The analysis of multimodal data collected by innovative imaging sensors, Internet of Things devices, and user interactions can provide smart and automatic distant monitoring of Parkinson's and Alzheimer's patients and reveal valuable insights for early detection and/or prevention of events related to their health. This article describes a novel system that involves data capturing and multimodal fusion to extract relevant features, analyze data, and provide useful recommendations. The system gathers signals from diverse sources in health monitoring environments, understands the user behavior and context, and triggers proper actions for improving the patient's quality of life. The system offers a multimodal, multi-patient, versatile approach not present in current developments. It also offers comparable or improved results for detection of abnormal behavior in daily motion. The system was implemented and tested during 10 weeks in real environments involving 18 patients.

Indoor/outdoor localization topic has gained a significant research interest due to the wide range of potential applications. Commonly, the Fingerprinting methods for spatial characterization of the environments monitored are employed in deterministic/statistical estimation. However, there are Fingerprint parameters that are generally neglected and can seriously affect the performance yielding to low accurate location. Nowadays, machine and deep learning (DL) methods are employed in this topic due to its ability to approximate complex non-linear models being capable of mitigating the undesirable effects of wireless propagation. In this paper, a complete overview of most influential aspects in Fingerprinting and indoor tracking methods is presented. Furthermore, a novel multi-modal complete tracking system, called SWiBluX, based on statistic and DL techniques is presented. The system relies on relevant feature extraction from available data sources to estimate user's/target indoor position using a multi-phase statistical Fingerprint and DL disruptive approach. In addition, a Gaussian outlier filter is applied to the position estimation model output to further reduce the error in the estimation. The set of experiments performed shows that Fingerprint positioning accuracy estimation can be improved up to 45% resulting in a final estimation error that outperforms related literature.

Abstract-Indoor Localization and Tracking have become an attractive research topic because of the wide range of potential applications. These applications are highly demanding in terms of estimation accuracy and rise a challenge due to the complexity of the scenarios modeled. Approaches for these topics are mainly based on either deterministic or probabilistic methods such as Kalman or Particles Filter. These techniques are improved by fusing information from different sources such as wireless or optical sensors. In this paper, a novel MUlti-sensor Fusion using Adaptive Fingerprint (MUFAF) Algorithm is presented and compared with several multi-sensor indoor localization and tracking methods. MUFAF is mainly divided in four phases: first, a Target Position Estimation (TPE) process is performed by every sensor; second, a Target Tracking Process (TTP) stage; third, a Multi-Sensor fusion (MMF) combines the sensor information and finally, an Adaptive Fingerprint Update (AFU) is applied. For TPE, a complete environment characterization in combination with a Kernel Density Estimation (KDE) technique are employed to obtain object position. A Modified Kalman Filter (MKF) is applied to TPE output in order to smooth target routes and avoid outliers effect. Moreover, two fusion methods are described in this work: Track-To-Track Fusion (TTTF) and Kalman Sensor Group Fusion (KSGF). Finally, AFU will endow the algorithm with responsiveness to environment changes by using Kriging interpolation to update the scenario fingerprint. MUFAF is implemented and compared in a testbed showing that it provides a significant improvement in estimation accuracy and long-term adaptivity to condition changes.

No abstract

The continuous evolution of multimedia applications is fostering applied research in order to dynamically enhance the services provided by platforms such as Spotify, Lastfm, or Billboard. Thus, innovative methods for retrieving specific information from large volumes of data related with music arises as a potential challenge within the Music Information Retrieval (MIR) framework. Moreover, despite the existence of several musical-based datasets, there is still a lack of information to properly assess an accurate estimation of the impact or the popularity of a song within a platform. Furthermore, the aforementioned platforms measure the popularity in various manners, thus increasing the difficulties in performing generalized and comparable models. In this paper, the creation of SpotGenTrack Popularity Dataset (SPD) is presented as an alternative solution to existing datasets that will facilitate researchers when comparing and promoting their models. In addition, an innovative multimodal end-to-end Deep Learning architecture named as HitMusicNet is presented for predicting popularity in music recordings. Experiments conducted show that the proposed architecture outperforms previous studies in the State-of-the-Art by incorporating three main modalities to the analysis, such as audio, lyrics and meta-data as well as a preliminary compression stage via autoencoder to better the capability of the model when predicting the popularity.