Fiber reinforced polymer (FRP) composites are susceptible to material degradation when exposed to environmental effects. To predict the residual tensile strength and modulus of pultruded FRP ...composites, an XGBoost decision tree model was developed in this work. XGBoost decision tree, as a machine learning technique, is able to provide accurate predictions for tabular dataset with a good prediction interpretability. In this work, the methodology of XGBoost decision tree was presented in detail. Datasets for training and testing included a total of 746 data points which were collected from an existing database. XGBoost decision tree model predictions were cross-validated with 149 test data, and an excellent agreement was observed, showing R2 values of 0.93 and 0.85 for tensile strength and modulus, respectively. In addition, attribute importance analysis was conducted to quantitatively evaluate the attributes pertaining to FRP degradations, including exposure time, exposure temperature, pH value of environment, fiber volume fraction, plate thickness, fiber type and matrix type. Exposure time and temperature were observed to have the greatest impacts on residual tensile properties. The proposed XGBoost decision tree model provides a new approach for predicting the long-term degradations of FRP composites subjected to environmental effects.
Catheter-associated urinary tract infections (CAUTIs) are the most common device-associated infections in hospitals and can be prevented. To identify the risk factors and develop a risk prediction ...model for CAUTIs among neurosurgical intensive care unit (NICU) patients.
All patients admitted to the NICU of a tertiary hospital between January 2019 and January 2020 were enrolled. Two decision tree models were applied to analyze the risk factors associated with CAUTIs in NICU patients. The performance of the decision tree model was evaluated.
A total of 537 patients admitted to the NICU with indwelling catheters were recruited for this study. The rate of CAUTIs was 4.44 per 1000 catheter days, and Escherichia coli was the predominant pathogen causing CAUTIs among indwelling catheter patients. The classification and regression tree model displayed good power of prediction (area under the curve : 0.920). Nine CAUTI risk factors (age ≥60 years (P = 0.004), Glasgow Coma Scale score ≤8 (P = 0.009), epilepsy at admission (P = 0.007), admission to the hospital during the summer (P < 0.001), ventilators use (P = 0.007), receiving less than 2 types of antibiotics (P < 0.001), albumin level <35 g/L (P = 0.002), female gender (P = 0.002), and having an indwelling catheter for 7–14 days (P = 0.001) were also identified.
We developed a novel scoring model for predicting the risk of CAUTIs in patients with neuro-critical illness in daily clinical practice. This model identified several risk factors for CAUTI among NICU patients, novel factors including epilepsy and admission during the summer, can be used to help providers prevent and reduce the risk of CAUTI among vulnerable groups.
•Determinants of energy consumption were analyzed using linear and nonlinear models.•Some obvious and important determinants were found to be common in both models.•A nonlinear model performs better ...in comprehensive analyses of determinants.
To effectively establish and implement energy-saving plans for existing buildings, it is important to identify the determinants that influence actual energy consumption. Linear statistical models that have widely used in prior studies present a major limitation in treating nonlinear problems. Therefore, any determinant having nonlinear relationship with the energy consumption has been hardly found. To address this problem, this study proposes a novel approach to discover hidden determinants, using both linear and nonlinear models: multiple linear regression (MLR) and decision tree (DT). This study used energy consumption and characteristics data of 71 apartment units in Seoul, South Korea, which were collected by smart-metering and field survey. Through MLR and DT models, building, system, and occupant characteristics that significantly affect each of energy consumption for each end use were identified. In the results, some determinants were common in both models, while some determinants (e.g. the year of the building permit, coefficient of performance of air conditioners, etc.) were found only in the DT. The findings in this study imply that it is desirable to use nonlinear models such as a DT rather than relying only on linear models for comprehensive analysis of the relationships and interactions between variables.
As known to all, problems consume more and more computational resources, for example, memory and time, with the gradual enhancements of both the size of the physical domain and complexity in ...numerical methods. Computational efficiencies have to be obviously influenced, especially for the finite-difference time-domain (FDTD) solver due to its inflexibility in discretization principle. To further overcome this problem, the neural turing machine (NTM) model, based on the differentiable decision tree (DDT), is chosen and incorporated to improve the efficiencies during the FDTD solver in our work. The DDT-based NTM model has the remarkable advantages of both trees and neural networks, which can better explain for the numerical data. Meanwhile, it has full differentiability through neural networks and can be trained by the powerful deep-learning processes. The proposed DDT-based NTM model could not only enhance both accuracy and efficiency but also successfully integrate into the FDTD solver to implement the microstrip transmission line.
Accurate monitoring of the depth of anesthesia (DoA) is essential for intraoperative and postoperative patient's health. Commercially available electroencephalograph (EEG)-based DoA monitors are ...recommended only for certain anesthetic drugs and specific age-group patients. This paper presents a machine learning classification processor for accurate DoA estimation irrespective of the patient's age and anesthetic drug. The classification is solely based on six features extracted from EEG signal, i.e., spectral edge frequency (SEF), beta ratio, and four bands of spectral energy (FBSE). A machine learning fine decision tree classifier is adopted to achieve a four-class DoA classification (deep, moderate, and light DoA versus awake state). The feature selection and the classification processor are optimized to achieve the highest classification accuracy for the state of moderate anesthesia required for the surgical operations. The proposed 256-point fast Fourier transform accelerator is implemented to realize SEF, beta ratio, and FBSE that enables minimal latency and high accuracy feature extraction. The proposed DoA processor is implemented using a 65 nm CMOS technology and experimentally verified using field programming gate array (FPGA) based on the EEG recordings of 75 patients undergoing elective surgery with different types of anesthetic agents. The processor achieves an average accuracy of 92.2% for all DoA states, with a latency of 1s The 0.09 mm 2 DoA processor consumes 140nJ/classification.
The present study developed a simplified decision-tree algorithm for fall prediction with easily measurable predictors using data from a longitudinal cohort study: 2520 community-dwelling older ...adults aged 65 years or older participated. Fall history, age, sex, fear of falling, prescribed medication, knee osteoarthritis, lower limb pain, gait speed, and timed up and go test were assessed in the baseline survey as fall predictors. Moreover, recent falls were assessed in the follow-up survey. We created a fall-prediction algorithm using decision-tree analysis (C5.0) that included 14 nodes with six predictors, and the model could stratify the probabilities of fall incidence ranging from 30.4% to 71.9%. Additionally, the decision-tree model outperformed a logistic regression model with respect to the area under the curve (0.70 vs. 0.64), accuracy (0.65 vs. 0.62), sensitivity (0.62 vs. 0.50), positive predictive value (0.66 vs. 0.65), and negative predictive value (0.64 vs. 0.59). Our decision-tree model consists of common and easily measurable fall predictors, and its white-box algorithm can explain the reasons for risk stratification; therefore, it can be implemented in clinical practices. Our findings provide useful information for the early screening of fall risk and the promotion of timely strategies for fall prevention in community and clinical settings.
Abstract
The process of automatically identifying the language used in a text or document is known as language identification. Language identification might represent a critical step in Natural ...Language Processing (NLP). It entails making an effort to foresee a text‘s natural language. Before any actions can be conducted, it is crucial to understand the language of the text. We must build a model that can anticipate the given language using the text as a guide. This provides an answer for many computational linguists and Artificial Intelligence (AI) applications. In this study, the language in the provided text was identified using machine learning algorithms and vectorization techniques. The performance of different classification algorithms like Naïve bayes, Logistic Regression, Decision Tree and Random Forest have been compared and analyzed. Vectorization technique has been done to convert the text into matrix. This paper presents the comparison of all the above algorithms performed through various measures.
PDF
