BUSCADOR RECOLECTA

This paper presents the Robot-at-Home dataset (Robot@Home), a collection of raw and processed sensory data from domestic settings aimed at serving as a benchmark for semantic mapping algorithms through the categorization of objects and/or rooms. The dataset contains 87,000+ time-stamped observations gathered by a mobile robot endowed with a rig of 4 RGB-D cameras and a 2D laser scanner. Raw observations have been processed to produce different outcomes also distributed with the dataset, including 3D reconstructions and 2D geometric maps of the inspected rooms, both annotated with the ground truth categories of the surveyed rooms and objects. The proposed dataset is particularly suited as a testbed for object and/or room categorization systems, but it can be also exploited for a variety of tasks, including robot localization, 3D map building, SLAM, and object segmentation. Robot@Home is publicly available for the research community at http://mapir.isa.uma.es/work/robot-at-home-dataset., This work has been funded by the Span- ish projects “IRO: Improvement of the sensorial and autonomous capability of Robots through Olfaction” [2012- TEP-530] and “PROMOVE: Advances in mobile robotics for promoting independent life of elders” [DPI2014-55826- R], and the European project “MoveCare: Multiple-actOrs Virtual Empathic CARgiver for the Elder” [Call: H2020- ICT-2016-1, contract number: 732158].

The progress in the field of inertial sensor technology and the widespread popularity of personal electronics such as smartwatches or smartphones have prompted the research on wearable Fall Detection Systems (FDSs). In spite of the extensive literature on FDSs, an open issue is the definition of a common framework that allows a methodical and agreed evaluation of fall detection policies. In this regard, a key aspect is the lack of a public repository of movement datasets that can be employed by the researchers as a common reference to compare and assess their proposals. This work describes UMAFall, a new dataset of movement traces acquired through the systematic emulation of a set of predefined ADLs (Activities of Daily Life) and falls. In opposition to other existing databases for FDSs, which only include the signals captured by one or two sensing points, the testbed deployed for the generation of UMAFall dataset incorporated five wearable sensing points, which were located on five different points of the body of the participants that developed the movements. As a consequence, the obtained data offer an interesting tool to investigate the importance of the sensor placement for the effectiveness of the detection decision in FDSs., Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

Coronary artery disease (CAD) remains the leading cause of death globally and invasive coronary angiography (ICA) is considered the gold standard of anatomical imaging evaluation when CAD is suspected. However, risk evaluation based on ICA has several limitations, such as visual assessment of stenosis severity, which has significant interobserver variability. This motivates to development of a lesion classification system that can support specialists in their clinical procedures. Although deep learning classification methods are well-developed in other areas of medical imaging, ICA image classification is still at an early stage. One of the most important reasons is the lack of available and high-quality open-access datasets. In this paper, we reported a new annotated ICA images dataset, CADICA, to provide the research community with a comprehensive and rigorous dataset of coronary angiography consisting of a set of acquired patient videos and associated disease-related metadata. This dataset can be used by clinicians to train their skills in angiographic assessment of CAD severity, by computer scientists to create computer-aided diagnostic systems to help in such assessment, and to validate existing methods for CAD detection. In addition, baseline classification methods are proposed and analysed, validating the functionality of CADICA with deep learning-based methods and giving the scientific community a starting point to improve CAD detection., Funding for open access charge: Universidad de Málaga/CBUA

[EN] The problem of training with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high num- ber of samples. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, using a limited number of samples. These sounds typically occur in domestic environments where many events corre- sponding to a wide variety of sound classes take place. Therefore, the detection of such alarms in a practi- cal scenario can be considered an open-set recognition (OSR) problem. To address the lack of a dedicated public dataset for audio FSL, researchers usually make modifications on other available datasets. This pa- per is aimed at providing the audio recognition community with a carefully annotated dataset1 for FSL in an OSR context comprised of 1360 clips from 34 classes divided into pattern sounds and unwanted sounds. To facilitate and promote research on this area, results with state-of-the-art baseline systems based on transfer learning are also presented., This work was supported by the EU Horizon 2020 programme [grant No 779158] . Grants DIN2018-009982, PTQ-17-09106, RTI2018-097045-B-C21/C22 funded by MCIN/AEI/10.13039/50110 0 011033, the latter also by "ERDF A way of making Europe ". Grants TED2021-131003B-C21/C22 funded by MCIN/AEI/10.13039/50110 0 011033 and by the "EU Union NextGenerationEU/PRTR ". Grants AICO/2020/154 and AEST/2020/012, funded by GVA. The authors acknowledge also the Artemisa computer resources funded by the EU ERDF and Comunitat Valenciana, and the technical support of IFIC (CSIC-UV) . Authors J. Naranjo, S. Perez and P. Zuccarello were working at Visualfy when this work was done, but they are now with the Instituto Tecnologico de Informatica (ITI) , Tyris AI and ITI, respectively.

[EN] The digital transformation of the defence sector is not exempt from innovative requirements and challenges, with the lack of availability of reliable, unbiased and consistent data for training automatisms (machine learning algorithms, decision-making, what-if recreation of operational conditions, support the human understanding of the hybrid operational picture, personnel training/education, etc.) being one of the most relevant gaps. In the context of cyber defence, the state-of-the-art provides a plethora of data network collections that tend to lack presenting the information of all communication layers (physical to application). They are synthetically generated in scenarios far from the singularities of cyber defence operations. None of these data network collections took into consideration usage profiles and specific environments directly related to acquiring a cyber situational awareness, typically missing the relationship between incidents registered at the hardware/software level and their impact on the military mission assets and objectives, which consequently bypasses the entire chain of dependencies between strategic, operational, tactical and technical domains. In order to contribute to the mitigation of these gaps, this paper introduces CYSAS-S3, a novel dataset designed and created as a result of a joint research action that explores the principal needs for datasets by cyber defence centres, resulting in the generation of a collection of samples that correlate the impact of selected Advanced Persistent Threats (APT) with each phase of their cyber kill chain, regarding mission-level operations and goals.

[EN] In this paper, a public dataset for Offline Handwriting Recognition, along with an appropriate evaluation method to provide benchmark indicators at sentence level, is presented. This dataset, called SPA-Sentences, consists of offline handwritten Spanish sentences extracted from 1617 forms produced by the same number of writers. A total of 13,691 sentences comprising around 100,000 word instances out of a vocabulary of 3288 words occur in the collection. Careful attention has been paid to make the baseline experiments both reproducible and competitive. To this end, experiments are based on state-of-the-art recognition techniques combining convolutional blocks with one-dimensional Bidirectional Long Short Term Memory (LSTM) networks using Connectionist Temporal Classification (CTC) decoding. The scripts with the entire experimental setting have been made available. The SPA-Sentences dataset and its baseline evaluation are freely available for research purposes via the institutional University repository. We expect the research community to include this corpus, as is usually done with English IAM and French RIMES datasets, in their battery of experiments when reporting novel handwriting recognition techniques.

[EN] Searching for information in printed scientific documents is a challenging problem that has recently received special attention from the Pattern Recognition research community. Mathematical expressions are complex elements that appear in scientific documents, and developing techniques for locating and recognizing them requires the preparation of datasets that can be used as benchmarks. Most current techniques for dealing with mathematical expressions are based on Machine Learning techniques which require a large amount of annotated data. These datasets must be prepared with ground-truth information for automatic training and testing. However, preparing large datasets with ground-truth is a very expensive and time-consuming task. This paper introduces the IBEM dataset, consisting of scientific documents that have been prepared for mathematical expression recognition and searching. This dataset consists of 600 documents, more than 8200 page images with more than 160000 mathematical expressions. It has been automatically generated from the Image 1 version of the documents and can be enlarged easily. The ground-truth includes the position at the page level and the Image 1 transcript for mathematical expressions both embedded in the text and displayed. This paper also reports a baseline classification experiment with mathematical symbols and a baseline experiment of Mathematical Expression Recognition performed on the IBEM dataset. These experiments aim to provide some benchmarks for comparison purposes so that future users of the IBEM dataset can have a baseline framework., This work has been partially supported by MCIN/AEI/10.13039/50110 0 011033 under the grant PID2020-116813RB-I00; the Generalitat Valenciana under the FPI grant CIACIF/2021/313; and by the support of the Valencian Graduate School and Research Network of Artificial Intelligence.

Characterizing the spatial patterns of variability is a fundamental aspect when investigating what could be the causes behind the spatial spreading of a set of variables. In this paper, a large multivariate dataset from the southeast of Belgium has been analyzed using factorial kriging. The purpose of the study is to explore and retrieve possible scales of spatial variability of heavy metals. This is achieved by decomposing the variance-covariance matrix of the multivariate sample into coregionalization matrices, which are, in turn, decomposed into transformation matrices, which serve to decompose each regionalized variable as a sum of independent factors. Then, factorial cokriging is used to produce maps of the factors explaining most of the variance, which can be compared with maps of the underlying lithology. For the dataset analyzes, this comparison identifies a few point scale concentrations that may reflect anthropogenic contamination, and it also identifies local and regional scale anomalies clearly correlated to the underlying geology and to known mineralizations. The results from this analysis could serve to guide the authorities in identifying those areas which need remediation.

Grant RTI2018-097045-B-C21/C22 funded by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe, Grant TED2021-131003B-C21/C22 funded by MCIN/AEI/10.13039/501100011033 and by the “EU Union NextGenerationEU/PRTR”, Grants AICO/2020/154 and AEST/2020/012, funded by GVA., The authors acknowledge also the Artemisa computer resources funded by the EU ERDF and Comunitat Valenciana, and the technical support of IFIC (CSIC-UV)., The problem of training with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, using a limited number of samples. These sounds typically occur in domestic environments where many events corresponding to a wide variety of sound classes take place. Therefore, the detection of such alarms in a practical scenario can be considered an open-set recognition (OSR) problem. To address the lack of a dedicated public dataset for audio FSL, researchers usually make modifications on other available datasets. This paper is aimed at providing the audio recognition community with a carefully annotated dataset for FSL in an OSR context comprised of 1360 clips from 34 classes divided into pattern sounds and unwanted sounds. To facilitate and promote research on this area, results with state-of-the-art baseline systems based on transfer learning are also presented., MCIN/AEI/10.13039/501100011033, ERDF, EU Union NextGenerationEU/PRTR, GVA