Search results for "lcsh:TK7885-7895"

showing 10 items of 94 documents

Do Randomized Algorithms Improve the Efficiency of Minimal Learning Machine?

2020

Minimal Learning Machine (MLM) is a recently popularized supervised learning method, which is composed of distance-regression and multilateration steps. The computational complexity of MLM is dominated by the solution of an ordinary least-squares problem. Several different solvers can be applied to the resulting linear problem. In this paper, a thorough comparison of possible and recently proposed, especially randomized, algorithms is carried out for this problem with a representative set of regression datasets. In addition, we compare MLM with shallow and deep feedforward neural network models and study the effects of the number of observations and the number of features with a special dat…

0209 industrial biotechnologyrandom projectionlcsh:Computer engineering. Computer hardwareComputational complexity theoryComputer scienceRandom projectionlcsh:TK7885-789502 engineering and technologyMachine learningcomputer.software_genresupervised learningapproximate algorithmsSet (abstract data type)regressioanalyysi020901 industrial engineering & automationdistance–based regressionalgoritmit0202 electrical engineering electronic engineering information engineeringordinary least–squaresbusiness.industrySupervised learningsingular value decompositionminimal learning machineMultilaterationprojektioRandomized algorithmkoneoppiminenmachine learningScalabilityFeedforward neural network020201 artificial intelligence & image processingArtificial intelligenceapproksimointibusinesscomputerMachine Learning and Knowledge Extraction
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

High temperature solid-catalized transesterification for biodiesel production

2010

Biodiesel has become more attractive recently because of its environmental benefits and the fact that it is made from renewable resources. Biodiesel is a mixture of monoalkyl esters of long chain fatty acids derived from renewable feed stock like vegetable oils and animal fats, mainly made of fatty acid glycerides. It is produced by transesterification processes in which oil or fat are reacted with a monohydric alcohol in the presence of a catalyst. The transesterification process is affected by reaction conditions, alcohol to oil molar ratio, type of alcohol, type and amount of catalysts, temperature and purity of reactants. Heterogeneous acid catalysts are quite efficient in promoting the…

BIODIESELsolid-catalized transesterificationlcsh:Computer engineering. Computer hardwareSettore ING-IND/25 - Impianti ChimiciComputingMethodologies_DOCUMENTANDTEXTPROCESSINGlcsh:TP155-156lcsh:TK7885-7895lcsh:Chemical engineeringComputingMilieux_MISCELLANEOUSbiodiesel transesterificationComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Batch Test Evaluation of Four Organic Substrates Suitable for Biological Groundwater Denitrification

2014

Nitrates pollution represents nowadays a serious issue related to the quality of groundwater; continuous growth of industrial-scale agricultures lead to an increase of nitrates content in groundwater in the last years. Several technologies have been validated as capable to promote in situ biological nitrates remediation, such as permeable reactive barriers (PRB), biotrench, biobarriers etc. These technologies are all characterised by the use of organic substrate that act as a slow release carbon source. In free dissolved oxygen absence, such organic carbon is further oxidised, by heterotrophic bacteria naturally present in soil, in compliance to anoxic metabolism by using nitrates bound oxy…

Biological groundwater Denitrificationlcsh:Computer engineering. Computer hardwareSettore ICAR/03 - Ingegneria Sanitaria-AmbientaleOrganic carbon source.lcsh:TP155-156lcsh:TK7885-7895Batch testlcsh:Chemical engineeringChemical Engineering Transactions
researchProduct

Agronomic Evaluation of Ethiopian Mustard (brassica Carinata A. Braun) Germplasm and Physical-energy Characterization of Crop Residues in a Semi-arid…

2017

Brassica carinata A. Braun is one of the most interesting oilseed crops suited to arid and semi-arid areas for energy purposes. Several studies have highlighted the possibility of introducing this species into cropping systems, typical of Mediterranean region. The aims of this study were to evaluate the agronomic performance of Brassica carinata germplasm under Mediterranean climatic conditions and to assess the physical and energy characteristics of crop residues and pellets made from the residues. A total of 20 different accessions of Brassica carinata were compared in a semi-arid area of Sicily (Italy). In the two-year test period, the main morphological and yield parameters of the acces…

Brassica carinatalcsh:Computer engineering. Computer hardwarecrop residuepelletfungifood and beverageslcsh:TP155-156lcsh:TK7885-7895lcsh:Chemical engineeringenergySettore AGR/02 - Agronomia E Coltivazioni ErbaceeChemical Engineering Transactions
researchProduct

Traditional Enterprise Business Intelligence Software Compared to Software as a Service Business Intelligence

2016

IntroductionBusiness Intelligence is a broad field of study. The major thrust of business intelligence theory analyzes certain factors to make highquality decisions. These factors include customers, competitors, business partners, economic environment and internal operations. Business Intelligence has the power to change the way people work, so that enterprises can compete more effectively and efficiently.A successful business intelligence solutions and successful implementation holds the key to the technological innovations together with the people, processes and culture of an organization to achieve a competitive and profitable BI strategy.Business Intelligence (BI) is the process of acqu…

Business ProcessesBusiness requirementsData WarehouseKnowledge managementlcsh:Computer engineering. Computer hardwarebusiness.industryBusiness ruleCloud Datalcsh:TK7885-7895Business modelBusiness Intelligence Solutionslcsh:Zlcsh:Bibliography. Library science. Information resourcesBusiness process managementProcessBusiness analyticsNew business developmentBusiness intelligenceBusiness casebusinessInformatică economică
researchProduct

Formation of Hematite Nanotubes by Two-Step Electrochemical Anodization for Efficient Degradation of Organic Pollutants

2016

[EN] Nowadays, hematite (alpha-Fe2O3) has emerged as a promising photocatalyst for efficient degradation of organic pollutants due to its properties such as suitable band-gap (similar to 2.1 eV), stability against photocorrosion, abundance and low cost. However, some drawbacks such as low carrier mobility and short hole diffusion length limit its efficiency. In order to overcome these issues, self-ordered nanotubes can be synthetized. Anodization is one of the simplest and most economic techniques to produce nanostructures with high control. In the present study, self-ordered hematite nanotubes were synthetized by two-step electrochemical anodization. In two-step anodization, a first-step w…

Electroquímicalcsh:Computer engineering. Computer hardwarelcsh:TP155-156lcsh:TK7885-7895lcsh:Chemical engineeringINGENIERIA QUIMICAChemical Engineering Transactions
researchProduct

Influence of the Heating Rate on the Annealing Treatment of Iron Oxide Nanostructures Obtained by Electrochemical Anodization under Hydrodynamic Cond…

2017

[EN] Iron oxide nanostructures are promising materials for photoelectrochemical applications such as water splitting. In this work, electrochemical anodization of iron is used to form different iron oxide nanostructures, and the influence of different anodization parameters was studied in order to find the most suitable nanostructure for photocatalysis applications. On the one hand, hydrodynamic conditions were evaluated by stirring the electrode at different rotation speeds during the electrochemical anodization to check their influence on the formation of the nanostructures. On the other hand, different heating rates during the annealing treatment were studied for obtaining efficient iron…

Electroquímicalcsh:Computer engineering. Computer hardwarelcsh:TP155-156lcsh:TK7885-7895lcsh:Chemical engineeringMaterialsINGENIERIA QUIMICA
researchProduct

A Novel System for Measuring Damaging Impacts on Table Olives

2015

The consumer today demands high quality products; fruit with defects or in poor condition generate dissatisfaction and a consequent reduction in consumption. In recent years, interesting systems have been used (i. e. "artificial fruit") in order to identify the cause of damage during mechanical harvesting and/or post-harvest operations. In this paper, the authors present a new system designed to measure the impacts received by table olives in the processing stages from harvesting to packaging. The device is an instrumented sphere designed and implemented by the Agricultural Mechanics Section of the Department of Agricultural and Forest Sciences, University of Palermo, Italy. It contains a t…

MEMSlcsh:Computer engineering. Computer hardwareFruitAccelerationpost harvestSettore AGR/09 - Meccanica AgrariaData acquisitionlcsh:TP155-156lcsh:TK7885-7895Instrumented Spherelcsh:Chemical engineeringAcceleration; Data acquisition; Fruits; MEMS; Instrumented Sphere; post harvestChemical Engineering Transactions
researchProduct

ADVANCED STATISTICAL ANALYSIS OF LOCAL BUBBLE SIZE DISTRIBUTIONS IN 2D GAS FLUIDIZED BEDS

2009

The principal difficulty in analysing fluidization quality and bubble dynamics is related to the possibility of measuring or predicting the physical and geometrical properties of gas bubbles rising in a granular medium. Even the development of detailed experimental correlations gives poor results, being necessary a fully statistical approach. On the above basis, the present work focuses on the statistical analysis of the behaviour of a 2-D fluidized bed operating under bubbling and slugging conditions, performing measurements of Local Bubble Size Distributions (BSD) along the bed. The analysis allowed to observe a characteristic bimodal shape of BSDs for different particles dimension and fl…

Physics::Fluid DynamicsSettore ING-IND/26 - Teoria Dello Sviluppo Dei Processi Chimicilcsh:Computer engineering. Computer hardwarefluidization bubble dynamicsSettore ING-IND/25 - Impianti ChimiciBUBBLE SIZE DISTRIBUTIONlcsh:TP155-156lcsh:TK7885-7895lcsh:Chemical engineeringBubbling fluidized bedChemical Engineering Transactions
researchProduct