Task Feedback Research Articles

A multi-task spatio-temporal fusion network for offshore wind power ramp events forecasting

With the accelerated development of offshore wind farms, the impact of Wind Power Ramp Events (WPRE) on power systems has become more pronounced. Accurate prediction of WPRE is essential for mitigating their adverse effects on the grid. However, current studies on offshore WPRE are limited, especially regarding their spatio-temporal correlations and variability across large wind farm clusters. To address this, a novel forecasting approach using a multi-task spatio-temporal fusion network is presented. This method improves WPRE prediction by integrating spatial and temporal data and utilizing multitask learning to characterize ramp features. Firstly, an index system for WPRE characterization is developed, including metrics such as power change rate and duration. Based on this, an X-means classification method for WPRE is established. Secondly, a spatio-temporal encoder combining graph convolutional networks and temporal attention mechanisms has been proposed to model the spatiotemporal dependencies of meteorological changes in offshore wind farms. Finally, a multitask learning framework has been introduced to predict WPRE characteristic indices and occurrence probabilities. This approach enhances feature extraction efficiency through the joint feedback of multiple related tasks, thereby improving prediction accuracy. A case study using data from five offshore wind farms in Eastern China validates the efficacy of the proposed method.

Instilling the perception of weight in augmented reality using minimal haptic feedback

Humans perceive gravitational forces on their surroundings through a mix of visual and sensorimotor cues. The accurate presentation of such cues is a difficult task in Mixed/Augmented Reality (MR/AR), technological paradigms that blend physical and virtual elements to enhance the way we interact with our environment. Realistically perceiving the weight of virtual elements within a MR/AR scenario aids in the embodiment of those elements within the user’s reality, further blurring the lines between what is real and virtual. Unfortunately, current force feedback devices are not designed for or are entirely compatible with MR/AR experiences. To address this need, we explore minimal haptic feedback for weight perception in MR/AR, aiming to simplify the rendering of gravitational cues that are crucial to an immersive experience. Our benchtop device, focused on wrist feedback, showed improved user experience even within an implicit weight feedback task, i.e., a task where weight perception was not required for task completion. However, challenges arose in mixed real-virtual environments, a cornerstone of MR/AR interaction, where weight discrimination was observed to be less accurate. To address this, we developed a compensation scheme for virtual weights, leading to performance on par with a purely virtual environment. Our work demonstrates the viability of minimal haptic feedback in MR/AR applications and highlights the importance of integrating weight perception for increased realism. Our work also fills a research gap in MR/AR development, providing insights for designing future MR/AR systems that integrate with human sensory mechanisms to create virtual interactions that more closely mirror the physical world.

Evaluating human error probability in maintenance task: An integrated system dynamics and machine learning approach

AbstractHuman error is often implicated in industrial accidents and is frequently found to be a symptom of broader issues within the sociotechnical system. Therefore, research exploring human error during maintenance activities is important. This article aims to assess the probability of human error in maintenance tasks at a cement factory using the Cognitive Reliability and Error Analysis Method and System Dynamics modeling. Given that human error probability (HEP) is influenced by various common performance conditions (CPCs) and their sub‐factors, and changes dynamically in response to other variables, the SD method offers a practical approach for estimating and predicting human error behavior over time. This study identifies and quantifies the variables affecting HEP, explores their interactions and feedback in maintenance tasks, and assesses the associated costs. The machine learning technique is then used to estimate the relationship between HEP and these costs. The optimal value of the HEP function, 0.000772, is determined by identifying the minimum point of a cubic function, thereby minimizing associated costs and occupational accidents. Determining the optimal HEP is crucial for minimizing excessive costs and investing in improved ergonomics and CPCs for better performance. This addresses a significant gap in existing research where the impact of human error on maintenance tasks has not been estimated as a function. Furthermore, three scenarios are presented to help managers allocate the organization's budget more effectively.

Investigating mechanoreceptor variability and morphometric proxies in Rhesus Macaques: Implications for primate precision touch studies.

The origin of primates has long been associated with an increased emphasis on manual grasping and touch. Precision touch, facilitated by specialized mechanoreceptors in glabrous skin, provides critical sensory feedback for grasping-related tasks and perception of ecologically-relevant stimuli. Despite its importance, studies of mechanoreceptors in primate hands are limited, in part due to challenges of sample availability and histological methods. Dermatoglyphs have been proposed as alternative proxies of mechanoreceptor density. We investigated the relationships between mechanoreceptors (Meissner and Pacinian corpuscles), dermatoglyphs, and demography in the apical finger pads of 15 juvenile to adult rhesus macaques (Macaca mulatta) from a free-ranging population at Cayo Santiago Primate Field Station (Puerto Rico). Our results indicate substantial interindividual variation in mechanoreceptor density (Meissner corpuscles: 11.9-43.3 corpuscles/mm2; Pacinian corpuscles: 0-4.5 corpuscles/mm2). While sex and digit were generally not associated with variation, there was strong evidence of a developmental effect. Specifically, apical pad length, Meissner corpuscle size, and Pacinian corpuscle depth increased while mechanoreceptor densities decreased throughout juvenescence, suggesting that primate mechanoreceptors change as fingers grow during adolescence and then stabilize at physical maturity. We also found Meissner corpuscle density was significantly associated with dermatoglyph ridge width and spacing, such that density predicted by a dermatoglyph model was strongly correlated with observed values. Dermatoglyphs thus offer a useful proxy of relative Meissner corpuscle density in primates, which opens exciting avenues of noninvasive research. Finally, our results underscore the importance of considering demographic factors and methodology in comparative studies of primate touch.

Method of Feedback for E-mail Tasks with Specific Readers: Using the Writing Support System “Sakura Dayori” as an Example

Method of Feedback for E-mail Tasks with Specific Readers: Using the Writing Support System “Sakura Dayori” as an Example

Mapping the complexity of task demands during constant observation of patients with complex health behaviors.

Unlicensed patient care assistants (PCAs) are often tasked with providingconstant observation (CO)of patients withcomplex health behaviors. The unique demands of CO are poorly understood, making it challenging to design effective training.Four-componentinstructional design theory suggests the tasks associated with CO featurenon-recurrentchallenges, such that effective, simulation-based deliberate practice must reflect real-life variability.This study aimed toelucidate the variety of challenges PCAsencounter during CO of patientswithcomplex health behaviors. We used a qualitativedescriptivedesignand developed apreliminary framework to code interviews.The data collection framework wasdesigned to support creating numerous realistic scenariosto support generalized and transferable learning.From our interviews with 16 participants, we identified 1,066 statements associated with variations in CO tasks. We grouped our findings by two domains, "patient factors" and "environmental contexts." Our results revealed many recurring and non-recurring challengesinherent in CO, requiring arange of skills to maintain patient and staff safety.Instructional design elements may include scenarios incorporatingenvironment and resource assessment,cognitive feedback for non-recurrent tasks, novel methods of self-harm initiated by the patient, and incorporating interdisciplinary staff in which the learner must navigate a complex conversation. This studyclarifiesthetask demands of CO andisuseful as a task analysis to guide scenario development for simulation-based experiences. A less systematic approachwould risk underrepresenting the difficulties inherent in the task, reinforcing a limited set of behaviors that may not generalize well to the non-recurrent challenges in CO.

Speech-induced suppression and vocal feedback sensitivity in human cortex

Across the animal kingdom, neural responses in the auditory cortex are suppressed during vocalization, and humans are no exception. A common hypothesis is that suppression increases sensitivity to auditory feedback, enabling the detection of vocalization errors. This hypothesis has been previously confirmed in non-human primates, however a direct link between auditory suppression and sensitivity in human speech monitoring remains elusive. To address this issue, we obtained intracranial electroencephalography (iEEG) recordings from 35 neurosurgical participants during speech production. We first characterized the detailed topography of auditory suppression, which varied across superior temporal gyrus (STG). Next, we performed a delayed auditory feedback (DAF) task to determine whether the suppressed sites were also sensitive to auditory feedback alterations. Indeed, overlapping sites showed enhanced responses to feedback, indicating sensitivity. Importantly, there was a strong correlation between the degree of auditory suppression and feedback sensitivity, suggesting suppression might be a key mechanism that underlies speech monitoring. Further, we found that when participants produced speech with simultaneous auditory feedback, posterior STG was selectively activated if participants were engaged in a DAF paradigm, suggesting that increased attentional load can modulate auditory feedback sensitivity.

Speech-induced suppression and vocal feedback sensitivity in human cortex.

Across the animal kingdom, neural responses in the auditory cortex are suppressed during vocalization, and humans are no exception. A common hypothesis is that suppression increases sensitivity to auditory feedback, enabling the detection of vocalization errors. This hypothesis has been previously confirmed in non-human primates, however a direct link between auditory suppression and sensitivity in human speech monitoring remains elusive. To address this issue, we obtained intracranial electroencephalography (iEEG) recordings from 35 neurosurgical participants during speech production. We first characterized the detailed topography of auditory suppression, which varied across superior temporal gyrus (STG). Next, we performed a delayed auditory feedback (DAF) task to determine whether the suppressed sites were also sensitive to auditory feedback alterations. Indeed, overlapping sites showed enhanced responses to feedback, indicating sensitivity. Importantly, there was a strong correlation between the degree of auditory suppression and feedback sensitivity, suggesting suppression might be a key mechanism that underlies speech monitoring. Further, we found that when participants produced speech with simultaneous auditory feedback, posterior STG was selectively activated if participants were engaged in a DAF paradigm, suggesting that increased attentional load can modulate auditory feedback sensitivity.

Harnessing Generative AI (GenAI) for Automated Feedback in Higher Education: A Systematic Review

In this systematic review, we synthesize ten empirical peer-reviewed articles published between 2019 and 2023 that used generative artificial intelligence (GenAI) for automated feedback in higher education. There are significant opportunities and challenges to integrate these tools effectively into learning environments as the demand for timely and personalized feedback grows. We examine the articles based on instructional contexts and system characteristics, identifying critical implementation possibilities for GenAI in automated feedback. Our findings reveal that GenAI provides diverse feedback across various contexts with multiple instructional purposes. GenAI systems can reduce instructor workload by automating routine grading and feedback tasks, allowing educators to focus on more complex teaching responsibilities with augmented capabilities. Additionally, these systems enhance communication, offer cognitive and emotional support, and improve accessibility by creating supportive, stress-free learning environments. Overall, implementing GenAI automated feedback systems improves educational outcomes and creates a more efficient and supportive learning environment for students and instructors. We conclude with future research directions to better integrate GenAI with human instruction by reconsidering instructors’ roles, especially in providing feedback to create more effective educational experiences.

A Machine Learning Approach to Classifying EEG Data Collected with or without Haptic Feedback during a Simulated Drilling Task.

Artificial Intelligence (AI), computer simulations, and virtual reality (VR) are increasingly becoming accessible tools that can be leveraged to implement training protocols and educational resources. Typical assessment tools related to sensory and neural processing associated with task performance in virtual environments often rely on self-reported surveys, unlike electroencephalography (EEG), which is often used to compare the effects of different types of sensory feedback (e.g., auditory, visual, and haptic) in simulation environments in an objective manner. However, it can be challenging to know which aspects of the EEG signal represent the impact of different types of sensory feedback on neural processing. Machine learning approaches offer a promising direction for identifying EEG signal features that differentiate the impact of different types of sensory feedback during simulation training. For the current study, machine learning techniques were applied to differentiate neural circuitry associated with haptic and non-haptic feedback in a simulated drilling task. Nine EEG channels were selected and analyzed, extracting different time-domain, frequency-domain, and nonlinear features, where 360 features were tested (40 features per channel). A feature selection stage identified the most relevant features, including the Hurst exponent of 13-21 Hz, kurtosis of 21-30 Hz, power spectral density of 21-30 Hz, variance of 21-30 Hz, and spectral entropy of 13-21 Hz. Using those five features, trials with haptic feedback were correctly identified from those without haptic feedback with an accuracy exceeding 90%, increasing to 99% when using 10 features. These results show promise for the future application of machine learning approaches to predict the impact of haptic feedback on neural processing during VR protocols involving drilling tasks, which can inform future applications of VR and simulation for occupational skill acquisition.

An efficient parallel self-attention transformer for CSI feedback

In massive multi-input multi-output (MIMO) systems, it is necessary for user equipment (UE) to transmit downlink channel state information (CSI) back to the base station (BS). As the number of antennas increases, the feedback overhead of CSI consumes a significant amount of uplink bandwidth resources. To minimize the bandwidth overhead, we propose an efficient parallel attention transformer, called EPAformer, a lightweight network that utilizes the transformer architecture and efficient parallel self-attention (EPSA) for CSI feedback tasks. The EPSA expands the attention area of each token within the transformer block effectively by dividing multiple heads into parallel groups and conducting self-attention in horizontal and vertical stripes. The proposed EPSA achieves better feature compression and reconstruction. The simulation results display that the EPAformer surpasses previous deep learning-based approaches in terms of reconstruction performance and complexity.

Exploring motor skill acquisition in bimanual coordination: insights from navigating a novel maze task

In this study, we introduce a novel maze task designed to investigate naturalistic motor learning in bimanual coordination. We developed and validated an extended set of movement primitives tailored to capture the full spectrum of scenarios encountered in a maze game. Over a 3-day training period, we evaluated participants’ performance using these primitives and a custom-developed software, enabling precise quantification of performance. Our methodology integrated the primitives with in-depth kinematic analyses and thorough thumb pressure assessments, charting the trajectory of participants’ progression from novice to proficient stages. Results demonstrated consistent improvement in maze performance and significant adaptive changes in joint behaviors and strategic recalibrations in thumb pressure distribution. These findings highlight the central nervous system’s adaptability in orchestrating sophisticated motor strategies and the crucial role of tactile feedback in precision tasks. The maze platform and setup emerge as a valuable foundation for future experiments, providing a tool for the exploration of motor learning and coordination dynamics. This research underscores the complexity of bimanual motor learning in naturalistic environments, enhancing our understanding of skill acquisition and task efficiency while emphasizing the necessity for further exploration and deeper investigation into these adaptive mechanisms.

Effect of Managerial Coaching on Employees’ Productivity in Commercial Banks in Calabar, Cross River State

The study examined effect of coaching dimensions (task guidance, task feedback and employee support) on employee in-role and innovative performance, with role clarity mediating the effect of managerial coaching on employee productivity. Descriptive survey design was adopted and data collected from staff commercial banks in Calabar Metropolis, Cross River State using structured questionnaire. The validity and reliability of the instrument were ascertained using Cronbach alpha, convergent and discriminant tests. The sample size was 268 staff conveniently sampled from the population of 810. Descriptive statistics and correlation analyses were conducted using SPSS 25 and Amos 24 to analyse the data. The test of direct effects of the hypotheses was performed through multivariate regression analyses while the mediating effect was tested using structural equation modelling with Sobel estimations. The findings revealed that task guidance, task feedback and employee support had positive and significant effect on employees’ in-role and innovative performance. Also, role clarity fully mediated the connection between managerial coaching and innovative performance but did not reveal any mediating effect between managerial coaching and in-role performance. The study expanded the extant notion on the results of managerial coaching on employee productivity. The findings provided justification for the inclusion of coaching practices in organisations and suggest direction for understanding the motivation underlying these relationships.

Nothing to lose? Neural correlates of decision, anticipation, and feedback in the balloon analog risk task.

Understanding the subprocesses of risky decision making is a prerequisite for understanding (dys-)functional decisions. For the present fMRI study, we designed a novel variant of the balloon-analog-risk task (BART) that measures three phases: decision making, reward anticipation, and feedback processing. Twenty-nine healthy young adults completed the BART. We analyzed neural activity and functional connectivity. Parametric modulation allowed assessing changes in brain functioning depending on the riskiness of the decision. Our results confirm involvement of nucleus accumbens, insula, anterior cingulate cortex, and dorsolateral prefrontal cortex in all subprocesses of risky decision-making. In addition, subprocesses were differentiated by the strength of activation in these regions, as well as by changes in activity and nucleus accumbens-connectivity by the riskiness of the decision. The presented fMRI-BART variant allows distinguishing activity and connectivity during the subprocesses of risky decision making and shows how activation and connectivity patterns relate to the riskiness of the decision. Hence, it is a useful tool for unraveling impairments in subprocesses of risky decision making in people with high risk behavior.

Outcome assessment of different reward stimuli in Internet gaming disorder by event-related potentials.

An imbalance in sensitivity to different types of reward stimuli may be an important cause of addiction that is mainly manifested in high sensitivity to addictive substance rewards and blunting of natural rewards. However, contradictions remain in the research results on the sensitivity of individuals with Internet gaming disorder (IGD) to different reward stimuli. Based on participants' neural responses to win and loss feedback (in door task), the event-related potential (ERP) technique was used to investigate the effects of different types of reward stimuli on the assessment of reward-processing outcomes in individuals with IGD. The results showed that in the gain condition, the FB-P3 amplitude induced by game stimuli in the IGD group was significantly higher than that in the control group, and the FN amplitude induced by money stimuli was significantly lower than that in the control group. However, the FB-P3 and FN amplitudes induced by food were not significantly different from those in the control group. In the loss condition, there were no between-group differences in the FB-P3 and FN amplitudes evoked by the three reward stimuli. This indicates that the IGD group showed increased hedonic responses to game stimuli and decreased hedonic responses to money but no differences in hedonic responses to food during the reward assessment phase. Therefore, heightened sensitivity to game rewards and diminished sensitivity to monetary rewards during outcome assessment may play a crucial role in the development of IGD.

Gender, choice of task, and the effect of feedback on competition: An experiment

We conduct a laboratory experiment to examine gender differences in task choices and competitiveness: Individuals have the option to self-select into one of two stereotypically different tasks and subsequently decide whether or not to engage in competition while receiving one of three different feedback treatments. Compared to a control setting, we study the effect of providing relative performance feedback (rankings), and additionally the effect of providing information about the gender of the competitors. We find a significant gender gap in the choice of the male task, only when presenting the ranking in addition to the gender composition of the group. Turning to the decision to enter competition, we observe that task choice, combined with ranking feedback on performance, reduces the gender gap in competition entry in both tasks compared to the control. The dynamics over treatments reveal that men primarily respond to feedback in the male task, while women respond to feedback in the word task. These findings highlight that gender differences in task choice and competitiveness are contingent on feedback, the underlying task, and the task choice set.

Subjective cognitive decline in healthy older adults is associated with altered processing of negative versus positive feedback in a probabilistic learning task.

Older adults who worry about their own cognitive capabilities declining, but who do not show evidence of actual cognitive decline in neuropsychological tests, are at an increased risk of being diagnosed with dementia at a later time. Since neural markers may be more sensitive to early stages of cognitive decline, in the present study we examined whether event-related potential responses of feedback processing, elicited in a probabilistic learning task, differ between healthy older adults recruited from the community, who either did (subjective cognitive decline/SCD-group) or did not report (No-SCD group) worry about their own cognition declining beyond the normal age-related development. In the absence of group differences in learning from emotionally charged feedback in the probabilistic learning task, the amplitude of the feedback-related negativity (FRN) varied with feedback valence differently in the two groups: In the No-SCD group, the FRN was larger for positive than negative feedback, while in the SCD group, FRN amplitude did not differ between positive and negative feedback. The P3b was enhanced for negative feedback in both groups, and group differences in P3b amplitude were not significant. Altered sensitivity in neural processing of negative versus positive feedback may be a marker of SCD.

Brain activation in response to art-based tasks using diverse materials based on the Expressive Therapy Continuum (ETC)

This study investigated the relationship between art creation and brain function using functional near-infrared spectroscopy (fNIRS) via a portable NIRSIT device, focusing on the frontal lobe’s oxygen saturation changes during art activities. Authorized by the Institutional Review Board of Seoul Women’s University, the research involved 26 healthy participants aged 20 to 29, without prior mental, medical, or substance use issues. They engaged in four art tasks, separated by rest periods, to monitor pre- and post-task brain activity through fNIRS scans.The research unfolded in two phases: initially, it analyzed brain activity based on the Expressive Therapies Continuum (ETC) framework, comparing different art mediums; next, it then examined differences between drawing on paper and on a digital tablet.Findings indicated unique activation patterns in various brain regions—including the Ventrolateral Prefrontal Cortex (VLPFC), Orbitofrontal Cortex (OFC), Dorsolateral Prefrontal Cortexes (DLPFC), and the parietal cortex—highlighting a notable increase in the Left Frontopolar and Orbitofrontal Cortexes during paper drawing compared to tablet drawing. These results provide insights into how different art mediums influence neural activation, particularly showing enhanced activity in regions linked to empathy and feedback in paper-based tasks. It clearly suggests that different art materials significantly influence varying brain region activation, highlighting the importance of art medium and art-making in art therapy in enhancing cognitive and emotional functions.By examining changes in frontal lobe oxygen saturation via diverse art activities grounded in the ETC framework, this study contributes to understanding art therapy’s neurological impact on cognitive and emotional functions. It offers evidence-based guidance for art therapists on selecting materials that meet therapeutic objectives. The study’s limitations include a small sample size that may affect the generalizability of the findings and the exclusive use of NIRSIT focusing on the frontal cortex, potentially neglecting the involvement of other brain regions like the temporal and parietal cortexes in art activities. Future research should therefore consider expanding the sample size and employing comprehensive neuroimaging techniques.

Speech-induced suppression and vocal feedback sensitivity in human cortex.

Across the animal kingdom, neural responses in the auditory cortex are suppressed during vocalization, and humans are no exception. A common hypothesis is that suppression increases sensitivity to auditory feedback, enabling the detection of vocalization errors. This hypothesis has been previously confirmed in non-human primates, however a direct link between auditory suppression and sensitivity in human speech monitoring remains elusive. To address this issue, we obtained intracranial electroencephalography (iEEG) recordings from 35 neurosurgical participants during speech production. We first characterized the detailed topography of auditory suppression, which varied across superior temporal gyrus (STG). Next, we performed a delayed auditory feedback (DAF) task to determine whether the suppressed sites were also sensitive to auditory feedback alterations. Indeed, overlapping sites showed enhanced responses to feedback, indicating sensitivity. Importantly, there was a strong correlation between the degree of auditory suppression and feedback sensitivity, suggesting suppression might be a key mechanism that underlies speech monitoring. Further, we found that when participants produced speech with simultaneous auditory feedback, posterior STG was selectively activated if participants were engaged in a DAF paradigm, suggesting that increased attentional load can modulate auditory feedback sensitivity.

Religiosity, Financial Risk Taking, and Reward Processing: An Experimental Study

AbstractThe present study investigated the extent to which financial risk-taking (FRT) perspectives and religiosity influenced an individual’s performance on financial decision-making tasks under risk and/or uncertainty. It further investigated the potential to measure this interaction using electro-encephalogram (EEG) assessments through reward-related event-related potentials (P3 and FRN). EEG data were collected from 37 participants undergoing four decision-making tasks comprising the Balloon Analogue Risk Task (BART), Iowa Gambling Test (IGT), Mixed-Gamble Loss-Aversion Task (MGLAT), and MGLA-Success Task (MGLAST). The present study found that BART performance may be affected by an interaction of FRT perspectives and religiosity. The physiological effects of task feedback were also distinguished between religious and non-religious individuals objectively with EEG data. Overall, while religiosity and FRT may not significantly influence IGT and MGLA performance, and interact with BART in a complex way, physiological reaction towards feedback after BART performance appears to be strongly affected by religiosity and FRT perspectives.