Parkinson's disease (PD) predominantly alters the motor performance of the affected individuals. In particular, the loss of dopaminergic neurons compromises the speed, the automaticity and fluidity of movements. As the disease evolves, PD patient's motion becomes slower and tremoric and the response to medication fluctuates along the day. In addition, the presence of involuntary movements deteriorates voluntary movement in advanced state of the disease. These changes in the motion can be detected by studying the variation of the signals recorded by accelerometers attached in the limbs and belt of the patients. The analysis of the most significant changes in these signals make possible to build an individualized motor profile of the disease, allowing doctors to personalize the medication intakes and consequently improving the response of the patient to the treatment. Several works have been done in a laboratory and supervised environments providing solid results; this work focused on the design of unsupervised method for the assessment of gait in PD patients. The development of a reliable quantitative tool for long-term monitoring of PD symptoms would allow the accurate detection of the clinical status during the different PD stages and the evaluation of motor complications. Besides, it would be very useful both for routine clinical care as well as for novel therapies testing.

Recommender Systems have become one of the most important tools for streaming and marketplace systems in recent years. Their increased use has revealed clear bias and unfairness against minorities and underrepresented groups. This paper seeks the origin of these biases and unfairness. To this end, it analyzes the demographic characteristics of a gold standard dataset and its prediction performance when used in a multitude of Recommender Systems. In addition, this paper proposes Soft Matrix Factorization (SoftMF), which tries to balance the predictions of different types of users to reduce the present inequality. The experimental results show that those biases and unfairness are not introduced by the different recommendation models and that they come from the socio-psychological and demographic characteristics of the used dataset. INDEX TERMSRecommender systems, collaborative filtering, fairness, MovieLens. SANTIAGO ALONSO received the B.S. degree in software engineering and the Ph.D. degree in computer science and artificial intelligence from the Universidad Politécnica de Madrid, in 2015. He is currently an Associate Professor with the Universidad Politécnica de Madrid, participating in master and degree subjects and doing work related with advanced databases. His main research interests include natural computing (P-systems) and did some work on genetic algorithms. His current research interests include machine learning, data analysis, and artificial intelligence.

Traditionally, recommender systems have been approached as regression models aiming to predict the score that a user would give to a particular item. In this work, we propose a recommender system that tackles the problem as a classification task instead of as a regression. The new model, Dirichlet Matrix Factorization (DirMF), provides not only a prediction but also its reliability, hence achieving a better balance between the quality and quantity of the predictions (i.e., reducing the prediction error by limiting the model’s coverage). The experimental results conducted show that the proposed model outperforms other models due to its ability to discard unreliable predictions. Compared to our previous model, which uses the same classification approach, DirMF shows a similar efficiency, outperforming the former on some of the datasets included in the experimental setup.

No abstract

No abstract