Graph Laplacian for Heterogeneous Data Clustering in Sensor-Based Internet of Things

Abstract

Traditional clustering algorithms are not suited for the heterogeneous data of the sensor-based Internet of Things. The accuracy of real-time data processing, in such applications, is further compromised because of the noise and missing values in the data. Considering the need for accurate clustering, a graph Laplacian-based heterogeneous data clustering is proposed in this work. Exploiting the correlation structure of the data, weight graphs are used to generate a graph Laplacian matrix to obtain co-related data points. Eigenvalues are further used to obtain distance-based, accurate clusters. The proposed algorithm is validated on five different real-world data sets and is able to outperform most of the existing algorithms. A detailed mathematical analysis followed by extensive simulation on real-world data sets proves the dexterity of the proposed method, as the performance gap, with respect to the state-of-the-art methods, in terms of accuracy and purity is as high as 30%.

KEYWORDS:

• Heterogeneous data
• Iinternet of things
• Machine learning
• Spectral clustering
• Ssensor-Based IoT

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Vishal Krishna Singh

Vishal K Singh received the bachelor's degree in information technology, in 2010, the Master's degree in computer technology and application from National Institute of Technical Teachers' Training and Teachers' Training and Research, Bhopal, India in 2013, and PhD degree in information technology from Indian Institute of Information Technology, Allahabad, India in 2018. He is currently working as an assistant professor in the Department of Computer Science, Indian Institute of Information Technology, Lucknow, India and is the head of Wireless Communications and Analytics Research Lab at IIIT Lucknow. His research interests include compressed sensing, in-network inference, Markov random field, wireless sensor networks, machine learning, Internet of things and data analytics. Corresponding author. Email: [email protected]

Gaurav Tripathi

Gaurav Tripathi received the bachelor's degree in information technology in 2013, the master's degree in computer science and engineering from Sant Longowal Institute of Engineering and Technology, Longowal, India in 2018. He is now pursuing PhD from Indian Institute of Information Technology, Lucknow, India and is associated with Wireless Communications and Analytics Research Lab at IIIT Lucknow. His research interests include machine learning internet of things and data analytics. Email: [email protected]

Aman Ojha

Aman Ojha received the bachelor's degree in information technology in 2016, the master's degree in computer science from Indian Institute of Information Technology, Lucknow, India in 2021. He worked at the Wireless Communications and Analytics Research Lab at Indian Institute of Information Technology, Lucknow and currently is working in Intel, Bengaluru, India. His research interests include machine learning, internet of things and data analytics. Email: [email protected]

Rajat Bhardwaj

Rajat Bhardwaj was born in Meerut, Uttar Pradesh, India. He completed Bachelors of Technology in computer science and engineering and the Master of Science in data science from Lancaster University Lancarter, England. Currently, he is working as a project manager in the H&M Artificial Intelligence department. His area of research and interest include consumer behavior analysis, financial risk modeling, anomaly detection and recommendation systems. Email: [email protected]

Haider Raza

Haider Raza received the bachelor's degree in computer science & engineering from the Integral University, Lucknow India, in 2008, the master's degree in computer engineering from the Manav Rachna International University, Faridabad India, in 2011, and the PhD degree in computer science from the University of Ulster, Derry Londonderry, UK, in 2016. He worked (July 2016 to Nov 2017) as a research officer (data science) in the Farr Institute of Health Informatics Research, Swansea University Medical School, UK. He is currently a senior lecturer in the School of Computer Science and Electronics Engineering, UK. Email: [email protected]