their interests, hobbies, and learning habits, providing a foundation for personalized education. Cluster analysis of students’ ideological and political performance using the [Formula: see text]-means algorithm can identify student groups with different ideological tendencies. This helps schools to carry out targeted ideological and political education work, and improve the pertinence and effectiveness of ideological and political education. Through quality tracking analysis of educational evaluation, it has carried out educational informatization tracking management using an information model. In the process of judging and analyzing different subjects, it utilized the hot topics of universities for a more comprehensive information intelligent tracking management.

Fuzzy Logic and Machine Learning Algorithms for Detection and Classification of Falls and Activities of Daily Living

This article analyses the movements of young and elderly people using data collected from an accelerometer and a gyroscope. This study proposes Type I fuzzy logic (FL) and several machine learning (ML) algorithms for the detection and classification of daily life movements and falls. The results obtained demonstrate that a fuzzy logic system can efficiently integrate data from an accelerometer and a gyroscope to classify falls and movements in daily life with 97.4% accuracy. When ML classifiers are used, the performance across several algorithms is also very high.

Cumulative learning based segmentation aided cell mixtures classification in digital holographic microscopy

The tumor microenvironment consists of several components like tumor cells, normal healthy cells, extracellular matrix, secreted factors, and other non-cellular components. The interaction among these components is crucial for tumor progression and metastasis. Identifying the presence of tumor cells among the normal healthy cells during the initial stages of cancer will aid in its early detection and treatment. One of the main features that differentiates a cancer cell from a normal healthy cell distinctively is its morphology. In this study, the effectiveness of machine learning algorithms is evaluated in classifying cells co-cultured in a Petri dish. To achieve this, digital holographic microscopy is used to capture the quantitative phase images of human dermal fibroblast and A375 human melanoma cancer cells co-cultured at 1:1, 1:2, and 2:1 ratios. Cell segmentation was performed using a cumulative learning approach. Subsequently, morphological and phase-based features were extracted to train the machine learning algorithms for binary classification of cells. Phase-based features in addition to the morphological features were found to provide improved performance of the classifier. The classifier demonstrated an average F1-score of 0.9 during testing.

Mapping schistosomiasis risk landscapes and implications for disease control: A case study for low endemic areas in the Middle Paranapanema river basin, São Paulo, Brazil.

Schistosomiasis, a chronic parasitic disease, remains a public health issue in tropical and subtropical regions, especially in low and moderate-income countries lacking assured access to safe water and proper sanitation. A national prevalence survey carried out by the Brazilian Ministry of Health from 2011 to 2015 found a decrease in human infection rates to 1%, with 19 out of 26 states still classified as endemic areas. There is a risk of schistosomiasis reemerging as a public health concern in low-endemic regions. This study proposes an integrated landscape-based approach to aid surveillance and control strategies for schistosomiasis in low-endemic areas. In the Middle Paranapanema river basin, specific landscapes linked to schistosomiasis were identified using a comprehensive methodology. This approach merged remote sensing, environmental, socioeconomic, epidemiological, and malacological data. A team of experts identified ten distinct landscape categories associated with varying levels of schistosomiasis transmission potential. These categories were used to train a supervised classification machine learning algorithm, resulting in a 92.5% overall accuracy and a 6.5% classification error. Evaluation revealed that 74.6% of collected snails from water collections in five key municipalities within the basin belonged to landscape types with higher potential for S. mansoni infection. Landscape connectivity metrics were also analysed. This study highlights the role of integrated landscape-based analyses in informing strategies for eliminating schistosomiasis. The methodology has produced new schistosomiasis risk maps covering the entire basin. The region's low endemicity can be partly explained by the limited connectivity among grouped landscape-units more prone to triggering schistosomiasis transmission. Nevertheless, changes in social, economic, and environmental landscapes, especially those linked to the rising pace of incomplete urbanization processes in the region, have the potential to increase risk of schistosomiasis transmission. This study will help target interventions to bring the region closer to schistosomiasis elimination.

Machine learning-assisted screening of efficient ionic liquids for catalyzing CO2 cycloaddition reaction

The catalysis of CO2 cycloaddition reactions by ionic liquids holds significant promise in addressing environmental and chemical synthesis challenges. However, the design of effective ionic liquid catalysts is hindered by the sheer diversity of cation-anion combinations, leading to challenges in targeted catalyst development. This study addresses these issues by utilizing experimental data collected from literature on reactions involving epoxy compounds as substrates, conducted without solvents or co-catalysts, to establish a database for machine learning (ML). Simple descriptors derived from the ion pair structures of ionic liquids are employed as inputs for five ML classification algorithms to predict the yield of CO2 cycloaddition reactions. Subsequently, the highly accurate ML models are applied to forecast the catalytic performance of 1344 ionic liquids under ambient conditions. This approach identifies 13 cation structures and 8 anion structures that exhibit superior catalytic properties. Further refinement through density functional theory (DFT) calculations selects ion pair structures capable of catalyzing CO2 cycloaddition reactions at ambient temperature and pressure, demonstrating the efficacy of this method in guiding the design and development of ionic liquid catalysts for CO2 conversion reactions involving epoxy compounds.

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.

Together we can do it! A roadmap to effectively tackle propaganda-related tasks

PurposeIn this paper, we address the need to study automatic propaganda detection to establish a course of action when faced with such a complex task. Although many isolated tasks have been proposed, a roadmap on how to best approach a new task from the perspective of text formality or the leverage of existing resources has not been explored yet.Design/methodology/approachWe present a comprehensive study using several datasets on textual propaganda and different techniques to tackle it. We explore diverse collections with varied characteristics and analyze methodologies, from classic machine learning algorithms, to multi-task learning to utilize the available data in such models.FindingsOur results show that transformer-based approaches are the best option with high-quality collections, and emotionally enriched inputs improve the results for Twitter content. Additionally, MTL achieves the best results in two of the five scenarios we analyzed. Notably, in one of the scenarios, the model achieves an F1 score of 0.78, significantly surpassing the transformer baseline model’s F1 score of 0.68.Research limitations/implicationsAfter finding a positive impact when leveraging propaganda’s emotional content, we propose further research into exploiting other complex dimensions, such as moral issues or logical reasoning.Originality/valueBased on our findings, we provide a roadmap for tackling propaganda-related tasks, depending on the types of training data available and the task to solve. This includes the application of MTL, which has yet to be fully exploited in propaganda detection.

Prediction of catchment efficiency in direct energy deposition using dimensional analysis and machine learning

Direct Energy Deposition (DED) is an additive manufacturing process used to fabricate thin/thick-walled structures and high-value component restorations. As blown powder-based DED gains prominence, catchment efficiency becomes imperative for enhancing material utilization and process effectiveness. This study focuses on predicting catchment efficiency within a DED process by investigating four significant process parameters: laser power, powder feed rate, carrier gas flow rate, and deposition speed. The primary objective is to devise a dimensionless number capable of predicting catchment efficiency based on a combination of these parameters, categorizing efficiency into low, medium, and high regions. This approach reduces the need for resource-intensive experimentation. The experimental validation of the proposed dimensionless number was conducted, showing an error rate of around 8%. Additionally, six machine learning classifier algorithms – Support Vector Machines, K-Nearest Neighbours, Decision Tree, Random Forest, Linear Regression, and Gaussian Naive Bayes – were employed to categorize catchment efficiency zones. Support Vector Machine demonstrated the best performance with a predictive accuracy of 0.98. This study provides a methodology for catchment efficiency prediction, enhancing decision-making and resource optimization, and can be used to optimize process parameters for thin-wall or relatively thin-wall fabrication.

CON-FOLD Explainable Machine Learning with Confidence

Abstract FOLD-RM is an explainable machine learning classification algorithm that uses training data to create a set of classification rules. In this paper, we introduce CON-FOLD which extends FOLD-RM in several ways. CON-FOLD assigns probability-based confidence scores to rules learned for a classification task. This allows users to know how confident they should be in a prediction made by the model. We present a confidence-based pruning algorithm that uses the unique structure of FOLD-RM rules to efficiently prune rules and prevent overfitting. Furthermore, CON-FOLD enables the user to provide preexisting knowledge in the form of logic program rules that are either (fixed) background knowledge or (modifiable) initial rule candidates. The paper describes our method in detail and reports on practical experiments. We demonstrate the performance of the algorithm on benchmark datasets from the UCI Machine Learning Repository. For that, we introduce a new metric, Inverse Brier Score, to evaluate the accuracy of the produced confidence scores. Finally, we apply this extension to a real-world example that requires explainability: marking of student responses to a short answer question from the Australian Physics Olympiad.

A multivariate analysis of the early dropout using classical machine learning and local interpretable model-agnostic explanations

Student dropout rates can have a significant negative impact on both the development of educational institutions and the personal growth of students. Consequently, many institutions are focused on identifying key factors that contribute to dropout and implementing strategies to mitigate them. This study aims to predict student dropout rates using classical machine learning algorithms while analyzing the key factors influencing these outcomes in higher education. The dataset includes demographic, socioeconomic, and academic information from various sources. Additionally, the study leverages the Local Interpretable Model-Agnostic Explanations (LIME) model to provide insights into the predictions, offering a clearer understanding of the factors driving dropout decisions. This knowledge is crucial for identifying influential factors and, more importantly, enhancing early intervention strategies and policies in educational settings, ultimately reducing dropout rates.

Machine Learning Algorithms for Image Classification: A Comparative Review

In the realm of computer vision, one of the most important challenges is image categorization. Its goal is to assign semantic labels to photographs based on a predetermined set of categories, and it does this via a process called semantic labeling. In attempt to find a solution to this issue, several distinct machine learning algorithms have been developed throughout the course of time; each strategy has its own unique mix of benefits and drawbacks. This article gives an in-depth review and comparison of a wide variety of well-known machine learning approaches for the classification of pictures. This review covers a wide range of algorithms, including more traditional approaches such as Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), and Transfer Learning using pretrained models such as VGG, Reset, and Inception.

Quantum data encoding: a comparative analysis of classical-to-quantum mapping techniques and their impact on machine learning accuracy

This study explores the integration of quantum data embedding techniques into classical machine learning (ML) algorithms; to assess performance enhancements and computational implications across a spectrum of models. We explored various classical-to-quantum mapping methods; ranging from basis encoding and angle encoding to amplitude encoding; for encoding classical data. We conducted an extensive empirical study encompassing popular ML algorithms, including Logistic Regression, K-Nearest Neighbors, Support Vector Machines, and ensemble methods like Random Forest, LightGBM, AdaBoost, and CatBoost. Our findings reveal that quantum data embedding contributes to improved classification accuracy and F1 scores, particularly notable in models that inherently benefit from enhanced feature representation. We observed nuanced effects on running time, with low-complexity models exhibiting moderate increases and more computationally intensive models experiencing discernible changes. Notably, ensemble methods demonstrated a favorable balance between performance gains and computational overhead.This study underscores the potential of quantum data embedding to enhance classical ML models and emphasizes the importance of weighing performance improvements against computational costs. Future research may involve refining quantum encoding processes to optimize computational efficiency and explore scalability for real-world applications. Our work contributes to the growing body of knowledge on the intersection of quantum computing and classical machine learning, offering insights for researchers and practitioners seeking to harness the advantages of quantum-inspired techniques in practical scenarios.

Design of ultra-broadband long-wave to ultra-long-wave infrared absorber based on machine learning

Abstract long-wave infrared (LWIR) and ultra-long-wave infrared (ULWIR) radiation find extensive utility in atmospheric monitoring, night reconnaissance, deep space exploration, and various other fields. However, achieving ultra-wideband absorption within these spectral ranges has persistently posed a significant challenge for researchers. Metasurfaces have attracted great interest due to their ability to manipulate electromagnetic (EM) waves with unprecedented precision and efficiency. In this paper, a metasurface absorber with a simple structure is proposed. Combined with machine learning (ML) of Random Forest algorithm for design optimization, the absorber achieves ultra-wideband perfect absorption of 42.54 μm within the LWIR-ULWIR band. Furthermore, the stability and accuracy of the Random Forest algorithm in absorber design are also evaluated and compared with other classical ML algorithms. The successful realization of this work can offer the advancement of thermal imaging, sensing, and communication systems operating within the LWIR and ULWIR spectra.

PV Module Soiling Detection Using Visible Spectrum Imaging and Machine Learning

During the last decades photovoltaic solar energy has continuously increased its share in the electricity mix and has already surpassed 5% globally. Even though photovoltaic (PV) installations are considered to require very little maintenance, their efficient exploitation relies on accounting for certain environmental factors that affect energy generation. One of these factors is the soiling of the PV surface, which could be observed in different forms, such as dust and bird droppings. In this study, visible spectrum data and machine learning algorithms were used for the identification of soiling. A methodology for preprocessing the images is proposed, which puts focus on any soiling of the PV surface. The performance of six classification machine learning algorithms is evaluated and compared—convolutional neural network (CNN), support vector machine (SVM), random forest (RF), k-nearest neighbor (kNN), naïve-Bayes, and decision tree. During the training and validation phase, RF proved to be the best-performing model with an F1 score of 0.935, closely followed by SVM, CNN, and kNN. However, during the testing phase, the trained CNN achieved the highest performance, reaching F1 = 0.913. SVM closely followed it with a score of 0.895, while the other two models returned worse results. Some results from the application of the optimal model after specific weather events are also presented in this study. They confirmed once again that the trained convolutional neural network can be successfully used to evaluate the soiling state of photovoltaic surfaces.

Machine Learning Techniques Towards Accurate Emotion Classification from EEG Signals

This article delves into using machine learning algorithms for emotion classification via EEG brain signals. The goal is to discover an accurate model beyond traditional methods, necessitating AI for classifying emotional EEG signals. This study, motivated by the complex link between emotions and neural activity, employs Random Forest, Support Vector Machines, and K-Nearest Neighbors. Notably, Random Forest achieves 99% accuracy, SVM 98%, and KNN 94%. These impressive results, backed by performance metrics like confusion matrices, reveal each model’s effectiveness in emotion classification. The dataset, rich in varied emotional stimuli and EEG placements, provides a robust foundation for detailed analysis. This research underscores significant applications in affective computing and mental health, offering a promising path to understanding the intricate relationship between EEG signals and human emotions.