Human activity recognition using smart phone for physical activity analysis
M. M. Sardeshmukh, Midhun Chakkaravarthy, Sagar Bhilaji Shinde, Divya Midhun Chakkaravarthy · Multidisciplinary Science Journal · 2024
Human Activity Recognition (HAR) is an active research area that is useful in many applications, such as elderly people monitoring, health parameter analysis, fall detection, video surveillance, etc. There are many challenges in HAR, such as generalized feature extraction, varying background and illumination, etc. The sensor based and image based are two major approaches in HAR. Image based is complex and can be used in the monitoring area only.The sensor based appraches are not user friendly as an individuals need to wear the sensors on the body which is not comfortable. The use of smart phones for HAR is increasing due to advancements in machine learning algorithms. We have proposed a convolutional neural network model for the classification of activities of daily leaving (ADLs) performed by 30 individuals carrying a smartphone. The model consists of two and three dense layers, respectively. We trained the model using 7352 unique samples from the database. We obtained the highest accuracy of 95.02% when testing the result on 2947 samples with 15 epochs. The accuracy and loss plotted is shown in fig 5 a to d which indicates the proper traing of the model. The model is neither overfitted nor underfitted. The hyper-parameter tuning helped in increasing the accuracy. The classification of the physical activities can be and useful inferences can be obtained by analyzing the activities and its time. This will useful in generating the health related alerts to an individual for the activities.