This one-day workshop consisted of two sub-workshops with both exclusive as well as partially overlapping joint sessions. The sub-workshops were called "AI Problems and Approaches for Intelligent Environments" and "Semantic Cities" respectively. However, the common theme was to drive intelligent ecosystems, whether at the level of individual systems like buildings or at the level of system of systems, like cities.
Proceeding Downloads
Real-life activity recognition: recognizing reading activities
How can we extract high level information about human actions and complex real world situations from heterogeneous ensembles of simple, often unreliable sensors embedded in commodity devices?
We focus on how to use body-worn devices for activity ...
Open data for inclusive governance
Government Agencies collect & generate huge amount of data in various sectors of development in the process of their day to day functioning. These data range from traffic, weather, geographical, tourist information, statistics, business, public sector ...
Demand-driven power saving by multiagent negotiation for HVAC control
Buildings account for roughly 40% of all U.S. energy use, and HVAC systems are a major culprit. The goal of this research is to reduce power consumption without sacrificing human comfort. This paper presents a cooling demand estimation from heat ...
Interdependent multi-issue negotiation for energy exchange in remote communities
We present a novel negotiation protocol to facilitate energy exchange between off-grid homes that are equipped with renewable energy generation and electricity storage. Our protocol imposes restrictions over negotiation such that it reduces the complex ...
A motion detection system for video surveillance
In this paper we describe a motion detection module, which is part of Horus, a video surveillance system already deployed in field. The module integrates and improves upon existing algorithms, whose combination proves to be particularly effective in ...
A framework for short-term activity-aware load forecasting
In this paper, we present a framework for implementing short-term load forecasting, in which statistical time series prediction methods and machine learning-based regression methods, can be configured to benchmark their performance against each other on ...
A semantic approach to retrieving, linking, and integrating heterogeneous geospatial data
There is a tremendous amount of geospatial data available, and there are numerous methods for extracting, processing and integrating geospatial sources. However, end-users' ability to retrieve, combine, and integrate heterogeneous geospatial data is ...
Democratizing mobile app development for disaster management
Smartphones are being used for a wide range of activities including messaging, social networking, calendar and contact management as well as location and context-aware applications. The ubiquity of handheld computing technology has been found to be ...
On the challenges of balancing privacy and utility of open health data
While health data has been collected at large scale for many years, this data is often difficult to obtain for the purpose of research. This is in part due to the cost and complexities involved in preparing this data for third parties. Health data must ...
A computational model for corruption assessment
Corruption afflicts public services world-wide and is universally considered undesirable. However, there is little prior work to formalize it so that it can be attacked effectively using computational (ICT) techniques. It is believed that trends like ...
Intention-aware routing to minimise delays at electric vehicle charging stations: the research related to this demonstration has been published at IJCAI 2013 [1]
En-route charging stations allow electric vehicles to greatly extend their range. However, as a full charge takes a considerable amount of time, there may be significant waiting times at peak hours. To address this problem, we propose a novel navigation ...