Goto

Collaborating Authors

Results


A Deep Learning and Gamification Approach to Energy Conservation at Nanyang Technological University

arXiv.org Machine Learning

The implementation of smart building technology in the form of smart infrastructure applications has great potential to improve sustainability and energy efficiency by leveraging humans-in-the-loop strategy. However, human preference in regard to living conditions is usually unknown and heterogeneous in its manifestation as control inputs to a building. Furthermore, the occupants of a building typically lack the independent motivation necessary to contribute to and play a key role in the control of smart building infrastructure. Moreover, true human actions and their integration with sensing/actuation platforms remains unknown to the decision maker tasked with improving operational efficiency. By modeling user interaction as a sequential discrete game between non-cooperative players, we introduce a gamification approach for supporting user engagement and integration in a human-centric cyber-physical system. We propose the design and implementation of a large-scale network game with the goal of improving the energy efficiency of a building through the utilization of cutting-edge Internet of Things (IoT) sensors and cyber-physical systems sensing/actuation platforms. A benchmark utility learning framework that employs robust estimations for classical discrete choice models provided for the derived high dimensional imbalanced data. To improve forecasting performance, we extend the benchmark utility learning scheme by leveraging Deep Learning end-to-end training with Deep bi-directional Recurrent Neural Networks. We apply the proposed methods to high dimensional data from a social game experiment designed to encourage energy efficient behavior among smart building occupants in Nanyang Technological University (NTU) residential housing. Using occupant-retrieved actions for resources such as lighting and A/C, we simulate the game defined by the estimated utility functions.


Microsoft's mixed reality isn't dead, it's just moving to where businesses will pay for it

PCWorld

Anyone concerned that Microsoft is evolving into a more accessible version of IBM, rather than the consumer company many would like it to be, isn't going to feel any better after the company's Build developer conference starting May 8 in Seattle. Two expected moves will reinforce that enterprise direction: a Kinect sensor for Azure, and two HoloLens apps that are being adapted for businesses using mixed reality. Microsoft chief executive Satya Nadella is expected to open Build on Monday by describing the "intelligent cloud and the intelligent edge," which has been Microsoft's unofficial mantra for about a year. Microsoft plans to define what it means by intelligent edge: By 2020, there will be about 30 billion connected devices, each generating about 1.5GB of data per day. Smart buildings and connected factories will add to that.


One of the world's biggest tech shows is about to begin

Mashable

If CES is the tech industry's Super Bowl, IFA is like the NCAA Football Bowl. Not quite the trendsetting tech event of the year, but still worth getting excited for. Held annually in Berlin, Germany, IFA is essentially Europe's version of CES with one big key difference: It's open to the public and not just industry folks. We'll be bringing you all the major tech news from the proceedings all week. It's been a quiet year for smartwatches.


Create a Smarter Home with Alexa - Amazon Apps & Games Developer Portal

#artificialintelligence

The Smart Home Skill API is a new addition to the Alexa Skills Kit (ASK) that enables developers to add capabilities, or skills, to Alexa. Alexa provides a set of built-in smart home capabilities. Examples of these skills include the ability to turn on the lights or turn up the heat, among others. Customers can access these new abilities by asking Alexa questions or making requests. Delight your customers by enabling them to control connected smart home devices via voice.