Search results for "NETWORK"

showing 10 items of 7718 documents

MFNet: Multi-feature convolutional neural network for high-density crowd counting

2020

The crowd counting task involves the issue of security, so now more and more people are concerned about it. At present, the most difficult problem of population counting consists in: how to make the model distinguish human head features more finely in the densely populated area, such as head overlap and how to find a small-scale local head feature in an image with a wide range of population density. Facing these challenges, we propose a network for multiple feature convolutional neural network, which is called MFNet. It aims to get high-quality density maps in the high-density crowd scene, and at the same time to perform the task of the count and estimation of the crowd. In terms of crowd c…

0209 industrial biotechnologyeducation.field_of_studyHuman headComputer sciencebusiness.industryPopulationPattern recognition02 engineering and technologyConvolutional neural networkImage (mathematics)Support vector machineTask (computing)Range (mathematics)020901 industrial engineering & automationFeature (computer vision)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligenceeducationbusiness2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)
researchProduct

Input Selection Methods for Soft Sensor Design: A Survey

2020

Soft Sensors (SSs) are inferential models used in many industrial fields. They allow for real-time estimation of hard-to-measure variables as a function of available data obtained from online sensors. SSs are generally built using industries historical databases through data-driven approaches. A critical issue in SS design concerns the selection of input variables, among those available in a candidate dataset. In the case of industrial processes, candidate inputs can reach great numbers, making the design computationally demanding and leading to poorly performing models. An input selection procedure is then necessary. Most used input selection approaches for SS design are addressed in this …

0209 industrial biotechnologylcsh:T58.5-58.64lcsh:Information technologyComputer Networks and CommunicationsComputer scienceFeature selectionprediction02 engineering and technologyFunction (mathematics)input selectionSoft sensorcomputer.software_genresoft sensor; inferential model; input selection; feature selection; regression; predictionfeature selection020901 industrial engineering & automationinferential model0202 electrical engineering electronic engineering information engineeringsoft sensorregression020201 artificial intelligence & image processingData miningInput selectioncomputerSelection (genetic algorithm)Future Internet
researchProduct

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

Using Inverse Reinforcement Learning with Real Trajectories to Get More Trustworthy Pedestrian Simulations

2020

Reinforcement learning is one of the most promising machine learning techniques to get intelligent behaviors for embodied agents in simulations. The output of the classic Temporal Difference family of Reinforcement Learning algorithms adopts the form of a value function expressed as a numeric table or a function approximator. The learned behavior is then derived using a greedy policy with respect to this value function. Nevertheless, sometimes the learned policy does not meet expectations, and the task of authoring is difficult and unsafe because the modification of one value or parameter in the learned value function has unpredictable consequences in the space of the policies it represents…

0209 industrial biotechnologyreinforcement learningComputer scienceGeneral Mathematics02 engineering and technologypedestrian simulationTask (project management)learning by demonstration020901 industrial engineering & automationAprenentatgeInformàticaBellman equation0202 electrical engineering electronic engineering information engineeringComputer Science (miscellaneous)Reinforcement learningEngineering (miscellaneous)business.industrycausal entropylcsh:MathematicsProcess (computing)020206 networking & telecommunicationsFunction (mathematics)inverse reinforcement learninglcsh:QA1-939Problem domainTable (database)Artificial intelligenceTemporal difference learningbusinessoptimizationMathematics
researchProduct

Dissipativity-Based Small-Gain Theorems for Stochastic Network Systems

2016

In this paper, some small-gain theorems are proposed for stochastic network systems which describe large-scale systems with interconnections, uncertainties and random disturbances. By the aid of conditional dissipativity and showing times of stochastic interval, small-gain conditions proposed for the deterministic case are extended to the stochastic case. When some design parameters are tunable in practice, we invaginate a simpler method to verify small-gain condition by selecting one subsystem as a monitor. Compared with the existing results, the existence-and-uniqueness of solution and ultimate uniform boundedness of input are removed from requirements of input-to-state stability and smal…

0209 industrial biotechnologystochastic systemsComputer Science Applications1707 Computer Vision and Pattern Recognition02 engineering and technologyInterval (mathematics)Stability (probability)Electronic mailComputer Science Applicationsinput-to-state stabilityDissipativity; input-to-state stability; network systems; stochastic systems; Control and Systems Engineering; Computer Science Applications1707 Computer Vision and Pattern Recognition; Electrical and Electronic EngineeringNonlinear system020901 industrial engineering & automationnetwork systemsControl and Systems EngineeringControl theoryControl system0202 electrical engineering electronic engineering information engineeringUniform boundedness020201 artificial intelligence & image processingStochastic optimizationElectrical and Electronic EngineeringDissipativityMathematicsIEEE Transactions on Automatic Control
researchProduct

Nonlinear statistical retrieval of surface emissivity from IASI data

2017

Emissivity is one of the most important parameters to improve the determination of the troposphere properties (thermodynamic properties, aerosols and trace gases concentration) and it is essential to estimate the radiative budget. With the second generation of infrared sounders, we can estimate emissivity spectra at high spectral resolution, which gives us a global view and long-term monitoring of continental surfaces. Statistically, this is an ill-posed retrieval problem, with as many output variables as inputs. We here propose nonlinear multi-output statistical regression based on kernel methods to estimate spectral emissivity given the radiances. Kernel methods can cope with high-dimensi…

0211 other engineering and technologies020206 networking & telecommunications02 engineering and technologyAtmospheric modelInfrared atmospheric sounding interferometerLeast squaresKernel method13. Climate actionKernel (statistics)Linear regression0202 electrical engineering electronic engineering information engineeringEmissivityKernel regressionPhysics::Atmospheric and Oceanic Physics021101 geological & geomatics engineeringRemote sensingMathematics2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
researchProduct

An Artificial Bee Colony Approach for Classification of Remote Sensing Imagery

2018

This paper presents a novel Artificial Bee Colony (ABC) approach for supervised classification of remote sensing images. One proposes to apply an ABC algorithm to optimize the coefficients of the set of polynomial discriminant functions. We have experimented the proposed ABC-based classifier algorithm for a Landsat 7 ETM+ image database, evaluating the influence of the ABC model parameters on the classifier performances. Such ABC model parameters are: numbers of employed/onlooker/scout bees, number of epochs, and polynomial degree. One has compared the best ABC classifier Overall Accuracy (OA) with the performances obtained using a set of benchmark classifiers (NN, NP, RBF, and SVM). The re…

021103 operations researchArtificial neural networkComputer science0211 other engineering and technologies02 engineering and technologyArtificial bee colony algorithmSupport vector machineStatistical classificationAbc modelComputingMethodologies_PATTERNRECOGNITIONDiscriminant0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingDegree of a polynomialClassifier (UML)Remote sensing2018 10th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)
researchProduct

PolyACO+: a multi-level polygon-based ant colony optimisation classifier

2017

Ant Colony Optimisation for classification has mostly been limited to rule based approaches where artificial ants walk on datasets in order to extract rules from the trends in the data, and hybrid approaches which attempt to boost the performance of existing classifiers through guided feature reductions or parameter optimisations. A recent notable example that is distinct from the mainstream approaches is PolyACO, which is a proof of concept polygon-based classifier that resorts to ant colony optimisation as a technique to create multi-edged polygons as class separators. Despite possessing some promise, PolyACO has some significant limitations, most notably, the fact of supporting classific…

021103 operations researchArtificial neural networkComputer sciencebusiness.industryPolygonsTraining timeMulti-levelling0211 other engineering and technologiesPattern recognition02 engineering and technologyAnt colonySupport vector machineArtificial IntelligenceMultiple time dimensionsPolygonAnt colony optimisation0202 electrical engineering electronic engineering information engineeringArtificial Ants020201 artificial intelligence & image processingArtificial intelligenceClassificationsbusinessClassifier (UML)
researchProduct

Aesthetic considerations for the min-max K-Windy Rural Postman Problem

2017

[EN] The aesthetic quality of routes is a feature of route planning that is of practical importance, but receives relatively little attention in the literature. Several practitioners have pointed out that the visual appeal of a proposed set of routes can have a strong influence on the willingness of a client to accept or reject a specific routing plan. While some work has analyzed algorithmic performance relative to traditional min-sum or min-max objective functions and aesthetic objective functions, we are not aware of any work that has considered a multi-objective approach. This work considers a multi-objective variant of the Min-Max K-Vehicles Windy Rural Postman Problem, discusses sever…

021103 operations researchComputer Networks and Communications0211 other engineering and technologiesMin-Max objective02 engineering and technologyMulti-Objective problemsCombinatoricsArc routing problemsAesthetic objectiveHardware and Architecture0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingMATEMATICA APLICADAHumanitiesSoftwareInformation SystemsMathematicsNetworks
researchProduct

The minimum mean cycle-canceling algorithm for linear programs

2022

Abstract This paper presents the properties of the minimum mean cycle-canceling algorithm for solving linear programming models. Originally designed for solving network flow problems for which it runs in strongly polynomial time, most of its properties are preserved. This is at the price of adapting the fundamental decomposition theorem of a network flow solution together with various definitions: that of a cycle and the way to calculate its cost, the residual problem, and the improvement factor at the end of a phase. We also use the primal and dual necessary and sufficient optimality conditions stated on the residual problem for establishing the pricing step giving its name to the algorith…

021103 operations researchInformation Systems and ManagementGeneral Computer ScienceLinear programmingDegenerate energy levels0211 other engineering and technologiesPhase (waves)0102 computer and information sciences02 engineering and technologyManagement Science and Operations ResearchResidualFlow network01 natural sciencesIndustrial and Manufacturing EngineeringDual (category theory)010201 computation theory & mathematicsModeling and SimulationCoefficient matrixRowAlgorithmMathematicsEuropean Journal of Operational Research
researchProduct