D. Manivarma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
D. Manivarma has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- A. Akilandeswari
Department of Electronics and Communication Engineering, Saveetha School of Engineering, SIMATS, Chennai, Tamilnadu, India. Pincode:602105
1 shared publication
Latest Publications
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2821 (1)
Performance analysis of vehicle detection using K-nearest neighbors comparing with fuzzy k-modes algorithm
The major goal of this research is to detect automobiles utilizing unique histogram equalization and machine learning techniques, namely the K-Nearest Neighbors’ approach, as opposed to Fuzzy k-modes. The K-Nearest Neighbors algorithm and the Fuzzy k-modes algorithm are the two groupings. With a total sample size of 20, we used the K-Nearest Neighbors algorithm with a sample size of 10 and the Fuzzy k-modes algorithm with a sample size of 10. The samples are estimated with an 80 percent pretest power, a 95 percent confidence interval, and a 0.05 error correction. The K-Nearest Neighbors algorithm has a higher accuracy (93.54%) than the Fuzzy k-modes technique (91.65 percent). 0.035 (p 0.05) is the statistical significance value. The K-Nearest Neighbors technique is much better at increasing novel histogram equalization based on the findings of the comparison. When compared to the Fuzzy k-modes method for traffic detection.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2821 (1)
Open AccessPerformance analysis of vehicle detection using K-nearest neighbors comparing with fuzzy k-modes algorithm
The major goal of this research is to detect automobiles utilizing unique histogram equalization and machine learning techniques, namely the K-Nearest Neighbors’ approach, as opposed to Fuzzy k-modes. The K-Nearest Neighbors algorithm and the Fuzzy k-modes algorithm are the two groupings. With a total sample size of 20, we used the K-Nearest Neighbors algorithm with a sample size of 10 and the Fuzzy k-modes algorithm with a sample size of 10. The samples are estimated with an 80 percent pretest power, a 95 percent confidence interval, and a 0.05 error correction. The K-Nearest Neighbors algorithm has a higher accuracy (93.54%) than the Fuzzy k-modes technique (91.65 percent). 0.035 (p 0.05) is the statistical significance value. The K-Nearest Neighbors technique is much better at increasing novel histogram equalization based on the findings of the comparison. When compared to the Fuzzy k-modes method for traffic detection.