Multi-sensor fusion refers to methods used for combining information coming from several sensors ... more Multi-sensor fusion refers to methods used for combining information coming from several sensors (in some cases, different ones) with the aim to make one sensor compensate for the weaknesses of others or to improve the overall accuracy or the reliability of a decision-making process. Indeed, this area has made progress, and the combined use of several sensors has been so successful that many authors proposed variants of fusion methods, to the point that it is now hard to tell which of them is the best for a given set of sensors and a given application context. To address the issue of choosing an adequate fusion method, we recently proposed a machine-learning data-driven approach able to predict the best merging strategy. This approach uses a meta-data set with the Statistical signatures extracted from data sets of a particular domain, from which we train a prediction model. However, the mentioned work is restricted to the recognition of human activities. In this paper, we propose to extend our previous work to other very different contexts, such as gas detection and grammatical face expression identification, in order to test its generality. The extensions of the method are presented in this paper. Our experimental results show that our extended model predicts the best fusion method well for a given data set, making us able to claim a broad generality for our sensor fusion method.
Sensors are becoming more and more ubiquitous as their price and availability continue to improve... more Sensors are becoming more and more ubiquitous as their price and availability continue to improve, and as they are the source of information for many important tasks. However, the use of sensors has to deal with noise and failures. The lack of reliability in the sensors has led to many forms of redundancy, but simple solutions are not always the best, and the precise way in which several sensors are combined has a big impact on the overall result. In this paper, we discuss how to deal with the combination of information coming from different sensors, acting thus as "virtual sensors", in the context of human activity recognition, in a systematic way, aiming for optimality. To achieve this goal, we construct meta-datasets containing the "signatures" of individual datasets, and apply machine-learning methods in order to distinguish when each possible combination method could be actually the best. We present specific results based on experimentation, supporting our claims of optimality.
Multi-sensor fusion refers to methods used for combining information coming from several sensors ... more Multi-sensor fusion refers to methods used for combining information coming from several sensors (in some cases, different ones) with the aim to make one sensor compensate for the weaknesses of others or to improve the overall accuracy or the reliability of a decision-making process. Indeed, this area has made progress, and the combined use of several sensors has been so successful that many authors proposed variants of fusion methods, to the point that it is now hard to tell which of them is the best for a given set of sensors and a given application context. To address the issue of choosing an adequate fusion method, we recently proposed a machine-learning data-driven approach able to predict the best merging strategy. This approach uses a meta-data set with the Statistical signatures extracted from data sets of a particular domain, from which we train a prediction model. However, the mentioned work is restricted to the recognition of human activities. In this paper, we propose to...
In Ambient Intelligence (AmI), the activity a user is engaged in is an essential part of the cont... more In Ambient Intelligence (AmI), the activity a user is engaged in is an essential part of the context, so its recognition is of paramount importance for applications in areas like sports, medicine, personal safety, and so forth. The concurrent use of multiple sensors for recognition of human activities in AmI is a good practice because the information missed by one sensor can sometimes be provided by the others and many works have shown an accuracy improvement compared to single sensors. However, there are many different ways of integrating the information of each sensor and almost every author reporting sensor fusion for activity recognition uses a different variant or combination of fusion methods, so the need for clear guidelines and generalizations in sensor data integration seems evident. In this survey we review, following a classification, the many fusion methods for information acquired from sensors that have been proposed in the literature for activity recognition; we examin...
The technology trend of context-aware computer systems carries the promise of more flexible autom... more The technology trend of context-aware computer systems carries the promise of more flexible automated systems, with a high degree of adaptation to the user’s situation, but it implies as a precondition that the context information (such as the place, time, activity, preferences, etc.) is indeed available. One very important aspect of the user context is the activity in which the human is currently involved. Human Activity Recognition (HAR) has become a trending topic in the last years because of its potential applications in pervasive health care, assisted living, exercise monitoring, etc. Most of the works on HAR either require from the user to label the activities as they are performed so the system can learn them, or rely on a trained device that expects a “typical” ideal user. The first approach is impractical, as the training process easily becomes time consuming, expensive, etc., while the second one drops the HAR precision for many non-typical users. In this work we propose a “crowdsourcing” method for building personalized models for HAR by combining the advantages of both user-dependent and general models, finding class similarities between the target user and the community users. We evaluated our approach on 4 different public datasets and showed that the personalized models outperformed the user-dependent and user-independent models when labeled data is scarce.
Journal of Advanced Computational Intelligence and Intelligent Informatics
As Ontologic knowledge gets more and more important in agent-based systems, its handling becomes ... more As Ontologic knowledge gets more and more important in agent-based systems, its handling becomes crucial for successful applications. We propose a hybrid approach, in which part of the ontology is handled locally, using a "client component", and the rest of the ontological knowledge is handled by an "ontology agent", which is accessed by the other agents in the system through their client component. We propose specific methods for representing, storing, querying and translating ontologies for effective use in the context of the "JITIK" system, which is a multiagent system for knowledge and information distribution. We report as well a working prototype implementing our proposal.
Indoor positioning systems (IPS) use sensors and communication technologies to locate objects in ... more Indoor positioning systems (IPS) use sensors and communication technologies to locate objects in indoor environments. IPS are attracting scientific and enterprise interest because there is a big market opportunity for applying these technologies. There are many previous surveys on indoor positioning systems; however, most of them lack a solid classification scheme that would structurally map a wide field such as IPS, or omit several key technologies or have a limited perspective; finally, surveys rapidly become obsolete in an area as dynamic as IPS. The goal of this paper is to provide a technological perspective of indoor positioning systems, comprising a wide range of technologies and approaches. Further, we classify the existing approaches in a structure in order to guide the review and discussion of the different approaches. Finally, we present a comparison of indoor positioning approaches and present the evolution and trends that we foresee.
2014 13th Mexican International Conference on Artificial Intelligence, 2014
Knowing in which activities users are involved is an essential part of their context, which becom... more Knowing in which activities users are involved is an essential part of their context, which become more and more important in modern context-aware applications, but determining these activities could be a daunting task. Many sensors have been used as information source for guessing human activity, such as accelerometers, video cameras, etc., but recently the availability of a sophisticated sensor designed specifically for tracking humans, as is the Microsoft Kinect has opened new opportunities. The aim of this paper is to determine some human activities, such as eating, reading, drinking, etc., while the person is seated, using the Kinect skeleton structure as input. In this paper we take an unsupervised approach based on K-means for clustering activities, and Hidden Markov Models (HMM) to recognize the activities captured with the Microsoft Kinect's skeleton tracking feature. We show also how the number of clusters affects the performance of the HMM, and that after reaching a certain number of clusters, the performance of the HMM models to recognize activities does not improve anymore.
User segmentation is a practice of clustering an audience based on mutually exclusive subsets of ... more User segmentation is a practice of clustering an audience based on mutually exclusive subsets of individuals that are similar in specific ways. Nowadays user segmentation is crucial not only for the industry but also for the field of User Centered Design, where achieving an accurate understanding of the user’s behavior in the current e-scenario is becoming a complex task. The segmentation could be based on demographic issues, social-economical features, psychographic data, physical characteristics and psychological profiles, etc. This paper proposes a novel strategy for the automatic detection of critical segmentation factors that divide users focused on their feelings and opinions towards a particular topic. Given a topic and on the basis of user’s text-based opinions posted at Web 2.0 services (such as social networks, microblogging platforms, online review systems, online news media, etc.), our proposal introduces an argument-oriented methodology that integrates argumentation theory, sentiment analysis and opinion mining including the computational treatment of incomplete, contradictory or potentially inconsistent information. The mining process is characterized in terms of dialectical analysis of opinions (atomic or more complex opinions constructed by an aggregation mechanism) according to a preference criterion given by topic and feature specificity. As a result, an “opinion analysis tree” rooted in the first original topic is automatically constructed and visualized, in which any node models a user segmentation, showing the factor that define the segmentation as well as the particularities that group the subset. This way, traditional problems associated with the subjective interpretation of user’s opinions expressed in natural language are minimized. Besides, instead of defining a user’s statistical sample, all available information is considered and possible, not evident critical segmentation factors could be discovered, thus enhancing a rational decision making process.
This document presents the design and implementation of a multiagent system dealing with a hunter... more This document presents the design and implementation of a multiagent system dealing with a hunter-prey scenario. The system utilizes ContractNET to organize cooperation efforts between agents. A prototype of the system was built in the NetLogo environment, from which results were taken. Keywords: Multiagent Systems, MAS, ContractNET, NetLogo, Gaia Resumen: Este documento presenta el diseño e implementación de un sistema multiagente que trabaja en un ambiente cazador-presa. El sistema utiliza ContractNET para organizar la cooperación entre agentes. Un prototipo del sistema se construyó en el ambiente NetLogo, del cual se tomaron los resultados.
2015 International Conference on Electronics, Communications and Computers (CONIELECOMP), 2015
Using a set of signal features (e.g. magnetic-field, light, sound), we can create a model to esti... more Using a set of signal features (e.g. magnetic-field, light, sound), we can create a model to estimate the location of a user in an indoor environment. In our previous work, we proposed a model with 46 features from the temporal and spectral evolution of the magnetic-field, which enables us to estimate the indoor location using the readings of a magnetometer built in a smartphone. Considering our previous results, some questions arise. Firstly, (1) Is it possible to estimate the location of a user in indoor environments with a single feature of the magnetic-field signal (univariate model)?; (2) Which model, univariate or multivariate, has higher performance in terms of accuracy? and (3) Which type of features (frequency/temporal) outweigh the indoor location? To answer these questions we propose an evaluation which consists of four experiments: i) building a model per feature, ii) constructing a model that contains only spectral features; iii) building a model composed by the temporal features, and iv) create a model that combines all features. Our results indicate that a multivariate model has higher accuracy in comparison to the univariate models, however, in the multivariate model a clever feature selection is needed to reduce the number of features required to explain the variance of our multivariate model.
Location-aware information systems is one of the most rapidly developing areas in IT. Location te... more Location-aware information systems is one of the most rapidly developing areas in IT. Location technologies, like GPS and cell-triangulation, offer to mobile devices possibilities for accessing information depending on its physical current location, giving the opportunity for new locationaware information services. In this paper we propose a method and a multiagent architecture for supporting impulse commerce (clients buy as they physically move through stores) by providing a negotiation brokering service. Mobile devices would act as personalized shopping guides for buyers, and merchants could ”push” offers to clients, according to their actual in-stock merchandise and their sales policies. A basic working prototype illustrating our proposal is reported
Uploads
inproceedings