1,720,963 research outputs found
Predicting Heart Disease using Tree-based Model
Get PDFThe paper presents a study on the use of machine learning algorithms for the prediction of heart disease, which is the leading cause of death worldwide. The study focuses on the use of decision tree algorithms, which have the advantage of considering a large number of risk factors. The heart disease data set was obtained from the UCI Machine Learning Repository and was analyzed using a decision tree classifier. The data set had 6 missing data points, which were deleted, leaving 279 instances for analysis. One-hot-encoding was performed on categorical variables with more than two responses. The decision tree classifier was optimized using 5-fold cross-validation to choose the best parameters. The results showed that the decision tree classifier had an accuracy of predicting correctly 81% of the patients as having heart disease and like wise 82% for not having heart disease, which was higher than other machine learning algorithms used in previous studies. This study demonstrates the potential of decision tree algorithms for predicting heart disease and highlights the importance of early identification of individuals at risk of developing cardiovascular disease
Developing a Data-Driven Statistical Model for Accurately Predicting the Superconducting Critical Temperature of Materials using Multiple Regression and Gradient-Boosted Methods
Get PDFThis study focuses on developing a statistical model for estimating the superconducting critical temperature (Tc) of materials using a data-driven strategy. The study analyzed 21,263 superconductors and used a combination of multiple regression and gradient-boosted models to make predictions. The analysis included a descriptive analysis of the distribution of Tc, feature selection using the Backwards selection method, and model diagnostics. The results showed that the gradient-boosted method outperformed the multiple linear regression method with an RMSE of 12.01 and an R2 value of 88.23 after fine-tuning its hyperparameters. The study concludes that the gradient-boosted method is an effective approach for accurately predicting Tc in superconducting materials
Variable Selection and Regression Analysis
Get PDFOne of the most valuable crop species, maize, has been the subject of genetic study and experimentation for more than a century. However, species that share similarities and differences across a wide spectrum have developed astonishing adaptations as a result of small changes throughout time. Because it is usual practice to determine the genotypes of thousands of single nucleotide polymorphism (SNP) markers for thousands of patients, the data set we are dealing with has an issue with small n and large p. The result of this is that there are noticeably more predictor factors than responder variables. The original data set has around 487 missing rows and has n = 4981 and p = 7390. We eliminated these entirely absent rows during the pre-processing phase. Additionally, we eliminated any columns that did not apply to our analysis. We then divided the data set into a train set and a test set, with a ratio of 80:20, respectively. We use regularization approaches for Lasso feature selection to solve the high dimensionality issue. The least-squares loss function of linear regression, an extension of linear regression, is given a regularization component in this approach. To impose the penalty (lower weights) against complexity, this is done. With a penalization λ of 0.2, this procedure was successful in identifying 22 traits as being extremely significant to the study. Finally, a Lasso regression model was constructed, and the test set’s RMSE value was found to be 3.494
Silent Agony: Automated Detection of Ethnic and Religious Cyberbullying Using Machine Learning
Get PDFThe use of electronic mobile devices, social media, and networking websites has increased tremendously in recent years. Despite the advantages of these systems, such as exchanging ideas and information, being sociable, and providing entertainment, users may encounter adverse behaviors like toxicity, bullying, extremism, and cruelty. The prevalence of such behaviors has grown significantly in cyberspace, posing a threat to individuals and communities. To address this issue, there is a high demand for automated cyberbullying detection systems. Machine learning algorithms have been widely used to build such systems by classifying and detecting cyberbullying. In this study, we employed popular machine learning models such as Logistic Regression (LR), Multinomial Naive Bayes (MNB), K-Nearest Neighbor (KNN), and Extreme Gradient Boosting (XGboost) on a Twitter textual dataset to detect cyberbullying related to ethnicity and religion. To convert the textual data into numerical sets, we used feature extraction techniques such as Bag of Words and TF-IDF. Our results indicate that XGboost and LR achieve the highest performance
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Comparison of Two Strategies of Screening Experiments: Single-shot Experiment vs. Two-stage Screening Experiment
Get PDFExperiments involving many factors are often complex, time-consuming, and expensive. Screening out the least important factors helps the experimenter(s) allocate the limited resources efciently to the most important factors. Supersaturated and orthogonal array designs are among the designs used to conduct screening experiments. Supersaturated designs (SSDs) are those where the number of runs (observations) is less than the number of factors, while orthogonal array (OA) designs are those where at least the columns are orthogonal to each other. In this study, we conduct a simulation study to compare two strategies of screening experiments. Strategy one is a single shot experiment using an orthogonal array. Strategy two is a two-stage screening experiment that involves supersaturated design in the frst stage and a follow-up using orthogonal array design in the second stage. The study investigates two models: (1) a model with a subset of main efects being active and (2) a model with a subset of main efects and some two-factor interaction effects active. The two strategies are analyzed via the Dantzig selector method. The power to detect active efects, type I error rate, and false discovery rate are computed and compared. Generally, strategy one performs better than strategy two. When efect sparsity is high, the two strategies are comparable
Bootstrap Regression for Investigating Macroeconomics Factors Affecting USA Home Prices
Get PDFThis study investigates the impact of macroeconomic indicators on US home prices, underscoring the importance of understanding these dynamics due to their signifcant socioeconomic consequences. Utilizing a dataset from Kaggle, originally collected by FRED, the research examines variables like the Consumer Price Index, Population, Unemployment, GDP, Stock Prices, Income, and Mortgage Rate to discern their efect on housing market fuctuations. The analysis identifes multicollinearity among predictors, necessitating a shift from traditional multiple linear regression to a more robust bootstrap regression method due to violations of parametric assumptions. Key fndings reveal that Real Disposable Income is a signifcant predictor of home prices, although the presence of multicollinearity complicates the model-building process. The bootstrap regression approach, favored for its resilience to assumption violations, confrms the infuence of selected macroeconomic factors on home prices. The study concludes that bootstrap regression provides a reliable alternative to parametric methods in cases of assumption non-compliance and highlights the critical role of addressing multicollinearity in regression analysis. This research ofers valuable insights for stakeholders involved in the housing market, emphasizing the need for careful econometric modeling in economic policy and investment decisions
Predicting Road Accident Injury Severity for Drivers in Automobile Crashes in United States Using Machine Learning Models and AI
Get PDFThis study analyzes data from the National Highway Trafc Safety Administration’s 2021 Crash Report Sampling System to identify key factors contributing to the severity of injuries in car accidents. By utilizing various machine learning algorithms and cross-validation techniques, we assessed metrics such as accuracy, sensitivity, precision, specifcity, and the area under the curve (AUC) to evaluate the efectiveness of predictive models. All data preprocessing and model building was done using KNIME Analytical software [9]. Our fndings reveal signifcant correlations between certain variables such as airbag injection, weather conditions, intoxication, vehicle state, driver distractions, and injury severity. These insights underscore the importance of stringent safety measures, including proper restraint system usage and advanced driver-assistance technologies, in reducing the risk of severe injuries in car accidents. Recommendations for policy enhancements and preventive measures are discussed to improve overall vehicle safety
A Report on Health Care Access by the United States Citizens.
Get PDFAccess to health care is a critical factor in ensuring public health. This study analyzes data from the National Health Interview Survey (NHIS) for the years 2015–2018 to examine the relationship between health care coverage, affordability, and costs among U.S. families. Re-sults indicate that families with at least one member covered by health insurance were more likely to afford medical care and incur lower health care costs. Despite a high proportion of families with health care coverage during this period, the number of insured family members declined over the years. These findings underscore the importance of health care coverage in reducing financial barriers to medical access and highlight areas for further exploration in health policy
- …
