Krishan Kumar

Krishan Kumar

Auto-generated profile, based on publicly available information

Krishan Kumar

Department of Computer Science Guru Nanak Dev Engineering College Ludhiana Punjab India

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 December 2024 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
KKKrishan Kumar
Krishan Kumar
KJKiran Jyoti
Kiran Jyoti
Uncontrolled fast cell growth causes brain tumors, posing a significant threat to global health and leading to millions of deaths annually. Early cancer detection is crucial to save lives. The purpose of this study is to investigates the capability of machine learning algorithms and feature extraction methods to detection and classification of brain tumors. We implemented six machine learning algorithms and three features extraction methods, including Image Loading, HOG, and LBP. The objective of this study is to identify best combination of machine learning and features extraction method for brain tumor detection and classification. This study utilized two Brain Tumor MRI Datasets downloaded from Kaggle. Our analysis revealed that Random Forest emerged as the most effective classifier by achieving an accuracy of 99% with image loading feature extraction method based on different metrics, closely followed by SVM and Logistic Regression. However, performance varied with KNN, Naive Bayes, and Decision Tree, highlighting the importance of tailored approaches for optimal classification accuracy. Further optimization and experimentation are crucial for improving algorithm performance in real-world applications of brain tumor classification. A case study with interpretable machine learning is also presented in the paper.

4 November 2024 in Cureus
Verified
Journal Article
Open access
PDF file
AMAnkita Mukul
Ankita Mukul
SSShashi B. Singh
Shashi B. Singh
VSVidya Sagar
Vidya Sagar
DPDilip K. Paswan
Dilip K. Paswan
SNSmiti Narain
Smiti Narain
DKDewesh Kumar
Dewesh Kumar
Introduction Administering the measles vaccine at an appropriate age and dosage in children is important for India to eliminate measles, a potentially deadly vaccine-preventable disease. Similarly, the Japanese encephalitis (JE) vaccine, particularly in endemic regions is important to prevent morbidity and high-case fatality from the disease. The study attempts to evaluate the coverage of measles and JE vaccines and their predictors. Materials and methods A mixed method study design, incorporating a three-stage cluster random sampling process was used in the cross-sectional survey conducted among 604 children aged 2-5 years in the Ormanjhi block of Ranchi, Jharkhand, from April 2023 to June 2024. The parents/caregivers of the eligible children were interviewed using a predesigned, pretested semi-structured questionnaire, and the immunization status of children was taken from vaccination cards. A focused group discussion (FGD) and an in-depth interview (IDI) with healthcare providers formed the qualitative component. We conducted descriptive, and logistic regression analysis using the IBM SPSS Statistics for Windows, Version 26 (Released 2019; IBM Corp., Armonk, New York, United States). The association between the coverage of the vaccine and sociodemographic variables was done using the Chi-square test. Logistic regression was used to study the predictors, and a p-value of <0.05 was considered statistically significant. Results In the household survey, the coverage of the measles-containing vaccine first dose (MCV-1) was 594 (98.3%), while the second dose (MCV-2) was 536 (88.7%) out of 604 participants. For the JE vaccine, the coverage of the first dose (JE-1) was 588 (97.4%), while the second dose (JE-2) coverage was 492 (81.5%). In the multivariate logistic regression, religion and the lack of parental knowledge about measles were significant predictors for lower MCV-2 uptake, while the for JE vaccine, religion, father's education, and household head's occupation remained statistically significant factors (p ≤ 0.05). Vaccine hesitancy had mixed perceptions with the child’s unavailability being the most significant reason for hesitancy in both MCV and JE vaccinations. In the FGD, child’s unavailability at times of vaccination and parent’s fear of side effects post vaccination were major factors for missing doses of the vaccine. Conclusion While the initial coverage of MCV and JE vaccines is commendable, the substantial drop in the second dose coverage and the delays in administration present significant challenges.