Dimensionality reduction for Images of IoT using Machine Learning

Abstract

Abstract Sensors, wearables, mobiles, and other Internet of Things (IoT) devices are becoming increasingly integrated into all aspects of our lives. They are capable of gathering enormous amounts of data (for example, image data) which can then be sent to the cloud for processing. However, this results in an increase in network traffic and latencies. In order to overcome these difficulties, edge computing has been proposed as a paradigm for computing that brings processing closer to the location where data is produced. This paper includes merging cloud and edge computing for IoT and investigates approaches using machine learning for dimensionality reduction of images on the edge, using the Autoencoder deep learning-based approach and Principal component analysis (PCA). Then the encoded data is sent to the cloud server, where it is used directly for any machine learning task without having a significant impact on the accuracy of the data processed on the cloud. The proposed approach has been evaluated on an object detection task using a set of 4,000 images randomly chosen from three datasets: COCO, human detection, and HDA datasets. Results show that 77% of data reduction did not have a significant impact on the object detection task accuracy.