Activity Recognition using Accelerometer Sensor and Machine Learning Classifiers
Development affirmation is considered as a huge endeavor in various applications, particularly in clinical consideration organizations. Among these applications consolidate clinical decisive, seeing of customers' consistently timetable and ID of unusual cases. Here we present an approach for the development affirmation using an accelerometer sensor embedded in a mobile phone. This strategy uses a transparently available accelerometer dataset as the unrefined information signal. The features of the sign are picked subject to the time and repeat space. By then, Principal Component Analysis (PCA) is used to diminish the dimensionality of the features and concentrate the primary ones that can describe human activities. An assessment collaboration is performed between the primary unrefined data and PCA-based features and moreover, time and repeat region features are similarly contemplated using a couple of AI classifiers. The got results show that the PCA-based features get higher affirmation rate while repeat region features have higher exactness, with the speed of 96.11% and 92.10% independently.