Affiliation:
1. Indian Institute of Technology Indore, Indore, Madhya Pradesh, India
2. Invision AI, Toronto, ON, Canada
Abstract
Internet of Things’ (IoT) deployments are increasingly dependent upon learning algorithms to analyse collected data, draw conclusions, and take decisions. The norm is to deploy such learning algorithms on the cloud and have IoT nodes interact with the cloud. While this is effective, it is rather wasteful in terms of energy expended and temporal latency. In this article, the endeavour is to develop a technique that facilitates classification, an important learning algorithm, within the extremely resource constrained environments of IoT nodes. The approach comprises selecting a small number of representative data points, called prototypes, from a large dataset and deploying these prototypes over IoT nodes. The prototypes are selected in a manner that they appropriately represent the complete dataset and are able to correctly classify new, incoming data. The novelty lies in the manner of prototype selection for a cluster that not only considers the location of datapoints of its own cluster but also that of datapoints in neighboring clusters. The efficacy of the approach is validated using standard datasets and compared with state-of-the-art classification techniques used in constrained environments. A real world deployment of the technique is done over an Arduino Uno-based IoT node and shown to be effective.
Publisher
Association for Computing Machinery (ACM)
Subject
Software,Information Systems,Hardware and Architecture,Computer Science Applications,Computer Networks and Communications
Reference40 articles.
1. Peter Wlodarczak Mustafa Ally and Jeffrey Soar. 2017. Data mining in IoT: Data analysis for a new paradigm on the internet. In Proceedings of the International Conference on Web Intelligence . 1100–1103.
2. A Simulation-driven Methodology for IoT Data Mining Based on Edge Computing
3. Matt Kusner Stephen Tyree Kilian Weinberger and Kunal Agrawal. 2014. Stochastic neighbor compression. In Proceedings of the 31st International Conference on Machine Learning . 622–630.
4. Feng Nan Joseph Wang and Venkatesh Saligrama. 2015. Feature-budgeted random forest. In Proceedings of the 32 nd International Conference on Machine Learning .
5. Song Han Huizi Mao and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. In Proceedings of ICLR .