Allocation Of Attentional Resources Research Articles

Directed connectivity in Parkinson's disease patients during over-ground and treadmill walking

Treadmill walking is considered a useful therapeutic tool for improving gait in Parkinson's disease (PD) patients. The study investigated the role of top-down, frontal-parietal versus bottom-up parietal-frontal networks, during over-ground and treadmill walking in PD and control subjects, using functional connectivity. To this end, EEG was recorded simultaneously, during a ten-minute period of continuous walking either over-ground or on a treadmill, in thirteen PD patients and thirteen age-matched controls. We evaluated EEG directed connectivity, using phase transfer entropy in three frequency bands: theta, alpha and beta. PD patients showed increased top-down connectivity during over-ground compared with treadmill walking, in the beta frequency range. Control subjects showed no significant differences in connectivity between the two walking conditions. Our results suggest that in PD patients, OG walking was associated with increased allocation of attentional resources, compared with that on the TL. These functional connectivity modulations may shed further light on the mechanisms underlying treadmill versus overground walking in PD.

Altered hemispheric asymmetry of attentional networks in patients with pituitary adenoma: an event-related potential study.

Emerging evidence has been reported of attentional dysfunction in pituitary adenoma patients. However, the effect of pituitary adenomas on lateralized attention network efficiency remained to be clear. Thus, the present study aimed to investigate the impairment of lateralized attention networks in patients with pituitary adenoma. Eighteen pituitary adenoma patients (PA group) and 20 healthy controls (HCs) were included in this study. Both behavioral results and event-related potentials (ERPs) were acquired while subjects performed the Lateralized Attention Network Test (LANT). Behavioral performances indicated the PA group had a slower reaction time and a similar error rate relative to the HCs group. Meanwhile, significantly increased executive control network efficiency suggested the dysfunction of inhibition control in PA patients. Regarding ERP results, there were no group differences in the alerting and orienting networks. The target-related P3 was significantly reduced in the PA group, suggesting an impairment of executive control function and attentional resources allocation. Moreover, the mean amplitude of P3 was significantly lateralized to the right hemisphere, and interacted with the visual field, exhibiting that the right hemisphere dominated the bilateral visual field, whereas the left hemisphere dominated the left visual field. In the specific high-conflict condition, the pattern of hemispheric asymmetry in the PA group was altered due to a mixed effect resulting from the compensatory recruitment of attentional resources in the left central parietal area and the destructive effects of hyperprolactinemia. These findings suggested that, in the lateralized condition, the decreased P3 in the right central parietal area and the diminished hemispheric asymmetry under high conflict load, may serve as the potential biomarkers of attentional dysfunction in patients with pituitary adenoma.

To be or not to be relevant: Comparing short- and long-term consequences across working memory prioritization procedures

Priority-based allocation of attentional resources has shown robust effects in working memory (WM) with both cue-based and reward-based prioritization. However, direct comparisons between these effects in WM are needed. Additionally, the consequences of WM prioritization for remembering in the long term remain unclear for both prioritization procedures. Here, we tested and compared the immediate and long-term memory (LTM) effects of cue-based versus reward-based retrospective prioritization of WM content. Participants encoded four memory items and were then indicated to prioritize one of the items through the presentation of either a retro-cue or a reward pattern. We then tested their immediate and delayed memory. The results of the first experiment showed better memory for prioritized than for unprioritized information in WM and LTM, but the WM effect was driven solely by the retro-cue, making it difficult to interpret any reward-based effects in LTM. In the second experiment, using a more explicit and meaningful reward-based manipulation, the results showed a prioritization benefit in WM for both prioritization procedures. In LTM, however, the prioritization effect was predominantly driven by the retro-cue manipulation. Taken together, we found that (1) the way in which attention is directed in WM impacts the size of the prioritization benefit in WM, (2) WM prioritization generally results in a prioritization effect in LTM, and (3) that the effect in LTM is more robust for cue-based prioritization. Exploratory analyses indicated that the LTM effect of cue-based prioritization reflected a cost in performance for noncued items rather than a benefit for cued items.

Placebo effect on gait: a way to reduce the dual-task cost in older adults

The ability to perform two tasks simultaneously is essential for daily activities. In older adults, this ability is markedly reduced, as evidenced by the dual-task cost on gait. Preliminary evidences indicate that the dual-task cost can be influenced by different types of manipulations. Here, we explored the effectiveness of a new approach to reduce the dual-task cost, based on the placebo effect, a psychobiological phenomenon whereby a positive outcome follows the administration of an inert device thought to be effective. Thirty-five healthy older adults were asked to walk on a sensorized carpet (single-task condition) and to walk while counting backward (dual-task condition) in two sessions (pre-test and post-test). A placebo group, randomly selected, underwent sham transcranial direct current stimulation over the supraorbital areas between sessions, along with information about its positive effects on concentration and attention. A control group did not receive any intervention between sessions. The dual-task cost was significantly reduced in the placebo group at the post-test session compared to the pre-test for several gait parameters (Cohen's d > 1.43). At the post-test session, the dual-task cost was also lower in the placebo group than in the control group (d > 0.73). Cognitive (number of subtractions and number of errors) and subjective (perceived mental fatigability) variables remained stable across sessions. The reduced dual-task cost in the placebo group could indicate the ability to re-establish the allocation of attentional resources between tasks. These findings could contribute to the development of cognitive strategies that leverage positive expectations to boost motor control in older adults.

High visual perceptual load reduces prepulse inhibition induced by task-unrelated and task-related sound.

Prepulse inhibition (PPI) is an automatic and pre-attentive sensorimotor gating process. Several studies have shown that advanced cognitive functions can modulate PPI. This study aimed to further elucidate the modulatory effect of attentional resource allocation on PPI. We examined the differences in PPI between high and low attentional loads. First, we verified that the adapted feature versus combination visual search paradigm could produce high and low perceptual load differences according to the task demands. Second, we measured the participants' task-unrelated PPI during the visual search task and found that the PPI in the high-load condition was significantly lower than that in the low-load condition. To further elucidate the role of attentional resources, we tested task-related PPI using a dual-task paradigm in which participants were instructed to complete a visual task with an auditory discrimination task. We found a result similar to that of the task-unrelated experiment. The participants in the high-load condition had less PPI than those in the low-load condition. Finally, we ruled out the possibility that the working memory load explains the modulation of PPI. In line with the theory of PPI modulation, these results suggest that allocating limited attentional resources to the prepulse modulates PPI. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Changes in Perceived Mental Load and Motor Performance during Practice-to-Learn and Practice-to-Maintain in Basketball

Attentional resource allocation during sports practice is associated with the players' perceived mental load. However, few ecological studies address this problem by considering the players' characteristics (e.g., practice experience, skill and cognition). Therefore, this study aimed to analyse the dose-response effect of two different types of practice, each with different learning objectives, on mental load and motor performance by using a linear mixed model analysis. Forty-four university students (age 20.36 ± 3.13 years) participated in this study. Two sessions were conducted, one based on a standard rules 1 × 1 basketball situation ("practice to maintain") and one with motor, temporal and spatial restrictions in 1 × 1 tasks ("practice to learn"). "Practice to learn" produced a higher perceived mental load (NASA-TLX scale) and a worse performance than "practice to maintain", but was moderated by experience and inhibition (p = 0.001). The same happens in the most demanding restriction (i.e., temporal, p < 0.0001). The results showed that increasing the difficulty of 1 × 1 situations through restrictions harmed the player's performance and increased their perceived mental load. These effects were moderated by previous basketball experience and the player's inhibition capacity, so the difficulty adjustment should be based on the athletes themselves.

An EEG Study of the Influence of Target Appearing in the Upper and Lower Visual Fields on Brain Attention Resource Allocation

Visuospatial selective attention can focus attention on a certain spatial area and rationally allocate attentional resources during visual target perception. Previous studies investigated the behavioral advantages of subjects when the target appeared in the upper and lower visual fields. However, the neurophysiological characteristics of the brain are not clear, and there is a lack of comprehensive analysis of the external behavior and the internal neurophysiological characteristics. We designed two task paradigms containing a spatial location orientation task and a visual search task. We used event-related potentials (ERP) components (P1 and P2) and electroencephalogram (EEG) rhythms (theta and alpha) to analyze the attention level and allocation of attention resources of the brain. The results showed that when the target appeared in the lower visual field in the spatial location orientation task, subjects consumed fewer attention resources and demonstrated better behavioral performance. In the visual search task, when the target appeared in the upper left visual field, subjects could better mobilize attention resources and behaved more advantageously. The study provides a basis for the design of the target in the upper and lower visual fields in the rehabilitation task, especially for stroke patients with low attention levels due to attention disorders such as spatial attention deficit.

Affective Priming Effects by Task‐Relevant and Task‐Irrelevant Emotional Pictures: An ERP Study

AbstractThe present study examined how task‐relevant and task‐irrelevant prime stimuli influence the affective priming effect. An emotional picture (unpleasant or neutral) and a checkerboard picture were presented simultaneously as a prime stimulus. Participants were required to pay attention to either the emotional picture (EP‐attended condition) or the checkerboard picture (CP‐attended condition). An emotionally neutral picture (target) was then presented, and participants were asked to evaluate the emotional valence of the target. The evaluation score was more negative following the unpleasant prime picture, and this priming effect was larger in the EP‐attended condition, in which the emotional prime picture was task‐relevant than in the CP‐attended condition, in which the emotional prime picture was task‐irrelevant. The late positive potentials (LPPs) elicited by the prime stimuli were larger when the emotional prime picture was unpleasant, whereas the LPPs elicited by the target stimuli were smaller when the emotional prime picture was unpleasant. More importantly, significant association between the LPP amplitudes and the magnitude of affective priming effects were observed in the EP‐attended condition but not in the CP‐attended condition. This indicates that the degree of the affective priming effect induced by the task‐relevant prime stimulus was related to attentional resource allocation, but this was not the case for the affective priming effect induced by the task‐irrelevant prime stimulus. The present results suggest that affective priming effects induced by task‐relevant and task‐irrelevant prime stimuli occur in a different manner in terms of attentional processing.

Event-related potential patterns of selective attention modulated by perceptual load.

A high perceptual load can effectively prevent attention from being drawn to irrelevant stimuli; however, the neural pattern underlying this process remains unclear. This study adopted a perceptual load paradigm to examine the temporal processes of attentional modulation by incorporating conditions of perceptual load, distractor-target compatibility, and eccentricity. The behavioral results showed that a high perceptual load significantly reduced attentional distraction caused by peripheral distractors. The event-related potential results further revealed that shorter P2 latencies were observed for peripheral distractors than for central distractors under a high perceptual load and that a suppressed compatibility effect with increasing load was reflected by the P3 component. These findings suggested that (1) P2 and P3 components effectively captured different sides of attentional processing modulated by load (i.e., the filter processing of the object and the overall attentional resource allocation) and (2) response patterns of selective attention modulated by perceptual load were influenced by eccentricity. Our electrophysiological evidence confirmed the behavioral findings, indicating the neural mechanisms of attentional modulation.

Selective spatial attention in lateralized multi-talker speech perception: EEG correlates and the role of age

Speech comprehension under dynamic cocktail party conditions requires auditory search for relevant speech content and focusing spatial attention on the target talker. Here, we investigated the development of these cognitive processes in a population of 329 participants aged 20–70 years. We used a multi-talker speech detection and perception task in which pairs of words (each consisting of a cue and a target word) were simultaneously presented from lateralized positions. Participants attended to predefined cue words and responded to the corresponding target. Task difficulty was varied by presenting cue and target stimuli at different intensity levels. Decline in performance was observed only in the oldest group (age range 53–70 years) and only in the most difficult condition. The EEG analysis of neurocognitive correlates of lateralized auditory attention and stimulus evaluation (N2ac, LPCpc, alpha power lateralization) revealed age-associated changes in focussing on and processing of task-relevant information, while no such deficits were found on early auditory search and target segregation. Irrespective of age, more challenging listening conditions were associated with an increased allocation of attentional resources.

Exploring the carry-over of top-down attentional settings in dynamic conditions.

A top-down attentional set can persist from a relevant task to an irrelevant task, influencing allocation of attentional resources, visual search, and performance. While this "carry-over" effect has been found across numerous experiments, past studies have utilised paradigms that present similar tasks to the same spatial location. The present research explored whether attentional settings persist in more dynamic situations. In Experiment 1, participants played a computer game that encouraged a horizontal, vertical, or random spread of search. After 10 or 30 s, they moved 90° to their right and monitored a driving video for hazards. Eye movements to the videos were not affected by the characteristics of the preceding game, revealing no carry-over of attentional settings. One possible explanation for this was the visuospatial shift between the tasks. To explore this further, Experiment 2 adopted a similar paradigm to previous research; participants searched horizontal, vertical, or random letter strings before completing an image search. In one block the tasks were presented to the same screen, and in one block the tasks were presented to different screens (incorporating a 90° visuospatial shift mid-trial). Carry-over was found in the one-screen block, with a significantly wider horizontal search and a narrower vertical search in the pictures after a horizontal letter search. However, there was no carry-over from the letter to the picture task in the two-screen block. This indicates the flexibility of attentional control in dynamic situations, and it is suggested that persistence of attentional settings will be most costly under stable conditions.

Attentional modulation as a mechanism for enhanced facial emotion discrimination: The case of action video game players

Action video game players (AVGPs) outperform nonvideo game players (NVGPs) on a wide variety of attentional tasks, mediating benefits to perceptual and cognitive decision processes. A key issue in the literature is the extent to which such benefits transfer beyond cognition. Using steady-state visual evoked potentials (SSVEP) as a neural measure of attentional resource allocation, we investigated whether the attentional benefit of AVGPs generalizes to the processing of rapidly presented facial emotions. AVGPs (n = 36) and NVGPs (n = 32) performed a novel, attention-demanding emotion discrimination task, requiring the identification of a target emotion in one of two laterally presented streams of emotional faces. The emotional faces flickered at either 2.0 Hz or 2.5 Hz. AVGPs outperformed NVGPs at detecting the target emotions regardless of the type of emotion. Correspondingly, attentional modulation of the SSVEP at parieto-occipital recording sites was larger in AVGPs compared with NVGPs. This difference appeared to be driven by a larger response to attended information, as opposed to a reduced response to irrelevant distractor information. Exploratory analyses confirmed that this novel paradigm elicited the expected pattern of event-related potentials associated with target detection and error processing. These components did not, however, differ between groups. Overall, the results indicate enhanced discrimination of facial emotions in AVGPs arising from enhanced attentional processing of emotional information. This presents evidence for the attentional advantage of AVGPs to extend beyond perceptual and cognitive processes.

Influence of facial attractiveness on the allocation of attentional resources: Moderating effect of evolutionary motivations

Influence of facial attractiveness on the allocation of attentional resources: Moderating effect of evolutionary motivations

Distinctive patterns of Multiple Object-Tracking performance trajectories in youth with deficits in attention, learning, and intelligence

There is a significant overlap in symptomology between individuals with deficits in attention and learning, which is explained by the co-dependent dynamic between the two cognitive constructs. Within this dynamic, attentional resources are allocated to salient stimuli while learning mechanisms distinguish relevant from irrelevant information. Moreover, individuals with deficits in higher-order cognition (i.e., intelligence) can demonstrate difficulties in attention and learning. The Multiple Object-Tracking (MOT) task is a sensitive and versatile measure of attention that has characterized individual differences in attention as a function of higher-order cognition. Exploiting the traditional MOT task’s ability to characterize the allocation of attentional resources to task demands, the current study compared learning exhibited on an attention-based task across neurodevelopmental conditions defined by deficits in attention (attention-deficit/hyperactivity disorder; ADHD), learning (specific learning disorder; SLD), and intelligence (intellectual developmental disorder; IDD). Children and adolescents (N = 101) completed 15 sessions on a Multiple Object-Tracking (MOT) task where performance trajectories were analyzed using latent growth curve modeling and conditioned by the presence of ADHD, SLD, or IDD while controlling for performance on a separate measure of attention, age, and sex. The sample, characterized by below-average IQ and problematic levels of attention, exhibited an effect of learning on MOT. However, individuals with an IDD diagnosis demonstrated decreased baseline MOT capability while ADHD and SLD profiles exhibited decreased slopes, relative to other neurodevelopmental conditions. Taken together, the results demonstrate distinct linear performance trajectories between neurodevelopmental conditions defined by deficits in attention, learning, and intelligence. The current study provides additional evidence to repurpose the traditional MOT task as a descriptor of attention and discusses alternative uses for the paradigm. Overall, these results suggest an eclectic approach that considers attention, learning, and higher-order cognition when diagnosing ADHD, SLD, or IDD.

Acute effects of exercise engagement on neurocognitive function: a systematic review and meta-analysis on P3 amplitude and latency

ABSTRACT Although the acute effect of exercise on behavioral cognitive performance is well-documented in the exercise psychology field, a comprehensive evaluation on neuroelectric brain activity that determines healthy cognitive functioning following acute exercise is lacking. This systematic review included 39 studies examining acute exercise effects on P3 of event-related potential through its amplitude and latency, which reflect the amounts of attentional resources allocated to and the processing speed for categorizing a stimulus. Exercise has small effects on increasing amplitude and decreasing latency. The amplitude effect was moderated by age and the type, intensity, and duration of exercise, with a smaller effect being observed for individuals aged ≤18 and 19–35 than >60 years, for high-intensity than moderate-intensity exercise, for high-intensity interval training exercise than aerobic, resistance, and combined exercise, as well as for exercise lasting ≤10 and 11–20 than exercise lasting 21–30 min. The latency effect was moderated by exercise duration, with 11–20 min exercise showing a smaller effect than exercise lasting ≤10 min. These results demonstrated that acute exercise enhances allocation of attentional resources and processing speed needed to implement cognitive processes underlying goal-directed behavior. Further, these effects may be manipulated through targeting specific age groups and prescribing specific exercise parameters.

Building blocks of suspense: subjective and physiological effects of narrative content and film music

The current study explores the role of narrative content and non-diegetic music, as well as their interplay in the creation of film suspense. In a between-subjects design, three audience groups watched either the full version (audio–video) of a suspenseful short movie (Love Field) or a video-only version or listened to the audio track only. Audience responses were assessed with a combination of continuous response measurement (CRM) and psychophysiological measures, comprising heart rate (i.e., inter-beat interval, IBI), pulse volume amplitude (PVA), and skin conductance level (SCL). Frame-by-frame content coding was performed to identify distinct plot segments and musical moods (tense vs. relaxing) and mark the critical visual and auditory events that directed the audience’s inferences about the nature of the plot and elicited specific outcome expectations. Results showed that continuous self-report data and objective physiological measures were largely dissociated, suggesting different processing modalities. Tense music alone induced feelings of suspense (CRM) even in the absence of any clues about the story content. Overall, the audio-only version led to the highest arousal levels, as indicated by SCL and PVA, while the video-only version led to the lowest arousal levels. IBI data revealed short-term heart rate deceleration responses to salient narrative clues that could be interpreted in terms of heightened attention and cognitive resource allocation. Results are discussed in light of a multidimensional framework of tension and suspense and a terminological differentiation of both concepts.

Effects of subjective and objective task difficulties for feedback- related brain potentials in social situations: An electroencephalogram study.

In this study, the relationship between two types of feedback task difficulties and feedback-related brain potentials, such as feedback-related negativity (FRN), reward positivity (RewP), and P300, was investigated in social situations where participants performed a task simultaneously by a pair. The electroencephalogram activity was measured while participants answered four-choice questions with their partners. Participants were informed about the general accuracy rate of the question (objective task difficulty) before responding to the questionnaire. The feedback outcome was definitely correct when the participants had the knowledge to answer the questions correctly. Therefore, the subjective task difficulty depended on the knowledge of the participant and differed from the objective task difficulty. In the task, the participants selected the choice they deemed correct. Before checking the answers, participants responded to the preceding question's subjective task difficulty. As one of the social factors, the task consisted of two types of conditions: one, in which one's response affected partner's reward, and another, in which it did not. The second social factor was the order of feedback outcomes; in our experiment, these outcomes were presented sequentially to pairs of participants. The effects of subjective and objective task difficulties and social factors on feedback-related brain potentials were comprehensively analyzed. The study showed that subjective task difficulty sensitively modulated the amplitude of gain-related P300, suggesting that it is sensitive to modulation in the allocation of attentional resources to own feedback outcome. The objective task difficulty sensitively modulated the amplitude of RewP after receiving the partner's incorrect feedback outcome. RewP was more sensitive to positive affective valence, such as feelings of superiority over the partner, than to task-dependent rewards received by the participants themselves. In contrast, FRN was more negative in the joint condition than in the individual condition, suggesting sensitivity to social responsibility felt by participants toward their partners.

MIND Dietary Pattern Adherence Is Selectively Associated with Cognitive Processing Speed in Middle-Aged Adults

Most previous work has focused on a single-nutrient, bottom-up approach when examining the influence of diet on neurocognition. Thus, the impact of dietary patterns on cognitive health is underinvestigated. We aimed to investigate the relation between different diet indices [i.e., Mediterranean, Dietary Approaches to Stop Hypertension (DASH), Healthy Eating Index-2015 (HEI-2015), and Mediterranean-DASH Intervention for Neurodegenerative Delay (MIND)] and attentional inhibition and neuroelectric function. We undertook a cross-sectional analysis of adults aged 34.1 ± 6.0 y (n = 207, 116 females) with a BMI of 18.5 to >40 kg/m2 who completed the Dietary History Questionnaire II (DHQII) FFQ (Past Month and Year with Serving Sizes) to assess adherence to different diet quality indices. Attentional inhibition was assessed using a modified Eriksen flanker task during which event-related potentials (ERPs) were recorded. The amplitude and latency of the P3/P300 ERP were used to index attentional resource allocation and information processing speed, respectively. P3 peak latency was inversely associated with greater adherence to the MIND dietary pattern during incongruent flanker trials (∆R2 = 0.02, β = -0.14, P = 0.043) but not during congruent trials. Adherence to the Mediterranean, DASH, and HEI-2015 patterns was not associated with P3 latency (P > 0.05). No associations were observed between the diet indices and attentional inhibition at the behavioral level (i.e., accuracy or reaction time) or P3 amplitude (all P values >0.05). Greater adherence to the MIND diet was selectively associated with faster information processing speed in middle-aged adults with healthy to obese BMI. Further, the influence of the MIND diet for faster information processing speed might be particularly beneficial when cognitive control demands are increased. Future intervention trials testing the effects of consuming a MIND diet on cognitive function are warranted to help inform dietary recommendations for healthy cognitive aging.

Bilingualism can cause enhanced monitoring and occasional delayed responses in a flanker task.

Complex cognitive tasks require different stages of processing (i.e. conflict monitoring, attentional resource allocation and stimulus categorisation). Performance differences between bilinguals and monolinguals on conflict tasks can be affected by the balance of these sub-processes. The current study investigated the effect of bilingualism on these sub-processes during a conflict task with medium monitoring demand. Behavioural responses and evoked potentials from bilinguals and monolinguals were examined during a flanker task with 25% incongruent trials. Behavioural differences were analysed by means of averaged response times and exponentially modified Gaussian analyses of response time distributions. For evoked potentials, the study focussed on N2 (reflecting conflict monitoring) and P3 responses (reflecting allocation of attentional resources for cognitive control). Bilinguals had significantly longer response distribution tails compared to monolinguals. Bilinguals were shown to have a more pronounced N2 and smaller P3 compared to monolinguals, independent of condition, suggesting a different balance of sub-processes for the two groups. This suggests that bilinguals were engaged more strongly in monitoring processes, leading to the allocation of fewer attentional resources during stimulus categorisation. Additionally, the P3 amplitudes were negatively related with the length of response distribution tails for bilinguals. These results are consistent with enhanced conflict monitoring in bilinguals that led to reduced engagement of attentional resources for stimulus categorisation. This enhanced conflict monitoring could lead to occasional extremely slow responses. Thus, the bilingual experience appears to impact the balance of cognitive control processes during conflict tasks, which might only be reflected in a minority of responses.

An Intelligent Recognition Method for Low-Grade Fault Based on Attention Mechanism and Encoder–Decoder Network Structure

Low-grade faults play an important role in controlling oil and gas accumulations, but their fault throw is small and difficult to identify. Traditional low-grade fault recognition methods are time-consuming and inaccurate. Therefore, this study proposes a combination of a simulated low-grade fault sample set and a self-constructed convolutional neural network to recognize low-grade faults. We used Wu’s method to generate 500 pairs of low-grade fault samples to provide the data for deep learning. By combining the attention mechanism with UNet, an SE-UNet with efficient allocation of limited attention resources was constructed, which can select the features that are more critical to the current task objective from ample feature information, thus improving the expression ability of the network. The network model is applied to real data, and the results show that the SE-UNet model has better generalization ability and can better recognize low-grade and more continuous faults. Compared with the original UNet model, the SE-UNet model is more accurate and has more advantages in recognizing low-grade faults.