Models Of Human Behavior Research Articles

Deep latent variable joint cognitive modeling of neural signals and human behavior

As the field of computational cognitive neuroscience continues to expand and generate new theories, there is a growing need for more advanced methods to test the hypothesis of brain-behavior relationships. Recent progress in Bayesian cognitive modeling has enabled the combination of neural and behavioral models into a single unifying framework. However, these approaches require manual feature extraction, and lack the capability to discover previously unknown neural features in more complex data. Consequently, this would hinder the expressiveness of the models. To address these challenges, we propose a Neurocognitive Variational Autoencoder (NCVA) to conjoin high-dimensional EEG with a cognitive model in both generative and predictive modeling analyses. Importantly, our NCVA enables both the prediction of EEG signals given behavioral data and the estimation of cognitive model parameters from EEG signals. This novel approach can allow for a more comprehensive understanding of the triplet relationship between behavior, brain activity, and cognitive processes.

Little Things Matter a Lot: The Significance of Implicit Bias, Practically & Legally

Abstract Skeptics point out that measures of implicit bias can only weakly predict discrimination. And it is true that under current technologies, the degree of correlation between implicit bias (for example, as measured by the Implicit Association Test) and discriminatory judgment and behavior is small to moderate. In this essay, I argue that these little effects nevertheless matter a lot, in two different senses. First, in terms of practical significance, small burdens can accumulate over time to produce a large impact in a person's life. When these impacts are integrated not only over time but double integrated over large populations, these little things become even more practically significant. Second, in terms of legal significance, an upgraded model of discrimination that incorporates implicit bias has started to reshape antidiscrimination law. This transformation reflects a commitment to “behavioral realism”: a belief that the law should reflect more accurate models of human thinking and behavior.

A tutorial on fitting joint models of M/EEG and behavior to understand cognition

We present motivation and practical steps necessary to find parameter estimates of joint models of behavior and neural electrophysiological data. This tutorial is written for researchers wishing to build joint models of human behavior and scalp and intracranial electroencephalographic (EEG) or magnetoencephalographic (MEG) data, and more specifically those researchers who seek to understand human cognition. Although these techniques could easily be applied to animal models, the focus of this tutorial is on human participants. Joint modeling of M/EEG and behavior requires some knowledge of existing computational and cognitive theories, M/EEG artifact correction, M/EEG analysis techniques, cognitive modeling, and programming for statistical modeling implementation. This paper seeks to give an introduction to these techniques as they apply to estimating parameters from neurocognitive models of M/EEG and human behavior, and to evaluate model results and compare models. Due to our research and knowledge on the subject matter, our examples in this paper will focus on testing specific hypotheses in human decision-making theory. However, most of the motivation and discussion of this paper applies across many modeling procedures and applications. We provide Python (and linked R) code examples in the tutorial and appendix. Readers are encouraged to try the exercises at the end of the document.

ИНТЕГРАЦИЯ ТЕХНОЛОГИИ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА ДЛЯ ПОВЫШЕНИЯ ЭФФЕКТИВНОСТИ ЭВАКУАЦИИ ЛЮДЕЙ ПРИ ПОЖАРЕ

The application of artificial intelligence technology to improve the evacuation control system at fires is considered. The focus is on the shortcomings of traditional evacuation methods and the potential of artificial intelligence in big data processing to optimize the flow of people. 
 The integration of artificial intelligence algorithms with models of human behavior to develop more effective evacuation scenarios that take into account the psychological and physiological aspects of human behavior in emergency situations is discussed.

Key influences on university students’ physical activity: a systematic review using the Theoretical Domains Framework and the COM-B model of human behaviour

BackgroundPhysical activity is important for all aspects of health, yet most university students are not active enough to reap these benefits. Understanding the factors that influence physical activity in the context of behaviour change theory is valuable to inform the development of effective evidence-based interventions to increase university students’ physical activity. The current systematic review a) identified barriers and facilitators to university students’ physical activity, b) mapped these factors to the Theoretical Domains Framework (TDF) and COM-B model, and c) ranked the relative importance of TDF domains.MethodsData synthesis included qualitative, quantitative, and mixed-methods research published between 01.01.2010—15.03.2023. Four databases (MEDLINE, PsycINFO, SPORTDiscus, and Scopus) were searched to identify publications on the barriers/facilitators to university students' physical activity. Data regarding study design and key findings (i.e., participant quotes, qualitative theme descriptions, and survey results) were extracted. Framework analysis was used to code barriers/facilitators to the TDF and COM-B model. Within each TDF domain, thematic analysis was used to group similar barriers/facilitators into descriptive theme labels. TDF domains were ranked by relative importance based on frequency, elaboration, and evidence of mixed barriers/facilitators.ResultsThirty-nine studies involving 17,771 participants met the inclusion criteria. Fifty-six barriers and facilitators mapping to twelve TDF domains and the COM-B model were identified as relevant to students’ physical activity. Three TDF domains, environmental context and resources (e.g., time constraints), social influences (e.g., exercising with others), and goals (e.g., prioritisation of physical activity) were judged to be of greatest relative importance (identified in > 50% of studies). TDF domains of lower relative importance were intentions, reinforcement, emotion, beliefs about consequences, knowledge, physical skills, beliefs about capabilities, cognitive and interpersonal skills, social/professional role and identity, and behavioural regulation. No barriers/facilitators relating to the TDF domains of memory, attention and decision process, or optimism were identified.ConclusionsThe current findings provide a foundation to enhance the development of theory and evidence informed interventions to support university students’ engagement in physical activity. Interventions that include a focus on the TDF domains 'environmental context and resources,' 'social influences,' and 'goals,' hold particular promise for promoting active student lifestyles.Trial registrationProspero ID—CRD42021242170.

AI-Based User Empowerment for Empirical Social Research

Manual labeling and categorization are extremely time-consuming and, thus, costly. AI and ML-supported information systems can bridge this gap and support labor-intensive digital activities. Since it requires categorization, coding-based analysis, such as qualitative content analysis, reaches its limits with large amounts of data and could benefit from AI and ML-based support. Empirical social research, its application domain, benefits from Big Data’s ability to create more extensive human behavior and development models. A range of applications are available for statistical analysis to serve this purpose. This paper aims to implement an information system that supports researchers in empirical social research in performing AI-supported qualitative content analysis. AI2VIS4BigData is a reference model that standardizes use cases and artifacts for Big Data information systems that integrate AI and ML for user empowerment. Thus, this work’s concepts and implementations try to achieve an AI2VIS4BigData-compliant information system that supports social researchers in categorizing text data and creating insightful dashboards. Thereby, the text categorization is based on an existing ML component. Furthermore, it presents two evaluations that were conducted for these concepts and implementations: a qualitative cognitive walkthrough assessing the system’s usability and a quantitative user study with 18 participants revealed that though the users perceive AI support as more efficient, they need more time to reflect on the recommendations. The research revealed that AI support increased the correctness of the users’ categorizations but also slowed down their decision-making. The assumption that this is due to the UI design and additional information for processing requires follow-up research.

Generative Environment-Representation Instance-Based Learning: A Cognitive Model

Instance-Based Learning Theory (IBLT) suggests that humans learn to engage in dynamic decision making tasks through the accumulation of experiences, represented by the decision task features, the actions performed, and the utility of decision outcomes. This theory has been applied to the design of Instance-Based Learning (IBL) models of human behavior in a variety of contexts. One key feature of all IBL model applications is the method of accumulating instance-based memory and performing recognition-based retrieval. In simple tasks with few features, this knowledge representation and retrieval could hypothetically be done using all relevant information. However, these methods do not scale well to complex tasks when exhaustive enumeration of features is unfeasible. This requires cognitive modelers to design task-specific representations of state features, as well as similarity metrics, which can be time consuming and fail to generalize to related tasks. To address this issue, we leverage recent advancements in Artificial Neural Networks, specifically generative models (GMs), to learn representations of complex dynamic decision making tasks without relying on domain knowledge. We evaluate a range of GMs in their usefulness in forming representations that can be used by IBL models to predict human behavior in a complex decision making task. This work connects generative and cognitive models by using GMs to form representations and determine similarity.

Models of Human Behavior for Human-Robot Interaction and Automated Driving: How Accurate Do the Models of Human Behavior Need to Be?

There are many examples of cases where access to improved models of human behavior and cognition has allowed creation of robots which can better interact with humans, and not least in road vehicle automation this is a rapidly growing area of research. Human-robot interaction (HRI) therefore provides an important applied setting for human behavior modeling - but given the vast complexity of human behavior, how complete and accurate do these models need to be? Here, we outline some possible ways of thinking about this problem, starting from the suggestion that modelers need to keep the right end goal in sight: A successful human-robot interaction, in terms of safety, performance, and human satisfaction. Efforts toward model completeness and accuracy should be focused on those aspects of human behavior to which interaction success is most sensitive. We emphasise that identifying which those aspects are is a difficult scientific objective in its own right, distinct for each given HRI context. We propose and exemplify an approach to formulating a priori hypotheses on this matter, in cases where robots are to be involved in interactions which currently take place between humans, such as in automated driving. Our perspective also highlights some possible risks of overreliance on machine-learned models of human behavior in HRI, and how to mitigate against those risks.

Fuzzy Logic-based Techniques for Human Driver Behavior Modelling during a Simple Lane-changing Task

The paper presents an experiment with fuzzy-logic-based models for approximating data representing human driver behavior during a simple lane-changing task. Data are acquired via the self-developed car driving simulator under defined conditions. Three fuzzy-logic-based models are considered: fuzzy Hammerstein model, fuzzy PD controller with a fixed structure (analogy to the linear PD controller) and fuzzy PD controller with an optimized structure. A comparison of the effectiveness of the individual approaches was evaluated using a criterion representing the fitness of the model output and the measured data. Although only one dataset was considered in the frame of this paper, the results indicate an investigative potential of the fuzzy models for this kind of task connected with the modelling of human behavior.

ХУДОЖНІЙ ТЕКСТ ЯК ВТІЛЕННЯ ПРАВДИ ПРО МИНУЛЕ

Background. The article is devoted to the study of the problem of post-totalitarian trauma in modern Ukrainian literature, in particular in novels, which, thanks to their genre features, are able to depict not only phenomena, facts, but also broad contexts. The relevance of the research lies in the analysis of various human behavioral models caused by the activities of the totalitarian system, the so-called big changes that are finally reflected in the literary texts of modern authors as those who are ready to offer for articulation the silenced and hidden. The purpose of the study is to demonstrate the ability of trauma novels to accumulate memory about the true past, despite the influence of totalitarian practices, to show the mechanisms and approaches when encountering a traumatic experience in the novels "Museum of Abandoned Secrets" by Oksana Zabuzhko and "Amadoka" by Sofia Andruhovich. Methods. To achieve the goal, the research used a historical and cultural approach, "memory studies", and a comparative method. Results. A novel text describing traumatic events and their consequences provides the possibility of a conditional encounter with the past. Memory serves as a tool for these meetings as a mediator between what was, is and will be. The work of memory is made much more difficult when the official history is falsified. Under such conditions, individual stories are of great value. Especially those that talk about the experience of living similar events in similar circumstances. A broad background, a large number of individual stories with a common denominator is needed to refute false narratives and promote a true past. Conclusions. It has been found that a literary text (as a tool and artifact) depicting trauma, the truth about it, can perform a therapeutic role, contribute to the strengthening or construction of identity, and counter falsified narratives. On the specific semantic lines of the analyzed texts, it is demonstrated how different persons in the same circumstances behave differently, and the common behavioral traits of the characters-actors who are directly confronted with the trauma of the past are traced.

Harnessing AI and analytics to enhance cybersecurity and privacy for collective intelligence systems.

Collective intelligence systems like Chat Generative Pre-Trained Transformer (ChatGPT) have emerged. They have brought both promise and peril to cybersecurity and privacy protection. This study introduces novel approaches to harness the power of artificial intelligence (AI) and big data analytics to enhance security and privacy in this new era. Contributions could explore topics such as: leveraging natural language processing (NLP) in ChatGPT-like systems to strengthen information security; evaluating privacy-enhancing technologies to maximize data utility while minimizing personal data exposure; modeling human behavior and agency to build secure and ethical human-centric systems; applying machine learning to detect threats and vulnerabilities in a data-driven manner; using analytics to preserve privacy in large datasets while enabling value creation; crafting AI techniques that operate in a trustworthy and explainable manner. This article advances the state-of-the-art at the intersection of cybersecurity, privacy, human factors, ethics, and cutting-edge AI, providing impactful solutions to emerging challenges. Our research presents a revolutionary approach to malware detection that leverages deep learning (DL) based methodologies to automatically learn features from raw data. Our approach involves constructing a grayscale image from a malware file and extracting features to minimize its size. This process affords us the ability to discern patterns that might remain hidden from other techniques, enabling us to utilize convolutional neural networks (CNNs) to learn from these grayscale images and a stacking ensemble to classify malware. The goal is to model a highly complex nonlinear function with parameters that can be optimized to achieve superior performance. To test our approach, we ran it on over 6,414 malware variants and 2,050 benign files from the MalImg collection, resulting in an impressive 99.86 percent validation accuracy for malware detection. Furthermore, we conducted a classification experiment on 15 malware families and 13 tests with varying parameters to compare our model to other comparable research. Our model outperformed most of the similar research with detection accuracy ranging from 47.07% to 99.81% and a significant increase in detection performance. Our results demonstrate the efficacy of our approach, which unlocks the hidden patterns that underlie complex systems, advancing the frontiers of computational security.

Evaluating the Effect of Fatigue on Driver’s Performance

The paper presents an experimental cybernetic approach for the evaluation of drivers’ performance in connection with fatigue based on mathematical modelling and description of human behavior during a simple lane-changing task. Data are acquired via the in-house developed car driving simulator under defined conditions. Statistical evaluation of the used parameters for 50 active drivers is presented as an initial data set for the determination of the described drivers’ performance decision-making system built on fuzzy logic. The system was then used for calculating the DPI (Driver performance index) as a self-determined relative measure of drivers’ performance. Then, an example of applying the method with three volunteers influenced by fatigue is presented. All of these participants reached lower DPI in the case of fatigue induced by a 3-hour-long simulated loading drive on a highway. Although the results cannot be statistically significantly interpreted, they indicate a potential for further and deeper research.

Konsep Kepribadian Seorang Muslimah Milenial Pada Era Revolusi Industri (Telaah Buku Amazing Stories)

In this modern and advanced era, the challenges of becoming a pious Muslim woman are much greater and more difficult. Personality means a series of normative human behavior, the norms of which are derived from the Koran, Sunnah and Ijtihad. An increasingly advanced civilization could also be a factor in the collapse of morals and morals. The progress and decline of Islamic generations cannot be separated from women. So there is a need for a female figure to be a role model, namely Fatimah Az-Zahra. Fatimah is a role model and exemplary example in her great qualities. The method used in this research is a qualitative research method, a type of library study research using content analysis. Muslim women are respected and given honor in Islam. Taking care of oneself, cleansing one's morals, covering one's private parts, wearing a hijab and dressing respectably are very noble and beautiful attitudes for Muslims. The character of Fatimah Az-Zahra greatly influences the development and personality of Muslim women in the current era. And Fatimah Az-Zahra's character can be a role model for shaping good human behavior for the development of her personality.

ЭВОЛЮЦИЯ МОДЕЛИ ЭКОНОМИЧЕСКОГО ПОВЕДЕНИЯ ЧЕЛОВЕКА В УСЛОВИЯХ ЦИФРОВОЙ ТРАНСФОРМАЦИИ

The development of information and communication technologies and the rapid digitalization of public life are driving fundamental transformations of socio-economic systems into a knowledge society and a digital economy. The speed of change in recent decades leads to the fact that “traditional” economic models are losing their methodological sufficiency for the modern level of science and need to be rethought. As a result, the purpose of the article is to propose an updated model of human economic behavior in the context of digital transformation based on an analysis of the evolution of economic behavior models. To achieve the goal of the study, the following tasks were set: to analyze models of human economic behavior in economics and the humanities; highlight key aspects of digitalization that significantly influence changes in the socio-economic sphere of public life; characterize changes in human economic behavior generated by the digital transformation of society. As a result of the study, factors determining economic behavior in the digital economy were identified. These include: facilitating access to information as a basic consumption product; the emergence of a new form of property (intellectual property) and new objects of property (information products); changing relations between producers and consumers, employers and employees; the formation of a “sharing” economy as an innovative form of trade. The article shows the significant impact of the digital economy on changing the model of human economic behavior. A model of economic behavior is understood as a system, the elements of which determine the guidelines and choices of a person in the economic sphere. These include: the presence of objective limitations and subjective preferences of the individual, the ability to assess possible behavior options, analysis of information, choice of behavior model. In addition to these constant determinants of economic behavior, the model also contains variable factors influencing economic choice. These include: attitude towards information and the ability to access it, motivation for economic activity, rationality of actions and irrationality in decision making, goal setting as a system-forming function of the individual. Variable elements undergo significant transformations, which must be taken into account in the updated model of the behavior of “economic homo.”

The Prediction Model of Human Household Behavior of the Refuse Management System with Artificial Neural Network

Efficient management of household trash is essential to maintaining a sustainable society and a good environment. Low community engagement in environmental cleanup has led to dozens of unused refuse management apps. Today’s refuse management system lacks a secure identification protocol for identifying users, especially those who have signed up for the app. Predicting and understanding human household behavior is needed, and it remains a complex challenge. Therefore, this study aims to predict human household behavior in the refuse management system using artificial neural networks (ANN). The work involved in developing the prediction model included data collection, data pre-processing, neural network model development, and performance validation. There are 505 participants, urban residents in Kuala Lumpur obtained for this study. ANN with one hidden layer is developed in MATLAB. The results show that the accuracy of the developed model is 83%. It indicates that ANN performed well in predicting household behavior in the refuse management system.

Ecological momentary assessments of real-world speech listening are associated with heart rate and acoustic condition

Background and aimEcological momentary assessment (EMA) can provide insights into the real-world auditory ecology of hearing aid (HA) users. To better understand what factors, influence the real-world listening experiences of this population, more detailed models of human auditory ecology and behavior are needed. Laboratory studies suggest that physiological measures are sensitive to different listening experiences, as changes in physiological signals (e.g., pupil dilation) have been associated with effortful listening. In addition, real-world heart rate (HR) has been shown to be sensitive to acoustic influences (e.g., sound pressure level, SPL, and signal-to-noise ratio, SNR). Here, we hypothesized that including physiological and acoustic data in models predicting EMA ratings can provide additional insights into real-world listening outcome. To test this, we collected and analyzed longitudinal data from individuals with normal hearing.MethodFifteen normal-hearing adults completed smartphone-based EMAs regarding their listening experiences during a 2-week period. When completing the EMAs, they had to indicate their current listening intent. The participants received a single HA each that they fastened to their collars. The HAs were used to collect continuous SPL and SNR data in the participants' daily environments. Wristbands worn by the participants were used to collect continuous HR data.ResultsLinear mixed-effects models with SPL, SNR, and HR as fixed effects and participant as random intercept showed that higher SPL and lower SNR were associated with lower (poorer) EMA ratings. Including listening intent in the analyses revealed increased HR in “speech communication” and “focused listening” situations to be associated with better EMA ratings relative to situations without any specific listening intent.ConclusionsOur findings indicate that including in-situ HR and acoustic measurements can improve the prediction of real-world listening experiences. Further, they suggest that listening intent significantly impacts self-reported listening experiences and their association with physiological responses. Specifically, better listening experiences in speech communication situations are associated with higher HR.

CNSC-12. PATHOLOGY SPECIFIC, PHARMACOLOGICALLY REVERSIBLE LOSS OF NEURONAL FUNCTION IN HUMAN GLIOMAS

Abstract Prior evidence has demonstrated that neuronal activity is preserved within glioma-infiltrated cortex and maintains the ability to engage in task specific computations albeit with information loss. These findings support a potential therapeutic target to rescue cognitive impairments seen in nearly all afflicted patients if neuronal activity can be recovered. We developed an in vivo human behavioral and electrophysiological model to assess neuronal population tuning responses within primary sensory cortex including the decodability of stimuli and task-related changes in population spiking in a cohort of 14 human patients undergoing awake resection. We placed high-density electrode arrays to record human local field potentials from gliomas projecting to the cortical surface. We next designed a static sensory detection threshold task, stimulating with a tachometer at two different face and hand sites totaling 11,200 trials while recording from macroelectrode cortical contacts over both tumor-infiltrated (50 electrodes) and normal appearing cortex (52 electrodes). In tumor-infiltrated cortex, the ability to decode the site of stimulation using the oscillatory power in both theta (4-8 Hz) and gamma (32-70 Hz) bands was reduced compared to normal appearing cortex. However, tumor-infiltrated cortex-maintained selectivity between hand and face stimulation. Targeted next-generation tumor sequencing uncovered novel molecular targets of glioma-neuronal integration. The degree of loss of selectivity correlated with WHO grade and pathology. WHO grade 4 tumors and oligodendrogliomas compared to astrocytomas demonstrating greater loss of selectivity. Gabaergic agonist has been postulated to restore neuronal selectivity in aging and neurodegenerative disease. Therefore, we next computed GABA agonist dose (estimated by time off Propofol and beginning of behavioral testing). Higher concentrations of GABA agonist correlated with improved theta band selectivity and decodability. These results suggest that loss of neuronal computations in glioma-infiltrated cortex is caused by loss of neuronal selectivity and is both tumor selective and pharmacologically reversible.

Accounting for Transfer of Learning Using Human Behavior Models

An important characteristic of human learning and decision-making is the flexibility with which we rapidly adapt to novel tasks. To this day, models of human behavior have been unable to emulate the ease and success with which humans transfer knowledge in one context to another. Humans rely on a lifetime of experience and a variety of cognitive mechanisms that are difficult to represent computationally. To address this problem, we propose a novel human behavior model that accounts for human transfer of learning using three mechanisms: compositional reasoning, causal inference, and optimal forgetting. To evaluate this proposed model, we introduce an experiment task designed to elicit human transfer of learning under different conditions. Our proposed model demonstrates a more human-like transfer of learning compared to models that optimize transfer or human behavior models that do not directly account for transfer of learning. The results of the ablation testing of the proposed model and a systematic comparison to human data demonstrate the importance of each component of the cognitive model underlying the transfer of learning.

Can competing demands affect pro-environmental behaviour: a study of the impact of exposure to partly related sequential experiments

The study of human behaviour is central to the development of appropriate policies for sustainability. We argue that mathematical models of human choice behaviour may produce biased results if they fail to account for the possibility of spillover effects, in particular the possibility that individual behaviour may change as a result of interventions along with competing demands (multiple demands), such as in the sequential exposure to partly related choice contexts. Using a sample of 751 individuals and a carefully constructed experiment, we develop mathematical models that jointly explain the choice between different pro-environmental actions and the willingness to donate money for environmental causes, and at the same time, allow us to test the indirect effect of exposure to multiple demands. We find that the strength of preferences for behavioural changes leading to greater CO2 reductions is (causally) shaped by participants previously considering other similar behavioural changes. The kind of spillover effects we find are relatively complex and often subtle, and thus warrant further replication studies. Care was taken to account for variation of tastes, formatting, order and learning effects, thus reducing the risk of the spillover-related results being influenced by differences across individuals in environmental preferences. Our study demonstrates the existence of a specific type of spillover effects, namely how prior exposure to related choice contexts may affect behaviour in subsequent settings and showcased the effectiveness of discrete choice models to test for it. Given our results, we believe that spillover effects need to be taken into account in the broader choice modelling literature, and at the same time we showcase a useful experimental framework for environmental psychologists and economists.

Stochastic replicator dynamics: A theoretical analysis and an experimental assessment

We study the dynamics of strategic choice in an environment where payoffs are perturbed by strategy-specific noise and strategy revision is governed by the simple proportional imitation protocol. Applying the stochastic replicator dynamic to a two-by-two symmetric game, we derive the steady-state frequencies of the strategies and show that the dominated strategy can persist in equilibrium if the variance of the payoff shocks exceeds a critical value. Additionally, the rate of decay of the dominated strategy decreases with increasing variance. The behaviours of our experimental subjects accord with these tendencies. Our findings add to the growing experimental literature that demonstrates that evolutionary models of human behaviour with simple adaptive rules have predictive ability, even in complex, volatile environments.