Abstract

Abstract

Abstract
In this paper, deep convolutional neural networks are used to segment heart sounds into their main components. The proposed method is based on the adoption of a novel deep convolutional neural network architecture, which is inspired by similar approaches used for image segmentation. A further post-processing step is applied to the output of the proposed neural network, which induces the output state sequence to be consistent with the natural sequence of states within a heart sound signal (S1, systole, S2, diastole). The proposed approach is tested on heart sound signals longer than 5 seconds from the publicly available PhysioNet dataset, and it is shown to outperform current state-of-the-art segmentation methods by achieving an average sensitivity of 93.4% and an average positive predictive value of 94.5% in detecting S1 and S2 sounds.

Abstract
Regular monitoring is essential to understand coastal morphodynamics and anthropic as well as natural impacts, at different temporal and spatial scales. A stereoscopic video-based terrestrial mobile mapping system, three airborne digital photography systems (mounted on a small manned airplane, a fixed-wing UAV and a multi-rotor UAV, respectively) and airborne LiDAR were compared in terms of: system features, such as range, autonomy, acquisition and operating costs; information supplied, its type and precision; and constraints to system applicability in coastal topographic surveys. Systems differed in resolution, efficiency, and applicability. The terrestrial and UAV-based systems provided the most accurate 3D data, being particularly suited for small-scale, high-resolution surveys. UAVs were easy to deploy, but limited by weather condition, particularly wind speed. Observations from a plane were most efficient and suited for larger areas. Airborne systems had the advantage of being less (UAV) to non-invasive (plane) and thus suitable for the monitoring of sensitive areas (e.g. dunes) and/or areas with difficult access. Systems should be chosen according to the specific survey aims, spatial scale, and local conditions, taking into account their applicability and cost-benefit ratios. They may complement each other to provide a comprehensive picture of coastal morphology and dynamics at different scales.

Abstract

Abstract
This paper presents a new concept for an approach to deal with measurements contaminated with gross errors, prior to power system state estimation. Instead of a simple filtering operation, the new procedure develops a screen-and-repair process, going through the phases of detection, identification and correction of multiple gross errors. The method is based on the definition of the coverage of the measurement set by a tiling scheme of 3-overlapping autoencoders, trained with denoising techniques and correntropy, that produce an ensemble-like set of three proposals for each measurement. These proposals are then subject to a process of fusion to produce a vector of proposed/corrected measurements, and two fusion methods are compared, with advantage to the Parzen Windows method. The original measurement vector can then be recognized as clean or diagnosed with possible gross errors, together with corrections that remove these errors. The repaired vectors can then serve as input to classical state estimation procedures, as only a small noise remains. A test case illustrates the effectiveness of the technique, which could deal with four simultaneous gross errors and achieve a result close to full recognition and correction of the errors.