Vancouver, Canada
Vancouver, Canada

Time filter

Source Type

An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms.


Patent
Pulse Energy | Date: 2015-10-27

An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms and bigram terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and bigram terms.


An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms.


An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms and trigram terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and trigram terms.


An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms and word order terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and word order terms.


An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms and part of speech terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms and part of speech terms.


An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms.


An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms.


Patent
Pulse Energy | Date: 2011-12-28

A system and method for predictive modeling of building energy consumption provides predicted building energy load values which are determined using kernel smoothing of historical building energy load values for a building using defined scaling factors for scaling predictor variables associated with building energy consumption. Predictor variables may include temperature, humidity, windspeed or direction, occupancy, time, day, date, and solar radiation. Scaling factor values may be defined by optimization training using historical building energy load values and measured predictor variable values for a building. Predicted and measured building energy load values are compared to determine if a preset difference threshold has been exceeded, in which case an alert signal or message is generated and transmitted to electronically and/or physically signal a user. The building energy monitoring system may be integrated with a building automation system, or may be operated as a separate system receiving building energy and predictor variable values.


Now in its 60th year, ASME Turbo Expo is recognized as the must-attend event for turbomachinery professionals. The technical conference has a well-earned reputation for bringing together the best and brightest experts from around the world to share the latest in turbine technology, research, development, and application in the following topic areas: gas turbines, steam turbines, wind turbines, fans & blowers, Rankine cycle, and supercritical CO2. Turbo Expo offers unrivalled networking opportunities with a dedicated and diverse trade show floor. The 3-day exhibition attracts the industry's leading professionals and key decision makers, whose innovation and expertise are helping to shape the future of the turbomachinery industry and will feature a Student Poster Session. "Maturing efficiency levels in turbomachinery combined with market and legislative pressures to improve performances and reliability, while reducing development costs are straining the limits of the conventional turbomachinery optimization methods” says Prof. Zangeneh, Managing Director of ADT, “3D Inverse Design approaches for turbomachinery optimization can deliver considerable reduction in development costs and times providing an ideal platform for multidisciplinary turbomachinery design and optimization compatible with industrial development standard." ADT’s TURBOdesign Suite application to answer the needs for high performance and high reliability turbomachinery requirements will be featured in a presentation on multidisciplinary optimization of radial and mixed-inflow turbines for improved performances and reliability, “Increasing Pulse Energy recovery of Turbocharger Radial Turbines by 3D inverse design method (GT2015-43579)” will be held during Session: 42-1 Radial Turbines on Wednesday, June 17, 2015 at 14:30 PM-17:30 PM. ADT engineers and representatives will be at Booth 513 to demonstrate the TURBOdesign Suite and show design engineers and turbomachinery manufacturers how to optimize preliminary designs as well as improve knowledge transfer between projects and design teams while significantly reducing design time and attaining higher performance and noise reduction. Registrations for the event are now open for limited places, for more information please visit http://www.adtechnology.co.uk/news/events/adt-event-asme2015 TURBOdesign Suite 5.2.5 in now available, the Suite runs on Windows systems. It operates on mid-range workstations with 2.4 Ghz or better processors, 2 GB RAM and 1Gb disk space. The TURBOdesign Suite is sold in modules starting from $15,000 USD with software training and technical support included. Advanced Design Technology (ADT) is a global leader in the development of advanced turbomachinery design and optimization methods to shorten development times and costs and improve turbomachinery performances. ADT’s aim is to put designers in direct control of the aerodynamic design and to considerably shorten the design time and time to market for a range of turbomachinery products. ADT’s clients, who represent some of the leading global players in the aerospace, automotive, power generation and marine fields, have achieved significant returns on investment in terms of reduction in design times, higher performance and ease of know-how transfer among different design teams and projects. For more information, call +44 (0) 20 7299 1170 or visit http://www.adtechnology.co.uk.

Loading Pulse Energy collaborators
Loading Pulse Energy collaborators