Artificial intelligence technology has revolutionized every industry and trade in recent years. However, its own development is encountering bottlenecks that it is unable to implement empathy with human emotions. So a...Artificial intelligence technology has revolutionized every industry and trade in recent years. However, its own development is encountering bottlenecks that it is unable to implement empathy with human emotions. So affective computing is getting more attention from researchers. In this paper, we propose an amygdala-inspired affective computing framework to realize the recognition of all kinds of human personalized emotions. Similar to the amygdala, the instantaneous emergency emotion is first computed more quickly in a low-redundancy convolutional neural network compressed by pruning and weight sharing with hashing trick. Then, the real-time process emotion is identified more accurately by the memory level neural networks, which is good at handling time-related signals. Finally, the intracranial emotion is recognized in personalized hidden Markov models. We demonstrate on Facial Expression of Emotion Dataset and the recognition accuracy of external emotions(including the emergency emotion and the process emotion) reached 85.72%. And the experimental results proved that the personalized affective model can generate desired intracranial emotions as expected.展开更多
This research is framed within the affective computing, which explains the importance of emotions in human cognition (decision making, perception, interaction and human intelligence). Applying this approach to a pedag...This research is framed within the affective computing, which explains the importance of emotions in human cognition (decision making, perception, interaction and human intelligence). Applying this approach to a pedagogical agent is an essential part to enhance the effectiveness of the teaching-learning process of an intelligent learning system. This work focuses on the design of the inference engine that will give life to the interface, where the latter is represented by a pedagogical agent. The inference engine is based on an affective-motivational model. This model is implemented by using artificial intelligence technique called fuzzy cognitive maps.展开更多
Traditional industrial process control activities relevant to multi-objective optimization problems,such as proportional integral derivative(PID)parameter tuning and operational optimizations,always demand for process...Traditional industrial process control activities relevant to multi-objective optimization problems,such as proportional integral derivative(PID)parameter tuning and operational optimizations,always demand for process knowledge and human operators’experiences during human-computer interactions.However,the impact of human operators’preferences on human-computer interactions has been rarely highlighted ever since.In response to this problem,a novel multilayer cognitive affective computing model based on human personalities and pleasure-arousal-dominance(PAD)emotional space states is established in this paper.Therein,affective preferences are employed to update the affective computing model during human-machine interactions.Accordingly,we propose affective parameters mining strategies based on genetic algorithms(GAs),which are responsible for gradually grasping human operators’operational preferences in the process control activities.Two routine process control tasks,including PID controller tuning for coupling loops and operational optimization for batch beer fermenter processes,are carried out to illustrate the effectiveness of the contributions,leading to the satisfactory results.展开更多
A personalized emotion space is proposed to bridge the"affective gap"in video affective content understanding.In order to unify the discrete and dimensional emotion model,fuzzy C-mean(FCM)clustering algorith...A personalized emotion space is proposed to bridge the"affective gap"in video affective content understanding.In order to unify the discrete and dimensional emotion model,fuzzy C-mean(FCM)clustering algorithm is adopted to divide the emotion space.Gaussian mixture model(GMM)is used to determine the membership functions of typical affective subspaces.At every step of modeling the space,the inputs rely completely on the affective experiences recorded by the audiences.The advantages of the improved V-A(Velance-Arousal)emotion model are the per-sonalization,the ability to define typical affective state areas in the V-A emotion space,and the convenience to explicitly express the intensity of each affective state.The experimental results validate the model and show it can be used as a personalized emotion space for video affective content representation.展开更多
As the frontier of intelligent computing technology,affective computing has been used in border inspection,case investigation,crime assessment,public opinion management,traffic management and other scenarios of public...As the frontier of intelligent computing technology,affective computing has been used in border inspection,case investigation,crime assessment,public opinion management,traffic management and other scenarios of public governance.However,there are still public risks associated with its failure to meet the basic requirements of modern public governance,and these risks are rooted in its technical characteristics.The technical characteristics of turning emotions into signals can give rise to such problems as degrading the right to informed consent,de-governance,and undermining human dignity when applied in public governance,and consequently can lead to social rights anxiety.Additionally,the affective modeling characteristics of affective computing tend to incur the rights risks of insufficient algorithm accuracy,algorithmic discrimination,and algorithmic black boxes.To avoid these risks,it is necessary to adopt the dynamic consent model as the premise for applying affective computing in public governance,and to regulate the auxiliary application of affective computing in public governance in a hierarchical manner,to achieve a balance between the application of affective computing technology and the protection of citizens'rights and the maintenance of public ethics.展开更多
Emotion recognition from electroencephalogram(EEG)signals has garnered significant attention owing to its potential applications in affective computing,human-computer interaction,and mental health monitoring.This pape...Emotion recognition from electroencephalogram(EEG)signals has garnered significant attention owing to its potential applications in affective computing,human-computer interaction,and mental health monitoring.This paper presents a comparative analysis of different machine learning methods for emotion recognition using EEG data.The objective of this study was to identify the most effective algorithm for accurately classifying emotional states using EEG signals.The EEG brainwave dataset:Feeling emotions dataset was used to evaluate the performance of various machine-learning techniques.Multiple machine learning techniques,namely logistic regression(LR),support vector machine(SVM),Gaussian Naive Bayes(GNB),and decision tree(DT),and ensemble models,namely random forest(RF),AdaBoost,LightGBM,XGBoost,and CatBoost,were trained and evaluated.Five-fold cross-validation and dimension reduction techniques,such as principal component analysis,tdistributed stochastic neighbor embedding,and linear discriminant analysis,were performed for all models.The least-performing model,GNB,showed substantially increased performance after dimension reduction.Performance metrics such as accuracy,precision,recall,F1-score,and receiver operating characteristic curves are employed to assess the effectiveness of each approach.This study focuses on the implications of using various machine learning algorithms for EEG-based emotion recognition.This pursuit can improve our understanding of emotions and their underlying neural mechanisms.展开更多
[目的/意义]在具身智能从工业自动化转向民生服务的战略背景下,社交机器人面临交互粘性不足与情境理解匮乏的现实困境,情感计算作为赋予机器感知、理解与模拟人类情感的核心技术,是支撑具身智能实现社会化的关键。研究旨在解析多模态感...[目的/意义]在具身智能从工业自动化转向民生服务的战略背景下,社交机器人面临交互粘性不足与情境理解匮乏的现实困境,情感计算作为赋予机器感知、理解与模拟人类情感的核心技术,是支撑具身智能实现社会化的关键。研究旨在解析多模态感知、动态适应策略与伦理边界的技术路径,为构建负责人智交互体系提供理论参考。[方法/过程]遵循PRISMA导向,检索Web of Science近10年具身智能与情感计算交叉领域文献。基于具身性、技术完整性及交互实证性标准筛选,因内容完整性剔除无法获取全文条目,最终选取97篇核心文献。从视觉鲁棒感知、副语言解码、生理信号洞察及多源异构数据融合等维度解析感知层级,并探讨大语言模型驱动下的生成式适应策略。[结果/结论]社交机器人情感计算正经历从单一信号统计向多模态语义融合、从静态规则映射向生成式动态适应的范式演进。研究证实,多模态感知的实质是对人类意图的深度解构而非简单的数据统计,基于此,本研究构建了以情境理解为起点、适应行动为核心、伦理约束为底线的动态交互框架。该框架强调,情感适应应从机械模仿转向认知共情,通过大语言模型驱动的生成式策略实现交互的个性化与连贯性,同时伦理边界并非外部附加的规制,而应是内生于算法决策的逻辑约束,旨在应对隐私不对称与心理操纵等内生风险。未来的创新范式应立足于真实环境的生态效度,通过融合长期记忆的终身学习机制对抗新奇效应的消退,并建立人在回路的安全熔断机制,从而确保具身智能在介入人类精神世界过程中的主权安全与科技向善。展开更多
The evolution of Driver Assistance Systems(DAS)is shifting focus from mere safety to integrating emotional and psychological well-being,1 transforming intelligent connected vehicles(ICVs)from passive tools into cognit...The evolution of Driver Assistance Systems(DAS)is shifting focus from mere safety to integrating emotional and psychological well-being,1 transforming intelligent connected vehicles(ICVs)from passive tools into cognitive partners that require complex,bidirectional interaction.1 Affective computing(AC),which enables machines to recognize and interpret human emotions,provides a crucial foundation for this shift.2 Large Language Models(LLMs)can significantly advance AC by processing multimodal data,enabling a transition from functional execution to empathetic human-machine interaction.1,3 Despite early applications like mandated fatigue monitoring,current systems are limited by passive responsiveness and opacity.4 While LLM-enhanced AC promises to address these issues,this integration creates a Collingridge's Dilemma(Figure 1).This commentary examines this paradox,focusing on the technical potential,limitations of LLM-empowered AC and the associated governance complexities,aiming to foster discussion on responsible innovation in next-generation intelligent driving.展开更多
基金supported by National Key R&D Program of China, No. 2018YFB1003905Natural Science Foundation of China, No.61873026the Fundamental Research Funds for the Central Universities, No.FRFTP-18-008A3
文摘Artificial intelligence technology has revolutionized every industry and trade in recent years. However, its own development is encountering bottlenecks that it is unable to implement empathy with human emotions. So affective computing is getting more attention from researchers. In this paper, we propose an amygdala-inspired affective computing framework to realize the recognition of all kinds of human personalized emotions. Similar to the amygdala, the instantaneous emergency emotion is first computed more quickly in a low-redundancy convolutional neural network compressed by pruning and weight sharing with hashing trick. Then, the real-time process emotion is identified more accurately by the memory level neural networks, which is good at handling time-related signals. Finally, the intracranial emotion is recognized in personalized hidden Markov models. We demonstrate on Facial Expression of Emotion Dataset and the recognition accuracy of external emotions(including the emergency emotion and the process emotion) reached 85.72%. And the experimental results proved that the personalized affective model can generate desired intracranial emotions as expected.
文摘This research is framed within the affective computing, which explains the importance of emotions in human cognition (decision making, perception, interaction and human intelligence). Applying this approach to a pedagogical agent is an essential part to enhance the effectiveness of the teaching-learning process of an intelligent learning system. This work focuses on the design of the inference engine that will give life to the interface, where the latter is represented by a pedagogical agent. The inference engine is based on an affective-motivational model. This model is implemented by using artificial intelligence technique called fuzzy cognitive maps.
基金the National Natural Science Foundation of China(No.61603023)。
文摘Traditional industrial process control activities relevant to multi-objective optimization problems,such as proportional integral derivative(PID)parameter tuning and operational optimizations,always demand for process knowledge and human operators’experiences during human-computer interactions.However,the impact of human operators’preferences on human-computer interactions has been rarely highlighted ever since.In response to this problem,a novel multilayer cognitive affective computing model based on human personalities and pleasure-arousal-dominance(PAD)emotional space states is established in this paper.Therein,affective preferences are employed to update the affective computing model during human-machine interactions.Accordingly,we propose affective parameters mining strategies based on genetic algorithms(GAs),which are responsible for gradually grasping human operators’operational preferences in the process control activities.Two routine process control tasks,including PID controller tuning for coupling loops and operational optimization for batch beer fermenter processes,are carried out to illustrate the effectiveness of the contributions,leading to the satisfactory results.
基金Supported by the National Natural Science Foundation of China(60703049)the"Chenguang"Foundation for Young Scientists(200850731353)the National Postdoctoral Foundation of China(20060400847)
文摘A personalized emotion space is proposed to bridge the"affective gap"in video affective content understanding.In order to unify the discrete and dimensional emotion model,fuzzy C-mean(FCM)clustering algorithm is adopted to divide the emotion space.Gaussian mixture model(GMM)is used to determine the membership functions of typical affective subspaces.At every step of modeling the space,the inputs rely completely on the affective experiences recorded by the audiences.The advantages of the improved V-A(Velance-Arousal)emotion model are the per-sonalization,the ability to define typical affective state areas in the V-A emotion space,and the convenience to explicitly express the intensity of each affective state.The experimental results validate the model and show it can be used as a personalized emotion space for video affective content representation.
基金a phased achievement of the 2020 Youth Fund Project of the Ministry of Education in Humanities and Social Sciences of China,titled“Legislative Research on Collaborative Dispute Resolution Mechanisms for Medical Disputes in the Guangdong-Hong Kong-Macao Greater Bay Area”(Project Number 20YJC820023)。
文摘As the frontier of intelligent computing technology,affective computing has been used in border inspection,case investigation,crime assessment,public opinion management,traffic management and other scenarios of public governance.However,there are still public risks associated with its failure to meet the basic requirements of modern public governance,and these risks are rooted in its technical characteristics.The technical characteristics of turning emotions into signals can give rise to such problems as degrading the right to informed consent,de-governance,and undermining human dignity when applied in public governance,and consequently can lead to social rights anxiety.Additionally,the affective modeling characteristics of affective computing tend to incur the rights risks of insufficient algorithm accuracy,algorithmic discrimination,and algorithmic black boxes.To avoid these risks,it is necessary to adopt the dynamic consent model as the premise for applying affective computing in public governance,and to regulate the auxiliary application of affective computing in public governance in a hierarchical manner,to achieve a balance between the application of affective computing technology and the protection of citizens'rights and the maintenance of public ethics.
文摘Emotion recognition from electroencephalogram(EEG)signals has garnered significant attention owing to its potential applications in affective computing,human-computer interaction,and mental health monitoring.This paper presents a comparative analysis of different machine learning methods for emotion recognition using EEG data.The objective of this study was to identify the most effective algorithm for accurately classifying emotional states using EEG signals.The EEG brainwave dataset:Feeling emotions dataset was used to evaluate the performance of various machine-learning techniques.Multiple machine learning techniques,namely logistic regression(LR),support vector machine(SVM),Gaussian Naive Bayes(GNB),and decision tree(DT),and ensemble models,namely random forest(RF),AdaBoost,LightGBM,XGBoost,and CatBoost,were trained and evaluated.Five-fold cross-validation and dimension reduction techniques,such as principal component analysis,tdistributed stochastic neighbor embedding,and linear discriminant analysis,were performed for all models.The least-performing model,GNB,showed substantially increased performance after dimension reduction.Performance metrics such as accuracy,precision,recall,F1-score,and receiver operating characteristic curves are employed to assess the effectiveness of each approach.This study focuses on the implications of using various machine learning algorithms for EEG-based emotion recognition.This pursuit can improve our understanding of emotions and their underlying neural mechanisms.
文摘[目的/意义]在具身智能从工业自动化转向民生服务的战略背景下,社交机器人面临交互粘性不足与情境理解匮乏的现实困境,情感计算作为赋予机器感知、理解与模拟人类情感的核心技术,是支撑具身智能实现社会化的关键。研究旨在解析多模态感知、动态适应策略与伦理边界的技术路径,为构建负责人智交互体系提供理论参考。[方法/过程]遵循PRISMA导向,检索Web of Science近10年具身智能与情感计算交叉领域文献。基于具身性、技术完整性及交互实证性标准筛选,因内容完整性剔除无法获取全文条目,最终选取97篇核心文献。从视觉鲁棒感知、副语言解码、生理信号洞察及多源异构数据融合等维度解析感知层级,并探讨大语言模型驱动下的生成式适应策略。[结果/结论]社交机器人情感计算正经历从单一信号统计向多模态语义融合、从静态规则映射向生成式动态适应的范式演进。研究证实,多模态感知的实质是对人类意图的深度解构而非简单的数据统计,基于此,本研究构建了以情境理解为起点、适应行动为核心、伦理约束为底线的动态交互框架。该框架强调,情感适应应从机械模仿转向认知共情,通过大语言模型驱动的生成式策略实现交互的个性化与连贯性,同时伦理边界并非外部附加的规制,而应是内生于算法决策的逻辑约束,旨在应对隐私不对称与心理操纵等内生风险。未来的创新范式应立足于真实环境的生态效度,通过融合长期记忆的终身学习机制对抗新奇效应的消退,并建立人在回路的安全熔断机制,从而确保具身智能在介入人类精神世界过程中的主权安全与科技向善。
基金funded by the National Natural Science Foundation of China(72525009,72431009,72171210,72350710798)Zhejiang Provincial Natural Science Foundation of China(LZ23E080002).
文摘The evolution of Driver Assistance Systems(DAS)is shifting focus from mere safety to integrating emotional and psychological well-being,1 transforming intelligent connected vehicles(ICVs)from passive tools into cognitive partners that require complex,bidirectional interaction.1 Affective computing(AC),which enables machines to recognize and interpret human emotions,provides a crucial foundation for this shift.2 Large Language Models(LLMs)can significantly advance AC by processing multimodal data,enabling a transition from functional execution to empathetic human-machine interaction.1,3 Despite early applications like mandated fatigue monitoring,current systems are limited by passive responsiveness and opacity.4 While LLM-enhanced AC promises to address these issues,this integration creates a Collingridge's Dilemma(Figure 1).This commentary examines this paradox,focusing on the technical potential,limitations of LLM-empowered AC and the associated governance complexities,aiming to foster discussion on responsible innovation in next-generation intelligent driving.
