Affiliations: [a] Department of Electronics and Communication Engineering, C. Abdul Hakeem College of Engineering and Technology, Hakeem Nagar, Melvisharam, Ranipet, TamilNadu, India
| [b] Department of Electronics and Communication Engineering, Sri Sivasubramaniya Nadar College of Engineering, Kalavakkam, Chennai, TamilNadu, India
Correspondence:
[*]
Corresponding author. B.A. Mohammed Hashim, Department of Electronics and Communication Engineering, C. Abdul Hakeem College of Engineering and Technology, Hakeem Nagar, Melvisharam, Ranipet, TamilNadu, India. E-mails: [email protected]; [email protected].
Abstract: Human Activity Recognition (HAR) is the most popular research area in the pervasive computing field in recent years. Sensor data plays a vital role in identifying several human actions. Convolutional Neural Networks (CNNs) have now become the most recent technique in the computer vision phenomenon, but still, it is premature to use CNN for sensor data, particularly in ubiquitous and wearable computing.Deep CNN requires huge dataset and models which increases the computational complexity. Transfer learning that uses the pre trained CNNwith fine tuning is the better alternative to reduce the training cost.In this paper, we have proposed the idea of transforming the raw accelerometer and gyroscope sensor data to the visual domain by using our novel activity image creation method (NAICM). Pre-trained CNN (AlexNet) has been used on the converted image domain information. The proposed method is evaluated on several online available human activity recognition dataset. The results show that the proposed novel activity image creation method (NAICM) has successfully created the activity images with a classification accuracy of 98.36% using pre trained CNN.
Keywords: Human activity recognition, CNN, pervasive computing, NAICM, transfer learning
