Search results for "31"
showing 10 items of 4401 documents
Day-ahead forecasting for photovoltaic power using artificial neural networks ensembles
2016
Solar photovoltaic plants power output forecasting using machine learning techniques can be of a great advantage to energy producers when they are implemented with day-ahead energy market data. In this work a model was developed using a supervised learning algorithm of multilayer perceptron feedforward artificial neural network to predict the next twenty-four hours (day-ahead) power of a solar facility using fetched weather forecast of the following day. Each set of tested network configuration was trained by the historical power output of the plant as a target. For each configuration, one hundred networks ensembles was averaged to give the ability to generalize a better forecast. The train…
Comment on: A critical analysis of the internal logic in the Life-Space Assessment (LSA) composite score and suggested solutions
2016
Background:An individual’s ability to live independently is commonly measured in health research interested in identifying risk factors associated with disablement processes. In order to inform clinical practice, population research has attempted to identify the contraction of “lived-space” by using various survey instruments.Problem:Studies assessing habitual movements over the environment with the Life-Space Assessment (LSA) survey instrument should carefully consider how the LSA Composite Score (LSA-CS) is computed. Until now, no publication has carefully delineated the assumptions guiding the internal logic used in the computation of the LSA-CS.Core argument:Because the internal logic o…
A new approach to partial discharge detection under DC voltage
2018
The continuing development of HVDC power transmission systems presents many problems related to evaluation of the reliability of power system assets [1]-[5]. In this context the identification of insulation defects plays a key role in preventing unexpected failures of electrical components. Partial discharge (PD) measurement is a useful approach to assessing the condition of HV power apparatus and cables. Such measurements are also widely employed for HVAC systems. The inception mechanisms of PD in AC systems are well-known, and measurements are usually performed following the IEC 60270 standard [6]. PD measurements under DC voltage present complexities related to the nature of the phenomen…
Performance Evaluation of a Three- Phase Five-Level Quasi-Z-Source Cascaded H-Bridge for Grid-Connected Applications
2018
In the field of the PV generation, Quasi-Z-source cascaded H-bridge (qZS-CHB) inverters are promising due to their features of modularity and high voltage conversion ratio. Thus, new topology structures and innovative modulation techniques are continuously being developed to improve the performance in terms of voltage stress and harmonic content. This paper proposes an innovative modulation technique that allows reducing the voltage stress and a specially designed grid-connected control strategy is also introduced. Through simulations in MATLAB, it has been validated that the performance of a three-phase five-level qZS-CHB is improved with the proposed solution.
Multi-modality of polysomnography signals’ fusion for automatic sleep scoring
2019
Abstract Objective The study aims to develop an automatic sleep scoring method by fusing different polysomnography (PSG) signals and further to investigate PSG signals’ contribution to the scoring result. Methods Eight combinations of four modalities of PSG signals, namely electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), and electrocardiogram (ECG) were considered to find the optimal fusion of PSG signals. A total of 232 features, covering statistical characters, frequency characters, time-frequency characters, fractal characters, entropy characters and nonlinear characters, were derived from these PSG signals. To select the optimal features for each signal fusion, …
A Meshfree Solver for the MEG Forward Problem
2015
Noninvasive estimation of brain activity via magnetoencephalography (MEG) involves an inverse problem whose solution requires an accurate and fast forward solver. To this end, we propose the Method of Fundamental Solutions (MFS) as a meshfree alternative to the Boundary Element Method (BEM). The solution of the MEG forward problem is obtained, via the Method of Particular Solutions (MPS), by numerically solving a boundary value problem for the electric scalar potential, derived from the quasi-stationary approximation of Maxwell’s equations. The magnetic field is then computed by the Biot-Savart law. Numerical experiments have been carried out in a realistic single-shell head geometry. The p…
Unmanned Aerial Vehicle-Based Non Destructive Diagnostics
2018
The paper proposes a cloud platform for analyzing the radiometric infrared videos uploaded by drones which patrol large photovoltaic plants. Thanks to artificial vision algorithms, it does not require any human support to select and associate the framed PV modules to the corresponding ones in the topology of the photovoltaic plant. The algorithm implements an innovative diagnostic protocol, which evaluates the thermal state of the photovoltaic module, whichever the environmental conditions are. The data automatically computed and collected in a multimedia database provide the O&M technicians with significant information to monitor the ageing of each module of the photovoltaic plant. The pro…
Synchronizing eye tracking and optical motion capture : How to bring them together
2018
Both eye tracking and motion capture technologies are nowadays frequently used in human sciences, although both technologies are usually used separately. However, measuring both eye and body movements simultaneously would offer great potential for investigating cross- modal interaction in human (e.g. music and language-related) behavior. Here we combined an Ergoneers Dikablis head mounted eye tracker with a Qualisys Oqus optical motion cap- ture system. In order to synchronize the recordings of both devices, we developed a gener- alizable solution that does not rely on any (cost-intensive) ready-made / company-provided synchronization solution. At the beginning of each recording, the partic…
Burst analysis tool for developing neuronal networks exhibiting highly varying action potential dynamics
2012
In this paper we propose a firing statistics based neuronal network burst detection algorithm for neuronal networks exhibiting highly variable action potential dynamics. Electrical activity of neuronal networks is generally analyzed by the occurrences of spikes and bursts both in time and space. Commonly accepted analysis tools employ burst detection algorithms based on predefined criteria. However, maturing neuronal networks, such as those originating from human embryonic stem cells (hESC), exhibit highly variable network structure and time-varying dynamics. To explore the developing burst/spike activities of such networks, we propose a burst detection algorithm which utilizes the firing s…
An Optimization Device for Series Parallel Connected PV Plants
2017
In this paper it is presented a testing prototype of a reconfiguration system for photovoltaic (PV) plants. The system enables to increase the total energy output by reducing the electrical mismatch between the PV array modules. The architecture of the implemented switching matrix, performing the dynamic electrical interconnections of the PV panels, enables to reconfigure nine solar modules in a series-parallel (SP) configuration. The contribution is organized as follows. A brief state of the art is first presented, followed by a comparison between the SP and Total-Cross-Tied (TCT) connections. The prototype then is thoroughly described as well as the main design choices. Finally some tests…