Number Of Correct Detections Research Articles

Research on the application of neural network based external location element settlement method in object location of geographic information

BackgroundGeographical information about human settlements is necessary to facilitate humanitarian aid, recognize the location of real-world objects, support local development and improve disaster resilience in settlements. Although deep learning is employed in object location in settlements, these models have computational complexity and less detection accuracy. Hence they require further development with regards to precision in object location from geographic data. ObjectiveTo efficiently identify the object location in Chinese settlements from geographic information, we proposed Artificial Neural Network (ANN) optimized by Red Fox (RF) optimization (ANN-RF) model in this research. MethodsThe multi-resolution Geographic information data was collected from Tongzhou District, Beijing, China. ANN applies the measures of length, area, distance and direction to recognize object location from this data. An RF algorithm is used to optimize the weight vector of the ANN architecture to improve the efficiency of the ANN architecture. The parameters such as precision, recall, F1-score, number of correct detections, overall actual matches and the total number of detections were computed for the proposed model. ResultsThe precision rate and F1-score for the proposed ANN based RF optimization are about 98.9% and 97.5% which are higher than that of conventional models. ConclusionThe proposed ANN-RF model shows promising results in detecting object location in settlements from geographic information.

Accuracy Improvement of Power Transformer Faults Diagnostic Using KNN Classifier With Decision Tree Principle

Dissolved gas analysis (DGA) is the standard technique to diagnose the fault types of oil-immersed power transformers. Various traditional DGA methods have been employed to detect the transformer faults, but their accuracies were mostly poor. In this light, the current work aims to improve the diagnostic accuracy of power transformer faults using artificial intelligence. A KNN algorithm is combined with the decision tree principle as an improved DGA diagnostic tool. A total of 501 dataset samples are used to train and test the proposed model. Based on the number of correct detections, the neighbor's number and distance type of the KNN algorithm are optimized in order to improve the classifier's accuracy rate. For each fault, indeed, several input vectors are assessed to select the most appropriate one for the classifier's corresponding layer, increasing the overall diagnostic accuracy. On the basis of the accuracy rate obtained by knots and type of defect, two models are proposed where their results are compared and discussed. It is found that the global accuracy rate exceeds 93% for the power transformer diagnosis, demonstrating the effectiveness of the proposed technique. An independent database is employed as a complimentary validation phase of the proposed research.

?A good odour to breathe?? The effect of pleasant ambient odour on human visual vigilance

The present study examined the effect of an alerting and a relaxing odour on human visual vigilance. Three groups of undergraduates (N = 54) completed a sustained visual vigilance task which required them to respond whenever a target stimulus appeared on a computer monitor. One group completed the task in the presence of an alerting odour (peppermint), another did so in the presence of a relaxing odour (bergamot) and a third group completed the task in an unscented environment. A 2×3×2 (sex×odour×diurnal preference) MANOVA was performed in order to determine group differences in response times and number of correct detections. Participants in the bergamot condition detected fewer targets correctly within 1.25 seconds of the target appearing than did those in the peppermint or no-odour groups. Exposure to bergamot was also associated with significantly fewer correct detections in the second than in the first half of the task, when compared with the other two conditions. The results suggest that sustained exposure to a relaxing odour can impair visual vigilance. Copyright © 2001 John Wiley & Sons, Ltd.

Time-Related Changes in Neural Systems Underlying Attention and Arousal During the Performance of an Auditory Vigilance Task

Vigilance behavior, or watch keeping, involves the focusing of attention on the detection of subtle changes in the environment that occur over a long period of time. We investigated the time course of changes in brain activity during the continuous performance of a 60-min auditory vigilance task. The task required the detection of an intensity drop that occurred in 5% of the auditory stimuli. Six 1-min samples of cerebral blood flow (CBF) and electroencephalographic (EEG) activity were obtained at l0-min intervals during the vigilance performance. Changes in CBF were measured by means of positron emission tomography (PET). Performance data (hits, false alarms, reaction time) were analyzed across six 10-min blocks. Eight healthy male volunteers participated in the study. During the 60-min test, the number of correct detections (hits) did not change, but both the reaction time and EEG activity in the theta (4 to 7 Hz) range progressively increased across testing. CBF in several subcortical structures (thalamus, substantia innominata, and putamen) and cortical areas (ventrolateral, dorsolateral, and orbital frontal cortex; parietal cortex; and temporal cortex) decreased as a function of time-on-task; changes in the cortical regions were limited to the right hemisphere. Blood flow also decreased in the temporalis muscles. At the same time, CBF increased in several visual cortical areas including the left and right fusiform gyri. Furthermore, the thalamic blood-flow response co-varied with that in the substantia innominata, the ponto-mesencephalic tegmentum, and the anterior cingulate cortex. The right ventrolateral-frontal blood-flow response covaried with that in the right parietal, orbitofrontal, and dorsolateral frontal cortex. 'Iko main conclusions are drawn from the obtained data. First, we suggest that the observed time-related changes in reaction time, EEG activity, and blood flow in the temporalis muscles are related to changes in the level of arousal (alertness) and that CBF changes in the thalamus-related neural circuitry represent a brain correlate of such changes. Second, we speculate that time-related CBF decreases in cortical regions of the right hemisphere underlie a shift from controlled to automatic attentional processing of the auditory stimuli.

Syllabic segmentation and literacy

Abstract A total of 40 unschooled Portuguese adults, either illiterates or ex-illiterates, were presented auditorily with short sentences and asked to detect the occurrence of a word initiated by a specified syllable-sized target. The target was either CV or CVC, and the target-bearing word was initiated by either a CV or a CVC syllable. The dependent variable was the number of correct detections. Ex-illiterates performed better than illiterates. There was a significant interaction between target type and word structure: Detections were more numerous when the target coincided with the first syllable of the target-bearing word than when it did not. This effect is similar to the one obtained by Mehler, Dommergues, Frauenfelder, and Segui (1981) in a reaction-time study with French literate subjects, and shows evidence of a syllabification procedure. The fact that this syllable effect is obtained with illiterate subjects, regardless of their overall performance, suggests that the development of a syllabifica...

Differences in the Vigilance Performance of Second-Grade Children as Related to Sex and Achievement

KIRCHNER, GRACE L., and KNOPF, IRWIN J. Differences in the Vigilance Performance of SecondGrade Children as Related to Sex and Achievement. CHILD DEVELOPMENT, 1974, 45, 490-495. 64 middleto upper-middle-class, white, second-grade children were tested on a visual vigilance task. They were selected on the basis of their scores on the Stanford Achievement Test in order to form high and low achievement groups. The vigilance task consisted of a 30-minute movie of a stationary jet plane. The children responded to a change in the star on the plane's fuselage, which occurred a total of 24 times at predetermined intervals of 30, 60, 90, and 120 seconds. The high achievers made a greater number of correct detections (p < .01) and a fewer number of false responses (p < .01), and there was a significant decline in the number of correct detections over time (p < .05). There were no sex differences in performance, and there was no relationship between performance and interval length.

STIMULUS DETECTION DURING PERIODS OF HIGH AND LOW HEART RATE

ABSTRACTThe study was designed to test Lacey's suggestion that elevated heart rate and blood pressure could lead to decreased sensory sensitivity and that a reduction in heart rate and blood pressure may facilitate sensory sensitivity. A tone of five intensities encompassing the subject's intensity threshold was presented randomly 25 times under high and 25 times under low transient heart rate. The results indicated no differences in the number of correct detections under high and low heart rate and no interaction between heart rate level and tone intensity. It was concluded that low heart rate may well be a necessary condition for increased sensory sensitivity, but that it is not a sufficient condition. Discussion was directed to the range of possible HR changes and the possible requirements of the sensitivity mechanism.

The effects of values and costs on the detection and identification of signals in auditory vigilance.

The effects on performance of the value of detecting a signal, the cost of a miss or false detection, and the size of the set from which the signals were drawn were studied in an auditory vigilance task. Seventy-two subjects were randomly assigned to each cell of a factorial arrangement of the cost and load variables and required to detect and identify each of several 49 db SPL pure tones differing only in frequency. Analyses of the number of correct detections, correct identifications, false detections and detection response time indicated a significant performance decrement with time for all measures and suggested that increasing costs for misses and false detections led to poorer detection performance while value had no effect. Load effected only identification performance, as higher loads led to a decrease in the percentage of signals correctly identified. The ď and β statistics of signal detection theory, indicated sensitivity to be invariant with manipulations of costs and with time. These findings imply that the performance decrement during a vigil is due to an increased strictness in the criterion the subject sets for deciding whether or not a signal was present. The cost factors were effective in manipulating performance by causing changes in the subjects' decision criteria.

THE EFFECTS OF NOISE AND DOUBLING THE SIGNAL FREQUENCY ON INDIVIDUAL DIFFERENCES IN VISUAL VIGILANCE PERFORMANCE

Four groups of 6 extraverts and 4 groups of 6 introverts, selected by the Maudsley Personality Inventory, performed a 32 min visual cancellation task under one of two conditions of signal frequency, high and low, and in either noise (95 db) or quiet (70 db). In quiet, at both levels of signal frequency, extraverts showed a steady decline in the number of signals detected correctly but introverts did not. Neither group showed a decrement under noise conditions. Noise, compared with quiet, significantly increased the number of correct detections made by extraverts under low signal frequency conditions but a similar increase under high signal frequency conditions was not significant. The addition of noise had no significant effect on the number of correct detections made by introverts. Doubling the signal frequency had no significant effect on the performance of introverts or extraverts in either noise or quiet. Introverts made significantly more errors of commission in quiet than in noise while extraverts made significantly more in noise than in quiet. Possible reasons for the findings are discussed.

Errors of commission as a function of age and temperament in a type of vigilance task.

Forty subjects monitored a 40 min. series of 10-sec. intervals containing digits (spoken at the rate of 1 per sec.), each followed by 10-sec. silence. The task was to report whether or not three consecutive and different odd digits occurred. Responses were forced. The results showed that there was no correlation between either age or temperament and the number of correct detections made. Older subjects, however, made more errors of commission, and were less able to distinguish wanted from unwanted events. The younger and introverted subjects appeared to be more cautious. The data is discussed in terms of the arousal theory of vigilance performance.