Feature selection from high dimensional data based on iterative qualitative mutual information

Nagpal, Arpita; Singh, Vijendra

doi:10.3233/jifs-181665

Cited by 10 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KNN [ 35 ] is a classification algorithm in supervised learning and also a lazy learning algorithm. The algorithm has the advantages of simple use, rapid calculation, and good predictive effects.…”

Section: Methodsmentioning

confidence: 99%

“…The stacking ensemble algorithm took into account the learning ability of the primary classifier and metaclassifier, so that the final classification performance was significantly improved [32][33][34]. [35] is a classification algorithm in supervised learning and also a lazy learning algorithm. The algorithm has the advantages of simple use, rapid calculation, and good predictive effects.…”

Section: Stacking Ensemble Learningmentioning

confidence: 99%

See 1 more Smart Citation

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Xiong

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Ensemble learning combines multiple learners to perform combinatorial learning, which has advantages of good flexibility and higher generalization performance. To achieve higher quality cancer classification, in this study, the fast correlation-based feature selection (FCBF) method was used to preprocess the data to eliminate irrelevant and redundant features. Then, the classification was carried out in the stacking ensemble learner. A library for support vector machine (LIBSVM), K -nearest neighbor (KNN), decision tree C4.5 (C4.5), and random forest (RF) were used as the primary learners of the stacking ensemble. Given the imbalanced characteristics of cancer gene expression data, the embedding cost-sensitive naive Bayes was used as the metalearner of the stacking ensemble, which was represented as CSNB stacking. The proposed CSNB stacking method was applied to nine cancer datasets to further verify the classification performance of the model. Compared with other classification methods, such as single classifier algorithms and ensemble algorithms, the experimental results showed the effectiveness and robustness of the proposed method in processing different types of cancer data. This method may therefore help guide cancer diagnosis and research.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Stacking Ensemble Learningmentioning

confidence: 99%

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Xiong

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…It also has the greatest influence on the prognostication model. The CFS built on BFS selects the fewest possible features on its own [16] [17] [18] [19]. To reduce the genes further with a motive to find biomarker genes, Consistency-BFS is beneficial.…”

Section: Grade Typesmentioning

confidence: 99%

Two-Stage Gene Selection Technique For Identifying Significant Prognosis Biomarkers In Breast Cancer

Lamba,

Munjal,

Gigras

2024

IJCDS

View full text Add to dashboard Cite

One crucial stage in the data preparation procedure for breast cancer classification involves extracting a selection of meaningful genes from microarray gene expression data. This stage is crucial because it discovers genes whose expression patterns can differentiate between different types or stages of breast cancer. Two highly effective algorithms, CONSISTENCY-BFS and CFS-BFS, have been developed for gene selection. These algorithms are designed to identify the genes that are most crucial in distinguishing between different types and stages of breast cancer by analysing large volumes of genetic data. A noteworthy advancement is a refined 2-Stage Gene Selection technique specifically designed for predicting subtypes in breast cancer. The initial phase of the 2-Stage Gene Selection (GeS) approach relies on the CFS-BFS algorithm, which plays a crucial role in effectively eliminating unnecessary, distracting, and redundant genes. The initial filtering process plays a crucial role in simplifying the dataset and identifying the genes that have the highest potential to shed light on the category of breast cancer. The CONSISTENCY-BFS algorithm guarantees that only the most pertinent genes are retained by further refining the gene selection process. This stage is essential for eliminating any remaining uncertainty and enhancing the overall efficiency of the algorithm. This innovative approach represents a significant advancement in the field of bioinformatics as it offers a more accurate and targeted method for selecting genes based on their relevance to breast cancer classification. When the 2-Stage GeS is constructed using Hidden Weight Naive Bayes, remarkably, it yields more precise and dependable outcomes. The indicators that demonstrate positive outcomes encompass recollection, accuracy, f-score, and fallout rankings. The Kaplan-Meier Survival Model was employed to further validate the top four genes, namely E2F3, PSMC3IP, GINS1, and PLAGL2. Presumably, precision therapy will specifically focus on targeting the genes E2F3 and GINS1.

show abstract

“…152 of July 27, 2006 "On Personal Data". The underlying distributed architecture can be implemented in case of compliance with information security requirements, in particular, the use of certified cryptographic tools (Nagpal & Singh, 2019).…”

Section: Automation Of the Study-practical Usementioning

confidence: 99%

Automation of intraoperative analysis of indicators the inflammatory response of neurosurgical patients undergoing brain tumors removal

et al. 2021

View full text Add to dashboard Cite

The data of the study of indicators of the inflammatory response, hormonal status, biochemical blood parameters in the perioperative period in neurosurgical patients undergoing surgery for tumors of the posterior cranial fossa are presented. This study included 65 patients. The surgery was performed under anesthesia with fentanyl (3-5 µg / kg-hour), clonidine (1-2 µg / kg-hour), and propofol (3-5 mg / kg-hour). A significant increase in the level of interleukin 10 was observed at the level of hemostasis. The day after surgery, the level of Interleukin 6 increased significantly. During hemostasis, there was a temporary increase in ACTH, cortisol, and prolactin levels. The day after the surgery, rates returned to their original levels. Under conditions of persistent neurovegetative, a sufficient humoral response to surgical trauma was noted.

show abstract

Feature selection from high dimensional data based on iterative qualitative mutual information

Cited by 10 publications

References 32 publications

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Cancer Classification with a Cost-Sensitive Naive Bayes Stacking Ensemble

Two-Stage Gene Selection Technique For Identifying Significant Prognosis Biomarkers In Breast Cancer

Automation of intraoperative analysis of indicators the inflammatory response of neurosurgical patients undergoing brain tumors removal

Contact Info

Product

Resources

About