Search

Consensus clustering is a useful tool for robust or distributed clustering applications. However, given the fact that time complexities of the consensus functions scale linearly or quadratically with the number of combined clusterings, execution can be slow or even impossible when operating on big cluster ensembles, a situation encountered when we pursue robust multimedia data clustering. This work introduces hierarchical consensus architectures, an inherently parallel approach based on the divide-and-conquer strategy for computationally efficient consensus clustering, in a bid to make faster, more effective consensus clustering possible in big multimedia cluster ensemble scenarios. Moreover, we define a specific implementation of hierarchical architectures, including a theoretical analysis of its fully parallel implementation computational complexity. In experiments conducted on unimodal and multimedia data sets involving small and big cluster ensembles, we find parallel hierarchical consensus architectures variants perform faster than traditional flat consensus in 75% of the experiments on small cluster ensembles, a percentage that rises to 100% on unimodal and multimedia big cluster ensembles, achieving an average speedup ratio of 30.5. Moreover, depending on the consensus function employed, the quality of the obtained consensus partitions ensures robust clustering results.

This work describes the design, implementation and evaluation of a multi-subject learning experience based on the principles of Constructionism, in which the construction of a videogame is the learning artifact that engages students in four different technical and management subjects included in the ICT engineering degree curricula of the School of Engineering at La Salle – Universitat Ramon Lull. Working in groups in a simulated corporate scenario, students learnt the basics of emergent technologies such as 3D audio, computer vision or speech recognition, while developing soft skills like negotiation or work planning. As regards the evaluation of the academic results, the proposed methodology made attendance rate rise from around 50% to over 90%, and average pass rate from 72% to 93%. Moreover, to capture their short and long-term view of the learning experience, students answered two opinion surveys along time: the first on completion of the project, and a second one 3–5 years after completing their graduate studies, with all of them integrated in the labor market. The analysis of these surveys reveals that over 85% of students showed a high degree of satisfaction, and an overwhelming preference for the new methodology over classic learning methodologies.

The proposed system pioneers purely audiovisual geotagging at Earth scale.Our proposal builds on our previous expertise on environmental sound recognition.It outperforms all MediaEval2011 audiovisual and visual-content based geotaggers. Tagging videos with the geo-coordinates of the place where they were filmed (i.e. geotagging) enables indexing online multimedia repositories using geographical criteria. However, millions of non geotagged videos available online are invisible to the eyes of geo-oriented applications, which calls for the development of automatic techniques for estimating the location where a video was filmed. The most successful approaches to this problem largely rely on exploiting the textual metadata associated to the video, but it is quite common to encounter videos with no title, description nor tags. This work focuses on this latter adverse scenario and proposes a purely audiovisual approach to geotagging based on audiovisual similarity retrieval, modality fusion and cluster density. Using a subset of the MediaEval 2011 Placing task data set, we evaluate the ability of several visual and acoustic features for estimating the videos location both separately and jointly (via fusion at feature and at cluster level). The optimally configured version of the proposed system is capable of geotagging videos within 1km of their real location at least 4 times more precisely than any of the audiovisual and visual content-based participants in the MediaEval 2011 Placing task.

Pressure injuries represent a tremendous healthcare challenge in many nations. Elderly and disabled people are the most affected by this fast growing disease. Hence, an accurate diagnosis of pressure injuries is paramount for efficient treatment. The characteristics of these wounds are crucial indicators for the progress of the healing. While invasive methods to retrieve information are not only painful to the patients but may also increase the risk of infections, non-invasive techniques by means of imaging systems provide a better monitoring of the wound healing processes without causing any harm to the patients. These systems should include an accurate segmentation of the wound, the classification of its tissue types, the metrics including the diameter, area and volume, as well as the healing evaluation. Therefore, the aim of this survey is to provide the reader with an overview of imaging techniques for the analysis and monitoring of pressure injuries as an aid to their diagnosis, and proof of the efficiency of Deep Learning to overcome this problem and even outperform the previous methods. In this paper, 114 out of 199 papers retrieved from 8 databases have been analyzed, including also contributions on chronic wounds and skin lesions.

Consensus clustering, i.e. the task of combining the outcomes of several clustering systems into a single partition, has lately attracted the attention of researchers in the unsupervised classification field, as it allows the creation of clustering committees that can be applied with multiple interesting purposes, such as knowledge reuse or distributed clustering. However, little attention has been paid to the development of algorithms, known as consensus functions, especially designed for consolidating the outcomes of multiple fuzzy (or soft) clustering systems into a single fuzzy partition-despite the fact that fuzzy clustering is far more informative than its crisp counterpart, as it provides information regarding the degree of association between objects and clusters that can be helpful for deriving richer descriptive data models. For this reason, this paper presents a set of fuzzy consensus functions capable of creating soft consensus partitions by fusing a collection of fuzzy clusterings. Our proposals base clustering combination on a cluster disambiguation process followed by the application of positional and confidence voting techniques. The modular design of these algorithms makes it possible to sequence their constituting steps in different manners, which allows to derive versions of the proposed consensus functions optimized from a computational standpoint. The proposed consensus functions have been evaluated in terms of the quality of the consensus partitions they deliver and in terms of their running time on multiple benchmark data sets. A comparison against several representative state-of-the-art consensus functions reveals that our proposals constitute an appealing alternative for conducting fuzzy consensus clustering, as they are capable of yielding high quality consensus partitions at a low computational cost.