Search results for "Word error rate"

showing 10 items of 26 documents

A new AR authoring tool using depth maps for industrial procedures

2013

Several augmented reality systems have been proposed for different target fields such as medical, cultural heritage and military. However, most of the current AR authoring tools are actually programming interfaces that are exclusively suitable for programmers. In this paper, we propose an AR authoring tool which provides advanced visual effect, such as occlusion or media contents. This tool allows non-programming users to develop low-cost AR applications, specially oriented to on-site assembly and maintenance/repair tasks. A new 3D edition interface is proposed, using photos and Kinect depth information to improve 3D scenes composition. In order to validate our AR authoring tool, two evalua…

0209 industrial biotechnologyGeneral Computer ScienceMultimediaInterface (Java)Computer scienceGeneral EngineeringProcess (computing)Word error rate020207 software engineering02 engineering and technologyOverlaycomputer.software_genreTask (computing)020901 industrial engineering & automationHuman–computer interaction0202 electrical engineering electronic engineering information engineeringAugmented reality systemsAugmented realitycomputerComputers in Industry
researchProduct

Multiplicity- and dependency-adjusted p-values for control of the family-wise error rate

2016

Abstract Under the multiple testing framework, we propose the multiplicity- and dependency-adjustment method (MADAM) which transforms test statistics into adjusted p -values for control of the family-wise error rate. For demonstration, we apply the MADAM to data from a genetic association study.

0301 basic medicineStatistics and ProbabilityWord error rateMultiplicity (mathematics)Familywise error rateMadam01 natural sciences010104 statistics & probability03 medical and health sciences030104 developmental biologyStatisticsMultiple comparisons problemŠidák correctionPer-comparison error rate0101 mathematicsStatistics Probability and UncertaintyMathematicsStatistical hypothesis testingStatistics & Probability Letters
researchProduct

PENERAPAN METODE SINGLE MOVING AVERAGE DAN EXSPONENTIAL SMOOTHING PADA USAHA ASRIE MODESTA

2020

This study  aims to (1) analyze the number of demands for batik products in the second period of 2018. (2) To analyze the most appropriate forecasting method. (3) To analyze the forecasting of the first period in 2019 using the selected forecasting method.
 This reseach uses primary data and secondary data with data collection techniques using interviews, observation, and documentation. The analysis used is Single Moving Averages and Exsponential Smoothing. 
 The results of research in forecasting demand for batik products in 2019 with the Single Moving Average method are 3,936 units with Mean Absolute Deviation (MAD) of 632.5 units and Mean Square Error (MSE) of 693,718 units. An…

Absolute deviationData collectionPolymers and PlasticsMean squared errorMoving averageAlpha ValueStatisticsWord error rateBusiness and International ManagementDemand forecastingIndustrial and Manufacturing EngineeringSmoothingMathematicsCakrawala Management Business Journal
researchProduct

Proactive interference of a sequence of tones in a two-tone pitch comparison task

2000

Subjects compared pitches of a standard tone and a comparison tone separated by 1,300-3,000 msec and responded according to whether the comparison tone sounded higher or lower in pitch than the standard tone. Three interfering tones at 300-msec intervals were presented before each pair of tones. Their pitch range varied, being either below or above the pitch of the standard tone; in some of the trials, their pitches were identical to the pitch of the standard tone (no interference). The highest error rate in performance was found when the interfering tones and the comparison tone deviated in the same direction in pitch from the standard tone. In turn, their deviations in the opposite direct…

AdultMaleSpeech recognitionInterference theoryWord error rateExperimental and Cognitive PsychologyContext (language use)Interference (wave propagation)Discrimination LearningSequence (music)Tone (musical instrument)Proactive InhibitionArts and Humanities (miscellaneous)otorhinolaryngologic diseasesDevelopmental and Educational PsychologyHumansCommunicationbusiness.industryhumanitiesPitch rangeTask (computing)Memory Short-TermAcoustic StimulationAuditory PerceptionFemalebusinessPsychologyMusicPsychonomic Bulletin & Review
researchProduct

Online detection of rem sleep based on the comprehensive evaluation of short adjacent eeg segments by artificial neural networks

1997

Abstract 1. 1. For scientific and clinical requirements the present objective is a robust automatic online algorithm to detect rapid eye movement (REM) steep from single channel sleep EEG data without using EMG or EOG information. 2. 2. For data preprocessing 20 seconds time periods of the continuous EEG activity are digitally filtered in 7 frequency bands. Then the RMS values of these filtered signals are calculated along segments of 2.5 seconds. The resulting matrix of RMS values is representing information on the power of the signal localized in time and frequency and serves as input to an artificial neural network. A pooled set of EEG data together with the corresponding manual evaluati…

AdultMaleTime FactorsChannel (digital image)Sleep REMWord error rateElectroencephalographyOnline SystemsSignalmedicineHumansWakefulnessOnline algorithmBiological PsychiatryPharmacologymedicine.diagnostic_testArtificial neural networkbusiness.industryReproducibility of ResultsEye movementElectroencephalographyPattern recognitionNeural Networks ComputerSleep StagesData pre-processingArtificial intelligencePsychologybusinessAlgorithmsProgress in Neuro-Psychopharmacology and Biological Psychiatry
researchProduct

FastEMD–CCA algorithm for unsupervised and fast removal of eyeblink artifacts from electroencephalogram

2020

Abstract Online detection and removal of eye blink (EB) artifacts from electroencephalogram (EEG) would be very useful in medical diagnosis and brain computer interface (BCI). In this work, approaches that combine unsupervised eyeblink artifact detection with empirical mode decomposition (EMD), and canonical correlation analysis (CCA), are proposed to automatically identify eyeblink artifacts and remove them in an online manner. First eyeblink artifact regions are automatically identified and an eyeblink artifact template is extracted via EMD, which incorporates an alternate interpolation technique, the Akima spline interpolation. The removal of eyeblink artifact components relies on the el…

Artifact (error)Cross-correlationmedicine.diagnostic_testComputer science0206 medical engineeringBiomedical EngineeringWord error rateHealth Informatics02 engineering and technologyElectroencephalography020601 biomedical engineeringHilbert–Huang transform[SPI]Engineering Sciences [physics]03 medical and health sciences0302 clinical medicineSignal ProcessingmedicineSpline interpolationAlgorithm030217 neurology & neurosurgeryInterpolationBrain–computer interfaceBiomedical Signal Processing and Control
researchProduct

Online detection and removal of eye blink artifacts from electroencephalogram

2021

Abstract The most prominent type of artifact contaminating electroencephalogram (EEG) signals are the eye blink (EB) artifacts, which could potentially lead to misinterpretation of the EEG signal. Online identification and elimination of eye blink artifacts are crucial in applications such a Brain-Computer Interfaces (BCI), neurofeedback, and epilepsy diagnosis. In this paper, algorithms that combine unsupervised eye blink artifact detection (eADA) with modified Empirical Mode Decomposition (FastEMD) and Canonical Correlation Analysis (CCA) are proposed, i.e., FastEMD-CCA2 and FastCCA, to automatically identify eye blink artifacts and remove them in an online setting. The average accuracy, …

Artifact (error)medicine.diagnostic_testComputer sciencebusiness.industryBiomedical EngineeringWord error rateHealth InformaticsPattern recognitionElectroencephalographySignalHilbert–Huang transformSignal ProcessingmedicineArtificial intelligenceSensitivity (control systems)NeurofeedbackbusinessBrain–computer interfaceBiomedical Signal Processing and Control
researchProduct

Unsupervised Eye Blink Artifact Identification in Electroencephalogram

2018

International audience; The most prominent type of artifact contaminating electroencephalogram (EEG) signals is the eye blink (EB) artifact. Hence, EB artifact detection is one of the most crucial pre-processing step in EEG signal processing before this artifact can be removed. In this work, an approach that identifies EB artifacts without human supervision and automated varying threshold setting is proposed and evaluated. The algorithm functions on the basis of correlation between two EEG electrodes, Fp1 and Fp2, followed by EB artifact threshold determination utilizing the amplitude displacement from the mean. The proposed approach is validated and evaluated in terms of accuracy and error…

Artifact (error)medicine.diagnostic_testbusiness.industryComputer science05 social sciencesFeature extractionWord error ratePattern recognitionElectroencephalography050105 experimental psychologyEB Artifacts03 medical and health sciencesIdentification (information)Electroencephalogram0302 clinical medicine[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processingmedicine0501 psychology and cognitive sciences[INFO]Computer Science [cs]Artificial intelligenceAutomated ThresholdbusinessEye blink030217 neurology & neurosurgery
researchProduct

Multimodal data as a means to understand the learning experience

2019

Most work in the design of learning technology uses click-streams as their primary data source for modelling & predicting learning behaviour. In this paper we set out to quantify what, if any, advantages do physiological sensing techniques provide for the design of learning technologies. We conducted a lab study with 251 game sessions and 17 users focusing on skill development (i.e., user's ability to master complex tasks). We collected click-stream data, as well as eye-tracking, electroencephalography (EEG), video, and wristband data during the experiment. Our analysis shows that traditional click-stream models achieve 39% error rate in predicting learning performance (and 18% when we perf…

Computer Networks and CommunicationsComputer scienceMultimodal data05 social sciencesWord error rateFeature selection02 engineering and technologyLibrary and Information SciencesSkill developmentVariety (cybernetics)Dreyfus model of skill acquisitionLearning experienceHuman–computer interaction020204 information systems0502 economics and business0202 electrical engineering electronic engineering information engineering050211 marketingSet (psychology)Information Systems
researchProduct

A random-walk benchmark for single-electron circuits

2021

Mesoscopic integrated circuits aim for precise control over elementary quantum systems. However, as fidelities improve, the increasingly rare errors and component crosstalk pose a challenge for validating error models and quantifying accuracy of circuit performance. Here we propose and implement a circuit-level benchmark that models fidelity as a random walk of an error syndrome, detected by an accumulating probe. Additionally, contributions of correlated noise, induced environmentally or by memory, are revealed as limits of achievable fidelity by statistical consistency analysis of the full distribution of error counts. Applying this methodology to a high-fidelity implementation of on-dema…

Computer scienceScienceFOS: Physical sciencesGeneral Physics and AstronomyWord error rateQuantum metrology02 engineering and technologyIntegrated circuit01 natural sciencesNoise (electronics)ArticleGeneral Biochemistry Genetics and Molecular Biologylaw.inventionComputer Science::Hardware ArchitecturelawMesoscale and Nanoscale Physics (cond-mat.mes-hall)0103 physical sciencesElectronic devicesQuantum metrology010306 general physicsQuantumQuantum computerQuantum PhysicsMultidisciplinaryCondensed Matter - Mesoscale and Nanoscale PhysicsQuantum dotsQGeneral Chemistry021001 nanoscience & nanotechnologyRandom walkComputerSystemsOrganization_MISCELLANEOUSBenchmark (computing)Quantum Physics (quant-ph)0210 nano-technologyAlgorithmNature Communications
researchProduct