Optimized Tree Strategy with Principal Component Analysis Using Feature Selection-Based Classification for Newborn Infant's Jaundice Symptoms
- Title
- Optimized Tree Strategy with Principal Component Analysis Using Feature Selection-Based Classification for Newborn Infant's Jaundice Symptoms
- Creator
- Samanta D.; Karthikeyan M.P.; Karuppiah M.; Parwani D.; Maheshwari M.; Shukla P.K.; Nuagah S.J.
- Description
- One of the most important and difficult research fields is newborn jaundice grading. The mitotic count is an important component in determining the severity of newborn jaundice. The use of principal component analysis (PCA) feature selection and an optimal tree strategy classifier to produce automatic mitotic detection in histopathology images and grading is given. This study makes use of real-time and benchmark datasets, as well as specific approaches for detecting jaundice in newborn newborns. According to research, the quality of the feature may have a negative impact on categorization performance. Additionally, compressing the classification method for exclusive main properties can result in a classification performance bottleneck. As a result, identifying appropriate characteristics for training the classifier is required. By combining a feature selection method with a classification model, this is possible. The major outcomes of this study revealed that image processing techniques are critical for predicting neonatal hyperbilirubinemia. Image processing is a method of translating analogue images to digital formats and manipulating them. The primary goal of medical image processing is to collect information useful for disease detection, diagnosis, monitoring, and therapy. Image datasets can be used to validate the performance of newborn jaundice detection. When compared to conventional approaches, it offers results that are accurate, quick, and time efficient. Accuracy, sensitivity, and specificity, which are common performance indicators, were also predictive. 2021 Debabrata Samanta et al.
- Source
- Journal of Healthcare Engineering, Vol-2021
- Date
- 2021-01-01
- Publisher
- Hindawi Limited
- Coverage
- Samanta D., Department of Computer Science, CHRIST Deemed to Be University, Bangalore, India; Karthikeyan M.P., Department of Computer Science, PPG College of Arts and Science, Coimbatore, India; Karuppiah M., Department of Computer Science and Engineering, SRM Institute of Science and Technology, Delhi-NCR Campus, Uttar Pradesh, Ghaziabad, 201204, India; Parwani D., Sant Hirdaram Girls College Bhopal, Madhya Pradesh, Bhopal, India; Maheshwari M., Department of Computer Application, MCNUJC, Madhya Pradesh, Bhopal, India; Shukla P.K., Computer Science and Engineering Department, University Institute of Technology Rajiv Gandhi Proudyogiki Vishwavidyalaya, Technological University of Madhya Pradesh, Bhopal, 462033, India; Nuagah S.J., Department of Electrical Engineering, Tamale Technical University, Tamale, Ghana
- Rights
- All Open Access; Gold Open Access; Green Open Access
- Relation
- ISSN: 20402295; PubMed ID: 34858565
- Format
- Online
- Language
- English
- Type
- Article
Collection
Citation
Samanta D.; Karthikeyan M.P.; Karuppiah M.; Parwani D.; Maheshwari M.; Shukla P.K.; Nuagah S.J., “Optimized Tree Strategy with Principal Component Analysis Using Feature Selection-Based Classification for Newborn Infant's Jaundice Symptoms,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 24, 2025, https://archives.christuniversity.in/items/show/15927.