I started my PhD from 2013 under Nirmalya Roy in the Mobile and Pervasive Sensing Group (MPSC) in the Information Systems Department at University of Maryland Baltimore County (UMBC). My research area is Energy Analytics and Pervasive Computing.
Nilavra Pathak
ITE 415,1000 Hilltop Circle,
UMBC, MD 21250 US
(+1)443-254-4828
nilavra1[at]umbc[dot]edu
PhD. Degree in Information Systems• August 2013 - onwards
My PhD is centered around energy analytics, big data analytics, signal processing and pervasive computing. My core focus is on Non-Intrusive Load Monitoring using signal processing and machine learning and optimization techniques.
M.E. Degree in Computer Science• 2011 - 2013
My Masters of Engineering in Computer Science in Jadavpur University was mostly inclined towards Machine Learning Applications and my Thesis was on Ensemble Clustering Techniques.
B. Tech in Computer Science• 2007-2011
I graduated from St Thomas' College of Engineering & Technology under West Bengal University and Technology in 2011.
Nirmalya Roy, Nilavra Pathak, and Archan Misra. “AARPA: Combining Mobile and Power-line Sensing for Fine-grained Appliance Usage and Energy Monitoring”, in Proceedings of the IEEE International Conference on Mobile Data Management (MDM), June 2015.
Roy, Nirmalya, Nilavra Pathak, and Archan Misra. "Fine-grained appliance usage and energy monitoring through mobile and power-line sensing." Pervasive and Mobile Computing 30 (2016): 132-150.
Nilavra Pathak, Md. Abdullah Al Hafiz Khan, and Nirmalya Roy. “Acoustic based appliance state identifications for fine grained energy analytics”, in Proceedings of the IEEE International Conference on Pervasive Computing and Communications (PerCom), March 2015. [acceptance rate: 15%]
Md. Abdullah Al Hafiz Khan, Sheung Lu, Nirmalya Roy, and Nilavra Pathak. “Demo Abstract: A Microphone Sensor based System for Green Building Applications”, in Proceedings of the IEEE International Conference on Pervasive Computing and Communications Demonstrations (PerCom, March 2015.
Mohammad Arif Ul Alam, Nilavra Pathak, Nirmalya Roy, “Mobeacon: An iBeacon-Assisted smart-phone-Based Real Time Activity Recognition Framework”, 12th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Mobiquitous 2015, Coimbra, Portugal
Nilavra Pathak, Nirmalya Roy and Animikh Biswas, " Iterative Signal Separation Assisted Energy Disaggregation ", in Proceedings of the sixth International Green and Sustainable Computing Conference (IGSC, December 2015).
David Lachut, Nilavra Pathak, Nilanjan Banerjee, Nirmalya Roy, Ryan Robucci, Longitudinal Energy Waste Detection with Visualization. Buildsys 2017.
Nilavra Pathak, James Foulds, Nirmalya Roy, Nilanjan Banerjee and Ryan Robucci. “Estimating Buildings’ Parameters over Time Including Prior Knowledge”. (Pre-print under submission in ACM E-Energy 2019. https://arxiv.org/pdf/1901.07469.pdfArXiv)
Nilavra Pathak, David Lachut, Nirmalya Roy, Nilanjan Banerjee and Ryan Robucci, Non-Intrusive Air Leakage Detection in Residential Homes, ICDCN 2018.
Nilavra Pathak. PhD Forum: Scalable Energy Disaggregation: Data, Dimension and Beyond. IEEE SmartComp, 2018.
Nilavra Pathak, Amadou Ba, Joern Ploennigs, and Nirmalya Roy. “A Study of Multivariate TimeSeries Forecasting for Non-Residential Gas Consumption”. (Under Review Pervasive and Mobile Computing)
Nilavra Pathak, Amadou Ba, Joern Ploennigs, and Nirmalya Roy. “Forecasting gas usage for big buildings using generalized additive models and deep learning.” IEEE SmartComp, 2018.
Being in MPSC its never enough to have focus towards only one area. My research interests are as follows sorted in the order of interest. The listed ones are the primary interests although it keeps growing with the passing of days.
To promote energy-efficient operations in residential and office buildings, non-intrusive load monitoring (NILM) techniques have been proposed to infer the fine-grained power consumption and usage patterns of appliances from powerline measurement data. Fine-grained monitoring of everyday appliances (such as toasters and coffee makers) can not only promote energy-efficient building operations, but also provide unique insights into the context and activities of individuals. Current building-level NILM techniques are unable to identify the consumption characteristics of relatively low-load appliances, whereas smart-plug based solutions incur significant deployment and maintenance costs. In this project, we investigate an intermediate architecture, where smart circuit breakers provide measurements of aggregate power consumption at room (or section) level granularity. We then investigate techniques to identify the usage and energy consumption of individual appliances from such measurements.
Context Aware Energy Analytics
Fine-grained monitoring of everyday appliances can provide better feedback to the consumers and motivate them to change behavior in order to reduce their energy usage. It also helps to detect abnormal power consumption events, long-term appliance malfunctions and potential safety concerns. Commercially available plug meters can be used for individual appliance monitoring but for an entire house, each such individual plug meters are expensive and tedious to setup. Alternative methods relying on Non-Intrusive Load Monitoring techniques help disaggregate electricity consumption data and learn about the individual appliance’s power states and signatures. However fine-grained events (e.g., appliance malfunctions, abnormal power consumption, etc.) remain undetected and thus inferred contexts (such as safety hazards etc.) become invisible. In this project, we correlate an appliance’s inherent acoustic noise with its energy consumption pattern individually and in presence of multiple appliances. Our approach helps to improve the performance of energy disaggregation algorithms and provide critical insights on appliance longevity, abnormal power consumption, consumer behavior and their everyday lifestyle activities.
Branding, Web Development
Energy Disaggregation gives the itemized energy consumption of the appliances. Research suggested that the itemized energy consumption might help reduce 15% of total residential energy consumption. Most of the commercially available energy analytic systems are intrusive and expensive. In the US about 33 million smart meters have been deployed which gives us huge amount of data. Even if we narrow our scope to a city the number of houses are above 500000 and the utility providers only provide feedback about the cumulative monthly consumption and some comparative analytic with neighbors' total consumption. In these cases itemized consumption and comparative analytic will prove more helpful. Our objective is to look for a scalable disaggregation algorithm for big data. The underlying assumption is appliances might have similar energy patterns and we can learn those characteristics from a set of appliances and transfer the knowledge for discovering the energy patterns in a larger set.
Branding
