Search results for "Pattern recognition"
showing 10 items of 2301 documents
Case-Sensitivity of Classifiers for WSD: Complex Systems Disambiguate Tough Words Better
2007
We present a novel method for improving disambiguation accuracy by building an optimal ensemble (OE) of systems where we predict the best available system for target word using a priori case factors (e.g. amount of training per sense). We report promising results of a series of best-system prediction tests (best prediction accuracy is 0.92) and show that complex/simple systems disambiguate tough/easy words better. The method provides the following benefits: (1) higher disambiguation accuracy for virtually any base systems (current best OE yields close to 2% accuracy gain over Senseval-3 state of the art) and (2) economical way of building more effective ensembles of all types (e.g. optimal,…
Linear and nonlinear parametric model identification to assess granger causality in short-term cardiovascular interactions
2008
We assessed directional relationships between short RR interval and systolic arterial pressure (SAP) variability series according to the concept of Granger causality. Causality was quantified as the predictability improvement (PI) of a time series obtained when samples of the other series were used for prediction, i.e. moving from autoregressive (AR) to AR exogenous (ARX) prediction. AR and ARX predictions were performed both by linear and nonlinear parametric models. The PIs of RR given SAP and of SAP given RR, measuring baroreflex and mechanical couplings, were calculated in 15 healthy subjects in the resting supine and upright tilt positions. Using nonlinear models we found a bilateral i…
Need of causal analysis for assessing phase relationships in closed loop interacting cardiovascular variability series
2003
The phase spectra obtained by the classical closed loop autoregressive model (2AR) and by an open loop autoregressive model (ARXAR) were compared to shed light on the need of introducing causality in the assessment of the delay between RR and arterial pressure oscillations. The reliability of the two approaches was tested in simulation and real data setting. In simulation, the coupling strength of a bivariate closed loop process was adjusted to obtain a range of working conditions from open to closed loop. In open loop condition, 2AR and ARXAR phases were comparable and in agreement with the imposed delay. In closed loop condition, ARXAR model returned the imposed delays, while 2AR showed a…
OPETH: Open Source Solution for Real-Time Peri-Event Time Histogram Based on Open Ephys
2019
Single cell electrophysiology remains one of the most widely used approaches of systems neuroscience. Decisions made by the experimenter during electrophysiology recording largely determine recording quality, duration of the project and value of the collected data. Therefore, online feedback aiding these decisions can lower monetary and time investment, and substantially speed up projects as well as allow novel studies otherwise not possible due to prohibitively low throughput. Real-time feedback is especially important in studies that involve optogenetic cell type identification by enabling a systematic search for neurons of interest. However, such tools are scarce and limited to costly co…
GTVcut for neuro-radiosurgery treatment planning: an MRI brain cancer seeded image segmentation method based on a cellular automata model
2018
Despite of the development of advanced segmentation techniques, achieving accurate and reproducible gross tumor volume (GTV) segmentation results is still an important challenge in neuro-radiosurgery. Nowadays, magnetic resonance imaging (MRI) is the most prominent modality in radiation therapy for soft-tissue anatomical districts. Gamma Knife stereotactic neuro-radiosurgery is a minimally invasive technology for dealing with inaccessible or insufficiently treated tumors with traditional surgery or radiotherapy. During a treatment planning phase, the GTV is generally contoured by experienced neurosurgeons and radiation oncologists using fully manual segmentation procedures on MR images. Unf…
Cerebellar learning of bio-mechanical functions of extra-ocular muscles: modeling by artificial neural networks
2003
A control circuit is proposed to model the command of saccadic eye movements. Its wiring is deduced from a mathematical constraint, i.e. the necessity, for motor orders processing, to compute an approximate inverse function of the bio-mechanical function of the moving plant, here the bio-mechanics of the eye. This wiring is comparable to the anatomy of the cerebellar pathways. A predicting element, necessary for inversion and thus for movement accuracy, is modeled by an artificial neural network whose structure, deduced from physical constraints expressing the mechanics of the eye, is similar to the cell connectivity of the cerebellar cortex. Its functioning is set by supervised reinforceme…
Analysis of neuronal networks in the visual system of the cat using statistical signals--simple and complex cells. Part II.
1978
Superimposing additively a two-dimensional noise process to deterministic input signals (bars) the neurons of area 17 show a class-specific reaction for the task of signal extraction. Moving both parts of the signals simultaneously and varying the signal to noise ratio (S/N) the simple cells achieve the same performance as resulted from the psychophysical experiment. Type I complex cells extract moving deterministic signals (i.e. bars) from the stationary noise, whereas in the answers of Type II complex cells the statistical parts of the signals predominate. Considering the different cell types each as a series of a linear and a nonlinear system one obtains the cell specific space-time freq…
Local symmetries of digital contours from their chain codes
1996
In this work symmetry is evaluated as a numeric feature for each point of a contour, using only the positions of a local vicinity of points. A measurement is defined, named as Local Symmetric Deficiency (LSD), so that the lower this quantity is, the higher the symmetry will be in the local region considered. This approach is very simple and it is based on a suitable manipulation of the chain code of the curve. Its computational cost is very low and it has the advantages of a parallel algorithm, since values for LSD can be computed for each point independently.
Modeling Multi-label Recurrence in Data Streams
2019
Most of the existing data stream algorithms assume a single label as the target variable. However, in many applications, each observation is assigned to several labels with latent dependencies among them, which their target function may change over time. Classification of such non-stationary multi-label streaming data with the consideration of dependencies among labels and potential drifts is a challenging task. The few existing studies mostly cope with drifts implicitly, and all learn models on the original label space, which requires a lot of time and memory. None of them consider recurrent drifts in multi-label streams and particularly drifts and recurrences visible in a latent label spa…
Variance Thresholded EMD-CCA Technique for Fast Eye Blink Artifacts Removal in EEG
2017
International audience; Eye blink (EB) artifacts generated during eye blinks often contaminate electroencephalogram (EEG) signal. Previously Empirical Mode Decomposition (EMD) and Canonical Correlation Analysis (CCA), hybrid EMD-CCA were developed for EB artifact removal in EEG. However, EMD restricts the hybrid algorithm for real time implementation due to its slow processing nature, hence the algorithm has to be enhanced so that it can be a viable solution for real-time EB artifact removal. In this research work, to avoid applying EMD repetitively as and when EB artifacts occur, a method to use EMD minimally is approached. A suitable EB artifact region is detected through a variance thres…