The effects of retinal image motion in a simple pattern recognition task

1962 ◽  
Vol 1 (5) ◽  
pp. 192-199 ◽  
Author(s):  
D. H. Fender ◽  
P. W. Nye
Keyword(s):  
Pattern Recognition ◽  
Retinal Image ◽  
Recognition Task ◽  
Image Motion ◽  
Simple Pattern ◽  
Retinal Image Motion ◽  
Pattern Recognition Task

The Heartbeat Classification Based on PCA

2012 ◽  
Vol 195-196 ◽  
pp. 402-406
Author(s):  
Xue Qin Chen ◽  
Rui Ping Wang
Keyword(s):  
Principal Component Analysis ◽  
Pattern Recognition ◽  
Recognition Task ◽  
Principal Component ◽  
True Positive Rate ◽  
True Positive ◽  
Heartbeat Classification ◽  
Positive Rate ◽  
Electrocardiogram Ecg ◽  
Pattern Recognition Task

Classify the electrocardiogram (ECG) into different pathophysiological categories is a complex pattern recognition task which has been tried in lots of methods. This paper will discuss a method of principal component analysis (PCA) in exacting the heartbeat features, and a new method of classification that is to calculate the error between the testing heartbeat and reconstructed heartbeat. Training and testing heartbeat is taken from the MIT-BIH Arrhythmia Database, in which 8 types of arrhythmia signals are selected in this paper. The true positive rate (TPR) is 83%.

scholarly journals Electric Source Localization Adds Evidence for Task-Specific CNVs

1998 ◽  
Vol 11 (1) ◽  
pp. 21-28 ◽  
Author(s):  
Ina M. Tarkka ◽  
Luis F. H. Basile
Keyword(s):  
Pattern Recognition ◽  
Source Localization ◽  
Clinical Neurophysiology ◽  
Recognition Task ◽  
Source Analysis ◽  
Visual Spatial ◽  
Spatio Temporal ◽  
Electric Source ◽  
Pattern Recognition Task ◽  
Spatial Recognition

This study was an attempt to replicate recent magnetoencephalographic (MEG) findings on human task-specific CNV sources (Basile et al., Electroencephalography and Clinical Neurophysiology 90, 1994, 157–165) by means of a spatio-temporal electric source localization method (Scherg and von Cramon, Electroencephalography and Clinical Neurophysiology 62, 1985, 32–44; Scherg and von Cramon, Electroencephalography and Clinical Neurophysiology 65, 1986, 344-360; Scherg and Berg, Brain Electric Source Analysis Handbook, Version 2). The previous MEG results showed CNV sources in the prefrontal cortex of the two hemispheres for two tasks used, namely visual pattern recognition and visual spatial recognition tasks. In the right hemisphere, the sources were more anterior and inferior for the spatial recognition task than for the pattern recognition task. In the present study we obtained CNVs in five subjects during two tasks identical to the MEG study. The elicited electric potentials were modeled with four spatio-temporal dipoles for each task, three of which accounted for the visual evoked response and one that accounted for the CNV. For all subjects the dipole explaining the CNV was always localized in the frontal region of the head, however, the dipole obtained during the visual spatial recognition task was more anterior than the one obtained during the pattern recognition task. Thus, task-specific CNV sources were again observed, although the stable model consisted of only one dipole located close to the midline instead of one dipole in each hemisphere. This was a major difference in the CNV sources between the previous MEG and the present electric source analysis results. We discuss the possible basis for the difference between the two methods used to study slow brain activity that is believed to originate from extended cortical patches.

Retinal Image Motion During Deliberate Fixation

2000 ◽  
Vol 78 (2) ◽  
pp. 131-142 ◽  
Author(s):  
James W. Ness ◽  
Harry Zwick ◽  
Bruce E. Stuck ◽  
David J. Lurid ◽  
Brian J. Lurid ◽  
...  
Keyword(s):  
Retinal Image ◽  
Image Motion ◽  
Retinal Image Motion

Retinal image motion alone does not control disconjugate postsaccadic eye drift

1990 ◽  
Vol 63 (5) ◽  
pp. 999-1009 ◽  
Author(s):  
Z. Kapoula ◽  
L. M. Optican ◽  
D. A. Robinson
Keyword(s):  
Retinal Image ◽  
Human Subjects ◽  
Field Method ◽  
The Other ◽  
Image Motion ◽  
Full Field ◽  
Before And After ◽  
Retinal Image Motion ◽  
Hering’S Law ◽  
Random Dot Pattern

1. In these experiments, postsaccadic ocular drift was induced by postsaccadic motion of the visual scene. In the most important case, the scene was moved in one eye but not the other. Six human subjects viewed the interior of a full-field hemisphere filled with a random-dot pattern. During training, eye movements were recorded by the electrooculogram. A computer detected the end of every saccade and immediately moved the pattern horizontally in the same or, in different experiments, in the opposite direction as the saccade. The pattern motion was exponential with an amplitude of 25% of the size of the antecedent saccade and a time constant of 50 ms. Before and after 3-4 h of such training, movements of both eyes were measured simultaneously by the eye coil-magnetic field method while subjects looked between stationary targets for calibration, explored the visual pattern with saccades, or made saccades in the dark to measure the effects of adaptation on postsaccadic ocular drift. The amplitude of this drift was expressed as a percentage of the size of the antecedent saccade. 2. In monocular experiments, subjects viewed the random-dot pattern with one eye. The other eye was patched. With two subjects, the pattern drifted backward in the direction opposite to the saccade; with the third, it drifted onward. The induced ocular drift was exponential, always in the direction to reduce retinal image motion, had zero latency, and persisted in the dark. After training, drift in the dark changed by 6.7% in agreement with our prior study with binocular vision, which produced a change of 6.0%. 3. In a dichoptic arrangement, one eye regarded the moveable random-dot pattern; the other, through mirrors, saw a different random-dot pattern (with similar spacing, contrast, and distance) that was stationary. These visual patterns were not fuseable and did not evoke subjective diplopia. In this case, the induced change in postsaccadic drift in the same three subjects was only 4.8%. In all cases the changes in postsaccadic drift were conjugate--they obeyed Hering's law. 4. Normal human saccades are characterized by essentially no postsaccadic drift in the abducting eye and a pronounced onward drift (approximately 4%) in the adducting eye. After training, this abduction-adduction asymmetry was preserved in the light and dark with monocular or dichoptic viewing, indicating again that all adaptive changes were conjugate. 5. When the subjects viewed the adapting stimulus after training, the zero-latency, postsaccadic drift always increased from levels in the dark.(ABSTRACT TRUNCATED AT 400 WORDS)

scholarly journals On the Use of Concentrated Time–Frequency Representations as Input to a Deep Convolutional Neural Network: Application to Non Intrusive Load Monitoring

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 911 ◽  
Author(s):  
Sarra Houidi ◽  
Dominique Fourer ◽  
François Auger
Keyword(s):  
Pattern Recognition ◽  
Recognition Task ◽  
Time Frequency ◽  
Neural Architecture ◽  
Signal Representations ◽  
Current State ◽  
Signal Features ◽  
Load Monitoring ◽  
Pattern Recognition Task

Since decades past, time–frequency (TF) analysis has demonstrated its capability to efficiently handle non-stationary multi-component signals which are ubiquitous in a large number of applications. TF analysis us allows to estimate physics-related meaningful parameters (e.g., F0, group delay, etc.) and can provide sparse signal representations when a suitable tuning of the method parameters is used. On another hand, deep learning with Convolutional Neural Networks (CNN) is the current state-of-the-art approach for pattern recognition and allows us to automatically extract relevant signal features despite the fact that the trained models can suffer from a lack of interpretability. Hence, this paper proposes to combine together these two approaches to take benefit of their respective advantages and addresses non-intrusive load monitoring (NILM) which consists of identifying a home electrical appliance (HEA) from its measured energy consumption signal as a “toy” problem. This study investigates the role of the TF representation when synchrosqueezed or not, used as the input of a 2D CNN applied to a pattern recognition task. We also propose a solution for interpreting the information conveyed by the trained CNN through different neural architecture by establishing a link with our previously proposed “handcrafted” interpretable features thanks to the layer-wise relevant propagation (LRP) method. Our experiments on the publicly available PLAID dataset show excellent appliance recognition results (accuracy above 97%) using the suitable TF representation and allow an interpretation of the trained model.

NATURAL RETINAL IMAGE MOTION: ORIGIN AND CHANGE

1981 ◽  
Vol 374 (1 Vestibular an) ◽  
pp. 312-329 ◽  
Author(s):  
H. Collewijn ◽  
A. J. Martins ◽  
R. M. Steinman
Keyword(s):  
Retinal Image ◽  
Image Motion ◽  
Retinal Image Motion

‘Generic-View Principle’ for Three-Dimensional-Motion Perception: Optics and Inverse Optics of a Moving Straight Bar

Perception ◽  
1996 ◽  
Vol 25 (7) ◽  
pp. 797-814 ◽  
Author(s):  
Michiteru Kitazaki ◽  
Shinsuke Shimojo
Keyword(s):  
Visual System ◽  
Motion Perception ◽  
Retinal Image ◽  
General Framework ◽  
Three Dimensional ◽  
Image Motion ◽  
Optical Process ◽  
Retinal Image Motion ◽  
The Subject ◽  
Three Components

The generic-view principle (GVP) states that given a 2-D image the visual system interprets it as a generic view of a 3-D scene when possible. The GVP was applied to 3-D-motion perception to show how the visual system decomposes retinal image motion into three components of 3-D motion: stretch/shrinkage, rotation, and translation. First, the optical process of retinal image motion was analyzed, and predictions were made based on the GVP in the inverse-optical process. Then experiments were conducted in which the subject judged perception of stretch/shrinkage, rotation in depth, and translation in depth for a moving bar stimulus. Retinal-image parameters—2-D stretch/shrinkage, 2-D rotation, and 2-D translation—were manipulated categorically and exhaustively. The results were highly consistent with the predictions. The GVP seems to offer a broad and general framework for understanding the ambiguity-solving process in motion perception. Its relationship to other constraints such as that of rigidity is discussed.

Sign in / Sign up

Export Citation Format

Share Document