34 research outputs found
Aide a la decision dans le risque: modele et logiciel
No full textSIGLEINIST T 76633 / INIST-CNRS - Institut de l'Information Scientifique et TechniqueFRFranc
Interactive microcomputer model for solar radiation evaluation and photovoltaic output comparison
No full textThe basic resource of all solar systems is the sun, and a knowledge of the quantity of the energy available is of prime importance. Although the solar radiation outside the atmosphere is known and almost constant, various climatic factors cause wide variations in its value on the earth's surface. In addition, the relative position of the sun with respect to local points of interest will allow surfaces with different orientations and tracking ability to receive different quantities of solar energy. This research focuses on the effect of cloud cover on the solar radiation received on the earth's surface and presents computer models that calculate its value for the best system configuration. Then a complete assessment of the electrical output of such a system is given. With this purpose in mind, two solar resource evaluation models have been developed; the first method is based on a direct statistical approach correlating clear sky total daily radiation with measured daily insolation. This approach has been applied to a few selected sites and offers the procedure for extending the same coefficients to other sites with similar weather patterns. This model has been tested for six sites in Bangladesh . These sites are located around a "reference" site . The predictions made have shown to be quite accurate. The second model uses an analytical approach that combines clear sky methods with "correction" factors which are based on long term recorded solar ra- diation. In addition, this model has been enhanced by an algorithm that selects the optimal surface orientation that maximizes solar output. Finally, the hourly electrical output of the photovoltaic system is calculated after accounting for the various losses. This is presented as part of a complete solar energy evaluation model.M.S
Audiovisual Analysis of Music Performances: Overview of an Emerging Field
No full textIn the physical sciences and engineering domains, music has traditionally been considered an acoustic phenomenon. From a perceptual viewpoint, music is naturally associated with hearing, i.e., the audio modality. Moreover, for a long time, the majority of music recordings were distributed through audio-only media, such as vinyl records, cassettes, compact discs, and mp3 files. As a consequence, existing automated music analysis approaches predominantly focus on audio signals that represent information from the acoustic rendering of music.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Multimedia Computin
Automatic Detection and Classification of Manufacturing Defects in Metal Boxes
No full textInternational audienc
Automatic detection and classification of manufacturing defects in metal boxes using deep neural networks
No full textThis paper develops a new machine vision framework for efficient detection and classification of manufacturing defects in metal boxes. Previous techniques, which are based on either visual inspection or on hand-crafted features, are both inaccurate and time consuming. In this paper, we show that by using autoencoder deep neural network (DNN) architecture, we are able to not only classify manufacturing defects, but also localize them with high accuracy. Compared to traditional techniques, DNNs are able to learn, in a supervised manner, the visual features that achieve the best performance. Our experiments on a database of real images demonstrate that our approach overcomes the state-of-the-art while remaining computationally competitive
