Abstract
Internet of things (IoT) which is the invasion in the present era led to the emergence of various wearable devices which are known as smart wearable to monitor or measure different health attributes based on the activities. Today, wearable technology is constantly expanding in the market as it is highly in demand from the year 2010. Since then around 400 wearable have been developed, and 60% of them are activity trackers. Now, activity recognition is a promising research field, originated from ubiquitous, context-aware computing as well as multimedia. In recent times, recognizing daily activities is also part of the challenges for pervasive computing. Wearable devices are equipped with various sensors such as humidity sensor, gyroscope, accelerometer, and biosensors, for self-monitoring of routine physical actions. In this paper with the help of Python language, we analysed wearable devices data set which are positioned on chest in terms of wearable single chest-mounted uncalibrated accelerometer data sets collected from fifteen candidates separately performing seven different activities such as Working at Computer, Standing Up, Walking and Going up/downstairs, Standing*, Walking, Going Up/Downstairs, Walking and Talking with Someone Talking while Standing. These activities pattern analyses are helpful in measuring numerous health outcomes.