César Llamas

Extracting Geographic Context from the Web: GeoReferencing in MyMoSe

Many Web pages are clearly related to specific locations. Identifying this geographic focus is the cornerstone of the next generation of geographic context aware search services. This paper shows a multistage method for assigning a geographic focus to Web pages (GeoReferencing), using several heuristics for toponym disambiguation and a scoring function for focus determination. We provide an experimental methodology for evaluating the accuracy of the system with Web pages in English and Spanish. Finally, we have obtained promising results, reaching an accuracy of over 70% with a town-level resolution.

A georeferencing multistage method for locating geographic context in web search

The geographic scope of Web pages is becoming an essential dimension of Web search, especially for mobile users. This paper shows a multistage method for assigning a geographic focus to Web pages (GeoReferencing) according to their text contents. We suggest several heuristics for the disambiguation toponyms and a scoring procedure for focus determination. Furthermore, we provide an experimental methodology for evaluating the accuracy. Finally, we obtained promising results of over 70% accuracy with a city-level resolution.

Open source platform for collaborative construction of wearable sensor datasets for human motion analysis and an application for gait analysis

Nearly every practical improvement in modeling human motion is well founded in a properly designed collection of data or datasets. These datasets must be made publicly available for the community could validate and accept them. It is reasonable to concede that a collective, guided enterprise could serve to devise solid and substantial datasets, as a result of a collaborative effort, in the same sense as the open software community does. In this way datasets could be complemented, extended and expanded in size with, for example, more individuals, samples and human actions. For this to be possible some commitments must be made by the collaborators, being one of them sharing the same data acquisition platform. In this paper, we offer an affordable open source hardware and software platform based on inertial wearable sensors in a way that several groups could cooperate in the construction of datasets through common software suitable for collaboration. Some experimental results about the throughput of the overall system are reported showing the feasibility of acquiring data from up to 6 sensors with a sampling frequency no less than 118Hz. Also, a proof-of-concept dataset is provided comprising sampled data from 12 subjects suitable for gait analysis.

Open source hardware based sensor platform suitable for human gait identification

Abstract Most initiatives about embedded sensing capabilities in computational systems lead to devise an ad hoc sensor platform, usually poorly reusable, as a first stage to prepare a data corpus or production prototype. In this paper, an open source hardware platform for sensing is described. This platform was intended to be used in data acquisition for gait identification, and is designed in a way general enough so many other projects could reuse the design to accelerate prototyping. The platform is based on popular open source hardware and software like Arduino and Raspberry Pi using well known languages and libraries. Some experimental results about the throughput of the overall system are reported showing the feasibility of acquiring data from up to 6 sensors with a sampling frequency no less than 118 Hz.

A survey on mobile devices use by university students

New mobile devices are changing the habits and preferences of students and instructors. In spite of the ever increasing market and software utilities that appear everyday, relatively little is known about the way the students use these tools in their study tasks. To alleviate this lack, a survey has been conducted with university students trying to portray how they use mobile devices in their studying activities. As a main result we see that more than half of the students use some mobile devices in their study tasks with different intensity, being the smartphone the preferred device. Some discrepancies have been found when comparing their use in the academic context and in the real life. The influence of the use of mobile devices on the way in which the students work is also studied; the habit of studying in-group and using mobile devices are closely related. Finally, the role of instructors, encouraging or forbidding the use of mobile devices, has also been analyzed. From the results of our survey, we can conclude the professors do not support enough the use of these devices for learning.

A representation of temporal aspects in knowledge based systems modelling: a monitoring example

One of the difficulties of using Artificial Neural Networks (ANNs) to estimate atmospheric temperature is the large number of potential input variables available. In this study, four different feature extraction methods were used to reduce the input vector to train four networks to estimate temperature at different atmospheric levels. The four techniques used were: genetic algorithms (GA), coefficient of determination (CoD), mutual information (MI) and simple neural analysis (SNA). The results demonstrate that of the four methods used for this data set, mutual information and simple neural analysis can generate networks that have a smaller input parameter set, while still maintaining a high degree of accuracy.