Search results for " NEURAL NETWORKS"

showing 10 items of 390 documents

Neural based MRAS sensorless techniques for high performance linear induction motor drives.

2010

This paper proposes a neural based MRAS (Model reference Adaptive System) speed observer suited for linear induction motors (LIM). Starting from the dynamical equation of the LIM in the synchronous reference frame in literature, the so-called voltage and current models of the LIM in the stationary reference frame, taking into consideration the end effects, have been deduced. Then, while the inductor equations have been used as reference model of the MRAS observer, the induced part equations have been discretized and rearranged so to be represented by a linear neural network (ADALINE). On this basis, the so called TLS EXIN neuron has been used to compute on-line, in recursive form, the machi…

EngineeringArtificial neural networkObserver (quantum physics)business.industrySettore ING-INF/04 - AutomaticaControl theoryLinear induction motorAdaptive systembusinessMRASReference modelStationary Reference FrameLinear Induction Motor (LIM) Sensorless control Model Reference Adaptive Systems (MRAS) Neural Networks (NN) Field Oriented Control (FOC)Reference frame
researchProduct

Application of learning pallets for real-time scheduling by use of artificial neural network

2011

Author's version of a chapter in the book: 5th International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA). Also available from the publisher at: http://dx.doi.org/10.1109/SKIMA.2011.6089986 Generally, this paper deals with the problem of autonomy in logistics. Specifically here, a complex problem in inbound logistics is considered as real-time scheduling in a stochastic shop floor problem. Recently, in order to comply with real-time decisions, autonomous logistic objects have been suggested as an alternative. Since pallets are common used objects in carrying materials (finished or semi-finished), so they have the possibility to undertake the …

EngineeringJob shop schedulingArtificial neural networkbusiness.industryVDP::Technology: 500Distributed objectManufacturing systemsIndustrial engineeringVDP::Mathematics and natural science: 400::Mathematics: 410Scheduling (computing)assembly systems learning neural networks real time systemsPalletOpen shopArtificial intelligenceDiscrete event simulationbusiness2011 5th International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA) Proceedings
researchProduct

The Application of Different Model of Multi-Layer Perceptrons in the Estimation of Wind Speed

2012

Wind speed forecasting is essential for effective planning of wind energy exploitation projects. The ability to predict short-term wind speed is a prerequisite for all the operators of the wind energy sector. Consequently it is essential to identify an efficient method for forecasts. In this paper, the wind speed in the province of Trapani (Sicily) is modeled by artificial neural network. Several model of neural network were generated and compared through error measures. Simulation results show that the estimated values of wind speed are in good agreement with the values measured by anemometers..

EstimationArtificial neural networks multi-layer perceptrons wind speed predictionEngineeringWind powerArtificial neural networkMeteorologybusiness.industryAstrophysics::High Energy Astrophysical PhenomenaGeneral EngineeringPerceptronWind speedAnemometerPhysics::Space PhysicsAstrophysics::Solar and Stellar AstrophysicsbusinessMulti layerPhysics::Atmospheric and Oceanic PhysicsAdvanced Materials Research
researchProduct

Back-Propagation Artificial Neural Network for ERP Adoption Cost Estimation

2011

Published version of a chapter in the book: Enterprise information systems, vol 220, part 2, 180-187. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-24355-4_19 Small and medium size enterprises (SMEs) are greatly affected by cost escalations and overruns Reliable cost factors estimation and management is a key for the success of Enterprise Resource Planning (ERP) systems adoptions in enterprises generally and SMEs specifically. This research area is still immature and needs a considerable amount of research to seek solid and realistic cost factors estimation. Majority of research in this area targets the enhancement of estimates calculated by COCOMO family models.…

EstimationERP cost estimation neural networks SMEsCost estimateArtificial neural networkFactor costbusiness.industryCOCOMOComputer scienceMachine learningcomputer.software_genreRisk analysis (engineering)Key (cryptography)Information systemVDP::Social science: 200::Library and information science: 320::Information and communication systems: 321Artificial intelligencebusinesscomputerEnterprise resource planning
researchProduct

Water adsorption on amorphous silica surfaces: A Car-Parrinello simulation study

2005

A combination of classical molecular dynamics (MD) and ab initio Car-Parrinello molecular dynamics (CPMD) simulations is used to investigate the adsorption of water on a free amorphous silica surface. From the classical MD SiO_2 configurations with a free surface are generated which are then used as starting configurations for the CPMD.We study the reaction of a water molecule with a two-membered ring at the temperature T=300K. We show that the result of this reaction is the formation of two silanol groups on the surface. The activation energy of the reaction is estimated and it is shown that the reaction is exothermic.

Exothermic reactionCar–Parrinello molecular dynamicsMaterials scienceAb initioFOS: Physical sciences02 engineering and technologyActivation energy010402 general chemistryRing (chemistry)01 natural scienceschemistry.chemical_compoundMolecular dynamicsAdsorptionGeneral Materials ScienceCondensed Matter - Materials ScienceMaterials Science (cond-mat.mtrl-sci)Disordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Disordered Systems and Neural Networks021001 nanoscience & nanotechnologyCondensed Matter Physics0104 chemical sciencesSilanolchemistry[PHYS.COND.CM-MS]Physics [physics]/Condensed Matter [cond-mat]/Materials Science [cond-mat.mtrl-sci]Physical chemistry0210 nano-technology
researchProduct

USE-Net: Incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets

2019

Prostate cancer is the most common malignant tumors in men but prostate Magnetic Resonance Imaging (MRI) analysis remains challenging. Besides whole prostate gland segmentation, the capability to differentiate between the blurry boundary of the Central Gland (CG) and Peripheral Zone (PZ) can lead to differential diagnosis, since tumor's frequency and severity differ in these regions. To tackle the prostate zonal segmentation task, we propose a novel Convolutional Neural Network (CNN), called USE-Net, which incorporates Squeeze-and-Excitation (SE) blocks into U-Net. Especially, the SE blocks are added after every Encoder (Enc USE-Net) or Encoder-Decoder block (Enc-Dec USE-Net). This study ev…

FOS: Computer and information sciences0209 industrial biotechnologyComputer Science - Machine LearningGeneralizationComputer scienceComputer Vision and Pattern Recognition (cs.CV)Cognitive NeuroscienceComputer Science - Computer Vision and Pattern RecognitionConvolutional neural network02 engineering and technologyConvolutional neural networkMachine Learning (cs.LG)Image (mathematics)Prostate cancer020901 industrial engineering & automationArtificial IntelligenceProstate0202 electrical engineering electronic engineering information engineeringmedicineMedical imagingAnatomical MRISegmentationBlock (data storage)Prostate cancermedicine.diagnostic_testSettore INF/01 - Informaticabusiness.industryAnatomical MRI; Convolutional neural networks; Cross-dataset generalization; Prostate cancer; Prostate zonal segmentation; USE-NetINF/01 - INFORMATICAMagnetic resonance imagingPattern recognitionUSE-Netmedicine.diseaseComputer Science Applicationsmedicine.anatomical_structureCross-dataset generalizationFeature (computer vision)Prostate zonal segmentation020201 artificial intelligence & image processingConvolutional neural networksArtificial intelligencebusinessEncoder
researchProduct

Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection

2021

The number of Earth observation satellites carrying optical sensors with similar characteristics is constantly growing. Despite their similarities and the potential synergies among them, derived satellite products are often developed for each sensor independently. Differences in retrieved radiances lead to significant drops in accuracy, which hampers knowledge and information sharing across sensors. This is particularly harmful for machine learning algorithms, since gathering new ground truth data to train models for each sensor is costly and requires experienced manpower. In this work, we propose a domain adaptation transformation to reduce the statistical differences between images of two…

FOS: Computer and information sciencesAtmospheric ScienceComputer Science - Machine LearningGenerative adversarial networks010504 meteorology & atmospheric sciencesComputer scienceRemote sensing applicationdomain adaptationGeophysics. Cosmic physics0211 other engineering and technologiesCloud computing02 engineering and technologycomputer.software_genre01 natural sciencesImage (mathematics)Data modelingMachine Learning (cs.LG)convolutional neural networksFOS: Electrical engineering electronic engineering information engineeringLandsat-8Computers in Earth SciencesAdaptation (computer science)TC1501-1800021101 geological & geomatics engineering0105 earth and related environmental sciencesbusiness.industryQC801-809Image and Video Processing (eess.IV)Electrical Engineering and Systems Science - Image and Video ProcessingOcean engineeringTransformation (function)cloud detectionSatelliteData miningProba-VTransfer of learningbusinesscomputer
researchProduct

A Deep Network Approach to Multitemporal Cloud Detection

2018

We present a deep learning model with temporal memory to detect clouds in image time series acquired by the Seviri imager mounted on the Meteosat Second Generation (MSG) satellite. The model provides pixel-level cloud maps with related confidence and propagates information in time via a recurrent neural network structure. With a single model, we are able to outline clouds along all year and during day and night with high accuracy.

FOS: Computer and information sciencesComputer Science - Machine Learning010504 meteorology & atmospheric sciencesComputer scienceFeature extraction0211 other engineering and technologiesCloud detectionFOS: Physical sciencesCloud computing02 engineering and technologyCloud detection01 natural sciencesMachine Learning (cs.LG)Laboratory of Geo-information Science and Remote SensingLaboratorium voor Geo-informatiekunde en Remote Sensing021101 geological & geomatics engineering0105 earth and related environmental sciencesRemote sensingbusiness.industrySeviriDeep learningDeep learningPE&RCPhysics - Atmospheric and Oceanic PhysicsRecurrent neural networkRecurrent neural networksAtmospheric and Oceanic Physics (physics.ao-ph)Convolutional neural networksSatelliteArtificial intelligencebusinessNetwork approachIGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
researchProduct

Transfer Learning with Convolutional Networks for Atmospheric Parameter Retrieval

2018

The Infrared Atmospheric Sounding Interferometer (IASI) on board the MetOp satellite series provides important measurements for Numerical Weather Prediction (NWP). Retrieving accurate atmospheric parameters from the raw data provided by IASI is a large challenge, but necessary in order to use the data in NWP models. Statistical models performance is compromised because of the extremely high spectral dimensionality and the high number of variables to be predicted simultaneously across the atmospheric column. All this poses a challenge for selecting and studying optimal models and processing schemes. Earlier work has shown non-linear models such as kernel methods and neural networks perform w…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceFeature extraction0211 other engineering and technologiesTranfer learningFOS: Physical sciences02 engineering and technologyAtmospheric modelInfrared atmospheric sounding interferometercomputer.software_genreConvolutional neural networkMachine Learning (cs.LG)0202 electrical engineering electronic engineering information engineeringInfrared measurements021101 geological & geomatics engineeringArtificial neural networkStatistical modelNumerical weather predictionParameter retrievalPhysics - Atmospheric and Oceanic PhysicsKernel method13. Climate actionAtmospheric and Oceanic Physics (physics.ao-ph)Convolutional neural networks020201 artificial intelligence & image processingData miningcomputerCurse of dimensionalityIGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
researchProduct

Neural Teleportation

2023

In this paper, we explore a process called neural teleportation, a mathematical consequence of applying quiver representation theory to neural networks. Neural teleportation "teleports" a network to a new position in the weight space and preserves its function. This phenomenon comes directly from the definitions of representation theory applied to neural networks and it turns out to be a very simple operation that has remarkable properties. We shed light on surprising and counter-intuitive consequences neural teleportation has on the loss landscape. In particular, we show that teleportation can be used to explore loss level curves, that it changes the local loss landscape, sharpens global m…

FOS: Computer and information sciencesComputer Science - Machine LearningGeneral MathematicsComputer Science (miscellaneous)Computer Science - Neural and Evolutionary ComputingQuantum PhysicsNeural and Evolutionary Computing (cs.NE)Engineering (miscellaneous)quiver representations; neural networks; teleportationMachine Learning (cs.LG)
researchProduct