Accurate Human Palm Recognition System in Cybercrime Analysis using Naive Bayes in comparison with Decision Tree

Aim: Main purpose for research work accurately recognizing human palm in cybercrime analysis using Naive Bayes (NB) and Decision Tree (DT) and palm recognition helps to identify a person easily. Materials and Methods: The proposed algorithm is Naive Bayes and the compared algorithm is Decision Tree. Both the algorithms work on human palm recognition for accuracy. Accuracy is analysed for human palm recognition. Naive Bayes is an act of processing technique based on Bayes' theorem. Decision Tree place with the group of guided learning calculations. Dissimilar with machine learning calculations, calculations related to decision trees take care of relapse and grouping issues. Palm recognition is performed by a Naive Bayes with size of sample $(\mathrm{N}=23)$ as well as Decision Tree of sample size $(\mathrm{N}=23)$, G-power takes 80%. Result: Naive Bayes (NB) accuracy is 94.173% along with Decision Tree (DT) of 91.739%. There is a significant contrast among two groups whose significance value 0.215 $(\mathrm{p} > 0.05)$. Conclusion: Naive Bayes (NB) generate better accuracy compared with Decision Tree (DT) in accuracy of human palm recognition in cybercrime analysis.