Diabetes is one among many chronic diseases. It is the most common disease and lots of peoples are affected by this. There are many things that are liable for diabetes, mainly age, obesity, weakness, sudden weight loss, and many more. Diabetes patients have high risk of diseases like cardiopathy, renal disorder, stroke, nerve damage, eye damage, etc. Detection of the disease isn't very easy and prediction is additionally costlier. In today's situation, hospitals are extremely busy due to COVID-19 pandemic, and it might be revolutionary if one could know if they're at risk of being diabetic without visiting a doctor. But the rise in Artificial Intelligence techniques can be used for disease prognosis. The objective of this study is to develop a model with significant accuracy to diagnose diabetes in patients. Moreover, this paper also presents an effective diabetes prediction model for better classification of diabetes and to enhance the accuracy in diabetes prediction using several machine learning algorithms. Different machine learning algorithms are utilized for early stage diabetes prediction, namely, Logistic Regression, Random Forest Classifier, Support Vector Machine, Decision Trees, K-Nearest Neighbors, Gaussian Process Classifier, AdaBoost Classifier, and Gaussian Naïve Bayes. The performances of these models are measured on respective criteria like Accuracy, Precision, Recall, F-Measure, and Error. For this research work, latest available dataset dated 22nd July, 2020, is being utilized. Latest updated dataset will show comparatively better result.

In today's world, where technology is advancing every single day, new methodologies are being developed, and are brought in everyday use making our lives simpler, faster, safer, and powerful. Similarly, Human Activity Recognition (HAR) is getting more popular with all the revolutions made in the technologies. Sensor Network Technology is used in industrial applications, smart homes and system. A massive amount of data can be obtained from these sensors which are linked to the human body. Recognition of Human Activities using these sensors, and wearable technologies has been actively studied. Behavior Recognition seeks to distinguish one or more people's activities and goals through a collection of observations on the actions and environmental conditions of the person. Health surveillance, aged treatment, and plenty of other domains can be used to automatically understand the behavioral context. An existing dataset consisting of 10 subjects (5 females, 5 males) is being used in the paper, which incorporates both young and old volunteers between 19 and 60 years of old with weights ranging from 55 to 85 kg. The dataset reflects motion data collected when subjects are engaged in 11 separate (static and dynamic) smart home activities: computer usage (1 min), telephone conversation (1 min), vacuum cleaning (1 min), book reading (1 min), TV watching (1 min), ironing (1 min), walking (1 min), exercise (1 min), cooking (1 min), drinking (20 times), hair brushing (1 min) (20 times). Most of the activities are similar because of the multi sensor environment which makes it more difficult. Using three tri axial IMU (inertial measurement unit), Magnetometer, Accelerometer, Gyroscope sensors attached to

No abstract