Adaptive Control Of Thought-Rational Research Articles

A risk evaluation method for human-machine interaction in emergencies based on multiple mental models-driven situation assessment

In the process of human-machine interaction (HMI) under abnormal situations, situation assessment (SAS) is a critical component as incorrect SAS can feed into inappropriate actions and cause severe accidents. Therefore, it is essential to model SAS for HMI risk evaluation. During emergency situations, SAS is predominantly affected by time pressure. However, current researches focus on deliberative SAS with sufficient time and have limitations in quantifying the time pressure effect on SAS during emergencies. This paper proposes a risk evaluation method for HMI in emergencies by quantitatively modeling the time pressure effect on SAS under the recognition-primed decision (RPD) model framework. Firstly, SAS process is characterized as identifying the first plausible cause of an abnormal phenomenon driven by multiple Bayesian network-based mental models, and a simulation algorithm for SAS process is proposed to evaluate HMI risk. Secondly, two effects of time pressure on SAS activities, i.e., filtration effect on information perception and impair effect on knowledge retrieval, are quantified based on the Saliency-Effort-Expectancy-Value (SEEV) model and the Adaptive Control of Thought-Rational (ACT-R) theory. Finally, this method is applied to a Boeing 737-31S accident with high time pressure and results demonstrate the effectiveness of the method.

Modeling Effects of Rumination on Free Recall Using ACT-R.

Ruminative thinking, characterized by a recurrent focus on negative and self-related thought, is a key cognitive vulnerability marker of depression and, therefore, a key individual difference variable. This study aimed to develop a computational cognitive model of rumination focusing on the organization and retrieval of information in memory, and how these mechanisms differ in individuals prone to rumination and individuals less prone to rumination. Adaptive Control of Thought-Rational (ACT-R) was used to develop a rumination model by adding memory chunks with negative valence to the declarative memory. In addition, their strength of association was increased to simulate recurrent negative focus, thereby making it harder to disengage from. The ACT-R models were validated by comparing them against two empirical datasets containing data from control and depressed participants. Our general and ruminative models were able to recreate the benchmarks of free recall while matching the behavior exhibited by the control and the depressed participants, respectively. Our study shows that it is possible to build a computational theory of rumination that can accurately simulate the differences in free recall dynamics between control and depressed individuals. Such a model could enable a more fine-tuned investigation of underlying cognitive mechanisms of depression and potentially help to improve interventions by allowing them to more specifically target key mechanisms that instigate and maintain depression.

Driver behavior and mental workload for takeover safety in automated driving: ACT-R prediction modeling approach

Objective Conditional automated driving (SAE level 3) requires the driver to take over the vehicle if the automated system fails. The mental workload that can occur in these takeover situations is an important human factor that can directly affect driver behavior and safety, so it is important to predict it. Therefore, this study introduces a method to predict mental workload during takeover situations in automated driving, using the ACT-R (Adaptive Control of Thought-Rational) cognitive architecture. The mental workload prediction model proposed in this study is a computational model that can become the basis for emerging crash avoidance technologies in future autonomous driving situations. Methods The methodology incorporates the ACT-R cognitive architecture, known for its robustness in modeling cognitive processes and predicting performance. The proposed takeover cognitive model includes the symbolic structure for repeatedly checking the driving situation and performing decision-making for takeover as well as Non-Driving-Related Tasks (NDRT). We employed the ACT-R cognitive model to predict mental workload during takeover in automated driving scenarios. The model’s predictions are validated against physiological data and performance data from the validation test. Results The model demonstrated high accuracy, with an r-square value of 0.97, indicating a strong correlation between the predicted and actual mental workload. It successfully captured the nuances of multitasking in driving scenarios, showcasing the model’s adaptability in representing diverse cognitive demands during takeover. Conclusions The study confirms the efficacy of the ACT-R model in predicting mental workload for takeover scenarios in automated driving. It underscores the model’s potential in improving driver-assistance systems, enhancing vehicle safety, and ensuring the efficient integration of human-machine roles. The research contributes significantly to the field of cognitive modeling, providing robust predictions and insights into human behavior in automated driving tasks.

ACT-R based human digital twin to enhance operators' performance in process industries.

To ensure safe and efficient operation, operators in process industries have to make timely decisions based on time-varying information. A holistic assessment of operators' performance is, therefore, challenging. Current approaches to operator performance assessment are subjective and ignore operators' cognitive behavior. In addition, these cannot be used to predict operators' expected responses during novel situations that may arise during plant operations. The present study seeks to develop a human digital twin (HDT) that can simulate a control room operator's behavior, even during various abnormal situations. The HDT has been developed using the ACT-R (Adaptive Control of Thought-Rational) cognitive architecture. It mimics a human operator as they monitor the process and intervene during abnormal situations. We conducted 426 trials to test the HDT's ability to handle disturbance rejection tasks. In these simulations, we varied the reward and penalty parameters to provide feedback to the HDT. We validated the HDT using the eye gaze behavior of 10 human subjects who completed 110 similar disturbance rejection tasks as that of the HDT. The results indicate that the HDT exhibits similar gaze behaviors as the human subjects, even when dealing with abnormal situations. These indicate that the HDT's cognitive capabilities are comparable to those of human operators. As possible applications, the proposed HDT can be used to generate a large database of human behavior during abnormalities which can then be used to spot and rectify flaws in novice operator's mental models. Additionally, the HDT can also enhance operators' decision-making during real-time operation.

Making movies of children's cortical electrical potentials: A practical procedure for dynamic source localization analysis with validating simulation

Dipole source localization analysis (DSLA) of brain's event-related electrical potentials (ERPs) often presumes time constraints potentially too rigid to capture complex neural dynamics. We present a practical procedure (dynamically-guided DSLA) combining in a novel way well-established off-the-shelf modeling (Independent Component Analysis, and proprietary software modules running on MATLAB, such as FASTICA and EEG-Lab DIPFIT) with the cognitive modeling simulation framework tool known as Adaptive Control of Thought-Rational (ACT-R). The integration of these multiple methods can narrow down the time-windows of interest for DSLA more flexibly. As a demonstration, we used dynamically-guided DSLA to re-analyze cluster-level ERPs from a visual target detection task involving the participation of 26 preschool children. The key analytic features were dynamic ERP movies vis-à-vis validating ACT-R simulation of comparison adult data for the same task. Spatial topography for the six estimated sources did not differ significantly in children's and adult simulated data, which generally showed high fit (predicted R2 > 0.97). A control comparison using the static DSLA showed discrepant fits for two sources, suggesting that dynamic DSLA may offer higher discriminant reliability. Given its high validity, flexibility and relative user-friendliness, dynamically-guided DSLA seems useful for assessing developmental homology and may be suitable for a variety of clinical and experimental applications specifically involving neurodevelopmental data. Statement of SignificanceAccurately determining the location of neural activity observed via electroencephalogram remains a well-known challenge. Under a variety of conditions, conventional dipole source localization analysis methodologies can result in underqualified data. In this work we present a novel process, known as dynamically-guided DSLA, which demonstrates how pre-existing tools can be appropriated to facilitate the examination and analysis of neurological activity in preschool-aged children. Because the effects exerted by a stimulus or event on EEG signals can be linked to behaviors and actions, at different levels of physical mechanisms of different degree of complexity, this neuroimaging tool offers the opportunity to cut across multiple layers of physical systems underlying cognitive and emotional functions, and therefore can be leveraged to reach invaluable insights. We highlight how the proposed technique can help link the electrophysiology to underlying physical alteration (e.g., neurodevelopmental disease); and how the proposed combination of methodologies can help "reverse engineer" physical defects or anomalies (and their locations) to quantify the EEG measurements in terms of dynamic interactive physical phenomena (movie of topographically mapped brain activity), as opposed to just giving a number against a disease or identifying a brain location.

A Preliminary Study of Modeling Driver Situational Awareness based on SEEV and ACT-R Models

In automated driving, it is important to maintain drivers’ situational awareness (SA) in order to help them avoid unnecessary interventions and negotiate challenging scenarios where human takeovers are needed. Our study developed computational models to predict a driver’s SA of a target object. Using the SEEV (Salience, Effort, Expectancy, and Value) and ACT-R (Adaptive Control of Thought-Rational) framework, the model achieved an accuracy of 78.3%, an F1-score of 0.66, and the area under the receiver operating characteristic (AUROC) value of 0.773 with object features as inputs. On average, the model had a Root Mean Square Error (RMSE) of 0.18 to predict the SA of a target object across participants. In relative to the existing models, our model not only had comparable predictive performance but also considered the underlying mechanism of SA to increase model interpretability. Our research will provide essential and necessary steps toward developing in-vehicle SA prediction and assistance systems.

Cognitive Modeling of Anticipation: Unsupervised Learning and Symbolic Modeling of Pilots' Mental Representations.

The ability to anticipate team members' actions enables joint action towards a common goal. Task knowledge and mental simulation allow for anticipating other agents' actions and for making inferences about their underlying mental representations. In human-AI teams, providing AI agents with anticipatory mechanisms can facilitate collaboration and successful execution of joint action. This paper presents a computational cognitive model demonstrating mental simulation of operators' mental models of a situation and anticipation of their behavior. The work proposes two successive steps: (1) A hierarchical cluster algorithm is applied to recognize patterns of behavior among pilots. These behavioral clusters are used to derive commonalities in situation models from empirical data (N = 13 pilots). (2) An ACT-R (adaptive control of thought - rational) cognitive model is implemented to mentally simulate different possible outcomes of action decisions and timing of a pilot. model tracing of ACT-R allows following up on operators' individual actions. Two models are implemented using the symbolic representations of ACT-R: one simulating normative behavior and the other by simulating individual differences and using subsymbolic learning. Model performance is analyzed by a comparison of both models. Results indicate the improved performance of the individual differences over the normative model and are discussed regarding implications for cognitive assistance capable of anticipating operatorbehavior.

Cognitive & motor skill transfer across speeds: A video game study.

We examined the detailed behavioral characteristics of transfer of skill and the ability of the adaptive control of thought rational (ACT-R) architecture to account for this with its new Controller module. We employed a simple action video game called Auto Orbit and investigated the control tuning of timing skills across speed perturbations of the environment. In Auto Orbit, players needed to learn to alternate turn and shot actions to blow and burst balloons under time constraints imposed by balloon resets and deflations. Cognitive and motor skill transfer was assessed both in terms of game performance and in terms of the details of their motor actions. We found that skill transfer across speeds necessitated the recalibration of action timing skills. In addition, we found that acquiring skill in Auto Orbit involved a progressive decrease in variability of behavior. Finally, we found that players with higher skill levels tended to be less variable in terms of action chunking and action timing. These findings further shed light on the complex cognitive and motor mechanisms of skill transfer across speeds in complex task environments.

Applying a fusion of wearable sensors and a cognitive inspired architecture to real-time ergonomics analysis of manual assembly tasks

High value manufacturing systems still require ergonomically intensive manual activities. Examples include the aerospace industry where the fitting of pipes and wiring into confined spaces in aircraft wings is still a manual operation. In these environments, workers are subjected to ergonomically awkward forces and postures for long periods of time. This leads to musculoskeletal injuries that severely limit the output of a shopfloor leading to loss of productivity. The use of tools such as wearable sensors could provide a way to track the ergonomics of workers in real time. However, an information processing architecture is required in order to ensure that data is processed in real time and in a manner that meaningful action points are retrieved for use by workers.In this work, based on the Adaptive Control of Thought—Rational (ACT-R) cognitive framework, we propose a Cognitive Architecture for Wearable Sensors (CAWES); a wearable sensor system and cognitive architecture that is capable of taking data streams from multiple wearable sensors on a worker’s body and fusing them to enable digitisation, tracking and analysis of human ergonomics in real time on a shopfloor. Furthermore, through tactile feedback, the architecture is able to inform workers in real time when ergonomics rules are broken. The architecture is validated through the use of an aerospace case study undertaken in laboratory conditions. The results from the validation are encouraging and in the future, further tests will be performed in an actual working environment.

Towards a Cognitive Theory of Cyber Deception.

This work is an initial step toward developing a cognitive theory of cyber deception. While widely studied, the psychology of deception has largely focused on physical cues of deception. Given that present-day communication among humans is largely electronic, we focus on the cyber domain where physical cues are unavailable and for which there is less psychological research. To improve cyber defense, researchers have used signaling theory to extended algorithms developed for the optimal allocation of limited defense resources by using deceptive signals to trick the human mind. However, the algorithms are designed to protect against adversaries that make perfectly rational decisions. In behavioral experiments using an abstract cybersecurity game (i.e., Insider Attack Game), we examined human decision-making when paired against the defense algorithm. We developed an instance-based learning (IBL) model of an attacker using the Adaptive Control of Thought-Rational (ACT-R) cognitive architecture to investigate how humans make decisions under deception in cyber-attack scenarios. Our results show that the defense algorithm is more effective at reducing the probability of attack and protecting assets when using deceptive signaling, compared to no signaling, but is less effective than predicted against a perfectly rational adversary. Also, the IBL model replicates human attack decisions accurately. The IBL model shows how human decisions arise from experience, and how memory retrieval dynamics can give rise to cognitive biases, such as confirmation bias. The implications of these findings are discussed in the perspective of informing theories of deception and designing more effective signaling schemes that consider human bounded rationality.

Reinforcement Learning for Production-Based Cognitive Models.

Production-based cognitive models, such as Adaptive Control of Thought-Rational (ACT-R) or Soar agents, have been a popular tool in cognitive science to model sequential decision processes. While the models have been useful in articulating assumptions and predictions of various theories, they unfortunately require a significant amount of hand coding, both with respect to what building blocks cognitive processes should consist of and with respect to how these building blocks are selected and ordered in a sequential decision process. Hand coding of large, realistic models poses a challenge for modelers, and also makes it unclear whether the models can be learned and are thus cognitively plausible. The learnability issue is probably most starkly present in cognitive models of linguistic skills, since linguistic skills involve richly structured representations and highly complex rules. We investigate how reinforcement learning (RL) methods can be used to solve the production selection and production ordering problem in ACT-R. We focus on four algorithms from the learning family, tabular and three versions of deep networks (DQNs), as well as the ACT-R utility learning algorithm, which provides a baseline for the algorithms. We compare the performance of these five algorithms in a range of lexical decision (LD) tasks framed as sequential decision problems. We observe that, unlike the ACT-R baseline, the agents learn even the more complex LD tasks fairly well. However, tabular and DQNs show a trade-off between speed of learning, applicability to more complex tasks, and how noisy the learned rules are. This indicates that the ACT-R subsymbolic system for procedural memory could be improved by incorporating more insights from RL approaches, particularly the function-approximation-based ones, which learn and generalize effectively in complex, more realistictasks.

Multi-agent modelling and situational awareness analysis of human-computer interaction in the aircraft cockpit: A case study

The loss of situational awareness by pilots is one of the harshest risk factors leading to catastrophic accidents. In this paper a situational awareness analysis model based on multiple agents is presented to simulate the human-computer interaction process in the aircraft cockpit. From the perspective of human-in-loop, the integrated model consists of modularized pilot agent model, technical system agent model and environment agent model. Following the structured levels of situational awareness, the pilot's cognitive behaviors are modelled based on Adaptive Control of Thought-Rational (ACT-R) theory and Bayesian network, with the triggering inputs from the visual and auditory sensory channels. Considering the effects of overlapping information from different channels, the formation and evolution mechanism of the pilot's situational awareness is analyzed in a probabilistic inference manner. The tests of input-output characteristics prove that the model can well reflect the distribution and resist the uncertain fluctuation of different cognitive elements. The safety issues based on two simplified real risk scenarios, under the background of the incidents/accidents related with Boeing 737-8 (MAX), were analyzed. The mechanism of accident evolution along with the possible preventive measures were discussed. It is concluded that an early control priority transmission from the technical system to the pilots and the display of direct prompt messages could make a difference in avoiding the serious risk.

Recovering Reliable Idiographic Biological Parameters from Noisy Behavioral Data: the Case of Basal Ganglia Indices in the Probabilistic Selection Task.

Behavioral data, despite being a common index of cognitive activity, is under scrutiny for having poor reliability as a result of noise or lacking replications of reliable effects. Here, we argue that cognitive modeling can be used to enhance the test-retest reliability of the behavioral measures by recovering individual-level parameters from behavioral data. We tested this empirically with the Probabilistic Stimulus Selection (PSS) task, which is used to measure a participant’s sensitivity to positive or negative reinforcement. An analysis of 400,000 simulations from an Adaptive Control of Thought-Rational (ACT-R) model of this task showed that the poor reliability of the task is due to the instability of the end-estimates: because of the way the task works, the same participants might sometimes end up having apparently opposite scores. To recover the underlying interpretable parameters and enhance reliability, we used a Bayesian Maximum A Posteriori (MAP) procedure. We were able to obtain reliable parameters across sessions (intraclass correlation coefficient ≈ 0.5). A follow-up study on a modified version of the task also found the same pattern of results, with very poor test-retest reliability in behavior but moderate reliability in recovered parameters (intraclass correlation coefficient ≈ 0.4). Collectively, these results imply that this approach can further be used to provide superior measures in terms of reliability, and bring greater insights into individual differences.

Developing an Improved ACT-R Model for Pilot Situation Awareness Measurement

According to a previously built situation-awareness (SA) model based on attention allocation, with the ACT-R (Adaptive Control of Thought, Rational) theory for analyzing pilot cognitive processes for situation elements, an SA mathematical model was improved to predict pilot SA during exposure to different display interfaces and missions. An indicator-display monitoring task was performed under different experimental conditions for SA model verification, while the SA global assessment technique (SAGAT), performance measures, 10-dimensional SA rating technique (10-D SART), and eye movement measures were adopted to comprehensively assess the operator’s SA. The experimental results revealed that theoretical prediction values calculated using the improved SA model were strongly correlated with the operation performance, and thus confirming the model validation. The SAGAT was shown to be a more effective method than SART in this research, and the overall SAGAT accuracy rate, as well as the accuracy response time, are effective indices for SA measurement. Eye-movement indices, such as the fixation/saccade ratio, which corresponds to the mode of information perception and extraction, was examined to be sensitive to operator’s SA changes. The Advances of the improved SA model have been achieved in predicting and indicating SA by using human behaviors, including operation performance, SAGAT response behaviors, and visual behaviors. Thereby, it provides a new auxiliary tool for quantitative characterization of pilot’s SA during cockpit interface design optimization and ergonomic evaluation.

Cognitive Modeling of Automation Adaptation in a Time Critical Task.

This paper presents a cognitive model that simulates an adaptation process to automation in a time-critical task. The paper uses a simple tracking task (which represents vehicle operation) to reveal how the reliance on automation changes as the success probabilities of the automatic and manual mode vary. The model was developed by using a cognitive architecture, ACT-R (Adaptive Control of Thought-Rational). We also introduce two methods of reinforcement learning: the summation of rewards over time and a gating mechanism. The model performs this task through productions that manage perception and motor control. The utility values of these productions are updated based on rewards in every perception-action cycle. A run of this model simulated the overall trends of the behavioral data such as the performance (tracking accuracy), the auto use ratio, and the number of switches between the two modes, suggesting some validity of the assumptions made in our model. This work shows how combining different paradigms of cognitive modeling can lead to practical representations and solutions to automation and trust in automation.

Computational cognitive modeling and validation of Dp140 induced alteration of working memory in Duchenne Muscular Dystrophy

Duchenne Muscular Dystrophy has emerged as a model to assess cognitive domains. The DMD gene variant location and its association with variable degrees of cognitive impairment necessitate identification of a common denominator. Computer architectures provide a framework to delineate the mechanisms involved in the cognitive functioning of the human brain. Copy number variations in the 79 exons of DMD gene were screened in 84 DMD subjects by Multiplex Ligation-dependent Probe Amplification (MLPA). DMD subjects were categorized based on the presence or absence of DP140 isoform. The cognitive and neuropsychological assessments were carried out as per inclusion criteria using standard scales. Instance-based learning theory (IBLT) based on the partial matching process was developed to mimic Stroop Color and Word Task (SCWT) performance on Adaptive Control of Thought-Rational (ACT-R) cognitive architecture based on IBLT. Genotype–phenotype correlation was conducted based on the mutation location in DMD gene. Assessment of specific cognitive domains in DP140 − ve group corresponded to the involvement of multiple brain lobes including temporal (verbal and visual learning and memory), parietal (visuo-conceptual and visuo-constructive abilities) and frontal (sustained and focused attention, verbal fluency, cognitive control). Working memory axis was found to be the central domain through tasks including RAVLT trial 1, recency effect, digit span backward, working memory index, arithmetic subtests in the Dp140 − ve group. IBLT validated the non-reliance of DMD subjects on recency indicating affected working memory domain. Modeling strategy revealed altered working memory processes in DMD cases with affected Dp140 isoform. DMD brain was observed to rely on primacy than the recency suggesting alterations in working memory capacity. Modeling revealed lowered activation of DMD brain with Dp140 − ve in order to retrieve the instances.

Retooling Computational Techniques for EEG-Based Neurocognitive Modeling of Children's Data, Validity and Prospects for Learning and Education.

This paper describes continuing research on the building of neurocognitive models of the internal mental and brain processes of children using a novel adapted combination of existing computational approaches and tools, and using electro-encephalographic (EEG) data to validate the models. The guiding working model which was pragmatically selected for investigation was the established and widely used Adaptive Control of Thought-Rational (ACT-R) modeling architecture from cognitive science. The anatomo-functional circuitry covered by ACT-R is validated by MRI-based neuroscience research. The present experimental data was obtained from a cognitive neuropsychology study involving preschool children (aged 4–6), which measured their visual selective attention and word comprehension behaviors. The collection and analysis of Event-Related Potentials (ERPs) from the EEG data allowed for the identification of sources of electrical activity known as dipoles within the cortex, using a combination of computational tools (Independent Component Analysis, FASTICA; EEG-Lab DIPFIT). The results were then used to build neurocognitive models based on Python ACT-R such that the patterns and the timings of the measured EEG could be reproduced as simplified symbolic representations of spikes, built through simplified electric-field simulations. The models simulated ultimately accounted for more than three-quarters of variations spatially and temporally in all electrical potential measurements (fit of model to dipole data expressed as R2 ranged between 0.75 and 0.98; P < 0.0001). Implications for practical uses of the present work are discussed for learning and educational applications in non-clinical and special needs children's populations, and for the possible use of non-experts (teachers and parents).

Neural Correlates of Workload Transition in Multitasking: An ACT-R Model of Hysteresis Effect.

This study investigated the effect of task demand transitions at multiple levels of analysis including behavioral performance, subjective rating, and brain effective connectivity, while comparing human data to Adaptive Control of Thought-Rational (ACT-R) simulated data. Three stages of task demand were designed and performed sequentially (Low-High-Low) during AF-MATB tasks, and the differences in neural connectivity during workload transition were identified. The NASA Task Load Index (NASA-TLX) and the Instantaneous Self-Assessment (ISA) were used to measure the subjective mental workload that accompanies the hysteresis effect in the task demand transitions. The results found significant hysteresis effects on performance and various brain network measures such as outflow of the prefrontal cortex and connectivity magnitude. These findings would assist in clarifying the direction and strength of the Granger Causality under demand transitions. As a result, these findings involving the neural mechanisms of hysteresis effects in multitasking environments may be utilized in applications of neuroergonomics research. The ability to compare data derived from human participants to data gathered by the ACT-R model allows researchers to better account for hysteresis effects in neuro-cognitive models in the future.

Presentation of ACT/R-RBF Hybrid Architecture to Develop Decision Making in Continuous and Non-continuous Data

Abstract Computational models are based on symbolic architecture. For this reason, computational models function problematically in dynamic, noisy, and continuous environments. The ACT/R (Adaptive Control of Thought-Rational) model is also problematic, as it is purely based on symbolic architecture like other computational models. The ACT/R decision-making process is based on the production operator on the input subject set. This approach firstly does not make a non-linear mapping between input and the decision-making result in ACT/R. Secondly, it is not possible to decide on the input subjects with a continuous input range because of the need to introduce numerous rules. The objective of presenting the ACT/R-radial basis function (RBF) hybrid architecture method was to create a communication network between input concepts in which the reception of and decision making on a combination of subjects and symbols are possible. Moreover, a non-linear mapping between input and the decision-making result can be created. The said capabilities have been obtained by the combination of ACT/R with an RBF neural network and calculation of the decision-making centers in the said network using clustering. The empirical experiments indicate desirable results in this regard.

EEG-based neural correlates of ACT-R model for multitasking

EEG-based neural correlates of ACT-R model for multitasking