El Modelado Difuso es un enfoque efectivo para la generacion de modelos que utiliza un lenguaje d... more El Modelado Difuso es un enfoque efectivo para la generacion de modelos que utiliza un lenguaje descriptivo basado en la logica difusa. Estos modelos se suelen extraer de los datos entrada-salida acerca de un sistema objetivo utilizando combinaciones de tecnicas que, a menudo, se hacen de una manera ad hoc. Se acusa, por tanto, la falta de herramientas en las que estas combinaciaones se hagan de una manera flexible y unificada. En este trabajo, por tanto, el objetivo final es el diseno de una herramienta en la que se pueden hibridar tecnicas para formar estrategias que resuelvan el proceso de modelado difuso. Para llevar a esa fase de diseno, sin embargo, se requiere un analisis previo de las tecnicas de modelado difuso desde una perspectiva modular. Por tanto, en esta tesis se aborda un proceso de analisis de dichas tecnicas para, en la segunda parte perfilar los fundamentos de diseno de un marco para la especificacion de tecnicas para, en al segunda parte perfilar los fundamentos ...
Journal of Ambient Intelligence and Smart Environments, 2021
The Internet of Things (IoT) has recently been applied in the domain of cultural exhibition enabl... more The Internet of Things (IoT) has recently been applied in the domain of cultural exhibition enabling the cultural sites to provide more personal and proactive experiences to their visitors. To come up with valuable services, several solutions to analyze the spatio-temporal trajectories of visitors have been put forward. However, they neither consider the inherent uncertainty of the underlying indoor positioning technologies – Bluetooth Low Energy (BLE), RFID, etc. – nor other visitors’ features apart from the spatio-temporal ones (e.g. the level of interaction with the museum displays). For that reason, the present work introduces RECITE, a framework to classify trajectories representing visitors’ actions that copes with the aforementioned limitations of existing solutions. Firstly, RECITE states a novel mapping process for a BLE-based indoor positioning system to accurately detect the visitors’ locations. On top of this mechanism, RECITE includes an ensemble of fuzzy rule classifie...
With the advent of smartphones, opportunistic mobile crowdsensing has become an instrumental appr... more With the advent of smartphones, opportunistic mobile crowdsensing has become an instrumental approach to perceive large-scale urban dynamics. In this context, the present work presents a novel approach based on such a sensing paradigm to automatically identify and monitor the areas of a city comprising most of the human transit. Unlike previous approaches, the system performs such detection in real time at the same time the opportunistic sensing is carried out. Furthermore, a novel multilayered grill partitioning to represent such areas is stated. Finally, the proposal is evaluated by means of a real-world dataset.
Personal route prediction has emerged as an important topic within the mobility mining domain. In... more Personal route prediction has emerged as an important topic within the mobility mining domain. In this context, many proposals apply an off-line learning process before being able to run the on-lin...
2015 IEEE 2nd World Forum on Internet of Things (WF-IoT), 2015
Social media has enabled a new breed of soft sensors that enriches the IoT paradigm with new form... more Social media has enabled a new breed of soft sensors that enriches the IoT paradigm with new forms of data. The present work introduces a novel approach for personal mobility mining that combines these new data-sources with built-in sensors of a smart-phone in order to timely extract personal mobility pattens by means of the Complex Event Processing (CEP) approach. Unlike previous solutions, the present work profits from both the textual and location data of social-network sites by also dealing with the actual scarcity of geo-tagged documents in those sites. Finally, a preliminary study of the feasibility of our proposal is stated.
2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015
The mining of transit-card transactions is nowadays an interesting solution for human mobility de... more The mining of transit-card transactions is nowadays an interesting solution for human mobility detection in urban areas. However, most existing approaches in this domain do not face current needs of most stakeholders that already require to extract meaningful knowledge from these transactions in real time. In this context, the present work introduces a novel method based on Complex Event Processing and fuzzy clustering to extract different profiles of travellers of a public transit system at the same time smart-card transactions are generated. Experiments in a real tram system scenario shows the suitability of the proposal.
The study of the mobility models that arise from the city dynamics has become instrumental to pro... more The study of the mobility models that arise from the city dynamics has become instrumental to provide new urban services. In this context, many proposals applied an off-line learning on historical data. However, at the dawn of the Big Data era, there is an increasing need for systems and architectures able to process data in a timely manner. The present work introduces a novel approach for online mobility model detection along with a new concept for trajectory abstraction based on velocity features. Finally, the proposal is evaluated with a real-world dataset.
ABSTRACT Over the last years, many data-sources have become available to monitor the marine traff... more ABSTRACT Over the last years, many data-sources have become available to monitor the marine traffic. This has motivated the development of support systems to automatically detect vessels’ behaviours of interest. The present work states a novel approach in this domain following the Complex Event Processing (CEP) paradigm. As a proof of concept, a CEP-based system has been developed to timely detect a set of vessel’s abnormal behaviours by performing an event-based processing of Automatic Identification System data. Experiments based on real-world and synthetic data proved the suitability and feasibility of the proposal.
Perceiving the whole context of a vehicle in an accurate and enriched way will be extremely usefu... more Perceiving the whole context of a vehicle in an accurate and enriched way will be extremely useful so as to develop in-vehicle services. However, current Context-Aware systems in the vehicular scope focus on particular domains, like safety, so their perception level does not give a general view of a vehicle's context. In this frame, the present work puts forward a novel general-purpose architecture to manage the environment of a vehicle. Such an architecture is based on the Complex Event Processing paradigm allowing to fuse different data-sources in almost real-time.
One of the goals of Advanced Driver Assistance Systems (ADASs) is to identify the role of a vehic... more One of the goals of Advanced Driver Assistance Systems (ADASs) is to identify the role of a vehicle in a scene even without Global Positioning System (GPS) information. Some researches solve the problem by implementing different kinematic models for the vehicle along with a mechanism to decide the most suitable model at the current instant. In this work, a Fuzzy Rule Based Classification System (FRBCS) takes such decision starting from the measures coming from different sensors in the vehicle. The FRBCS is obtained through Data Driven Fuzzy Modeling (DDFM) techniques. In fact, several FRBCSs with promising results are generated. Most discovered models achieve better classification rates than previous researches while being simpler. Therefore, they are more suitable for implementation into an ADAS. Besides, some FRBCSs are far simpler while achieving similar rates. Finally, some tests have been done. They show the feasibility and suitability of this approach behind different situations.
El Modelado Difuso es un enfoque efectivo para la generacion de modelos que utiliza un lenguaje d... more El Modelado Difuso es un enfoque efectivo para la generacion de modelos que utiliza un lenguaje descriptivo basado en la logica difusa. Estos modelos se suelen extraer de los datos entrada-salida acerca de un sistema objetivo utilizando combinaciones de tecnicas que, a menudo, se hacen de una manera ad hoc. Se acusa, por tanto, la falta de herramientas en las que estas combinaciaones se hagan de una manera flexible y unificada. En este trabajo, por tanto, el objetivo final es el diseno de una herramienta en la que se pueden hibridar tecnicas para formar estrategias que resuelvan el proceso de modelado difuso. Para llevar a esa fase de diseno, sin embargo, se requiere un analisis previo de las tecnicas de modelado difuso desde una perspectiva modular. Por tanto, en esta tesis se aborda un proceso de analisis de dichas tecnicas para, en la segunda parte perfilar los fundamentos de diseno de un marco para la especificacion de tecnicas para, en al segunda parte perfilar los fundamentos ...
Journal of Ambient Intelligence and Smart Environments, 2021
The Internet of Things (IoT) has recently been applied in the domain of cultural exhibition enabl... more The Internet of Things (IoT) has recently been applied in the domain of cultural exhibition enabling the cultural sites to provide more personal and proactive experiences to their visitors. To come up with valuable services, several solutions to analyze the spatio-temporal trajectories of visitors have been put forward. However, they neither consider the inherent uncertainty of the underlying indoor positioning technologies – Bluetooth Low Energy (BLE), RFID, etc. – nor other visitors’ features apart from the spatio-temporal ones (e.g. the level of interaction with the museum displays). For that reason, the present work introduces RECITE, a framework to classify trajectories representing visitors’ actions that copes with the aforementioned limitations of existing solutions. Firstly, RECITE states a novel mapping process for a BLE-based indoor positioning system to accurately detect the visitors’ locations. On top of this mechanism, RECITE includes an ensemble of fuzzy rule classifie...
With the advent of smartphones, opportunistic mobile crowdsensing has become an instrumental appr... more With the advent of smartphones, opportunistic mobile crowdsensing has become an instrumental approach to perceive large-scale urban dynamics. In this context, the present work presents a novel approach based on such a sensing paradigm to automatically identify and monitor the areas of a city comprising most of the human transit. Unlike previous approaches, the system performs such detection in real time at the same time the opportunistic sensing is carried out. Furthermore, a novel multilayered grill partitioning to represent such areas is stated. Finally, the proposal is evaluated by means of a real-world dataset.
Personal route prediction has emerged as an important topic within the mobility mining domain. In... more Personal route prediction has emerged as an important topic within the mobility mining domain. In this context, many proposals apply an off-line learning process before being able to run the on-lin...
2015 IEEE 2nd World Forum on Internet of Things (WF-IoT), 2015
Social media has enabled a new breed of soft sensors that enriches the IoT paradigm with new form... more Social media has enabled a new breed of soft sensors that enriches the IoT paradigm with new forms of data. The present work introduces a novel approach for personal mobility mining that combines these new data-sources with built-in sensors of a smart-phone in order to timely extract personal mobility pattens by means of the Complex Event Processing (CEP) approach. Unlike previous solutions, the present work profits from both the textual and location data of social-network sites by also dealing with the actual scarcity of geo-tagged documents in those sites. Finally, a preliminary study of the feasibility of our proposal is stated.
2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015
The mining of transit-card transactions is nowadays an interesting solution for human mobility de... more The mining of transit-card transactions is nowadays an interesting solution for human mobility detection in urban areas. However, most existing approaches in this domain do not face current needs of most stakeholders that already require to extract meaningful knowledge from these transactions in real time. In this context, the present work introduces a novel method based on Complex Event Processing and fuzzy clustering to extract different profiles of travellers of a public transit system at the same time smart-card transactions are generated. Experiments in a real tram system scenario shows the suitability of the proposal.
The study of the mobility models that arise from the city dynamics has become instrumental to pro... more The study of the mobility models that arise from the city dynamics has become instrumental to provide new urban services. In this context, many proposals applied an off-line learning on historical data. However, at the dawn of the Big Data era, there is an increasing need for systems and architectures able to process data in a timely manner. The present work introduces a novel approach for online mobility model detection along with a new concept for trajectory abstraction based on velocity features. Finally, the proposal is evaluated with a real-world dataset.
ABSTRACT Over the last years, many data-sources have become available to monitor the marine traff... more ABSTRACT Over the last years, many data-sources have become available to monitor the marine traffic. This has motivated the development of support systems to automatically detect vessels’ behaviours of interest. The present work states a novel approach in this domain following the Complex Event Processing (CEP) paradigm. As a proof of concept, a CEP-based system has been developed to timely detect a set of vessel’s abnormal behaviours by performing an event-based processing of Automatic Identification System data. Experiments based on real-world and synthetic data proved the suitability and feasibility of the proposal.
Perceiving the whole context of a vehicle in an accurate and enriched way will be extremely usefu... more Perceiving the whole context of a vehicle in an accurate and enriched way will be extremely useful so as to develop in-vehicle services. However, current Context-Aware systems in the vehicular scope focus on particular domains, like safety, so their perception level does not give a general view of a vehicle's context. In this frame, the present work puts forward a novel general-purpose architecture to manage the environment of a vehicle. Such an architecture is based on the Complex Event Processing paradigm allowing to fuse different data-sources in almost real-time.
One of the goals of Advanced Driver Assistance Systems (ADASs) is to identify the role of a vehic... more One of the goals of Advanced Driver Assistance Systems (ADASs) is to identify the role of a vehicle in a scene even without Global Positioning System (GPS) information. Some researches solve the problem by implementing different kinematic models for the vehicle along with a mechanism to decide the most suitable model at the current instant. In this work, a Fuzzy Rule Based Classification System (FRBCS) takes such decision starting from the measures coming from different sensors in the vehicle. The FRBCS is obtained through Data Driven Fuzzy Modeling (DDFM) techniques. In fact, several FRBCSs with promising results are generated. Most discovered models achieve better classification rates than previous researches while being simpler. Therefore, they are more suitable for implementation into an ADAS. Besides, some FRBCSs are far simpler while achieving similar rates. Finally, some tests have been done. They show the feasibility and suitability of this approach behind different situations.
Uploads
Papers