Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized beat-to-beat (R–R) intervals and features relative to the width of the ventricular depolarization waves (QRS complex) are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats, respectively. In comparison with other state-of-the-art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

Recommender systems usually propose items to single users. However, in some domains like Mobile IPTV or Satellite Systems it might be impossible to generate a program schedule for each user, because of bandwidth limitations.A few approaches were proposed to generate group recommendations. However, these approaches take into account that groups of users already exist and no recommender system is able to detect intrinsic users communities.This paper describes an algorithm that detects groups of users whose preferences are similar and predicts recommendations for such groups. Groups of different granularities are generated through a modularity-based Community Detection algorithm, making it possible for a content provider to explore the trade off between the level of personalization of the recommendations and the number of channels. Experimental results show that the quality of group recommendations increases linearly with the number of groups created.

Edge computing is the best approach for meeting the exponential demand and the real-time requirements of many video analytics applications. Since most of the recent advances regarding the extraction of information from images and video rely on computation heavy deep learning algorithms, there is a growing need for solutions that allow the deployment and use of new models on scalable and flexible edge architectures. In this work, we present Deep-Framework, a novel open source framework for developing edge-oriented real-time video analytics applications based on deep learning. Deep-Framework has a scalable multi-stream architecture based on Docker and abstracts away from the user the complexity of cluster configuration, orchestration of services, and GPU resources allocation. It provides Python interfaces for integrating deep learning models developed with the most popular frameworks and also provides high-level APIs based on standard HTTP and WebRTC interfaces for consuming the extracted video data on clients running on browsers or any other web-based platform.

Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized R-R intervals and features relative to the width of the QRS complex are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats respectively. In comparison with other state of the art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

The cost of manual metadata production is high, especially for audiovisual content, where a time-consuming inspection is usually required in order to identify the most appropriate annotations. There is a growing need from digital content industries for solutions capable of automating such a process. In this work we present ACTIVE, a platform for indexing and cataloging audiovisual collections through the automatic recognition of faces and speakers. Adopted algorithms are described and our main contributions on people clustering and caption-based people identification are presented. Results of experiments carried out on a set of TV shows and audio files are reported and analyzed. An overview of the whole architecture is presented as well, with a focus on chosen solutions for making the platform easily extensible (plug-ins) and for distributing CPU-intensive calculations across a network of computers.