Publications by authors named "Zhaozhao Xu"
An inexpensive and high-performing solid Coumarone resin was added to Styrene-butadiene-styrene (SBS) copolymer-modified asphalt to enhance its storage stability and road performance. To assess the effect of Coumarone resin dosage on the SBS-modified asphalt, a series of laboratory tests were conducted. The composite modified asphalt's segregation test was used to evaluate its storage stability, Dynamic Shear Rheometer (DSR) and Multiple Stress Creep Recovery (MSCR) tests were employed to investigate its high-temperature performance and permanent deformation resistance, and the Bending Beam Rheology (BBR) test was utilized to measure its low-temperature performance.
View Article and Find Full Text PDFCGUFS: A clustering-guided unsupervised feature selection algorithm for gene expression data.
J King Saud Univ Comput Inf Sci
October 2023
Article Synopsis
- - The study addresses the challenges in gene expression data analysis, particularly high dimensionality, limited sample sizes, and feature redundancy, by proposing a new algorithm called Clustering-Guided Unsupervised Feature Selection (CGUFS).
- - CGUFS offers three key improvements: an adaptive strategy for assigning cluster pseudo-labels, a feature grouping method to handle redundancy, and an adaptive filtering strategy to retain the most relevant features.
- - Experimental results demonstrate that CGUFS outperforms existing algorithms, achieving higher accuracy rates (74.37% for C4.5 and significantly improved results for the Adaboost classifier) in selecting optimal features.
Article Synopsis
- Cancer diagnosis using machine learning, especially with Support Vector Machines (SVM), can struggle due to the complexity and redundancy in gene expression data, leading to poor classification results.
- This paper introduces a hybrid feature selection algorithm called IG-GPSO that effectively ranks and groups features based on their information gain, enabling better data organization for the SVM.
- Experimental findings reveal that IG-GPSO enhances SVM's accuracy to 98.50%, outperforming traditional feature selection methods and demonstrating superior classification performance compared to KNN algorithms.
A Synthetic Minority Oversampling Technique Based on Gaussian Mixture Model Filtering for Imbalanced Data Classification.
IEEE Trans Neural Netw Learn Syst
March 2024
Data imbalance is a common phenomenon in machine learning. In the imbalanced data classification, minority samples are far less than majority samples, which makes it difficult for minority to be effectively learned by classifiers. A synthetic minority oversampling technique (SMOTE) improves the sensitivity of classifiers to minority by synthesizing minority samples without repetition.
View Article and Find Full Text PDFThe problem of imbalanced data classification often exists in medical diagnosis. Traditional classification algorithms usually assume that the number of samples in each class is similar and their misclassification cost during training is equal. However, the misclassification cost of patient samples is higher than that of healthy person samples.
View Article and Find Full Text PDFFrom the perspective of clinical decision-making in a Medical IoT-based healthcare system, achieving effective and efficient analysis of long-term health data for supporting wise clinical decision-making is an extremely important objective, but determining how to effectively deal with the multi-dimensionality and high volume of generated data obtained from Medical IoT-based healthcare systems is an issue of increasing importance in IoT healthcare data exploration and management. A novel classifier or predicator equipped with a good feature selection function contributes effectively to classification and prediction performance. This paper proposes a novel bagging C4.
View Article and Find Full Text PDF