Ander Pijoan

Regression Based Emission Models for Vehicle Contribution to Climate Change

The reduction of carbon emissions within the transportation sector is one of the most important steps against the threat of global warming. Unless strict emissions-reduction and fuel economy policies are in place, the resulting pollution is expected to increase dramatically along with the amount of vehicles on the roads. An accurate quantification of the emissions produced by each type of vehicle is essential in order to evaluate the social and environmental impacts derived. The literature shows a wide range of pollutant emission models, whether empirical, database centric or regression based. In this paper, we propose and analyze 3 regression based models built on data from pollutant emission databases and knowledge models. The first model is based on an exponential regression that improves the results given in the state of the art. In contrast, the other two models are based on different Artificial Intelligence techniques, namely Artificial Neural Networks and Support Vector Regression, which further improve the results.

Bridging the Gap between Real and Simulated Environments: A Hybrid Agent-Based Smart Home Simulator Architecture for Complex Systems

Deployment, maintenance of Smart Homes, Smart Grids in real environments is an expensive, lengthy process. In this paradigm, simulations play an important role by providing means of emulating the behaviour of the aforementioned systems. However, these simulations may suffer from lack of accuracy due to the inability to properly reproduce the operation of complex technologies such as solar panels, Heating, Ventilating, Air Conditioning systems (HVAC), sewerage networks or water provisioning. Within this context, this paper presents a Smart-Home Simulation architecture that is able to carry out more representational simulations by merging agent-based simulation of human behaviour with real-world modelling capabilities such as those provided by the Simulink software. Based on the simulation of human behaviour, water, electricity consumption profiles are generated, sent to Simulink models using the TCP/IP communication protocol. The obtained results show that a synchronized connection of both platforms in feasible, enabling a more accurate representation of the systems involved.

On-demand energy monitoring and response architecture in a ubiquitous world

Energy demand is increasing globally, and in consequence greenhouse-gas emissions from this sector are on the rise as well. This trend is set to continue, driven primarily by the economic growth and the rising population. Solutions in this area go hand in hand with the worldwide deployment of policies that look forward a better management and usage of energy in both domestic and industrial scopes. In this line, load balancing through demand-response strategies comes out as one of the most effective and immediate actions aimed at achieving efficiency in the use of energy resources. We present GeoWorldSim, an agent-based simulation platform that integrates the development of a human activity model as well as the communication middleware known as FI-WARE in order to test the best communication architectures available for the implementation of demand-response strategies.

MASSHA: An agent-based approach for human activity simulation in intelligent environments

Abstract Human activity recognition has the potential to become a real enabler for ambient assisted living technologies. Research on this area demands the execution of complex experiments involving humans interacting with intelligent environments in order to generate meaningful datasets, both for development and validation. Running such experiments is generally expensive and troublesome, slowing down the research process. This paper presents an agent-based simulator for emulating human activities within intelligent environments: MASSHA. Specifically, MASSHA models the behaviour of the occupants of a sensorised environment from a single-user and multiple-user point of view. The accuracy of MASSHA is tested through a sound validation methodology, providing examples of application with three real human activity datasets and comparing these to the activity datasets produced by the simulator. Results show that MASSHA can reproduce behaviour patterns that are similar to those registered in the real datasets, achieving an overall accuracy of 93.52% and 88.10% in frequency and 98.27% and 99.09% in duration for the single-user scenario datasets; and a 99.3% and 88.25% in terms of frequency and duration for the multiple-user scenario.

Mixed Environments for MAS: Bringing Humans in the Loop

In many application domains for agents and MAS, the interaction between the systems and human users is a main element. In some cases, the interaction occurs behind a traditional computing device, such as a computer desktop or a smartphone. In other cases, the interaction occurs through the physical world. This is the case, for instance, of smart/intelligent environment applications, and more generally in the wide context of Internet-of-Things based apps. Can the concept of agent environment for MAS play a role in the design of such systems, where humans are in the loop? In this position paper we further develop this question, providing some reflections and suggestions for future works.

GTPlat: Geosimulation for Assessing the Application of Incentives to Transport Planning

Motor vehicle abuse entails emitting large amounts of greenhouse gases to the atmosphere. In order to reduce climate change and life expectancy loss, authorities want to launch a set of sustainable travel policies which should be evaluated before their deployment. Although multi-agent systems for traffic analyses are very popular, they mainly focus on faithfully reproducing vehicle displacement and interaction between vehicles. It is therefore necessary to go one step further and integrate the transport choice factors that take place before starting everyday journeys. We present the baseline Geosimulation that integrates all the steps of citizens home-to-work commutes for assessing the impact green travelling policies would have.

Agent Based Simulations for the Estimation of Sustainability Indicators

Abstract We present a methodology to improve the estimation of several Sustainability Indicators based on the measurement of walking distance to infrastructures combining Agent Based Simulation with Volunteer Geographic Information. Joining these two forces we construct a more realistic and accurate distribution of the infrastructures based on knowledge created by citizens and their perceptions instead of official data sources. A Situated Multi-Agent System is in charge of simulating not only the functional disparity and sociodemographic characteristics of the population but also the geographic reality in a dynamic way. Namely, the system will analyze different geographic barriers for each collective bringing new possibilities to improve the assessment of the needs of the population for a more sustainable development of the city. In this article we will describe the methodology to carry on several sustainability indicator measurements and present the results of the proposed methodology applied to several municipalities.