This book discusses various machine learning applications and models, developed using heterogeneous data, which helps in a comprehensive prediction, optimization, association analysis, cluster analysis and classification-related applications for various activities in urban area. It details multiple types of data generating from urban activities and suitability of various machine learning algorithms for handling urban data. The book is helpful for researchers, academicians, faculties, scientists and geospatial industry professionals for their research work and sets new ideas in the field of urban computing.

Autorentext

Dr. Mainak Bandyopadhyay did his Ph.D. in GIS and Remote Sensing from MNNIT Allahabad, Prayagraj, in 2018 after his M.Tech. from MNNIT Allahabad, Prayagraj, in 2012. He is currently working as Assistant Professor, School of Computer Engineering, KIIT Deemed to be University. He has a total of 3 years of teaching experience. His area of interest includes machine learning, urban computing and spatial algorithms. He has published a total of 10 research papers in various journals and international conferences. He is the reviewer of International Journal of Applied Geospatial Research (IGI Global), Arabian Journal of Geoscience (Springer), International Journal of Knowledge and Systems Science (IGI Global) and Process Safety and Environmental Protection Journal (Elsevier).

Dr. Minakhi Rout is currently working as Assistant Professor in the School of Computer Engineering, KIIT Deemed to be University. She has received M.Tech. and Ph.D. degree in Computer Science & Engineering from Siksha 'O' Anusandhan University, Odisha, India, in 2009 and 2015, respectively. She has more than 14 years of teaching and research experience in many reputed institutes. Her research interests include computational finance, data mining and machine learning. She has published more than 30 research papers in various reputed journals and international conferences as well as guided several M.Tech. and Ph.D. thesis. She is Editorial Member of Turkish Journal of Forecasting.

Dr. Suresh Chandra Satapathy did his Ph.D. in Computer Science and Engineering from JNTU, Hyderabad, after completing his M.Tech. from NIT Rourkela. He is currently working as Professor, School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, Odisha. He is also Dean of Research for Computer Engineering at KIIT Deemed to be University. He has over 30 years of teaching and research experience. He is Life Member of CSI and Senior Member of IEEE. He has been instrumental in organizing more than 59 international conferences in India and abroad as Organizing Chair and Corresponding Editor over more than 47 Book Volumes from Springer LNCS, AISC, LNEE and SIST Series. He is quite active in research in the areas of warm intelligence, machine learning and data mining. More than 70 PG projects are supervised by him. Currently, 8 scholars are pursuing Ph.D. under him. His first Ph.D. Scholar got her Ph.D. degree with GOLD medal from her University for the outstanding work done by her in the areas of warm intelligence optimization. He has over 150 research articles in various journals with SCI impact factors and SCOPUS index and also in conference proceedings of Springer, IEEE, etc. He is in Editorial Board of IGI Global, Inderscience, Growing Science journals, Springer AJSE, etc. He is the developer of a new evolutionary optimization technique called SGO and SELO. He was the recipient of Leadership in Academic award by ASSOCHEM in the year 2017.

Inhalt

Urbanization: Pattern, Effects and Modelling.- Extraction of Information from Hyperspectral Imaging using Deep Learning.- Vehicle Detection and count in the captured Stream Video using Machine Learning.- Dimensionality Reduction and Classification in Hyperspectral Images using Deep Learning.- Machine learning and deep learning algorithms in the diagnosis of chronic diseases.- Security Enhancement of Contact less Tachometer Based Cyber Physical System.- Optimization of Loss Function on Human Faces Using Generative Adversarial Networks.