Online ISSN: 2515-8260

Keywords : Machine learning algorithms


A Study On Covid-19 Data Of India, Andhra Pradesh And Telangana Using Machine Learning Algorithms

K.L.S. Soujanya; Challa Madhavi Latha; N. Sandeep Chaitanya

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 7, Pages 371-380

The epidemic of Covid-19 has created a disastrous situation around the globe. The spread of Covid-19 is drastically increasing day by day. Machine learning is one of the efficient tools to track the outbreak of the disease, forecast the probable confirmed and death cases as well as the fatality rate. This study applies multiple regression analysis which is one of the supervised machine learning algorithms to analyze and forecast the fatality rate. The study was conducted to predict the spread of Covid-19 in areas of Telangana, Andhra Pradesh, and India. R-Square (R2), Mean square error (MSE), Root mean square error (RSME) and Mean absolute error (MAE) are the main measures used to predict the accuracy of the algorithm. The results reveal that the case fatality rate is higher in Telangana compared to Andhra Pradesh and India, and more diseased cases are observed in Andhra Pradesh. The study was conducted with the available data; if sufficient data is available then the more precise predictions could be possible using multiple regression analysis.

Detection of Human Activity Performance Analysis Utilizing Machine Learning Algorithms

Ashish Sharma; Dilip Kumar Sharma

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 82-87

Human Activity detection is a talented region has the capacity to earn the human culture by creating assistive advances so that assist old, incessantly sick and for those with exceptional requirements. Precise movement acknowledgment is testing since human action is mind boggling and profoundly assorted. Writing overview acted approximately that has exposed data mining technique are utilized for grouping of exercises. Data mining methods, Naive Bayes with SVM and KNN with Neural Network are end up by proficient in ordering the accelerometers understanding data. This datasets have huge preparation of occurrence by numerous earnings by values. Building categorisers the group like data is as yet a difficult errand. Arbitrary woodland is known for accomplishing high precision in characterization. Its strength in arranging enormous informational indexes is capable. Present paper projects random forest representation for characterizing/anticipating the way of performance. Present data is pre handled to complete stability. Occurrences by organizing dataset are attracted irregular for n tests, and n choice tree are built. Thus, a random based forest is built for ordering initiates depended accelerometers information esteems. To anticipate unlabeled exercise information, total of n trees is presented. Exploratory investigations are led to consider the action acknowledgment capacity of the representation; the outcomes are contrasted and well known managed order strategies. It is seen that the projected representation hits the other grouping methods in relative examination. The planned grouping representation is constrained to perform movement acknowledgment with regards to weight lifting works out. Human Activity acknowledgment is can be applied to some reality, human-driven issues

Feature Selection of Breast Cancer Data Using Gradient Boosting Techniques of Machine Learning

Anusha Derangula; Prof. SrinivasaReddy Edara; Praveen Kumar Karri

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 2, Pages 3488-3504

Cancer is described as a very alarming disease among humankind. The second main
reason for death among modern women is Breast cancer. It affects the physical, mental, social
lifestyles of the people. It is possible to treat cancer in the early stages. The importance of cancer
cells classification into begnin and malignant has led to many research areas in the medical field.
Medical practitioners were adopting machine learning techniques to detect, classify, and predict the
malignant tumour effectively. The machine learning algorithms yield better results in the diagnosis
of malignant tissue. The learning algorithm performs well with optimal features. The objective of
this paper is to identify optimal features in Wisconsin breast cancer Diagnostic data. The techniques
used for feature selection here are Light Gradient Boosting Model (LGBM), Catboost and Extreme
gradient boosting (XGB). The optimized features were given to the Naive Bayes classifier and got an
accuracy of 96.49%.