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
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
Emotion recognition from speech data is an active and emerging area of research that plays an important role in numerous applications,such as robotics,virtual reality,behavior assessments,and emergency call centers.Re...Emotion recognition from speech data is an active and emerging area of research that plays an important role in numerous applications,such as robotics,virtual reality,behavior assessments,and emergency call centers.Recently,researchers have developed many techniques in this field in order to ensure an improvement in the accuracy by utilizing several deep learning approaches,but the recognition rate is still not convincing.Our main aim is to develop a new technique that increases the recognition rate with reasonable cost computations.In this paper,we suggested a new technique,which is a one-dimensional dilated convolutional neural network(1D-DCNN)for speech emotion recognition(SER)that utilizes the hierarchical features learning blocks(HFLBs)with a bi-directional gated recurrent unit(BiGRU).We designed a one-dimensional CNN network to enhance the speech signals,which uses a spectral analysis,and to extract the hidden patterns from the speech signals that are fed into a stacked one-dimensional dilated network that are called HFLBs.Each HFLB contains one dilated convolution layer(DCL),one batch normalization(BN),and one leaky_relu(Relu)layer in order to extract the emotional features using a hieratical correlation strategy.Furthermore,the learned emotional features are feed into a BiGRU in order to adjust the global weights and to recognize the temporal cues.The final state of the deep BiGRU is passed from a softmax classifier in order to produce the probabilities of the emotions.The proposed model was evaluated over three benchmarked datasets that included the IEMOCAP,EMO-DB,and RAVDESS,which achieved 72.75%,91.14%,and 78.01%accuracy,respectively.展开更多
In response to many multi-attribute decision-making(MADM)problems involved in chemical processes such as controller tuning,which suffer human's subjective preferential nature in human–computer interactions,a nove...In response to many multi-attribute decision-making(MADM)problems involved in chemical processes such as controller tuning,which suffer human's subjective preferential nature in human–computer interactions,a novel affective computing and preferential evolutionary solution is proposed to adapt human–computer interaction mechanism.Based on the stimulating response mechanism,an improved affective computing model is introduced to quantify decision maker's preference in selections of interactive evolutionary computing.In addition,the mathematical relationship between affective space and decision maker's preferences is constructed.Subsequently,a human–computer interactive preferential evolutionary algorithm for MADM problems is proposed,which deals with attribute weights and optimal solutions based on preferential evolution metrics.To exemplify applications of the proposed methods,some test functions and,emphatically,controller tuning issues associated with a chemical process are investigated,giving satisfactory results.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.
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.
基金supported by the National Research Foundation of Korea funded by the Korean Government through the Ministry of Science and ICT under Grant NRF-2020R1F1A1060659 and in part by the 2020 Faculty Research Fund of Sejong University。
文摘Emotion recognition from speech data is an active and emerging area of research that plays an important role in numerous applications,such as robotics,virtual reality,behavior assessments,and emergency call centers.Recently,researchers have developed many techniques in this field in order to ensure an improvement in the accuracy by utilizing several deep learning approaches,but the recognition rate is still not convincing.Our main aim is to develop a new technique that increases the recognition rate with reasonable cost computations.In this paper,we suggested a new technique,which is a one-dimensional dilated convolutional neural network(1D-DCNN)for speech emotion recognition(SER)that utilizes the hierarchical features learning blocks(HFLBs)with a bi-directional gated recurrent unit(BiGRU).We designed a one-dimensional CNN network to enhance the speech signals,which uses a spectral analysis,and to extract the hidden patterns from the speech signals that are fed into a stacked one-dimensional dilated network that are called HFLBs.Each HFLB contains one dilated convolution layer(DCL),one batch normalization(BN),and one leaky_relu(Relu)layer in order to extract the emotional features using a hieratical correlation strategy.Furthermore,the learned emotional features are feed into a BiGRU in order to adjust the global weights and to recognize the temporal cues.The final state of the deep BiGRU is passed from a softmax classifier in order to produce the probabilities of the emotions.The proposed model was evaluated over three benchmarked datasets that included the IEMOCAP,EMO-DB,and RAVDESS,which achieved 72.75%,91.14%,and 78.01%accuracy,respectively.
基金Supported by the Fundamental Research Funds for the Central Universities(ZY1347and YS1404)
文摘In response to many multi-attribute decision-making(MADM)problems involved in chemical processes such as controller tuning,which suffer human's subjective preferential nature in human–computer interactions,a novel affective computing and preferential evolutionary solution is proposed to adapt human–computer interaction mechanism.Based on the stimulating response mechanism,an improved affective computing model is introduced to quantify decision maker's preference in selections of interactive evolutionary computing.In addition,the mathematical relationship between affective space and decision maker's preferences is constructed.Subsequently,a human–computer interactive preferential evolutionary algorithm for MADM problems is proposed,which deals with attribute weights and optimal solutions based on preferential evolution metrics.To exemplify applications of the proposed methods,some test functions and,emphatically,controller tuning issues associated with a chemical process are investigated,giving satisfactory results.
