Search

The development of IoT devices has allowed to install large amounts of sensors in different environments. Consequently, monitoring small houses and entire buildings has become possible. In addition, buildings are one of the biggest energy consumers, so the monitoring of the energy waste, and its sources, is gaining attention. Human behaviour has been reported as being the main discrepancy source between energy usage simulations and real usage, thus being able to easily monitor such behaviour will bring greater insight in the building usage. In this paper, an IoT sensor network is proposed to model occupancy profiles at room level. Such measurement of users’ behaviour along with additional information such as temperature or humidity can be used to develop strategies to save energy, especially regarding heating, ventilating and airconditioning (HVAC) systems. The proposed equipment has been gathering data for some months in a workplace containing several meeting rooms. Four of those rooms were monitored and later analysed to test the validity of the proposed approach. The results show that it is possible to obtain occupancy profiles by using simple IoT equipment. Unai Saralegui is grateful to the Tecnalia Research & Innovation Foundation for funding through a PhD fellowship. Olatz Arbelaitz and Javier Muguerza’s research was partially supported by the Department of Education, Universities and Research of the Basque Government under Grant IT980- 16 and by the Ministry of Economy and Competitiveness of the Spanish Government and the European Regional Development fund- ERFD (PhysComp project, TIN2017- 85409-P).

Autonomous robotic systems operating in the vicinity of other agents, such as humans, manually driven vehicles and other robots, can model the behaviour and estimate intentions of the other agents to enhance efficiency of their operation, while preserving safety. We propose a data-driven approach to model the behaviour of other agents, which is based on a set of trajectories navigated by other agents. Then, to evaluate the proposed behaviour modelling approach, we propose and compare two methods for agent intention estimation based on: (i) particle filtering, and (ii) decision trees. The proposed methods were validated using three datasets that consist of real-world bicycle and car trajectories in two different scenarios, at a roundabout and at a t-junction with a pedestrian crossing. The results validate the utility of the data-driven behaviour model, and show that decision-tree based intention estimation works better on a binary-class problem, whereas the particle-filter based technique performs better on a multi-class problem, such as the roundabout, where the method yielded an average gain of 14.88 m for correct intention estimation locations compared to the decision-tree based method.

Constructive combat simulation is widely used across Defence Science and Technology Group, typically using behavioural models written by software developers in a scripting or programming language for a specific simulation. This approach is time-consuming, can lead to inconsistencies between the same behaviour in different simulations, and is difficult to engage military subject matter experts in the elicitation and verification of behaviours. Therefore, a representation is required that is both comprehensible to non-programmers and is translatable to different simulation execution formats. This paper presents such a representation, the Hierarchical Behaviour Model and Notation (HBMN), which incorporates aspects of existing business process and behaviour representations to provide a hierarchical schema allowing an incremental approach to developing and refining behaviour models from abstract partial models to concrete executable models. The HBMN representation is combined with automated processes for translating written military doctrine texts to HBMN and from HBMN to executable simulation behaviours, providing a cohesive solution to modelling combat behaviours across all stages of development. Refereed/Peer-reviewed

Human societies appear in many types of simulations. Particularly, a lot of new computer games contain a virtual world that imitates the real world. A few of the most important and the most difficult society elements to be modelled are the social context and individuals cooperation. In this paper we show how the social context and cooperation ability can be provided using agents that are equipped with internal visions of mutual social relations. Internal vision is a representation of social relations from the agent's point of view so, due to being subjective, it may be inconsistent with the reality. We introduce the agent model and the mechanism of rebuilding the agent's internal vision that is similar to that used by humans. An experimental proof of concept implementation is also presented.

Most reported MDA approaches give much attention to structural aspects in PSMs and in generated code, and less attention to the PIM level and the behaviour of the modelled applications. Consequently, application behaviour is generally not (well) defined at the PIM level. This paper presents an MDA-based approach that incorporates behaviour modelling at the PIM level in the development of a specific category of applications, i.e., context-aware mobile applications. The paper also illustrates a behaviour model transformation realized by using Medini QVT , which is a tool that implements the Query/ View/ Transformation (QVT) Relations specification defined by OMG for model-to-model transformations.

The complexity of interactions governing the coordination of loosely-coupled services, which forms the core of current software, brought behavioural issues up to the front of architectural concerns. This paper takes such a challenge seriously by lifting typical behaviour modelling techniques to the specification of both types and instances of architectural patterns in which the later ones are connected by ports that behave according to a water flow metaphor. A specific language is introduced for this purpose as well as a translator to mCRL2 so that the simulation and analysis techniques available in the corresponding toolset can be used to reason about (the behavioural layer of) software architectures. The approach is illustrated in a few examples, (undefined)

The study described in this paper developed a model of animal movement, which explicitly recognised each individual as the central unit of measure. The model was developed by learning from a real dataset that measured and calculated, for individual cows in a herd, their linear and angular positions and directional and angular speeds. Two learning algorithms were implemented: a Hidden Markov model (HMM) and a long-term prediction algorithm. It is shown that a HMM can be used to describe the animal's movement and state transition behaviour within several “stay” areas where cows remained for long periods. Model parameters were estimated for hidden behaviour states such as relocating, foraging and bedding. For cows’ movement between the “stay” areas a long-term prediction algorithm was implemented. By combining these two algorithms it was possible to develop a successful model, which achieved similar results to the animal behaviour data collected. This modelling methodology could easily be applied to interactions of other animal species.