Fred Popowich

AMPds: A public dataset for load disaggregation and eco-feedback research

A home-based intelligent energy conservation system needs to know what appliances (or loads) are being used in the home and when they are being used in order to provide intelligent feedback or to make intelligent decisions. This analysis task is known as load disaggregation or non-intrusive load monitoring (NILM). The datasets used for NILM research generally contain real power readings, with the data often being too coarse for more sophisticated analysis algorithms, and often covering too short a time period. We present the Almanac of Minutely Power dataset (AMPds) for load disaggregation research; it contains one year of data that includes 11 measurements at one minute intervals for 21 sub-meters. AMPds also includes natural gas and water consumption data. Finally, we use AMPds to present findings from our own load disaggregation algorithm to show that current, rather than real power, is a more effective measure for NILM.

A Smarter Smart Home: Case Studies of Ambient Intelligence

Technological support for sustainable home use lies in more subtle and contextually appropriate interventions that integrate informative models of occupant behavior, provide hybrid levels of automated control, and use ambient sensing for localized decisions.

Question Answering Summarization of Multiple Biomedical Documents

In this paper we introduce a system that automatically summarizes multiple biomedical documents relevant to a question. The system extracts biomedical and general concepts by utilizing concept-level knowledge from domain-specific and domain-independent sources. Semantic role labeling, semantic subgraph-based sentence selection and automatic post-editing are involved in the process of finding the information need. Due to the absence of expert-written summaries of biomedical documents, we propose an approximate evaluation by taking MEDLINE abstracts as expert-written summaries. Evaluation results indicate that our system does help in answering questions and the automatically generated summaries are comparable to abstracts of biomedical articles, as evaluated using the ROUGE measure.

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

Understanding how appliances in a house consume power is important when making intelligent and informed decisions about conserving energy. Appliances can turn ON and OFF either by the actions of occupants or by automatic sensing and actuation (e.g., thermostat). It is also difficult to understand how much a load consumes at any given operational state. Occupants could buy sensors that would help, but this comes at a high financial cost. Power utility companies around the world are now replacing old electro-mechanical meters with digital meters (smart meters) that have enhanced communication capabilities. These smart meters are essentially free sensors that offer an opportunity to use computation to infer what loads are running and how much each load is consuming (i.e., load disaggregation). We present a new load disaggregation algorithm that uses a super-state hidden Markov model and a new Viterbi algorithm variant which preserves dependencies between loads and can disaggregate multi-state loads, all while performing computationally efficient exact inference. Our sparse Viterbi algorithm can efficiently compute sparse matrices with a large number of super-states. Additionally, our disaggregator can run in real-time on an inexpensive embedded processor using low sampling rates.

Adapting a synonym database to specific domains

This paper describes a method for adapting a general purpose synonym database, like WordNet, to a specific domain, where only a subset of the synonymy relations defined in the general database hold. The method adopts an eliminative approach, based on incrementally pruning the original database. The method is based on a preliminary manual pruning phase and an algorithm for automatically pruning the database. This method has been implemented and used for an Information Retrieval system in the aviation domain.

Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014.

With the cost of consuming resources increasing (both economically and ecologically), homeowners need to find ways to curb consumption. The Almanac of Minutely Power dataset Version 2 (AMPds2) has been released to help computational sustainability researchers, power and energy engineers, building scientists and technologists, utility companies, and eco-feedback researchers test their models, systems, algorithms, or prototypes on real house data. In the vast majority of cases, real-world datasets lead to more accurate models and algorithms. AMPds2 is the first dataset to capture all three main types of consumption (electricity, water, and natural gas) over a long period of time (2 years) and provide 11 measurement characteristics for electricity. No other such datasets from Canada exist. Each meter has 730 days of captured data. We also include environmental and utility billing data for cost analysis. AMPds2 data has been pre-cleaned to provide for consistent and comparable accuracy results amongst different researchers and machine learning algorithms.

The cognitive power meter: Looking beyond the smart meter

The smart meter is often heralded as the key component supporting energy displays that can notify home occupants of their energy usage. But, a smart meter is only a digital power meter with enhanced communications capabilities - it is not actually smart. We need to look beyond the smart meter and define what intelligence is needed to actually make a meter smart. One area with promise is load disaggregation. Load disaggregation can be used to determine what loads contributing to the consumption reading at the smart meter. A smart meter incorporating load disaggregation intelligence can be seen as going beyond the traditional smart meter - what we call a cognitive power meter (c-meter). However, using load disaggregation, in its current form, is not feasible. We critically review the requirements for a c-meter and provide insights as to how load disaggregation research needs to change to make the c-meters a reality.

Machine Translation of Closed Captions

Traditional Machine Translation (MT) systems are designed to translate documents. In this paper we describe an MT system that translates the closed captions that accompany most North American television broadcasts. This domain has two identifying characteristics. First, the captions themselves have properties quite different from the type of textual input that many MT systems have been designed for. This is due to the fact that captions generally represent speech and hence contain many of the phenomena that characterize spoken language. Second, the operational characteristics of the closed-caption domain are also quite distinctive. Unlike most other translation domains, the translated captions are only one of several sources of information that are available to the user. In addition, the user has limited time to comprehend the translation since captions only appear on the screen for a few seconds. In this paper, we look at some of the theoretical and implementational challenges that these characteristics pose for MT. We present a fully automatic large-scale multilingual MT system, ALTo. Our approach is based on Whitelocks Shake and Bake MT paradigm, which relies heavily on lexical resources. The system currently provides wide-coverage translation from English to Spanish. In addition to discussing the design of the system, we also address the evaluation issues that are associated with this domain and report on our current performance.

What is Example-Based Machine Translation?

We maintain that the essential feature that characterizes a Machine Translation approach and sets it apart from other approaches is the kind of knowledge it uses. From this perspective, we argue that Example-Based Machine Translation is sometimes characterized in terms of nonessential features. We show that Example-Based Machine Translation, as long as it is linguistically principled, significantly overlaps with other linguistically principled approaches to Machine Translation. We make a proposal for translation knowledge bases that make such an overlap explicit. We relate our proposal to translation by analogy, which stands out as an inherently example-based technique.

Parallel scanning with bitstream addition: an XML case study

A parallel scanning method using the concept of bitstream addition is introduced and studied in application to the problem of XML parsing and well-formedness checking. On processors supporting W-bit addition operations, the method can perform up to W finite state transitions per instruction. The method is based on the concept of parallel bitstream technology, in which parallel streams of bits are formed such that each stream comprises bits in one-to-one correspondence with the character code units of a source data stream. Parsing routines are initially prototyped in Python using its native support for unbounded integers to represent arbitrary-length bitstreams. A compiler then translates the Python code into low-level C-based implementations. These low-level implementations take advantage of the SIMD (single-instruction multipledata) capabilities of commodity processors to yield a dramatic speed-up over traditional alternatives employing byte-at-a-time parsing.