• Predicting the success of online petitions leveraging multidimensional time-series

  Proskurnia, Julia; Grabowicz, Przemyslaw; Kobayashi, Ryota; Castillo, Carlos; Cudré-Mauroux, Philippe; Aberer, Karl (ACM Association for Computer Machinery, 2017)

  Applying classical time-series analysis techniques to online content is challenging, as web data tends to have data quality issues and is often incomplete, noisy, or poorly aligned. In this paper, we tackle the problem of ...
• FA*IR: a fair top-k ranking algorithm

  Zehlike, Meike; Bonchi, Francesco; Castillo, Carlos; Hajian, Sara; Megahed, Mohamed; Baeza-Yates, Ricardo (ACM Association for Computer Machinery, 2017)

  In this work, we define and solve the Fair Top-k Ranking problem, in which we want to determine a subset of k candidates from a large pool of n>>k candidates, maximizing utility (i.e., select the “best” candidates) subject ...
• Ranking of social media alerts with workload bounds in emergency operation centers

  Purohit, Hemant; Castillo, Carlos; Imran, Muhammad; Pandey, Rahul (Institute of Electrical and Electronics Engineers (IEEE), 2018)

  xtensive research on social media usage during emergencies has shown its value to provide life-saving information, if a mechanism is in place to filter and prioritize messages. Existing ranking systems can provide a ...
• Facilitating the manual snnotation of sounds when using large taxonomies

  Favory, Xavier; Fonseca, Eduardo; Font, Frederic; Serra, Xavier (FRUCT, 2018)

  Properly annotated multimedia content is crucial for supporting advances in many Information Retrieval applications. It enables, for instance, the development of automatic tools for the annotation of large and diverse ...
• General-purpose tagging of Freesound audio with audioSet labels: task description, dataset, and baseline

  Fonseca, Eduardo; Plakal, Manoj; Font, Frederic; Ellis, Daniel P. W.; Favory, Xavier; Pons, Jordi; Serra, Xavier (Tampere University of Technology, 2018)

  This paper describes Task 2 of the DCASE 2018 Challenge, titled “General-purpose audio tagging of Freesound content with AudioSet labels”. This task was hosted on the Kaggle platform as “Freesound General-Purpose Audio ...
• Overcoming catastrophic forgetting with hard attention to the task

  Serrà, Joan; Surís, Dídac; Miron, Marius; Karatzoglou, Alexandros (Proceedings of Machine Learning Research, 2018)

  Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential ...
• Automatic assessment of violin performance using dynamic time warping classification

  Giraldo, Sergio; Ortega, Ariadna; Perez, Alfonso; Ramírez, Rafael; Waddell, George; Williamon, Aaron (Institute of Electrical and Electronics Engineers (IEEE), 2018)

  The automatic assessment of music performance has become an area of special interest due to the increasing amount of technology-enhanced music learning systems. However, in most of these systems the assessment of the musical ...
• A Simple fusion of deep and shallow learning for acoustic scene classification

  Fonseca, Eduardo; Gong, Rong; Serra, Xavier (Cyprus University of Technology, 2018)

  In the past, Acoustic Scene Classification systems havebeen based on hand crafting audio features that are input toa classifier. Nowadays, the common trend is to adopt datadriven techniques, e.g., deep learning, where audio ...
• Makam recognition using extended pitch distribution features and multi-layer perceptrons

  Yesiler, Furkan; Bozkurt, Baris; Serra, Xavier (Cyprus University of Technology, 2018)

  This work focuses on automatic makam recognition taskfor Turkish makam music (TMM) using pitch distributionsthat are widely used in mode recognition tasks for variousmusic traditions. Here, we aim to improve the performanceof ...
• Early risk detection of anorexia on social media

  Ramíırez-Cifuentes, Diana; Mayans Yern, Marc; Freire, Ana (Springer, 2018)

  This paper proposes an approach for the early detection of anorexia nervosa (AN) on social media. We present a machine learning approach that processes the texts written by social media users. This method relies on a set ...
• Early prediction of Alzheimer's disease with non-local patch-based longitudinal descriptors

  Sanromà, Gerard; Andrea, Víctor; Benkarim, Oualid M.; Manjón, José V.; Coupé, Pierrick; Camara, Oscar; Piella Fenoy, Gemma; González Ballester, Miguel Ángel, 1973- (Springer, 2017)

  Alzheimer’s disease (AD) is characterized by a progressive decline in the cognitive functions accompanied by an atrophic process which can already be observed in the early stages using magnetic resonance images (MRI). ...
• Audio-aligned jazz harmony dataset for automatic chord transcription and corpus-based research

  Serra, Xavier (International Society for Music Information Retrieval (ISMIR), 2018)

  In this paper we present a new dataset of time-aligned jazz harmony transcriptions. This dataset is a useful resource for content-based analysis, especially for training and evaluating chord transcription algorithms. Most ...
• Automatic Makam recognition using chroma features

  Demirel, Emir; Bozkurt, Baris; Serra, Xavier (2018)

  This work focuses on the automatic makam recognition task for Turkish Makam Music using chroma features. Chroma features are widely used for music identification and tonal recognition tasks such as key estimation or chord ...
• FDOT reconstruction and setting optimization using singular value analysis with automatic thresholding

  Chamorro Servent, Judit; Aguirre, Juan; Ripoll, Jorge; Vaquero, Juan J.; Deseo, Manuel (Institute of Electrical and Electronics Engineers (IEEE), 2009)

  Fluorescence Enhanced Diffuse Optical Tomography (FDOT) retrieves 3D distributions of fluorophore concentration in small animals, non-invasively and in vivo. The FDOT problem can be formulated as a system of equations, ...
• Blended MOOCs: university teachers’ perspective

  Albó Pérez, Laia; Hernández Leo, Davinia; Oliver Riera, Miquel (CEUR Workshop Proceedings, 2015)

  Blended Massive Open Online Courses (bMOOCs) have arisen as a blended learning strategy that combines the use of MOOC platform-supported activities and video-based content with in-class face-to-face activities in ...
• A Proposal for the description of audio in the context of MPEG-7

  Herrera Boyer, Perfecto; Serra, Xavier; Peeters, Geoffroy (1999)

  Sound content description is one of the aims of the MPEG-7 initiative. Although MPEG-7 focuses on indexing and retrieval of audio, there are other sound content-based processing applications waiting to be developed once ...
• Extracting relations from unstructured text sources for music recommendation

  Sordo, Mohamed; Oramas, Sergio; Espinosa-Anke, Luis (Springer, 2015)

  This paper presents a method for the generation of struc- tured data sources for music recommendation using information extracted from unstructured text sources. The proposed method identi es entities in text that are ...
• Two-port networks to model galvanic coupling for intrabody communications and power transfer to implants

  Ivorra Cano, Antoni, 1974-; Becerra-Fajardo, Laura; Tudela-Pi, Marc; Ivorra Cano, Antoni, 1974- (Institute of Electrical and Electronics Engineers (IEEE), 2018)

  Galvanic coupling, or more precisely, volume conduction, can be used to communicate with and to transfer power to electronic implants. Since no bulky components for power, such as coils or batteries, are required within ...
• DysMusic: detecting dyslexia by web-based games with music elements

  Rauschenberger, Maria (ACM Association for Computer Machinery, 2016)

  The aim of this research is to show that a playful approach combined with music can detect children with dyslexia. Early detection will prevent children from suffering in school until they are detected due to bad grades. ...
• Terrain backscatter and oil sand exploration: average reflectivity analysis

  Ezeoke, Maurice; Borda Fortuny, Cristina; Tong, Kenneth (Institute of Electrical and Electronics Engineers (IEEE), 2014)

  A barefaced terrain scattering model for oil sand exploration will enable the discrimination of different terrain types using incoherent polarimetric decomposition. We use computer electromagnetic modeling with finite ...

Mostra'n més