• Anupriya Hamilton
• Prof. Sugan Patel

In this research work present a hybrid model that is combination of linear regression model and cascaded feed forward network with back propagation training. The detection of the diabetic type 2 patient shows better accuracy as compare to other previous methods. In the different previous method analysis got the drawbacks of previous method that is over come in the proposed method that is shown in the result discussion. The outcome proposed method shown that can be detected with an awfully high accuracy, up to 96.54 % in the different diabetic patient datasets. The proposed method also shows lower complexity and better timing due to regression model soft threshold values. In the proposed hybrid model is the combination of CFFNN and Linear Regression method. Cascade-forward networks are similar to feed-forward networks, but include a connection from the input and every previous layer to following layers. As with feed-forward networks, a two-or more layer cascade network can learn any finite input-output relationship arbitrarily well given enough hidden neurons. For greater accuracy on low-dimensional through medium-dimensional data sets, fit a linear regression model. There are major parts of proposed work that is describe in this thesis work. The accuracy of the proposed methods comparison of different methods such as Discrim, MLP, Logdisc, SMART, Bayesnet, Naive bay, Random Forent, J48, SGD, SMO, Backiprop, RBF, LMT nad proposed hybrid model shows better outcome as compare to other previous methods, that is shown in simulation and result.

Diabetic Type 2, Cascaded Feed Forward Network, Linear Regression, Machine Learning Processes, Random Forent And Accuracy

" A MACHINE LEARNING APPROACH FOR DIABETICS PATIENT DETECTION USING ENHANCED ANN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 11, page no.a547-a556, November-2021, Available :http://www.jetir.org/papers/JETIR2111071.pdf

" A MACHINE LEARNING APPROACH FOR DIABETICS PATIENT DETECTION USING ENHANCED ANN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 11, page no. ppa547-a556, November-2021, Available at : http://www.jetir.org/papers/JETIR2111071.pdf