Search results for " image processing."

showing 10 items of 2265 documents

Population Monte Carlo Schemes with Reduced Path Degeneracy

2017

Population Monte Carlo (PMC) algorithms are versatile adaptive tools for approximating moments of complicated distributions. A common problem of PMC algorithms is the so-called path degeneracy; the diversity in the adaptation is endangered due to the resampling step. In this paper we focus on novel population Monte Carlo schemes that present enhanced diversity, compared to the standard approach, while keeping the same implementation structure (sample generation, weighting and resampling). The new schemes combine different weighting and resampling strategies to reduce the path degeneracy and achieve a higher performance at the cost of additional low computational complexity cost. Computer si…

Computational complexity theoryMonte Carlo methodApproximation algorithm020206 networking & telecommunications02 engineering and technology01 natural sciencesStatistics::ComputationWeighting010104 statistics & probabilitysymbols.namesake[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingGaussian noiseResamplingPath (graph theory)0202 electrical engineering electronic engineering information engineeringsymbols0101 mathematicsDegeneracy (mathematics)Algorithm[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processingComputingMilieux_MISCELLANEOUS
researchProduct

RNN- and LSTM-Based Soft Sensors Transferability for an Industrial Process

2021

The design and application of Soft Sensors (SSs) in the process industry is a growing research field, which needs to mediate problems of model accuracy with data availability and computational complexity. Black-box machine learning (ML) methods are often used as an efficient tool to implement SSs. Many efforts are, however, required to properly select input variables, model class, model order and the needed hyperparameters. The aim of this work was to investigate the possibility to transfer the knowledge acquired in the design of a SS for a given process to a similar one. This has been approached as a transfer learning problem from a source to a target domain. The implementation of a transf…

Computational complexity theoryProcess (engineering)Computer sciencesulfur recovery unit02 engineering and technologytransfer learningMachine learningcomputer.software_genrelcsh:Chemical technologyBiochemistryRNNField (computer science)ArticleAnalytical ChemistryDomain (software engineering)0202 electrical engineering electronic engineering information engineeringlcsh:TP1-1185Electrical and Electronic EngineeringInstrumentationsystem identificationHyperparameterbusiness.industry020208 electrical & electronic engineeringdynamical modelsSystem identificationAtomic and Molecular Physics and OpticsNonlinear systemRecurrent neural networksoft sensors020201 artificial intelligence & image processingArtificial intelligenceTransfer of learningbusinessLSTMcomputerDynamical models; LSTM; RNN; Soft sensors; Sulfur recovery unit; System identification; Transfer learningSensors
researchProduct

Creation and cognition for humanoid live dancing

2016

Abstract Computational creativity in dancing is a recent and challenging research field in Artificial Intelligence and Robotics. We present a cognitive architecture embodied in a humanoid robot capable to create and perform dances driven by the perception of music. The humanoid robot is able to suitably move, to react to human mate dancers and to generate novel and appropriate sequences of movements. The approach is based on a cognitive architecture that integrates Hidden Markov Models and Genetic Algorithms. The system has been implemented on a NAO robot and tested in public setting-up live performances, obtaining positive feedbacks from the audience.

Computational creativityComputer scienceComputational creativityGeneral MathematicsCognitive robotics02 engineering and technologyCognitive architectures03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineeringHidden Markov modelDancing robotSettore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionibusiness.industryRoboticsCognitionCognitive architectureCognitive architectureComputer Science ApplicationsControl and Systems EngineeringEmbodied cognition020201 artificial intelligence & image processingArtificial intelligenceCognitive roboticsbusiness030217 neurology & neurosurgerySoftwareHumanoid robotCognitive roboticRobotics and Autonomous Systems
researchProduct

From Deep Learning to Deep University: Cognitive Development of Intelligent Systems

2018

Search is not only an instrument to find intended information. Ability to search is a basic cognitive skill helping people to explore the world. It is largely based on personal intuition and creativity. However, due to the emerged big data challenge, people require new forms of training to develop or improve this ability. Current developments within Cognitive Computing and Deep Learning enable artificial systems to learn and gain human-like cognitive abilities. This means that the skill how to search efficiently and creatively within huge data spaces becomes one of the most important ones for the cognitive systems aiming at autonomy. This skill cannot be pre-programmed, it requires learning…

Computational creativityComputer sciencemedia_common.quotation_subjectBig dataCognitive computingsyväoppiminen02 engineering and technologycomputational creativity020204 information systems0202 electrical engineering electronic engineering information engineeringCognitive developmentCognitive skillmedia_commonexploratory searchbusiness.industryIntelligent decision support systemdeep learningCognitionCreativityData sciencecognitive systemdeep university020201 artificial intelligence & image processingkognitiivinen kehitysbusinessAutonomyIntuition
researchProduct

An automatic system for humanoid dance creation

2016

Abstract The paper describes a novel approach to allow a robot to dance following musical rhythm. The proposed system generates a dance for a humanoid robot through the combination of basic movements synchronized with the music. The system made up of three parts: the extraction of features from audio file, estimation of movements through the Hidden Markov Models and, finally, the generation of dance. Starting from a set of given movements, the robot choices sequence of movements a suitable Hidden Markov Model, and synchronize them processing musical input. The proposed approach has the advantage that movement execution probabilities could be changed according evaluation of the dance executi…

Computational creativityDanceRobotComputational creativityCognitive NeuroscienceExperimental and Cognitive Psychology02 engineering and technology03 medical and health sciences0302 clinical medicineArtificial IntelligenceRobustness (computer science)0202 electrical engineering electronic engineering information engineeringHidden Markov modelSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniMovement (music)business.industryCognitive architectureDanceRobotCo-creative toolMusic perception020201 artificial intelligence & image processingArtificial intelligencePsychologybusiness030217 neurology & neurosurgeryHumanoid robotBiologically Inspired Cognitive Architectures
researchProduct

Evaluation of Structural and Temporal Properties of Ego Networks for Data Availability in DOSNs

2017

The large diffusion of Online Social Networks (OSNs) has influenced the way people interact with each other. OSNs present several drawbacks, one of the most important is the problem of privacy disclosures. Distributed Online Social Networks (DOSNs) have been proposed as a valid alternative solution to solve this problem. DOSNs are Online Social Networks implemented on a distributed platform, such as a P2P system or a mobile network. However, the decentralization of the control presents several challenges, one of the main ones is guaranteeing data availability without relying on a central server. To this aim, users’ data allocation strategies have to be defined and this requires the knowledg…

Computer Networks and CommunicationsComputer scienceCommunity detection; Data availability; DOSN; P2P; Social networks; Temporal affinity; Software; Information Systems; Hardware and Architecture; Computer Networks and CommunicationsControl (management)Information System02 engineering and technologySocial networksField (computer science)Task (project management)Order (exchange)0202 electrical engineering electronic engineering information engineeringDOSNSocial networkStructure (mathematical logic)P2PCommunity detectionSocial networkbusiness.industry020206 networking & telecommunicationsData scienceData availabilityData availabilityHardware and ArchitectureCellular network020201 artificial intelligence & image processingTemporal affinitybusinessSoftwareInformation SystemsComputer networkMobile Networks and Applications
researchProduct

A Fly-Inspired Mushroom Bodies Model for Sensory-Motor Control Through Sequence and Subsequence Learning

2016

Classification and sequence learning are relevant capabilities used by living beings to extract complex information from the environment for behavioral control. The insect world is full of examples where the presentation time of specific stimuli shapes the behavioral response. On the basis of previously developed neural models, inspired by Drosophila melanogaster, a new architecture for classification and sequence learning is here presented under the perspective of the Neural Reuse theory. Classification of relevant input stimuli is performed through resonant neurons, activated by the complex dynamics generated in a lattice of recurrent spiking neurons modeling the insect Mushroom Bodies n…

Computer Networks and CommunicationsComputer scienceDecision MakingModels NeurologicalAction PotentialsContext (language use)Insect mushroom bodies bio-inspired control spiking neurons02 engineering and technologyVariation (game tree)Motor Activitybio-inspired control03 medical and health sciences0302 clinical medicineRewardSubsequence0202 electrical engineering electronic engineering information engineeringAnimalsLearningComputer SimulationMushroom BodiesTRACE (psycholinguistics)NeuronsSequencebio-inspired control; Insect mushroom bodies; learning; neural model; resonant neurons; spiking neurons; Action Potentials; Animals; Computer Simulation; Decision Making; Drosophila melanogaster; Learning; Motor Activity; Mushroom Bodies; Neurons; Perception; Reward; Robotics; Models Neurological; Neural Networks Computerspiking neuronsbusiness.industryRoboticsGeneral MedicineInsect mushroom bodiesComplex dynamicsDrosophila melanogasterMushroom bodiesPerception020201 artificial intelligence & image processingNeural Networks ComputerArtificial intelligenceSequence learningbusiness030217 neurology & neurosurgery
researchProduct

Performance analysis of user-centric SBS deployment with load balancing in heterogeneous cellular networks: A Thomas cluster process approach

2020

Abstract In conventional heterogeneous cellular networks (HCNets), the locations of user equipments (UEs) and base stations (BSs) are modeled randomly using two different homogeneous Poisson point processes (PPPs). However, this might not be a suitable assumption in case of UE distribution because UE density is not uniform everywhere in HCNets. Keeping in view the existence of nonuniform UEs, the small base stations (SBSs) are assumed to be deployed in the areas with high UE density, which results in correlation between UEs and BS locations. In this paper, we analyse the performance of HCNets with nonuniform UE deployment containing a union of clustered and uniform UE sets. The clustered UE…

Computer Networks and CommunicationsComputer scienceDistributed computing020206 networking & telecommunications02 engineering and technologyLoad balancing (computing)Poisson distributionsymbols.namesakeBase station0202 electrical engineering electronic engineering information engineeringsymbolsCellular network020201 artificial intelligence & image processingNetwork performanceStochastic geometryComputer Networks
researchProduct

Practical considerations for acoustic source localization in the IoT era: Platforms, energy efficiency, and performance

2019

The rapid development of the Internet of Things (IoT) has posed important changes in the way emerging acoustic signal processing applications are conceived. While traditional acoustic processing applications have been developed taking into account high-throughput computing platforms equipped with expensive multichannel audio interfaces, the IoT paradigm is demanding the use of more flexible and energy-efficient systems. In this context, algorithms for source localization and ranging in wireless acoustic sensor networks can be considered an enabling technology for many IoT-based environments, including security, industrial, and health-care applications. This paper is aimed at evaluating impo…

Computer Networks and CommunicationsComputer scienceDistributed computingContext (language use)02 engineering and technologyParallel architectures0202 electrical engineering electronic engineering information engineeringParallel processingWirelessSignal processingMulti-core processorHeterogeneous (hybrid) systemsbusiness.industry020206 networking & telecommunicationsAcoustic source localizationWireless acoustic sensor networks (WASNs)Computer Science ApplicationsEnergy efficiencyHardware and ArchitectureSignal Processing020201 artificial intelligence & image processingElectrónicabusinessWireless sensor networkSource localizationInformation SystemsEfficient energy useAcoustic signal processing
researchProduct

Learning Automata-based Misinformation Mitigation via Hawkes Processes

2021

AbstractMitigating misinformation on social media is an unresolved challenge, particularly because of the complexity of information dissemination. To this end, Multivariate Hawkes Processes (MHP) have become a fundamental tool because they model social network dynamics, which facilitates execution and evaluation of mitigation policies. In this paper, we propose a novel light-weight intervention-based misinformation mitigation framework using decentralized Learning Automata (LA) to control the MHP. Each automaton is associated with a single user and learns to what degree that user should be involved in the mitigation strategy by interacting with a corresponding MHP, and performing a joint ra…

Computer Networks and CommunicationsComputer scienceDistributed computingStochastic optimizationSocial media Misinformation02 engineering and technologyCrisis mitigationArticleTheoretical Computer ScienceLearning automata020204 information systemsConvergence (routing)0202 electrical engineering electronic engineering information engineeringState spaceSocial mediaMisinformationVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550Social networkLearning automatabusiness.industryAutomaton020201 artificial intelligence & image processingStochastic optimizationbusinessHawkes processesSoftwareInformation Systems
researchProduct