Cognitive Systems Research最新文献_第3页

Optimizing resource allocation in home care services using MaxSAT 利用 MaxSAT 优化家庭护理服务的资源分配

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-15 DOI: 10.1016/j.cogsys.2024.101291

Irene Unceta , Bernat Salbanya , Jordi Coll , Mateu Villaret , Jordi Nin

In large urban areas, enhancing the personal care and quality of life for elderly individuals poses a critical societal challenge. As the population ages and the amount of people requiring assistance grows, so does the demand for home care services. This will inevitably put tremendous pressure on a system that has historically struggled to provide high-quality assistance with limited resources, all while managing urgent, unforeseen additional demands. This scenario can be framed as a resource allocation problem, wherein caregivers must be efficiently matched with services based on availability, qualifications, and schedules. Given its scale and complexity, traditional computational approaches have struggled to address this problem effectively, leaving it largely unresolved. Currently, many European cities emphasize geographical and emotional proximity, offering a model for home care services based on reduced social urban sectors. This new paradigm provides opportunities for tackling the resource allocation problem while promoting desirable pairings between caregivers and elderly people. This paper presents a MaxSAT-based solution in this context. Our approach efficiently allocates services across various configurations, maximizing caregiver-user pairings’ similarity and consistency while minimizing costs. Moreover, we show that our method solves the resource allocation problem in a reasonable amount of time. Consequently, we can either provide an optimal allocation or highlight the limits of the available resources relative to the service demand.

在大城市地区，提高老年人的个人护理和生活质量是一项严峻的社会挑战。随着人口老龄化和需要帮助的人数增加，对家庭护理服务的需求也在增加。这将不可避免地给该系统带来巨大压力，因为该系统一直以来都在努力利用有限的资源提供高质量的援助，同时还要应对紧急的、不可预见的额外需求。这种情况可以归结为资源分配问题，即必须根据可用性、资质和时间安排，有效地将护理人员与服务相匹配。鉴于其规模和复杂性，传统的计算方法难以有效解决这一问题，导致问题在很大程度上得不到解决。目前，许多欧洲城市强调地理和情感上的接近性，在减少城市社会部门的基础上为家庭护理服务提供了一种模式。这种新模式为解决资源分配问题提供了机会，同时促进了护理人员与老年人之间的理想配对。本文在此背景下提出了一种基于 MaxSAT 的解决方案。我们的方法能在各种配置中有效地分配服务，最大限度地提高护理人员与用户配对的相似性和一致性，同时最大限度地降低成本。此外，我们还证明，我们的方法能在合理的时间内解决资源分配问题。因此，我们既能提供最优分配，也能突出可用资源相对于服务需求的局限性。

{"title":"Optimizing resource allocation in home care services using MaxSAT","authors":"Irene Unceta , Bernat Salbanya , Jordi Coll , Mateu Villaret , Jordi Nin","doi":"10.1016/j.cogsys.2024.101291","DOIUrl":"10.1016/j.cogsys.2024.101291","url":null,"abstract":"<div><div>In large urban areas, enhancing the personal care and quality of life for elderly individuals poses a critical societal challenge. As the population ages and the amount of people requiring assistance grows, so does the demand for home care services. This will inevitably put tremendous pressure on a system that has historically struggled to provide high-quality assistance with limited resources, all while managing urgent, unforeseen additional demands. This scenario can be framed as a resource allocation problem, wherein caregivers must be efficiently matched with services based on availability, qualifications, and schedules. Given its scale and complexity, traditional computational approaches have struggled to address this problem effectively, leaving it largely unresolved. Currently, many European cities emphasize geographical and emotional proximity, offering a model for home care services based on reduced social urban sectors. This new paradigm provides opportunities for tackling the resource allocation problem while promoting desirable pairings between caregivers and elderly people. This paper presents a MaxSAT-based solution in this context. Our approach efficiently allocates services across various configurations, maximizing caregiver-user pairings’ similarity and consistency while minimizing costs. Moreover, we show that our method solves the resource allocation problem in a reasonable amount of time. Consequently, we can either provide an optimal allocation or highlight the limits of the available resources relative to the service demand.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101291"},"PeriodicalIF":2.1,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SimplifEx: Simplifying and Explaining Linear Programs SimplifEx：简化和解释线性规划

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-11 DOI: 10.1016/j.cogsys.2024.101298

Claire Ott, Frank Jäkel

Linear Programming is one of the most common methods for finding optimal solutions to complex problems. Despite its extensive use, solutions are not usually accompanied by explanations, especially explanations for non-experts. Our new tool SimplifEx combines well-known preprocessing techniques with cognitively adequate heuristics to simplify a given linear program, structure its variables, and explain the optimal solution that was found. SimplifEx is meant to improve intuitive understanding of linear programs. In addition, we introduce a generalization of the classical dominance relation in Linear Programming. The order of dominant and dominated variables in an optimal solution can give valuable insights into the structure of a problem and fits well with how humans approach linear programs. The resulting, automatically generated explanations include detailed step-wise listings of processing steps and graphs that provide an overview. The heuristics are based on historical and experimental observations of people solving linear programs by hand. We apply SimplifEx to Stigler’s diet problem as a running example.

线性规划是为复杂问题寻找最优解的最常用方法之一。尽管线性规划被广泛使用，但其解决方案通常并不附带解释，尤其是针对非专业人士的解释。我们的新工具 SimplifEx 结合了著名的预处理技术和认知启发式方法，可简化给定的线性规划、构建变量结构并解释找到的最优解。SimplifEx 旨在提高对线性规划的直观理解。此外，我们还引入了线性规划中经典支配关系的一般化。最优解中支配变量和被支配变量的顺序可以让人深入了解问题的结构，非常符合人类处理线性规划的方式。由此自动生成的解释包括处理步骤的详细分步列表和提供概览的图表。启发式方法基于人们手工解决线性程序的历史和实验观察。我们将 SimplifEx 作为一个运行示例应用于斯蒂格勒的饮食问题。

引用次数: 0

Supporting risk management through cyberspace: An adaptive network model simulating AI coach effects by inducing adherence to guidelines in neonatal medical protocols 通过网络空间支持风险管理：自适应网络模型模拟人工智能教练效应，引导遵守新生儿医疗规程指南

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-11 DOI: 10.1016/j.cogsys.2024.101290

Raghav Chawla , Fakhra Jabeen , Jan Treur , H. Rob Taal , Peter H.M.P. Roelofsma

In this article, it is shown how second-order adaptive agent-based network models can be used to support a medical team in healthcare institutions to adhere to specific Neonatal Hypoglycemia and Neonatal Hyperbilirubinemia treatment guidelines through the integration of an Artificial Intelligence (AI) Virtual Coach. The proposed AI Coach is designed to provide timely interventions and correct deviations when lapses in the health care practitioner’s internal mental model occur. Through simulating three different scenarios, the internal dynamics of these mental models, adaptive changes of these mental models (learning and forgetting), and the interaction between health care practitioners and the world is shown when: (1) There is perfect adherence to guidelines, (2) There is imperfect adherence to guidelines and (3) There is both perfect and imperfect adherence to guidelines alongside interventions of the AI Coach in the latter case.

本文展示了如何利用基于二阶自适应代理的网络模型，通过整合人工智能（AI）虚拟教练，支持医疗机构的医疗团队遵守特定的新生儿低血糖和新生儿高胆红素血症治疗指南。拟议的人工智能教练旨在提供及时的干预，并在医护人员的内部心理模型出现失误时纠正偏差。通过模拟三种不同的情景，展示了这些心理模型的内部动态、这些心理模型的适应性变化（学习和遗忘）以及在以下情况下医疗从业者与世界之间的互动：(1)完全遵守指南；(2)不完全遵守指南；(3)完全和不完全遵守指南，同时在后一种情况下人工智能教练进行干预。

引用次数: 0

Deconstructing emotions in self-control through computational modeling 通过计算建模解构自我控制中的情绪

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-10 DOI: 10.1016/j.cogsys.2024.101294

Andriani Nikodemou, Chris Christodoulou

Positive and negative emotions have a determining role in self-control, a vital aspect of human decision-making, defined as the dilemma between a smaller sooner reward and a larger later reward. Self-control, as an internal conflict between the higher (pre-frontal cortex) and the lower (limbic system) parts of the brain, has already been simulated using the Iterated Prisoner’s Dilemma game with learning in a computational model. However, the concept of emotions, defined as states elicited by positive and negative reinforcers, is absent from the existing self-control model. By increasing and decreasing the values of the reinforcement signals in the Prisoner’s Dilemma payoff matrix in-between the rounds, we simulated the increment or decrement of positive or negative emotions’ intensity and thus the effects of the presence of emotions, rather than the emotions per se. Our results reflect the restorative role of positive emotions on self-control, the necessity of negative emotions for successful self-control and the impairment of self-control due to intense negative emotions. Furthermore, our results reveal the importance of parameters in self-regulation, such as the intensity of emotions and the frequency it changes. In conclusion, we incorporated the effect of emotions in a computational model of self-control, and with our results complying with cognitive science literature, we demonstrated the cognitive adequacy of our model. We anticipate in this way to provide novel approaches for comprehending self-control behaviour, and to contribute to the general attempt of modeling human behaviour.

积极情绪和消极情绪对自我控制起着决定性作用，而自我控制是人类决策的一个重要方面，被定义为在较小的早期回报和较大的后期回报之间的两难选择。自我控制是大脑高层（前额叶皮层）和低层（边缘系统）之间的内部冲突，已经有人利用迭代囚徒困境（Iterated Prisoner's Dilemma）游戏在计算模型中模拟了这种冲突。然而，现有的自我控制模型中并没有情绪的概念，情绪被定义为由正强化物和负强化物引起的状态。通过在两轮游戏之间增加或减少囚徒困境回报矩阵中的强化信号值，我们模拟了积极或消极情绪强度的增加或减少，从而模拟了情绪存在的影响，而不是情绪本身。我们的结果反映了积极情绪对自我控制的恢复作用、消极情绪对成功自我控制的必要性以及强烈消极情绪对自我控制的损害。此外，我们的结果还揭示了自我调节参数的重要性，如情绪的强度和变化频率。总之，我们将情绪的影响纳入了自我控制的计算模型中，我们的结果与认知科学文献相符，证明了我们的模型在认知上的充分性。我们希望通过这种方式为理解自我控制行为提供新的方法，并为人类行为建模的总体尝试做出贡献。

{"title":"Deconstructing emotions in self-control through computational modeling","authors":"Andriani Nikodemou, Chris Christodoulou","doi":"10.1016/j.cogsys.2024.101294","DOIUrl":"10.1016/j.cogsys.2024.101294","url":null,"abstract":"<div><div>Positive and negative emotions have a determining role in self-control, a vital aspect of human decision-making, defined as the dilemma between a smaller sooner reward and a larger later reward. Self-control, as an internal conflict between the higher (pre-frontal cortex) and the lower (limbic system) parts of the brain, has already been simulated using the Iterated Prisoner’s Dilemma game with learning in a computational model. However, the concept of emotions, defined as states elicited by positive and negative reinforcers, is absent from the existing self-control model. By increasing and decreasing the values of the reinforcement signals in the Prisoner’s Dilemma payoff matrix in-between the rounds, we simulated the increment or decrement of positive or negative emotions’ intensity and thus the effects of the presence of emotions, rather than the emotions per se. Our results reflect the restorative role of positive emotions on self-control, the necessity of negative emotions for successful self-control and the impairment of self-control due to intense negative emotions. Furthermore, our results reveal the importance of parameters in self-regulation, such as the intensity of emotions and the frequency it changes. In conclusion, we incorporated the effect of emotions in a computational model of self-control, and with our results complying with cognitive science literature, we demonstrated the cognitive adequacy of our model. We anticipate in this way to provide novel approaches for comprehending self-control behaviour, and to contribute to the general attempt of modeling human behaviour.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101294"},"PeriodicalIF":2.1,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142526110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Neuromodulatory developmental learning of the mobile robots corresponding to the unexpected obstacles 移动机器人应对意外障碍的神经调节发展学习

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-10 DOI: 10.1016/j.cogsys.2024.101296

Hongyan Zhao , Dongshu Wang , Lei Liu

With the gradual expansion of robot applications, the operating environment is becoming more and more complex, and various uncertainty may be encountered. Investigating how to efficiently respond to various uncertainty in the environment has become an important challenge in the field of robotics research. For the autonomous obstacle avoidance of mobile robots in case of sudden appeared obstacles, a dynamic obstacle avoidance algorithm with a motivated developmental network that simulates the visual attention mechanism is proposed. Simulating the response mechanism of biological vision, a depth camera is used to achieve the detection and recognition of obstacles. To enhance the behavioral regulation of mobile robots, the response mechanism of the human brain attention network is simulated, and an attention model containing the ventral attention network and dorsal attention network is proposed, then a motivated developmental network is designed to simulate this attention mechanism. Furthermore, the working mechanism of the neuromodulation system is simulated to better regulate the robot’s motion and improve its ability to quickly respond to dynamic obstacles suddenly appeared in the environment. A new collision risk is designed by considering the influence of the obstacle’s speed, direction, and distance to the mobile robot. Finally, the feasibility of the proposed method is verified by the experimental results in different physical environments.

随着机器人应用领域的逐步扩大，其工作环境也变得越来越复杂，可能会遇到各种不确定性。研究如何有效地应对环境中的各种不确定性已成为机器人研究领域的一个重要挑战。针对移动机器人在突然出现障碍物时的自主避障问题，提出了一种模拟视觉注意机制的动机发展网络动态避障算法。模拟生物视觉的反应机制，利用深度摄像头实现障碍物的检测和识别。为了加强对移动机器人的行为调控，模拟了人脑注意力网络的反应机制，提出了一个包含腹侧注意力网络和背侧注意力网络的注意力模型，并设计了一个动机发展网络来模拟这种注意力机制。此外，还模拟了神经调节系统的工作机制，以更好地调节机器人的运动，提高其对环境中突然出现的动态障碍物的快速反应能力。考虑到障碍物的速度、方向和与移动机器人距离的影响，设计了一种新的碰撞风险。最后，通过在不同物理环境下的实验结果验证了所提方法的可行性。

{"title":"Neuromodulatory developmental learning of the mobile robots corresponding to the unexpected obstacles","authors":"Hongyan Zhao , Dongshu Wang , Lei Liu","doi":"10.1016/j.cogsys.2024.101296","DOIUrl":"10.1016/j.cogsys.2024.101296","url":null,"abstract":"<div><div>With the gradual expansion of robot applications, the operating environment is becoming more and more complex, and various uncertainty may be encountered. Investigating how to efficiently respond to various uncertainty in the environment has become an important challenge in the field of robotics research. For the autonomous obstacle avoidance of mobile robots in case of sudden appeared obstacles, a dynamic obstacle avoidance algorithm with a motivated developmental network that simulates the visual attention mechanism is proposed. Simulating the response mechanism of biological vision, a depth camera is used to achieve the detection and recognition of obstacles. To enhance the behavioral regulation of mobile robots, the response mechanism of the human brain attention network is simulated, and an attention model containing the ventral attention network and dorsal attention network is proposed, then a motivated developmental network is designed to simulate this attention mechanism. Furthermore, the working mechanism of the neuromodulation system is simulated to better regulate the robot’s motion and improve its ability to quickly respond to dynamic obstacles suddenly appeared in the environment. A new collision risk is designed by considering the influence of the obstacle’s speed, direction, and distance to the mobile robot. Finally, the feasibility of the proposed method is verified by the experimental results in different physical environments.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101296"},"PeriodicalIF":2.1,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142441841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Context-dependent communication under environmental constraints 环境制约下的语境依赖型通信

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-10 DOI: 10.1016/j.cogsys.2024.101293

Krzysztof Główka, Julian Zubek, Joanna Rączaszek-Leonardi

There is significant evidence that real-world communication cannot be reduced to sending signals with context-independent meaning. In this work, based on a variant of the classical Lewis (1969) signalling model, we explore the conditions for the emergence of context-dependent communication in an agent-based situated model. In particular, we demonstrate that pressure to minimise the vocabulary size is sufficient for such emergence. At the same time, we study the environmental conditions and cognitive capabilities that enable contextual disambiguation of symbol meanings. We show that (a) regularities in the context are not necessary for context-dependent communication and that (b) environmental constraints on the receiver’s referent choice can be unilaterally exploited by the sender, without disambiguation capabilities on the receiver’s end. Consistent with common assumptions, the sender’s awareness of the context appears to be required for contextual communication. Our results further demonstrate the crucial role of the environment in the seemingly multilayered phenomenon of context-dependent communication — where language is influenced not only by the distribution of objects in the context, as indicated by previous studies, but also by the very presence of environmental constraints on referent choice. The computational model developed in this work is a demonstration of how signals may be ambiguous out of context, but still allow for near-perfect communication accuracy.

有大量证据表明，现实世界中的交流不能简化为发送与语境无关的信号。在这项研究中，我们基于经典的刘易斯（1969 年）信号模型的变体，探讨了在基于代理的情景模式中出现与语境相关的交流的条件。特别是，我们证明了将词汇量最小化的压力足以导致这种情况的出现。同时，我们还研究了环境条件和认知能力，以实现符号含义的上下文消歧。我们证明：(a) 上下文中的规律性并不是依赖上下文进行交流的必要条件；(b) 接收者在选择指代时受到的环境限制可以被发送者单方面利用，而接收者并不具备歧义辨析能力。与通常的假设一致，发送者对语境的认知似乎是语境交流的必要条件。我们的研究结果进一步证明了环境在语境依赖性交际这一看似多层次的现象中所起的关键作用--在语境依赖性交际中，语言不仅会受到语境中对象分布的影响（如之前的研究所示），而且还会受到环境对指代选择的制约。这项工作中开发的计算模型展示了信号在语境之外可能是模糊的，但仍能实现近乎完美的交流准确性。

{"title":"Context-dependent communication under environmental constraints","authors":"Krzysztof Główka, Julian Zubek, Joanna Rączaszek-Leonardi","doi":"10.1016/j.cogsys.2024.101293","DOIUrl":"10.1016/j.cogsys.2024.101293","url":null,"abstract":"<div><div>There is significant evidence that real-world communication cannot be reduced to sending signals with context-independent meaning. In this work, based on a variant of the classical Lewis (1969) signalling model, we explore the conditions for the emergence of context-dependent communication in an agent-based situated model. In particular, we demonstrate that pressure to minimise the vocabulary size is sufficient for such emergence. At the same time, we study the environmental conditions and cognitive capabilities that enable contextual disambiguation of symbol meanings. We show that (a) regularities in the context are not necessary for context-dependent communication and that (b) environmental constraints on the receiver’s referent choice can be unilaterally exploited by the sender, without disambiguation capabilities on the receiver’s end. Consistent with common assumptions, the sender’s awareness of the context appears to be required for contextual communication. Our results further demonstrate the crucial role of the environment in the seemingly multilayered phenomenon of context-dependent communication — where language is influenced not only by the distribution of objects in the context, as indicated by previous studies, but also by the very presence of environmental constraints on referent choice. The computational model developed in this work is a demonstration of how signals may be ambiguous out of context, but still allow for near-perfect communication accuracy.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101293"},"PeriodicalIF":2.1,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing cognitive abilities through the POE teaching strategy in a virtual learning environment 通过虚拟学习环境中的 POE 教学策略提高认知能力

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-09 DOI: 10.1016/j.cogsys.2024.101295

Ancheng Jiang , Gaofeng Li

With the introduction of information technology into education, the educational environment has undergone qualitative changes, that is, from a real learning environment to a digital learning environment. In a virtual learning environment (VLE), learners not only perceive themselves in new ways but also construct themselves in new ways. However, the POE (Prediction-Observation-Explanation) teaching strategy includes prediction, observation, and explanation. At the entry point of the learning strategy, the effective interaction between teachers and students can promote the development of cognitive ability. Therefore, this paper analyzed the perceptual entropy and matching degree through the radar target tracking algorithm, aiming at analyzing the current situation of the classroom and the advantages of POE teaching strategies. The findings of the study indicate that the POE teaching strategy greatly enhances students’ cognitive ability by teaching through prediction, observation, and interpretation. The research offers a novel contribution to the field of POE teaching strategy under a virtual cultural learning environment by expanding the comprehensive benefits of its students’ cognitive ability cultivation, exploring its impact on students’ academic performance, and offering practical recommendations for its implementation in the learning environment. The research demonstrates that POE strategies have positive effects on students’ academic performance and attitudes toward physics. Under the radar target tracking algorithm, the model matching degree and simplified entropy of the POE teaching strategy were both increasing. The mean of the model fit was 0.61, which was 0.40 higher than that of the first day, and the mean of the simplified entropy was 0.38, which was 0.12 higher than that of the first day. Finally, the cognitive ability and cognitive regulation ability of students under the POE teaching strategy were higher than those of the traditional teaching strategy. Compared with the traditional teaching strategy, cognitive ability was 9% higher, and cognitive regulation ability was 6% higher.

随着信息技术引入教育领域，教育环境发生了质的变化，即从真实学习环境转变为数字学习环境。在虚拟学习环境（VLE）中，学习者不仅以新的方式感知自我，而且以新的方式建构自我。然而，POE（预测-观察-解释）教学策略包括预测、观察和解释。在学习策略的切入点上，师生之间的有效互动能促进学生认知能力的发展。因此，本文通过雷达目标跟踪算法分析了感知熵和匹配度，旨在分析课堂现状和 POE 教学策略的优势。研究结果表明，POE教学策略通过预测、观察和解释进行教学，大大提高了学生的认知能力。该研究拓展了虚拟文化学习环境下 POE 教学策略对学生认知能力培养的综合效益，探讨了其对学生学业成绩的影响，并为其在学习环境中的实施提供了切实可行的建议，为虚拟文化学习环境下的 POE 教学策略领域做出了新的贡献。研究表明，POE 策略对学生的学习成绩和物理学习态度有积极影响。在雷达目标跟踪算法下，POE 教学策略的模型匹配度和简化熵均呈上升趋势。模型拟合度的平均值为 0.61，比第一天提高了 0.40；简化熵的平均值为 0.38，比第一天提高了 0.12。最后，POE 教学策略下学生的认知能力和认知调节能力均高于传统教学策略。与传统教学策略相比，认知能力提高了 9%，认知调节能力提高了 6%。

{"title":"Enhancing cognitive abilities through the POE teaching strategy in a virtual learning environment","authors":"Ancheng Jiang , Gaofeng Li","doi":"10.1016/j.cogsys.2024.101295","DOIUrl":"10.1016/j.cogsys.2024.101295","url":null,"abstract":"<div><div>With the introduction of information technology into education, the educational environment has undergone qualitative changes, that is, from a real learning environment to a digital learning environment. In a virtual learning environment (VLE), learners not only perceive themselves in new ways but also construct themselves in new ways. However, the POE (Prediction-Observation-Explanation) teaching strategy includes prediction, observation, and explanation. At the entry point of the learning strategy, the effective interaction between teachers and students can promote the development of cognitive ability. Therefore, this paper analyzed the perceptual entropy and matching degree through the radar target tracking algorithm, aiming at analyzing the current situation of the classroom and the advantages of POE teaching strategies. The findings of the study indicate that the POE teaching strategy greatly enhances students’ cognitive ability by teaching through prediction, observation, and interpretation. The research offers a novel contribution to the field of POE teaching strategy under a virtual cultural learning environment by expanding the comprehensive benefits of its students’ cognitive ability cultivation, exploring its impact on students’ academic performance, and offering practical recommendations for its implementation in the learning environment. The research demonstrates that POE strategies have positive effects on students’ academic performance and attitudes toward physics. Under the radar target tracking algorithm, the model matching degree and simplified entropy of the POE teaching strategy were both increasing. The mean of the model fit was 0.61, which was 0.40 higher than that of the first day, and the mean of the simplified entropy was 0.38, which was 0.12 higher than that of the first day. Finally, the cognitive ability and cognitive regulation ability of students under the POE teaching strategy were higher than those of the traditional teaching strategy. Compared with the traditional teaching strategy, cognitive ability was 9% higher, and cognitive regulation ability was 6% higher.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101295"},"PeriodicalIF":2.1,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142526107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interpretable logical-probabilistic approximation of neural networks 神经网络的可解释逻辑概率逼近

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-09 DOI: 10.1016/j.cogsys.2024.101301

Evgenii Vityaev , Alexey Korolev

The paper proposes the approximation of DNNs by replacing each neuron by the corresponding logical-probabilistic neuron. Logical-probabilistic neurons learn their behavior based on the responses of initial neurons on incoming signals and discover all logical-probabilistic causal relationships between the input and output. These logical-probabilistic causal relationships are, in a certain sense, most precise – it was proved in the previous works that they are theoretically (when probability is known) can predict without contradictions. The resulting logical-probabilistic neurons are interconnected by the same connections as the initial neurons after replacing their signals on true/false. The resulting logical-probabilistic neural network produces its own predictions that approximate the predictions of the original DNN. Thus, we obtain an interpretable approximation of DNN, which also allows tracing of DNN by tracing its excitations through the causal relationships. This approximation of DNN is a Distillation method such as Model Translation, which train alternative smaller interpretable models that mimics the total input/output behavior of DNN. It is also locally interpretable and explains every particular prediction. It explains the sequences of logical probabilistic causal relationships that infer that prediction and also show all features that took part in this prediction with the statistical estimation of their significance. Experimental results on approximation accuracy of all intermedia neurons, output neurons and softmax output of DNN are presented, as well as the accuracy of obtained logical-probabilistic neural network. From the practical point of view, interpretable transformation of neural networks is very important for the hybrid artificial intelligent systems, where neural networks are integrated with the symbolic methods of AI. As a practical application we consider smart city.

本文提出用相应的逻辑-概率神经元替换每个神经元，从而近似 DNN。逻辑-概率神经元根据初始神经元对输入信号的反应来学习自己的行为，并发现输入和输出之间的所有逻辑-概率因果关系。从某种意义上说，这些逻辑-概率因果关系是最精确的--前人的研究已经证明，它们在理论上（当概率已知时）可以无矛盾地预测。逻辑概率神经元在替换了真/假信号后，与初始神经元通过相同的连接相互连接。由此产生的逻辑-概率神经网络所产生的预测结果近似于原始 DNN 的预测结果。这样，我们就得到了 DNN 的可解释近似值，还可以通过因果关系追踪 DNN 的激励。DNN 的这种近似方法是一种蒸馏法，如模型转换法，它可以训练替代的较小的可解释模型，从而模仿 DNN 的总输入/输出行为。它也是局部可解释的，并能解释每个特定的预测。它解释了推断该预测的逻辑概率因果关系序列，还显示了参与该预测的所有特征及其重要性的统计估计。实验结果显示了 DNN 所有中间神经元、输出神经元和软最大输出的近似精度，以及逻辑概率神经网络的精度。从实用的角度来看，神经网络的可解释变换对于混合人工智能系统非常重要，在混合人工智能系统中，神经网络与人工智能的符号方法相结合。作为实际应用，我们考虑了智能城市。

{"title":"Interpretable logical-probabilistic approximation of neural networks","authors":"Evgenii Vityaev , Alexey Korolev","doi":"10.1016/j.cogsys.2024.101301","DOIUrl":"10.1016/j.cogsys.2024.101301","url":null,"abstract":"<div><div>The paper proposes the approximation of DNNs by replacing each neuron by the corresponding logical-probabilistic neuron. Logical-probabilistic neurons learn their behavior based on the responses of initial neurons on incoming signals and discover all logical-probabilistic causal relationships between the input and output. These logical-probabilistic causal relationships are, in a certain sense, most precise – it was proved in the previous works that they are theoretically (when probability is known) can predict without contradictions. The resulting logical-probabilistic neurons are interconnected by the same connections as the initial neurons after replacing their signals on true/false. The resulting logical-probabilistic neural network produces its own predictions that approximate the predictions of the original DNN. Thus, we obtain an interpretable approximation of DNN, which also allows tracing of DNN by tracing its excitations through the causal relationships. This approximation of DNN is a Distillation method such as Model Translation, which train alternative smaller interpretable models that mimics the total input/output behavior of DNN. It is also locally interpretable and explains every particular prediction. It explains the sequences of logical probabilistic causal relationships that infer that prediction and also show all features that took part in this prediction with the statistical estimation of their significance. Experimental results on approximation accuracy of all intermedia neurons, output neurons and softmax output of DNN are presented, as well as the accuracy of obtained logical-probabilistic neural network. From the practical point of view, interpretable transformation of neural networks is very important for the hybrid artificial intelligent systems, where neural networks are integrated with the symbolic methods of AI. As a practical application we consider smart city.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101301"},"PeriodicalIF":2.1,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142427175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bilateral Turing Test: Assessing machine consciousness simulations 双边图灵测试：评估机器意识模拟

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-05 DOI: 10.1016/j.cogsys.2024.101299

Ge Wang, Xianhong Li, Shenghua Xie

Recent advancements in Artificial Intelligence (AI) have brought discussions on machine consciousness back to the forefront. However, methodologies for assessing machine consciousness simulations remain highly constrained and lack consensus. This study introduces the Bilateral Turing Test, a thought experiment to assess machine consciousness simulations based on a functionalist perspective, focusing on external behavior and cognitive characteristics associated with consciousness. The test involves both machines and humans participating as judges in an enhanced Turing Test, and compares the external behavior of machine-simulated consciousness with the behavior of human consciousness. We derive the experimental principles via three theoretical propositions reflecting the human–machine cognitive relationship and elucidate the basic conditions and procedures of the thought experiment. A systematic measure is employed to evaluate emulation against human benchmarks, and we establish a statistical threshold for successful consciousness simulations. Our study provides a comprehensive framework for redefining machine consciousness simulations and enhancing interdisciplinary conversations across computer science, neuroscience, and philosophy. This framework also advances bottom-up approaches for assessing machine consciousness simulations and provides pivotal insights into human–machine interaction dynamics.

人工智能（AI）的最新进展使有关机器意识的讨论再次成为焦点。然而，评估机器意识模拟的方法仍然受到很大限制，而且缺乏共识。本研究介绍了 "双边图灵测试"，这是一项基于功能主义视角的思想实验，用于评估机器意识模拟，重点关注与意识相关的外部行为和认知特征。该测试由机器和人类共同参与，作为增强型图灵测试的评委，比较机器模拟意识的外部行为和人类意识的行为。我们通过反映人机认知关系的三个理论命题推导出实验原理，并阐明了思想实验的基本条件和程序。我们采用了一种系统的测量方法来评估仿真与人类基准的对比，并为成功的意识仿真建立了一个统计阈值。我们的研究为重新定义机器意识模拟和加强计算机科学、神经科学和哲学之间的跨学科对话提供了一个全面的框架。这一框架还推进了自下而上的机器意识模拟评估方法，并为人机交互动力学提供了重要见解。

{"title":"Bilateral Turing Test: Assessing machine consciousness simulations","authors":"Ge Wang, Xianhong Li, Shenghua Xie","doi":"10.1016/j.cogsys.2024.101299","DOIUrl":"10.1016/j.cogsys.2024.101299","url":null,"abstract":"<div><div>Recent advancements in Artificial Intelligence (AI) have brought discussions on machine consciousness back to the forefront. However, methodologies for assessing machine consciousness simulations remain highly constrained and lack consensus. This study introduces the Bilateral Turing Test, a thought experiment to assess machine consciousness simulations based on a functionalist perspective, focusing on external behavior and cognitive characteristics associated with consciousness. The test involves both machines and humans participating as judges in an enhanced Turing Test, and compares the external behavior of machine-simulated consciousness with the behavior of human consciousness. We derive the experimental principles via three theoretical propositions reflecting the human–machine cognitive relationship and elucidate the basic conditions and procedures of the thought experiment. A systematic measure is employed to evaluate emulation against human benchmarks, and we establish a statistical threshold for successful consciousness simulations. Our study provides a comprehensive framework for redefining machine consciousness simulations and enhancing interdisciplinary conversations across computer science, neuroscience, and philosophy. This framework also advances bottom-up approaches for assessing machine consciousness simulations and provides pivotal insights into human–machine interaction dynamics.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101299"},"PeriodicalIF":2.1,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142427174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An adaptive dynamical system model for development of schizophrenia: Epigenetics and false memories 精神分裂症发展的自适应动力系统模型：表观遗传学与虚假记忆

IF 2.1 3区心理学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Cognitive Systems Research

Pub Date : 2024-10-02 DOI: 10.1016/j.cogsys.2024.101288

Ilma Jaganjac , Sophie C.F. Hendrikse , Jan Treur

This paper introduces a fifth-order adaptive dynamical system model represented as a self-modelling network model to understand the role of epigenetic factors in developing schizophrenia, particularly about the occurrence of false memories. Schizophrenia, affecting a significant portion of the global population, presents complex challenges due to its symptoms across cognitive, emotional, and social domains. Central to this paper is the exploration of epigenetic influences on the development of schizophrenia, with a focus on how these epigenetic factors contribute to the generation of false memories, a notable symptom of the disorder. The model assumes that early adverse experiences significantly affect hippocampal development, which is crucial for memory processes. By employing a fifth-order adaptive dynamical system model represented as a self-modelling network, this paper examines the intricate dynamics between genetic predispositions, environmental factors, and epigenetic modifications in schizophrenia. The model’s sophistication allows for a nuanced understanding of the gene-environment interactions, particularly highlighting the role of early-life trauma in shaping lifelong cognitive outcomes. This approach offers a comprehensive framework for analyzing the multifaceted nature of schizophrenia, contributing to a deeper understanding of its etiology and progression.

本文介绍了以自建模网络模型为代表的五阶自适应性动力系统模型，以了解表观遗传因素在精神分裂症发展过程中的作用，尤其是关于错误记忆的发生。精神分裂症影响着全球相当一部分人口，其症状横跨认知、情感和社会领域，带来了复杂的挑战。本文的核心内容是探讨表观遗传对精神分裂症发展的影响，重点是这些表观遗传因素如何导致产生虚假记忆这一精神分裂症的显著症状。该模型假定早期的不良经历会严重影响海马体的发育，而海马体对记忆过程至关重要。通过采用以自建模网络为代表的五阶自适应性动力系统模型，本文研究了精神分裂症的遗传倾向、环境因素和表观遗传修饰之间错综复杂的动态关系。该模型的复杂性使得人们能够细致入微地理解基因与环境之间的相互作用，尤其突出了早期生活创伤在塑造终生认知结果中的作用。这种方法为分析精神分裂症的多面性提供了一个全面的框架，有助于加深对其病因和进展的理解。

{"title":"An adaptive dynamical system model for development of schizophrenia: Epigenetics and false memories","authors":"Ilma Jaganjac , Sophie C.F. Hendrikse , Jan Treur","doi":"10.1016/j.cogsys.2024.101288","DOIUrl":"10.1016/j.cogsys.2024.101288","url":null,"abstract":"<div><div>This paper introduces a fifth-order adaptive dynamical system model represented as a self-modelling network model to understand the role of epigenetic factors in developing schizophrenia, particularly about the occurrence of false memories. Schizophrenia, affecting a significant portion of the global population, presents complex challenges due to its symptoms across cognitive, emotional, and social domains. Central to this paper is the exploration of epigenetic influences on the development of schizophrenia, with a focus on how these epigenetic factors contribute to the generation of false memories, a notable symptom of the disorder. The model assumes that early adverse experiences significantly affect hippocampal development, which is crucial for memory processes. By employing a fifth-order adaptive dynamical system model represented as a self-modelling network, this paper examines the intricate dynamics between genetic predispositions, environmental factors, and epigenetic modifications in schizophrenia. The model’s sophistication allows for a nuanced understanding of the gene-environment interactions, particularly highlighting the role of early-life trauma in shaping lifelong cognitive outcomes. This approach offers a comprehensive framework for analyzing the multifaceted nature of schizophrenia, contributing to a deeper understanding of its etiology and progression.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101288"},"PeriodicalIF":2.1,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142441840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0