Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring (NILM)

Today, I learnt that my journal paper was accepted for publication in IEEE Transactions on Smart Grid (TSG) wich has an impact factor of 4.25. Co-authors were Fred Popowich, Ivan V. Bajic, Bob Gill, and Lyn Bartram. This paper is an expansion of my PhD thesis which and discusses an improved HMM-based NILM algorithm. Here is… Read More

Appliance Water Disaggregation via Non-Intrusive Load Monitoring (NILM)

Last week, I learnt that a paper Bradley Ellert, myself, and Fred Popowich wrote was accepted for presentation at the EAI International Conference on Big Data and Analytics for Smart Cities in Toronto October 13 to 14. Here is the abstract: The world’s fresh water supply is rapidly dwindling. Informing homeowners of their water use patterns can… Read More

Mixed-Initiative for Big Data: The Intersection of Human + Visual Analytics + Prediction

This week I learnt that a paper I and my co-authors (Daniel McVeigh, Wolfgang Stuerzlinger, Khoa Tran, Fred Popowich) submitted to Hawaii International Conference on System Sciences (HICSS-49) was accepted to presentation. This survey forms a large part of the research during 2015 as a postdoc in Computing Science at SFU. Here is the paper abstract:… Read More

Leveraging Submetered Electricity Loads to Disaggregate Household Water-Use

It is with great excitement to announce that Bradley Ellert successfully defended his Masters thesis on water disaggregation (NILM) last week. Titled Leveraging Submetered Electricity Loads to Disaggregate Household Water-Use, his thesis is now online for downloading. I helped mentor Bradley and provided advice for him on NILM and AMPds. I am very proud of the work he… Read More

Earlier 2010 House Dataset on Harvard Dataverse

Last night I stumbled upon Harvard Dataverse. I decided to sign up and upload one of my early datasets. This dataset 2010 ZigBee Sensor Data Collected From a House (in Vancouver, Canada) Dataset contains power meter, ambient light, and ambient temperature sensors readings; including weather and daylight data. Sensor readings are at 15 minute intervals for about 8… Read More

The 2nd EU NILM Workshop

I will be attending the next EU NILM Workshop happening this July 8 at Imperial College London. I have been invited to be one of the technical speakers. I am excited to talk about what I and my research assistants have been doing in the NILM field (socioeconomic, water/gas NILM, AMPds R3, and other things). The day… Read More