Decision Tree Research Articles

NIPP: Non-Invasive PCOS Prediction using XG-boost Machine Learning Model

Polycystic Ovary Syndrome (PCOS) is a common endocrine disorder that affects women of reproductive age, leading to hormonal imbalances and ovarian dysfunction. Early detection and intervention are vital for effective management and prevention of complications. This study compares PCOS prediction using the XGBoost machine learning model against four traditional models: Logistic Regression (LR), Support Vector Machine (SVM), Decision Trees (DT), and Random Forests (RF). LR and SVM achieve accuracies of 95% and 96%, respectively, demonstrating strong predictive capabilities. In contrast, DT had a lower accuracy (82%), indicating limitations in PCOS data complexity. RF showed competitive performance with 96% accuracy, underscoring its effectiveness in ensemble learning. XGBoost achieves 98% accuracy with its parameter configuration. The scale pos weight parameter adjusts the positive class weight in im- balanced datasets, addressing underrepresentation by assigning more weight to the minority class, and thereby improving the training focus. The gradient boosting framework incrementally builds models to address complex feature interactions and dependencies, enhancing the accuracy and stability in predicting intricate PCOS dataset. This analysis highlights the importance of advanced machine learning models such as XGBoost for accurate and reliable PCOS predictions. This re- search advances PCOS prediction, demonstrates the potential of machine learning in healthcare, and clarifies the strengths and limitations of different algorithms with complex medical datasets.

Enhancing Adversarial Examples for Evading Malware Detection Systems: A Memetic Algorithm Approach

Malware detection using Machine Learning techniques has gained popularity due to their high accuracy. However, ML models are susceptible to Adversarial Examples, specifically crafted samples intended to deceive the detectors. This paper presents a novel method for generating evasive AEs by augmenting existing malware with a new section at the end of the PE file, populated with binary data using memetic algorithms. Our method hybridizes global search and local search techniques to achieve optimized results. The Malconv Model, a well-known state-of-the-art deep learning model designed explicitly for detecting malicious PE files, was used to assess the evasion rates. Out of 100 tested samples, 98 successfully evaded the MalConv model. Additionally, we investigated the simultaneous evasion of multiple detectors, observing evasion rates of 35% and 44% against KNN and Decision Tree machine learning detectors, respectively. Furthermore, evasion rates of 26% and 10% were achieved against Kaspersky and ESET commercial detectors. In order to prove the efficiency of our memetic algorithm in generating evasive adversarial examples, we compared it to the most used evolutionary-based attack: the genetic algorithm. Our method demonstrated significantly superior performance while utilizing fewer generations and a smaller population size.

The relationship between activities of daily living and speech impediments based on evidence from statistical and machine learning analyses

IntroductionSpeech impediments (SIs) are increasingly prevalent among middle-aged and older adults, raising concerns within public health. Early detection of potential SI in this demographic is critical. This study investigates the potential of Activities of Daily Living (ADL) as a predictive marker for SI, utilizing data from the 2018 China Health and Retirement Longitudinal Study (CHARLS), which includes 10,136 individuals aged 45 and above. The Barthel Index (BI) was used to assess ADL, and the correlation between ADL and SI was examined through statistical analyses. Machine learning algorithms (Support Vector Machine, Decision Tree, and Logistic Regression) were employed to validate the findings and elucidate the underlying relationship between ADL and SI.BackgroundSI poses significant challenges to the health and quality of life of middle-aged and older adults, increasing the demands on community-based and home care services. In the context of global aging, it is crucial to investigate the factors contributing to SI. While the role of ADL as a potential biomarker for SI remains unclear, this study aims to provide new evidence supporting ADL as an early predictor of SI through statistical analysis and machine learning validation.MethodsData were derived from the 2018 CHARLS national baseline survey, comprising 10,136 participants aged 45 and above. ADL was evaluated using the BI, and SI was assessed based on the CHARLS records of “Speech impediments.” Statistical analyses, including independent sample t-tests, chi-square tests, Pearson and Spearman correlation tests, and hierarchical multiple linear regression, were conducted using SPSS 25.0. Machine learning algorithms, specifically Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression (LR), were implemented in Python 3.10.2.ResultsAnalysis of demographic characteristics revealed that the average BI score in the “With Speech impediments” group was 49.46, significantly lower than the average score of 85.11 in the “Without Speech impediments” group. Pearson correlation analysis indicated a significant negative correlation between ADL and SI (r = −0.205, p < 0.001). Hierarchical multiple linear regression confirmed the robustness of this negative correlation across three models (B = −0.001, β = −0.168, t = −16.16, 95% CI = −0.001 to −0.001, p = 0.000). Machine learning algorithms validated the statistical findings, confirming the predictive accuracy of ADL for SI, with the area under the curve (AUC) scores of SVM-AUC = 0.648, DT-AUC = 0.931, and LR-AUC = 0.666. The inclusion of BI in the models improved the overall predictive performance, highlighting its positive impact on SI prediction.ConclusionThe study employed various statistical methodologies to demonstrate a significant negative correlation between ADL and SI, a finding further corroborated by machine learning algorithms. Impairment in ADL increases the likelihood of SI occurrence, underscoring the importance of maintaining ADL in middle-aged and older populations to mitigate the risk of SI.

A comparison of different machine learning classifiers in predicting xerostomia and sticky saliva due to head and neck radiotherapy using a multi-objective, multimodal radiomics model.

Background and Purpose. Although radiotherapy techniques are a primary treatment for head and neck cancer (HNC), they are still associated with substantial toxicity and side effects. Machine learning (ML) based radiomics models for predicting toxicity mostly rely on features extracted from pre-treatment imaging data. This study aims to compare different models in predicting radiation-induced xerostomia and sticky saliva in both early and late stages HNC patients using CT and MRI image features along with demographics and dosimetric information.Materials and Methods.A cohort of 85 HNC patients who underwent radiation treatment was evaluated. We built different ML-based classifiers to build a multi-objective, multimodal radiomics model by extracting 346 different features from patient data. The models were trained and tested for prediction, utilizing Relief feature selection method and eight classifiers consisting eXtreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (NB), Logistic Regression (LR), and Decision Tree (DT). The performance of the models was evaluated using sensitivity, specificity, area under the curve (AUC), and accuracy metrics.Results.Using a combination of demographics, dosimetric, and image features, the SVM model obtained the best performance with AUC of 0.77 and 0.81 for predicting early sticky saliva and xerostomia, respectively. Also, SVM and MLP classifiers achieved a noteworthy AUC of 0.85 and 0.64 for predicting late sticky saliva and xerostomia, respectively.Conclusion. This study highlights the potential of baseline CT and MRI image features, combined with dosimetric data and patient demographics, to predict radiation-induced xerostomia and sticky saliva. The use of ML techniques provides valuable insights for personalized treatment planning to mitigate toxicity effects during radiation therapy for HNC patients.

Optimization of Intrusion Detection System with Machine Learning for Detecting Distributed Attacks on Server

This study develops an intrusion detection system optimized with machine learning techniques for efficient and effective detection of Distributed Denial-of-Service (DDoS) attacks. Using the Decision Tree algorithm, the system is designed to maximise accuracy in the identification and classification of DDoS attacks. The CIC-DDoS2019 dataset, which consists of various comprehensive simulated attack scenarios, is used as the basis for training and validation, providing the model with robust capabilities in recognizing DDoS attacks with high accuracy. This IDS successfully achieved a 100% detection rate, which is a significant result in the network security environment. The system is integrated into the existing network infrastructure, monitoring data flows in real-time and performing predictive analysis to detect early indications of attacks. Each attack detection immediately triggers a notification sent via a Telegram bot, ensuring that the security team can react quickly to isolate and address the attack. These notifications include details such as the source, type of attack, detection time, and involved protocol information, enabling more informed and strategic response actions. The use of Telegram bots for real-time communication not only enhances the speed of response to threats but also supports system scalability by facilitating adjustments and integration across various operational scenarios. The system's quick detection and response is a big step forward for machine learning-based intrusion detection systems (IDS). It provides opportunities for further research and practical applications that can adapt to various digital security scenarios.

Research on the Circuit Breaker State Judgment Method Based on Ant Colony Optimization Dempster-Shafer Evidence Theory

The paper proposes a method for circuit breaker state judgment based on ant colony algorithm-optimized Dempster-Shafer evidence theory.It can improve the accuracy and robustness of state judgment. As a key device in the power system, the state judgment of circuit breakers is crucial for the safety and stability of the power grid. Existing methods have limitations in handling conflicts and uncertainties of multi-source data, and a single model is difficult to meet the needs of complex data fusion. Therefore, the paper applies the ant colony algorithm to optimize the basic probability assignment in Dempster-Shafer evidence theory to improve the fusion effect of multi-source data. The ant colony algorithm, through its global search and adaptive characteristics, can effectively optimize evidence combination and enhance the accuracy of the fusion results. The experiment used a support vector machine model based on current signals and a decision tree model based on vibration signals for data fusion and discrimination. The results showed that the Dempster-Shafer evidence theory model optimized by the ant colony algorithm achieved a discrimination accuracy of 75% under various circuit breaker conditions. Compared to the Dempster-Shafer evidence theory fusion model, it improved by approximately 8.3%, and compared to the current research’s Dempster-Shafer evidence theory and neural network methods, it improved by 5%.. This method has broad application prospects in enhancing the operational stability of power grid equipment and improving fault detection efficiency.

A logistic regression model to predict long-term survival for borderline resectable pancreatic cancer patients with upfront surgery

BackgroundThe machine learning model, which has been widely applied in prognosis assessment, can comprehensively evaluate patient status for accurate prognosis classification. There still has been a debate about which predictive strategy is better in patients with borderline resectable pancreatic cancer (BRPC). In the present study, we establish a logistic regression model, aiming to predict long-term survival and identify related prognostic factors in patients with BRPC who underwent upfront surgery.MethodsMedical records of patients with BRPC who underwent upfront surgery with portal vein resection and reconstruction from Jan. 2011 to Dec. 2020 were reviewed. Based on postoperative overall survival (OS), patients were divided into the short-term group (≤ 2 years) and the long-term group (> 2 years). Univariate and multivariate analyses were performed to compare perioperative variables and long-term prognoses between groups to identify related independent prognostic factors. All patients are randomly divided into the training set and the validation set at a 7:3 ratio. The logistic regression model was established and evaluated for accuracy through the above variables in the training set and the validation set, respectively, and was visualized by Nomograms. Meanwhile, the model was further verified and compared for accuracy, the area under the curve (AUC) of the receiver operating characteristic curves (ROC), and calibration analysis. Then, we plotted and sorted perioperative variables by SHAP value to identify the most important variables. The first 4 most important variables were compared with the above independent prognostic factors. Finally, other models including support vector machines (SVM), random forest, decision tree, and XGBoost were also constructed using the above 4 variables. 10-fold stratified cross-validation and the AUC of ROC were performed to compare accuracy between models.Results104 patients were enrolled in the study, and the median OS was 15.5 months, the 0.5-, 1-, and 2- years OS were 81.7%, 57.7%, and 30.8%, respectively. In the long-term group (n = 32) and short-term group (n = 72), the overall median survival time and the 1-, 2-, 3- years overall survival were 38 months, 100%, 100%, 61.3% and 10 months, 38.9%, 0%, 0%, respectively. 4 variables, including age, vascular invasion length, vascular morphological malformation, and local lymphadenopathy were confirmed as independent risk factors between the two groups following univariate and multivariate analysis. The AUC between the training set (n = 72) and the validation set (n = 32) were 0.881 and 0.875. SHAP value showed that the above variables were the first 4 most important. The AUC following 10-fold stratified cross-validation in the logistic regression (0.864) is better than SVM (0.693), random forest (0.789), decision tree (0.790), and XGBoost (0.726).ConclusionAge, vascular invasion length, vascular morphological malformation, and local lymphadenopathy were independent risk factors for long-term survival of BRPC patients with upfront surgery. The logistic regression model plays a predictive role in long-term survival and may further assist surgeons in deciding the treatment option for BRPC patients.

Mobile Botnet Attacks Detection Using Supervised Learning Algorithms

ABSTRACTIn today's era of increased smart device usage, the prevalence of malicious attacks targeting mobile devices has risen significantly. Malware developers aim to infect as many mobile devices as possible, capitalizing on the vulnerabilities present in different operating systems that often host sensitive programs such as educational and banking applications. To combat this issue, this article introduces a mobile botnet detection system that leverages machine learning algorithms such as random forest, k‐nearest neighbor, logistic regression, and decision trees. Additionally, the system incorporates the use of the golden ratio evolutionary algorithm for dimension reduction and feature selection. The proposed method's performance is evaluated using detection accuracy, Precision, F1 Score, and Recall as evaluation criteria on NSL‐KDD, Drebin, and ISCX datasets. The results are compared with evaluation values obtained without applying the golden ratio feature selection algorithm and once again with the proposed method. The findings demonstrate that the proposed method, particularly when combined with the random forest algorithm, achieves the highest accuracy in the desired dataset. Moreover, the decision tree and k‐nearest neighbor algorithms also exhibit superior detection accuracy within the proposed method's framework. By utilizing the proposed method, the training time is reduced through feature selection, enabling swift mobile botnet identification.

Detection and Prevention of Brute Force attacks using Machine Learning

With the development in remote correspondence, there are numerous security dangers over the web. The interruption discovery framework (IDS) assists with tracking down the assaults on the framework and the interlopers are identified. Already different AI (ML) procedures are applied on the IDS and attempted to work on the outcomes on the discovery of intruders and to improve the IDS's accuracy. The paper has suggested method for using the principal component analysis to create effective IDS (PCA) as well as the random forest classification method Where the PCA can assist arrange the dataset by lessening the dimensionality of the dataset and the arbitrary forest will make classification easier. According to the obtained results, the proposed method performs more effectively and accurately than other methods such as Decision Tree, Naive Bayes, and SVM. The outcomes acquired by proposed strategy are having the qualities for execution time (min) is 3.24 minutes, Exactness rate (%) is 96.78 %, and the Mistake rate (%) is 0.21 %.

Evaluating Dimensionality Reduction Techniques in Bitcoin Ransomware Detection: Comparative Analysis of Incremental PCA and UMAP

ABSTRACTThis study investigates the classification performance of various machine learning algorithms on the Bitcoin Heist ransomware dataset, focusing on the effects of dimensionality reduction techniques. The primary objective was to evaluate the classifiers' effectiveness in distinguishing between malicious and benign transactions under three experimental scenarios: without dimensionality reduction, utilizing Incremental Principal Component Analysis (IPCA), and applying Uniform Manifold Approximation and Projection (UMAP). The methodology involved rigorous experimentation with four classifiers: K‐Nearest Neighbors (KNN), XGBoost, Decision Tree, and Multi‐Layer Perceptron (MLP). The results demonstrated that dimensionality reduction techniques, particularly UMAP, improved the performance of KNN and Decision Tree classifiers while adversely affecting the performance of XGBoost and MLP. Notably, KNN consistently outperformed the other classifiers across different scenarios, indicating its robustness in handling reduced feature spaces. This study concludes that the effectiveness of dimensionality reduction is contingent upon the specific characteristics of the classifiers employed.

Machine learning insights into the strain-stress behavior of nitinol alloys at low temperatures: Utilizing the orange data mining tool

This study entails a new technique, based on machine learning algorithms, for predicting the strain-stress behavior of Nitinol alloys. The study utilizes Orange data mining software to determine if algorithms like Linear Regression, Random Forest, k-nearest neighbors, and decision tree are related to the effectiveness. The nitinol-based alloy, which has both shape memory and superelasticity, is used in a wide range of biomedical devices, aerospace constructions, and automated apparatus. Temperature variation is a main factor affecting the Nitinol behavior. It is therefore required to carry out an in-depth analysis of strain-stress patterns. Employing machine learning algorithms along with data mining tools allows the exact prediction of the Nitinol alloy performance under any given condition. The research is purposed to establish the relationship between temperature and mechanical strength of Nitinol by analyzing strain-stress curves that were obtained from tensile tests carried out at different temperatures. Looking at overall results, kNN has the highest accuracy of the models upon comparing MSE and RMSE, and has higher R² and, therefore stands as the model of high reliability. Results show that machine learning algorithms successfully forecast the mechanical responses of Nitinol under temperature variations, which assists in determining their formability properties and hence, advancing Nitinol applications in various fields. This research demonstrates machine learning uses in developing materials science and engineering knowledge by showing the ability to predict Nitinol alloy behavior, which includes strain-stress characteristics at low temperatures. Furthermore, the research's significance lies in addressing ethical considerations and practical issues, such as the necessity of implementing an organized approach to achieve environmental benefits.

An Intelligent Intrusion Detection System for VANETs Using Adaptive Fusion Models

Vehicular Ad Hoc Networks (VANETs) play a vital role in the development of Cyber-Physical Systems (CPS) to enable real-time communication for improving road safety and traffic efficiency. Due to the VANETs' decentralized and dynamic nature, they are prone to various types of cyber-attacks, including intrusion, spoofing, and denial-of-service (DoS) attacks. This article presents an Adaptive Fusion Intrusion Detection Model (AFIDM), a multi-level framework that uses machine learning techniques, such as Random Forest, XGBoost, Decision Trees, and K-Nearest Neighbor (KNN), to deal with such vulnerabilities. AFIDM also employs a dynamic weight adjusting mechanism and an adaptive feedback loop to adapt to the evolving threats and achieve better detection accuracy. AFIDM achieved 98.7% accuracy, 96.5% precision, and recall of 95.8% on the VeReMi dataset used for training and validation and outperformed other baseline models. With low latency and scalability, the proposed model presents a robust solution for real-time intrusion detection in VANETs for the secure and efficient operation of intelligent transportation systems

Estimation of Hematocrit Volume Using Blood Glucose Concentration through Extreme Gradient Boosting Regressor Machine Learning Model.

Lifestyle diseases such as cardiovascular disorders, diabetes, etc. affect the physiological metabolism and become chronic upon negligence. Diabetes is one of the key factors that is interlinked with a plethora of diseases. Health management can be achieved through balanced diet, physical exercise, and periodic examination of blood glucose level and hematocrit volume. Our study developed a model to estimate the hematocrit volume (red blood cells) from the correlation of the glucose concentration obtained from a glucometer by employing machine learning techniques. This Article explores the prediction of hematocrit volume in whole blood by applying various machine learning (ML) models such as linear regression (LR), support vector regressor (SVR), decision tree (DT), random forest regressor (RFR), artificial neural network (ANN), and extreme gradient boosting regressor model (XGBoost). We used amperometric signals generated from an electrochemical glucose sensor or glucose strip, which produces current values on glucose concentration. We estimated the hematocrit volume via processing of the amperometric signals to enhance diagnostic capabilities with the least error in the field of biomedical signal processing. The ML models were trained on the data set comprising 80% training set and 20% testing set in the Python programming language. The models were evaluated based on the metrics such as R-squared (R2), mean squared error (MSE), and root mean squared error (RMSE) values, and their reliability was assessed through the three validation mechanisms, namely, the relative error, K-fold cross-validation, and analysis of confidence interval. We observed that the XGBoost regression results were comparatively better than the LR and ANN results as corroborated through reliability analysis. It was concluded that XGBoost demonstrated 15% relative error between actual and predicted data and 68% accuracy with 6% standard deviation in the prediction obtained via a 5-fold cross-validation technique. The XGBoost model demonstrates comparatively better performance in terms of flexibility in tuning and interpretability options, which make it suitable for the regression task in the predictive biomedical analytics.

Clinical validation and optimization of machine learning models for early prediction of sepsis

IntroductionSepsis is a global health threat that has a high incidence and mortality rate. Early prediction of sepsis onset can drive effective interventions and improve patients’ outcome.MethodsData were collected retrospectively from a cohort of 2,329 adult patients with positive bacteria cultures from a tertiary hospital in China between October 1, 2019 and September 30, 2020. Thirty six clinical features were selected as inputs for the models. We trained models in predicting sepsis by machine learning (ML) methods, including logistic regression, decision tree, random forest (RF), multi-layer perceptron, and light gradient boosting. We evaluated the performance of the five ML models and the evaluation metrics were: area under the ROC curve (AUC), accuracy, F1-score, sensitivity and specificity. The data of another cohort of 2,286 patients between October 1, 2020 and April 1, 2022 were used to validate the performance of the model performing best in the in the internal validation set. Shapley additive explanations (SHAP) method was applied to evaluate feature importance and explain the predictions of this model.ResultsOf the five machine learning models developed, the RF model demonstrated the best performance in terms of AUC (0.818), F1 value (0.38), and sensitivity (0.746). The RF model also has a comparable AUC (0.771) in the external validation set. The SHAP method identified procalcitonin, albumin, prothrombin time, and sex as the important variables contributing to the prediction of sepsis.DiscussionThe RF model we developed showed the greatest potential for early prediction of sepsis in admitted patients, which could aid clinicians in their decision-making process. Our findings also suggested that male patients with bacterial infections and high procalcitonin levels, lower albumin levels, or prolonged prothrombin times were more likely to develop sepsis.

Ranking Influential Non-Content Factors on Scientific Papers’ Citation Impact: A Multidomain Comparative Analysis

The influence of scientific papers is measured by their citations. Although predicting the papers’ citation impact based on non-content factors has garnered extensive attention, the influence of such factors is rarely compared. In this article, we compare the influence of non-content factors on the citation counts of academic publications across three fields, i.e., math, computer science, and management. We consider different methods in this study, including three machine learning approaches, namely, XGBoost, Gradient Boosting Decision Tree, and Random Forest, along with statistical techniques such as linear regression and quantile analysis. Our findings reveal that no matter the field or analytical method applied, author prestige and the number of references consistently stand out as the most influential factors, while the breadth of categories covered by the paper has minimal impact. In mathematics, the first citation date and article length are almost equally important as author prestige, while the number of authors and the journal impact factor are crucial for computer science papers. In management, the number of collaborating countries is relatively influential with respect to the paper’s citations. The results of the quantile regression indicate that at higher quantile levels, the impact of author prestige and the number of authors on the papers’ citation impact are more pronounced across all three disciplines, while the journal impact factor and paper length have the greatest influence at low and medium quantile levels. Our findings indicate that the reliance of academic citations on author prestige and journal impact factors not only highlights the unequal distribution of resources within the current academic system but also further exacerbates citation inequality.

Federated learning based reference evapotranspiration estimation for distributed crop fields

Water resource management and sustainable agriculture rely heavily on accurate Reference Evapotranspiration (ETo). Efforts have been made to simplify the (ETo) estimation using machine learning models. The existing approaches are limited to a single specific area. There is a need for ETo estimations of multiple locations with diverse weather conditions. The study intends to propose ETo estimation of multiple locations with distinct weather conditions using a federated learning approach. Traditional centralized approaches require aggregating all data in one place, which can be problematic due to privacy concerns and data transfer limitations. However, federated learning trains models locally and combines the knowledge, resulting in more generalized ETo estimates across different regions. The three geographical locations of Pakistan, each with diverse weather conditions, are selected to implement the proposed model using the weather data from 2012 to 2022 of the selected three locations. At each selected location, three machine learning models named Random Forest Regressor (RFR), Support Vector Regressor (SVR), and Decision Tree Regressor (DTR), are evaluated for local Evapotranspiration (ET) estimation and the federated global model. The feature importance-based analysis is also performed to assess the impacts of weather parameters on machine learning performance at each selected local location. The evaluation reveals that Random Forest Regressor (RFR) based federated learning outperformed other models with coefficient of determination (R2) = 0.97%, Root Mean Squared Error (RMSE) = 0.44, Mean Absolute Error (MAE) = 0.33 mm day−1, and Mean Absolute Percentage Error (MAPE) = 8.18%. The Random Forest Regressor (RFR) performance yields the local machine learning models against each selected site. The analysis results suggest that maximum temperature and wind speed are the most influential factors in Evapotranspiration (ET) predictions.

Shuffle Model of Differential Privacy: Numerical Composition for Federated Learning

In decentralized scenarios without fully trustable parties (e.g., in mobile edge computing or IoT environments), the shuffle model has recently emerged as a promising paradigm for differentially private federated learning. Despite many efforts of privacy accounting for federated learning with many sequential rounds in the shuffle model, they suffer from generality and tightness. For example, existing accounting methods are targeted to single-message shuffle protocols (which have intrinsic utility barriers compared to multi-message ones), and are untight for the commonly used vector randomized response randomizer. As countermeasures, we first present a tight total variation characterization of vector randomized response randomizers in the shuffle model, which demonstrates over 20% budget conservation. We then unify the representation of single-message and multi-message shuffle protocols and derive their privacy loss distribution (PLD). The PLDs are finally composed by Fourier analysis to obtain the overall privacy loss of many sequential rounds in the shuffle model. Through simulations in federated decision tree building and federated deep learning, we show that our approach saves up to 80% budget when compared to existing methods.

Consumer Behavior Analysis and Enterprise Marketing Strategy Optimization Based on Decision Tree Model and Association Rule Algorithm

Consumer Behavior Analysis and Enterprise Marketing Strategy Optimization Based on Decision Tree Model and Association Rule Algorithm

Evolving prognostic paradigms in lung adenocarcinoma with brain metastases: a web-based predictive model enhanced by machine learning

IntroductionPatients with lung adenocarcinoma (LUAD) who develop brain metastases (BM) face significantly poor prognoses. A well-crafted prognostic model could greatly assist clinicians in patient counseling and in devising tailored therapeutic strategies.MethodsThe study cohort comprised LUAD patients with BM identified from the surveillance, epidemiology, and end results database between 2000 and 2018. We pinpointed independent prognostic features for overall survival (OS) using Lasso regression analyses. Predictive models were built using Random Forest, XGBoost, Decision Trees, and Artificial Neural Networks, with their performance evaluated via metrics including the area under the receiver operating characteristic curve (AUC), calibration plots, brier score, and decision curve analysis (DCA).ResultsWe extracted a total of 9121 eligible patients from the database, identifying eleven clinical parameters that significantly influenced OS prognostication. The XGBoost model exhibited superior discriminative power, achieving AUC values of 0.829 and 0.827 for 1- and 2-year survival, respectively, in the training cohort, and 0.816 and 0.809 in the validation cohort. In comparison to other models, the XGBoost model excelled in both training and validation phases, as demonstrated by substantial differences in AUC, DCA, calibration, and Brier score. This model has been made accessible via a web-based platform.ConclusionsThis study has developed an XGBoost-based machine learning model with an accompanying web-based application, providing a novel resource for clinicians to support personalized decision-making and enhance treatment outcomes for LUAD patients with BM.

A novel aggregated coefficient ranking based feature selection strategy for enhancing the diagnosis of breast cancer classification using machine learning.

Effective Breast cancer (BC) analysis is crucial for early prognosis, controlling cancer recurrence, timely medical intervention, and determining appropriate treatment procedures. Additionally, it plays a significant role in optimizing mortality rates among women with breast cancer and increasing the average lifespan of patients. This can be achieved by performing effective critical feature analysis of the BC by picking superlative features through significant ranking-based Feature Selection (FS). Various authors have developed strategies relying on single FS, but this approach may not yield excellent results and could lead to various consequences, including time and storage complexity issues, inaccurate results, poor decision-making, and difficult interpretation of models. Therefore, critical data analysis can facilitate the development of a robust ranking methodology for effective feature selection. To solve these problems, this paper suggests a new method called Aggregated Coefficient Ranking-based Feature Selection (ACRFS), which is based on tri chracteristic behavioral criteria. This strategy aims to significantly improve the ranking for an effective Attribute Subset Selection (ASSS). The proposed method utilized computational problem solvers such as chi-square, mutual information, correlation, and rank-dense methods. The work implemented the introduced methodology using Wisconsin-based breast cancer data and applied the Synthetic Minority Oversampling Technique (SMOTE) to the obtained data subset. Later, we employed models such as decision trees, support vector machines, k-nearest neighbors, random forests, stochastic gradient descent, and Gaussian naive bayes to determine the type of cancer. The classification metrics such as accuracy, precision, recall, F1 score, kappa score, and Matthews coefficient were utilized to evaluate the effectiveness of the suggested ACRFS approach. The proposed method has demonstrated superior outcomes with fewer features and a minimal time complexity.