Comparing the Dementia Patient Monitoring Using Modern Algorithm Through Novel Deep Learning Technique and Transfer Learning

Abstract

The main aim of this study is to monitor and detect the dementia patients using modern algorithms, deep learning technology, and comparing the accuracy rate between the deep learning algorithm and transfer learning. Materials and methods: Samples were collected, deep learning algorithm (N=20), transfer learning (N=20) in accordance to total sample size calculated using clinical.com. The accuracy rate of dementia patients was evaluated by using the novel Deep Learning Algorithm (DPLA) with the standard dataset. Results: Comparison of accuracy rate was done by independent sample T-test using SPSS software. There is a statistically insignificant difference (p>0.05). DPLA(80%) showed better results in comparison with transfer learning (40%). Conclusion: Novel deep learning algorithms appear to give better results than transfer learning to monitor and detect dementia patients.