Bouchachia A.,Bournemouth University |
Vanaret C.,National School of Civil Aviation
IEEE Transactions on Fuzzy Systems | Year: 2014
In this paper, we propose a Growing Type-2 Fuzzy Classifier (GT2FC) for online rule learning from real-time data streams. While in batch rule learning, the training data are assumed to be drawn from a stationary distribution, in online rule learning, data can dynamically change over time becoming potentially nonstationary. To accommodate dynamic change, GT2FC relies on a new semi-supervised online learning algorithm called G rowing Gaussian Mixture Model (2G2M). In particular, 2G2M is used to generate the type-2 fuzzy membership functions to build the type-2 fuzzy rules. GT2FC is designed to accommodate data online and to reconcile labeled and unlabeled data using self-learning. Moreover, GT2FC maintains low complexity of the rule base using online optimization and feature selection mechanisms. GT2FC is tested on data obtained from an ambient intelligence application, where the goal is to exploit sensed data to monitor the living space on behalf of the inhabitants. Because sensors are prone to faults and noise, type-2 fuzzy modeling is very suitable for dealing with such an application. Thus, GT2FC offers the advantage of dealing with uncertainty in addition to self-adaptation in an online manner. For illustration purposes, GT2FC is also validated on synthetic and classic UCI data-sets. The detailed empirical study shows that GT2FC performs very well under various experimental settings. © 1993-2012 IEEE. Source
Agency: Cordis | Branch: FP7 | Program: CP | Phase: Galileo.2011.3.1-1. | Award Amount: 1.98M | Year: 2012
The e-HIMALAYA project aims at prototyping innovative GNSS-based core technologies and concepts, with the objective to build key Galileo differentiators in a multi-GNSS hybridized receiver. Several markets are addressed with the main weight put on Mass-Market and transport, which represents the main Galileo receiver market. The project will develop a list of key features to enable a higher penetration of Galileo compatible receivers on the market, and especially the ASIC developed under Himalaya project. First of all it will develop a high accuracy technology made available even in bad reception conditions, thanks to a robust aided PLL processing tuned for the Galileo pilot channels. It will also address a smart integrity function taking into account the local effects, through an ultra tight coupling with inertial sensors approach. It also addresses improved performances thanks to an extensive improvement of telecommunication assistance dissemination. In particular, a robust anti spoofing function is also developed, prototyped and demonstrated. The project will have several impacts. The first one is to build a ready to market localization solution based on an efficient use of Galileo. The second is to control key market levers technologies, and therefore propose a feedback both on standardization bodies, or future Galileo signal definition, and on the products roadmaps (GNSS ASIC). Finally, the project will develop an indoor technology that is today seen as a very promising one, blending GNSS measurements and LTE ones.
Agency: Cordis | Branch: FP7 | Program: CSA-SA | Phase: AAT.2012.7-26. | Award Amount: 665.49K | Year: 2012
The objectives of META-CDM (Multimodal, Efficient Transportation in Airports and Collaborative Decision Making) are to study the conditions under which Collaborative Decision Making, which has been so successful at enabling advanced air transportation concepts such as ground delay programs and airport departure managers, can help air transportation stakeholders deal with major disruptive events that affect civil aviation. Crisis events cause the air transport system and society huge cost and the passenger bears the practical consequences. This project will take an integrated look at the effectiveness of airside and landside CDM and its effectiveness in minimizing the impact upon the traveler. In this work, the passenger becomes the center of attention, and the goal is to make his journey as short and as efficient as possible, beginning when he leaves his living or working quarters at his origin location and ending when he drops his luggage at home or at the hotel. The possible impediments to travel are highly disruptive events, such as strong snow storms, volcano ash clouds or labour unrest. We will examine the coherence and co-ordination of the many systems that are part of delivering the traveler through an airport and, when crisis hits, how well contingency plans can help to minimize penalties to the passenger. The passenger-centric approach also looks at how alternative transport modes and communication can step in during crisis situations to minimize personal disruption. This study will deliver a broad understanding of systems strengths and weaknesses, the areas where co-ordination can be improved and an assessment of the implications of disruptive events from many perspectives. It will also deliver a comprehensive update on airside-CDM throughout the world. Clear messages in these areas will help scope the frame for new EU research that can deliver tools and procedures to ensure greater system resilience and a better passenger experience when crises strike.
Agency: Cordis | Branch: FP7 | Program: CP-FP | Phase: AAT.2012.6.3-2. | Award Amount: 760.20K | Year: 2013
This project proposes the investigation of radically new airspace design concepts for scenarios, which are extreme when compared to today in terms of traffic density, complexity and constraints. Extrapolating the current developments in aerospace technology, it is considered likely that the following two new types of air vehicles will have arrived in the second half of this century: - personal air vehicles, used for door-to-door transport, controlled semi-automatically - unmanned, autonomous flying cargo vehicles in different weight classes and sizes Considering the door-to-door aspect, even with inter-local trips, the personal vehicles will especially cause congestion in and around cities. From the same door-to-door philosophy, it follows that the smallest cargo Unmanned Aerial Vehicles (UAVs) will fly in high numbers and even within cities. This brings up a completely new challenge for Air Traffic Management (ATM): urban airspace design. The challenge is to provide a concept which can handle high volumes, many constraints and autonomous control for these vehicle types. Apart from being prepared for this potential revolution in aerospace, there is a more fundamental, but still practical, question underlying this challenge. Research so far has shown, that in todays en-route airspace, dispersing the traffic over the airspace and reducing therefore the structure, reduces the number of potential conflicts and therefore increases both capacity and efficiency. In the urban airspace scenarios, many envision that these extreme traffic densities will require a very well defined, very structured airspace. The question is: Is this true? And if so, what causes this reversal? This project has 2 main goals: - Exploratore options for future urban airspace design - Provide a better understanding of air traffic using extreme scenarios The knowledge gained through studying these radical scenarios for air transport will impact the airspace and traffic complexity.
Agency: Cordis | Branch: FP7 | Program: JTI-CP-ARTEMIS | Phase: SP1-JTI-ARTEMIS-2010-8 | Award Amount: 14.36M | Year: 2011
Transportation based on cars, aircraft and ships is a key factor for modern human societies. Human operators have historically been in charge of the two main facets of transportation: vehicle control and traffic control. Technological innovations have progressively allowed the introduction of advanced automated assistance systems leading to a complex interplay of humans and automation which has been shown to lead in many cases to new types of human errors, incidents and sometimes accidents. It has been recognized that further automation alone cannot solve the problem and the crucial issue is how to achieve an adequate level of human-machine cooperation with shared authority. The proposal addresses missing key enablers for market penetration of innovative dynamic Distributed Cooperative Human-Machine Systems (DCoS). The proposal intends to develop affordable methods, techniques and tools which go beyond assistance systems and consequently address the design, development and evaluation of cooperative systems from a multi-agent perspective where human and machine agents are in charge of common tasks, assigned to the system as a whole. A high quality user interface is inevitable to meet user expectations and to gain market acceptance of cooperative systems with increased levels of automation. Already today the development of a user interface of Embedded Systems is a substantial cost driver that is constantly increasing. The proposal strives to boost cost efficiency of highly innovative DCoS with several interactive Embedded Systems. This will be achieved by supporting and closing the industrial development process chain from (1) DCoS composition over (2) interaction design to (3) system design and (4) interface design and by allowing to evaluate the overall system safety, efficiency and effectiveness already in early process phases. An Innovation Eco System for cooperative embedded HMI will be established during the project and will be maintained afterwards.