• Gudiwaka vijayalakshmi
• Rongala Rajesh

ABSTRACT The rapid rise in the prevalence of obesity and an unhealthy lifestyle eventually reflects the incidence and frequency of liver-related disorders in the general population In this effort, patient data sets are analysed for their predictability of having a liver disease based solely on a widely studied classification model Because pre-existing processes for analysing patient and classifier data exist, the more significant aspect here is to forecast the same decisive outcome with a better rate of accuracy This procedure is divided into five main stages To begin, the min-max algorithm is applied to the original liver patient data set obtained from the UCI repository Using PSO feature selection, key properties are delineated in the second step In the third phase, classification algorithms are used for comparative analysis and categorization The fourth phase is the accuracy calculation It makes use of the Root Mean Square Value and the Root Error Value The fifth and final phase is the evaluation phase With an accuracy rate of 95.04%, the CNN algorithm is considered to be a superior performing algorithm when it comes to feature selection.

Obesity,Liverdisease,Patient datasets,classification model,PSO featureselection, cRoot Mean Square, Root Error Value,

"ANALYSIS AND PREDICTION OF LIVER DISEASE USING CNN AND KNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.j364-j372, June-2023, Available :http://www.jetir.org/papers/JETIR2306950.pdf

"ANALYSIS AND PREDICTION OF LIVER DISEASE USING CNN AND KNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. ppj364-j372, June-2023, Available at : http://www.jetir.org/papers/JETIR2306950.pdf