Online ISSN: 2515-8260

Keywords : linear regression


Panjala Sravani, V. Rama Krishna

European Journal of Molecular & Clinical Medicine, 2023, Volume 10, Issue 3, Pages 1081-1089

ML-based simulations have been shown to be helpful in predicting intraoperative outcomes in order to enhance judgment on the course of action. ML strategies are being used in this research to predict future COVID cases, and they are being evaluated to identify whichever algorithm is most appropriate for the COVID sample. This research confirms how ML algorithms can anticipate the proportion of upcoming Covid-19 individuals who will be harmed. Forecasting models such as LR, Random Forest, SVR, KNN, DT, and Elastic net were used to make the projections. For the upcoming 10 days, the number of newly infected cases is predicted by each model. The consequences display that the Decision Tree achieves top amongst those simulations, trailed by Linear Regression and K-NN, which are good at predicting new confirmed cases. Whereas SVR performs worst among those models using the dataset that is currently available.


Soumya sri. S; Yuvaraj Babu. K

European Journal of Molecular & Clinical Medicine, 2022, Volume 9, Issue 8, Pages 340-347

INTRODUCTION : Stature estimation is taken as an important framework in person identification and also in forensic examinations. Human ears are always an important determining feature of the face and its construction demonstrates various signs of age and sex
AIM : Aim of the present study was to  estimate stature using measurements of external ear in females.
MATERIALS AND METHODS: This study was done among 50 females students studying Dental in a college, within the age group 18 to 20 years. the measurements of both external ears and also the height of subjects was measured. The data collected was  tabulated and statistically analysed using SPSS software (version 23) and a linear regression equation was calculated using the data.
RESULT: The linear regression equation was calculated using the formula y = a+bx to be, For Female Right ear, height (y)   = 120.33 + 4.39 X1; Right ear, breadth(y)  =  120.33 + 5.41 X2 The (r) value was 0.532, it had moderate correlation. For Female Left ear, height (y)   =   120.08 + 3.96 X1;   Left ear breadth (y)   =   120.08 + 6.35 X2. The ‘r’ value was 0.559, it had moderate correlation.
CONCLUSION : The present study concludes that there was moderate correlation among females between stature and ear measurements, it was found to be statistically significant hence, ear measurements can be used at moderate level to estimate stature in females.

Performance Study of ML Models and Neural Networks for Detection of Parkinson Disease using Dysarthria Symptoms

Harisudha Kuresan; Dhanalakshmi Samiappan; Arathy Jeevan; Sukirti Gupta

European Journal of Molecular & Clinical Medicine, 2021, Volume 8, Issue 3, Pages 767-779

Parkinson Disease (PD) is brain disorder that affects the central nervous system
that results in damage of nerve cells causing dopamine to drop. PD has a severe effect on
vocal features termed as Dysarthria symptoms including varied pitch, extended pauses,
monotonous and speaking slowly or with a slur. In this paper, a dataset containing various
vocal features are taken as input to analyze the performance of various Machine Learning
algorithms including Naive Bayes, Random Forest Classifier, Support Vector Machines
(SVM), Linear Regression, K Nearest Neighbor (KNN) and Neural Networks such as ANN
and LSTM. The best classification accuracy was obtained by ANN around 90.00%.

Movie Prior Release Box Office Prediction A Machine Learning Based Approach

V. Gangadhara Reddy; K. Radheer Reddy; A. Krishnamoorthy; R. Kannadasan; P. Boominathan

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 2, Pages 5016-528

The “Movie Box Office Prediction” includes different factors that influence the movie revenue at the Box Office. Some of the factors include Budget, Genres, Spoken languages, Cast, Crew. In this paper, various plots are made in order to understand and observe the relations between the variables and the amount of effect of factors on the Revenue. Linear Regression, Random Forest and XGBoost are the models used for Training and Testing the Data.