Pattern Identification Task Research Articles

FPRnet: A lightweight multi-domain multi-stream network for complex horizontal oil-water two-phase flow pattern recognition

The complicated spatio-temporal structure of horizontal oil-water flows renders the identification of flow patterns exceedingly challenging, owing to the presence of interfacial waves and droplet entrainment. In this study, a multi-domain fusion feature (MFF) as flow pattern descriptors (FPD) and a lightweight multi-stream networks (LMN) as flow pattern classifier (FPC) are proposed to identify the flow patterns of horizontal oil-water two-phase flow. MFF can map time series into different domains and compactly encode them into higher dimensional expressions, thus displaying implicit flow pattern signals incorporating nonlinear, time-frequency, and probabilistic transition domain features. Finally, the comparison of LMN, variational and other networks is evaluated on the horizontal oil-water flows pattern identification task. Extensive comparison experiments show that the time-frequency feature exhibits optimal characterization for the D O/W flow pattern, the URP feature is most accurately characterized for the D W/O and D O/W flow patterns, and the MTF feature exhibits superior characterization for the remaining three flow patterns. The 98.40 % recognition accuracy demonstrates that MFF has a good representation of flow patterns and the proposed LMN outperforms existing classifiers in flow pattern recognition.

Pre-stimulus brain state predicts auditory pattern identification accuracy

Recent studies show that pre-stimulus band-specific power and phase in the electroencephalogram (EEG) can predict accuracy on tasks involving the detection of near-threshold stimuli. However, results in the auditory modality have been mixed, and few works have examined pre-stimulus features when more complex decisions are made (e.g. identifying supra-threshold sounds). Further, most auditory studies have used background sounds known to induce oscillatory EEG states, leaving it unclear whether phase predicts accuracy without such background sounds. To address this gap in knowledge, the present study examined pre-stimulus EEG as it relates to accuracy in a tone pattern identification task. On each trial, participants heard a triad of 40-ms sinusoidal tones (separated by 40-ms intervals), one of which was at a different frequency than the other two. Participants' task was to indicate the tone pattern (low-low-high, low-high-low, etc.). No background sounds were employed. Using a phase opposition measure based on inter-trial phase consistencies, pre-stimulus 7–10 Hz phase was found to differ between correct and incorrect trials ∼200 to 100 ms prior to tone-pattern onset. After sorting trials into bins based on phase, accuracy was found to be lowest at around π−+ relative to individuals’ most accurate phase bin. No significant effects were found for pre-stimulus power. In the context of the literature, findings suggest an important relationship between the complexity of task demands and pre-stimulus activity within the auditory domain. Results also raise interesting questions about the role of induced oscillatory states or rhythmic processing modes in obtaining pre-stimulus effects of phase in auditory tasks.

Analysis of Electroencephalography (EEG) Signals using Visualization Techniques

The feasibility of machine learning and data mining has been recognized by past research in the analysis of biomedical device data. The proposed work analyses the biomedical Electroencephalography (EEG) device data using visualization techniques and these techniques have potential for extracting information from huge data sets. The presented work includes extraction of visual patterns using different visualization techniques. The pattern identification task is performed in several stages like outlier removal from EEG. After outlier detection data is divided into manageable segments to avoid overcrowding of data points. Then random method is applied to select a segment and identify prominent patterns by application of visual mapping techniques.

Informational Masking in Normal-Hearing and Hearing-Impaired Listeners Measured in a Nonspeech Pattern Identification Task.

Individuals with sensorineural hearing loss (SNHL) often experience more difficulty with listening in multisource environments than do normal-hearing (NH) listeners. While the peripheral effects of sensorineural hearing loss certainly contribute to this difficulty, differences in central processing of auditory information may also contribute. To explore this issue, it is important to account for peripheral differences between NH and these hearing-impaired (HI) listeners so that central effects in multisource listening can be examined. In the present study, NH and HI listeners performed a tonal pattern identification task at two distant center frequencies (CFs), 850 and 3500 Hz. In an attempt to control for differences in the peripheral representations of the stimuli, the patterns were presented at the same sensation level (15 dB SL), and the frequency deviation of the tones comprising the patterns was adjusted to obtain equal quiet pattern identification performance across all listeners at both CFs. Tonal sequences were then presented at both CFs simultaneously (informational masking conditions), and listeners were asked either to selectively attend to a source (CF) or to divide attention between CFs and identify the pattern at a CF designated after each trial. There were large differences between groups in the frequency deviations necessary to perform the pattern identification task. After compensating for these differences, there were small differences between NH and HI listeners in the informational masking conditions. HI listeners showed slightly greater performance asymmetry between the low and high CFs than did NH listeners, possibly due to central differences in frequency weighting between groups.

Analytic and divided listening in normal-hearing and hearing-impaired listeners measured in a nonspeech pattern identification task

In multisource listening environments, it is important to be able to attend to a single sound source (analytic listening) while concurrently monitoring unattended sources for potentially useful information (divided listening). Previous studies have indicated that hearing-impaired (HI) listeners have more difficulty with analytic listening than do normal-hearing (NH) listeners. Although central factors (e.g., selective attention and memory) clearly play a role, the extent to which differences in peripheral factors (e.g., auditory filter characteristics) contribute to this effect is not clear. In this study, performance in a closed-set nonspeech tonal pattern identification task was measured in NH and HI listeners for patterns centered at 850 and 3500 Hz. The frequency spacing among the tones forming the patterns was adjusted to equate performance across listeners at each center frequency separately to control for peripheral frequency resolution. Patterns were then played at both frequencies concurrently. Listeners were instructed to attend to either the low or high frequency and identify the pattern. In a second condition, patterns were randomly presented at one frequency with a foil at the other frequency, requiring the listener to monitor both frequencies to identify the pattern. Preliminary findings suggest that peripheral and central factors contributed to performance. [Support: NIH-NIDCD.]

Sensitivity to Lexical Stress in Dyslexia: a Case of Cognitive not Perceptual Stress

Sensitivity to lexical stress in adult German-speaking students with reading difficulty was investigated using minimal pair prepositional verbs whose meaning and syntax depend on the location of the stressed syllable. Two tests of stress perception were used: (i) a stress location task, where listeners indicated the location of the perceptually most prominent syllable, and (ii) a stress pattern identification task, where listeners indicated if the stress pattern was appropriate for its semantic frame. The students with reading difficulties performed worse than the normally reading students on both tasks. Their poorer performance did not reflect the lack of a percept for lexical stress rather patterns of performance across the two tasks suggested that each loaded onto different underlying cognitive abilities. Deficits in these, rather than perceptual difficulties, explained observed group differences. Students with reading difficulties have a normal implicit knowledge of lexical stress usage but lack the necessary cognitive resources for developing an explicit metalinguistic awareness of it. Deficits in these skills not deficiencies in lexical stress perception are implicated in their reading difficulties.

Q-nary pattern identifier based on committee of vector perceptrons

A method of estimation of the quality of data identification by a parametric perceptron is presented. The method allows one to combine the parametric perceptrons into a committee. It is shown by the example of the Potts perceptrons that the storage capacity of the committee grows linearly with the increase of the number of perceptrons forming the committee. The combination of perceptrons into a committee is useful when given task parameters (image dimension and chromaticity, the number of patterns, distortion level, identification reliability) one perceptron is unable to solve the identification task. The method can be applied in q-nary or binary pattern identification task.

Release from masking due to spatial separation of sources in the identification of nonspeech auditory patterns.

A nonspeech pattern identification task was used to study the role of spatial separation of sources on auditory masking in multisource listening environments. The six frequency patterns forming the signal set were comprised of sequences of eight 60-ms tone bursts. Bursts of masking sounds were played synchronously with the signals. The main variables in the study were (1) the difference in spatial separation in the horizontal plane between signals and maskers and (2) the nature of the masking produced by the maskers. Spatial separation of signal and masker ranged from 0-180 degrees. The maskers were of two types: (1) a sequence of eight 60-ms bursts of Gaussian noise intended to produce predominantly peripherally based "energetic masking" and (2) a sequence of eight 60-ms bursts of eight-tone complexes intended to produce primarily centrally based "informational masking." The results indicated that identification performance improved with increasing separation of signal and masker. The amount of improvement depended upon the type of masker and the center frequency of the signal patterns. Much larger improvements were found for spatial separation of the signal and informational masker than for the signal and energetic masker. This was particularly apparent when the acoustical advantage of the signal-to-noise ratio in the more favorable of the two ears (the ear nearest the signal) was taken into account. The results were interpreted as evidence for an important role of binaural hearing in reducing sound source or message uncertainty and may contribute toward solving the "cocktail party problem."

Global versus local processing in haptic perception of form

Preliminary experiments on a “tactile analog” of Navon’s (1977) global/local pattern-identification task are reported. Sighted, early-blind, and late-blind subjects were exposed to large shapes comprised of different, smaller geometric forms, and were asked to “name the shape.” In addition, groups of early- and late-blind subjects attempted identification of conflict braille stimuli, with large braille patterns made up of smaller, standard braille. The pattern of responses was neither totally local nor global for geometric-form information. Braille, however, was size specific, with most early-blind subjects responding locally. Visual and haptic experience altered the pattern of responses for both braille and geometric forms.