Search results for " network"

showing 10 items of 6428 documents

Exploring the use of multi-gene genetic programming in regional models for the simulation of monthly river runoff series

2023

The use of new data-driven approaches based on the so-called expert systems to simulate runoff generation processes is a promising frontier that may allow for overcoming some modeling difficulties related to more complex traditional approaches. The present study highlights the potential of expert systems in creating regional hydrological models, for which they can benefit from the availability of large database. Different soft computing models for the reconstruction of the monthly natural runoff in river basins are explored, focusing on a new class of heuristic models, which is the Multi-Gene Genetic Programming (MGGP). The region under study is Sicily (Italy), where a regression based rain…

Artificial Neural NetworkSoft computingEnvironmental EngineeringRegional Runoff ModelSettore ICAR/02 - Costruzioni Idrauliche E Marittime E IdrologiaGenetic ProgrammingEnvironmental ChemistryEvolutionary OptimizationSafety Risk Reliability and QualityGeneral Environmental ScienceWater Science and Technology
researchProduct

Stochastic Vulnerability Assessment of Masonry Structures: Concepts, Modeling and Restoration Aspects

2019

A methodology aiming to predict the vulnerability of masonry structures under seismic action is presented herein. Masonry structures, among which many are cultural heritage assets, present high vulnerability under earthquake. Reliable simulations of their response to seismic stresses are exceedingly difficult because of the complexity of the structural system and the anisotropic and brittle behavior of the masonry materials. Furthermore, the majority of the parameters involved in the problem such as the masonry material mechanical characteristics and earthquake loading characteristics have a stochastic-probabilistic nature. Within this framework, a detailed analytical methodological approac…

Artificial Neural Networkfailure criteriaComputer scienceRestoration mortarStructural system0211 other engineering and technologiesVulnerability020101 civil engineering02 engineering and technologylcsh:Technology0201 civil engineeringlcsh:Chemistryfragility analysisFragilitySeismic assessmentVulnerability assessmentForensic engineeringGeneral Materials ScienceMasonry structurelcsh:QH301-705.5InstrumentationArtificial Neural NetworksmonumentsFluid Flow and Transfer Processes021110 strategic defence & security studieslcsh:Tbusiness.industryProcess Chemistry and TechnologyGeneral EngineeringProbabilistic logicMonumentMasonrylcsh:QC1-999Computer Science ApplicationsCultural heritageSettore ICAR/09 - Tecnica Delle Costruzionilcsh:Biology (General)lcsh:QD1-999restoration mortarslcsh:TA1-2040Fragility analysiseismic assessmentlcsh:Engineering (General). Civil engineering (General)businessdamage indexlcsh:Physicsmasonry structuresstochastic modelingApplied Sciences
researchProduct

Early prediction of COVID-19 outcome using artificial intelligence techniques and only five laboratory indices

2022

We aimed to develop a prediction model for intensive care unit (ICU) hospitalization of Coronavirus disease-19 (COVID-19) patients using artificial neural networks (ANN). We assessed 25 laboratory parameters at first from 248 consecutive adult COVID-19 patients for database creation, training, and development of ANN models. We developed a new alpha-index to assess association of each parameter with outcome. We used 166 records for training of computational simulations (training), 41 for documentation of computational simulations (validation), and 41 for reliability check of computational simulations (testing). The first five laboratory indices ranked by importance were Neutrophil-to-lymphoc…

Artificial intelligence Artificial neural networks COVID-19 Laboratory indices SARS-CoV2Settore ICAR/09 - Tecnica Delle CostruzioniImmunologyImmunology and Allergy
researchProduct

Exploiting deep learning algorithms and satellite image time series for deforestation prediction

2022

In recent years, we have witnessed the emergence of Deep Learning (DL) methods, which have led to enormous progress in various fields such as automotive driving, computer vision, medicine, finances, and remote sensing data analysis. The success of these machine learning methods is due to the ever-increasing availability of large amounts of information and the computational power of computers. In the field of remote sensing, we now have considerable volumes of satellite images thanks to the large number of Earth Observation (EO) satellites orbiting the planet. With the revisit time of satellites over an area becoming shorter and shorter, it will probably soon be possible to obtain daily imag…

Artificial intelligenceDeforestation predictionRéseaux de neurones récurrentsApprentissage profondRecurrent neural networks[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingImage time seriesDeep learningSatellite imagesSéries temporelles d'imagesIntelligence artificiellePrédiction déforestationImages satellitaires
researchProduct

Multi-layer intrusion detection system with ExtraTrees feature selection, extreme learning machine ensemble, and softmax aggregation

2019

Abstract Recent advances in intrusion detection systems based on machine learning have indeed outperformed other techniques, but struggle with detecting multiple classes of attacks with high accuracy. We propose a method that works in three stages. First, the ExtraTrees classifier is used to select relevant features for each type of attack individually for each (ELM). Then, an ensemble of ELMs is used to detect each type of attack separately. Finally, the results of all ELMs are combined using a softmax layer to refine the results and increase the accuracy further. The intuition behind our system is that multi-class classification is quite difficult compared to binary classification. So, we…

Artificial intelligencelcsh:Computer engineering. Computer hardwareExtreme learning machineEnsemble methodsComputer scienceBinary numberlcsh:TK7885-7895Feature selection02 engineering and technologyIntrusion detection systemlcsh:QA75.5-76.95Machine learning0202 electrical engineering electronic engineering information engineeringVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550Multi layerExtreme learning machinebusiness.industryIntrusion detection system020206 networking & telecommunicationsPattern recognitionComputer Science ApplicationsBinary classificationFeature selectionSignal ProcessingSoftmax function020201 artificial intelligence & image processinglcsh:Electronic computers. Computer scienceArtificial intelligencebusinessClassifier (UML)EURASIP Journal on Information Security
researchProduct

Development of artificial neural network for condition assessment of bridges based on hybrid decision making method – Feasibility study

2021

Abstract Managing a bridge at an appropriate level of reliability requires knowledge of its technical condition, which is decisive in terms of maintenance and repair activities. This is a multi-criteria decision-making problem which results from the need to allocate limited financial resources to this work. Although many calculation models have been suggested in published sources, none of them has ever met these requirements. The algorithm presented by the authors allows for the assessment of any number of bridges, taking into account the diversity of solutions in terms of materials and structures, and can provide a solution to this problem. This hybrid calculation model, combining the modi…

Artificial neural network (ANN)Railway bridge0209 industrial biotechnologyExtent analysis fuzzy analytic hierarchy process (EA FAHP)Artificial neural networkComputer scienceGeneral EngineeringMulti-criteria decision analysis (MCDA)Analytic hierarchy process02 engineering and technologyCondition assessmentBridge (nautical)ManagementComputer Science ApplicationsReliability engineering020901 industrial engineering & automationDevelopment (topology)Work (electrical)Artificial IntelligenceDecision making methodsDominant analytic hierarchy process (DAHP)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingBridge management system (BMS)Reliability (statistics)Expert Systems with Applications
researchProduct

Using machine learning to disentangle LHC signatures of Dark Matter candidates

2019

We study the prospects of characterising Dark Matter at colliders using Machine Learning (ML) techniques. We focus on the monojet and missing transverse energy (MET) channel and propose a set of benchmark models for the study: a typical WIMP Dark Matter candidate in the form of a SUSY neutralino, a pseudo-Goldstone impostor in the shape of an Axion-Like Particle, and a light Dark Matter impostor whose interactions are mediated by a heavy particle. All these benchmarks are tensioned against each other, and against the main SM background ($Z$+jets). Our analysis uses both the leading-order kinematic features as well as the information of an additional hard jet. We explore different representa…

Artificial neural network010308 nuclear & particles physicsbusiness.industryComputer sciencePhysicsQC1-999Dark matterFOS: Physical sciencesGeneral Physics and AstronomySupersymmetryMachine learningcomputer.software_genre01 natural sciencesConvolutional neural networkHigh Energy Physics - PhenomenologyHigh Energy Physics - Phenomenology (hep-ph)Robustness (computer science)0103 physical sciencesPrincipal component analysisProbability distributionArtificial intelligence010306 general physicsbusinessLight dark mattercomputerSciPost Physics
researchProduct

Highly Performant, Deep Neural Networks with sub-microsecond latency on FPGAs for Trigger Applications

2020

Artificial neural networks are becoming a standard tool for data analysis, but their potential remains yet to be widely used for hardware-level trigger applications. Nowadays, high-end FPGAs, often used in low-level hardware triggers, offer theoretically enough performance to include networks of considerable size. This makes it very promising and rewarding to optimize a neural network implementation for FPGAs in the trigger context. Here an optimized neural network implementation framework is presented, which typically reaches 90 to 100% computational efficiency, requires few extra FPGA resources for data flow and controlling, and allows latencies in the order of 10s to few 100s of nanoseco…

Artificial neural network010308 nuclear & particles physicsbusiness.industryPhysicsQC1-99901 natural sciencesData flow diagramMicrosecondEmbedded system0103 physical sciencesDeep neural networksLatency (engineering)010306 general physicsField-programmable gate arraybusinessEPJ Web of Conferences
researchProduct

Biodegradability Prediction of Fragrant Molecules by Molecular Topology

2016

Biodegradability is a key property in the development of safer fragrances. In this work we present a green methodology for its preliminary assessment. The structure of various fragrant molecules is characterized by computing a large set of topological indices. Those relevant to biodegradability are selected by means of a hybrid stepwise selection method to build a linear classifier. This model is compared with a more complex artificial neural network trained with the indices previously found. After validation, the models show promise for time and cost reduction in the development of new, safer fragrances. The methodology presented could easily be adapted to many quasi-big data problems in R…

Artificial neural network010405 organic chemistryRenewable Energy Sustainability and the EnvironmentComputer scienceStatistical learningGeneral Chemical EngineeringNanotechnologyLinear classifierGeneral Chemistry01 natural sciences0104 chemical sciencesCost reduction010404 medicinal & biomolecular chemistryDevelopment (topology)SAFEREnvironmental ChemistryBiodegradability predictionBiochemical engineeringMolecular topologyACS Sustainable Chemistry & Engineering
researchProduct

Acoustic Emission Waveform Picking with Time Delay Neural Networks during Rock Deformation Laboratory Experiments

2020

Abstract We report a new method using a time delay neural network to transform acoustic emission (AE) waveforms into a time series of instantaneous frequency content and permutation entropy. This permits periods of noise to be distinguished from signals. The model is trained in sequential batches, using an automated process that steadily improves signal recognition as new data are added. The model was validated using AE data from rock deformation experiments, using Darley Dale sandstone in fully drained conditions at a confining pressure of 20 MPa (approximately 800 m simulated depth). The model is initially trained by manual picking of five high-amplitude waveforms randomly selected from t…

Artificial neural networkAcousticsAcoustic EmissionsRock Physics0211 other engineering and technologiesNeural Network02 engineering and technologyDeformation (meteorology)01 natural sciences010305 fluids & plasmasGeophysicsAcoustic emission0103 physical sciencesWaveformGeology021101 geological & geomatics engineeringRock Physics Acoustic Emissions Neural Network
researchProduct