基于模糊逻辑的智能Agent情感建模

情感是人类智能中的一个重要表现形式,在人类决策过程中起着重要的作用。认知科学、生理学以及人工智能领域的研究者已提出各类情感模型,但大部分模型都集中于智能agent的反应行为,为此它们通常是根据一些静态的规则或者事先确定的领域知识来生成agent的情感。本文提出了一个新的情感计算模型,并尝试利用模糊逻辑的表征方法建立事件和情感状态间的联系。     

FLAME—Fuzzy Logic Adaptive Model of Emotions

Emotions are an important aspect of human intelligence and have been shown to play a significant role in the human decision-making process. Researchers in areas such as cognitive science, philosophy, and artificial intelligence have proposed a variety of models of emotions. Most of the previous models focus on an agent's reactive behavior, for which they often generate emotions according to static rules or pre-determined domain knowledge. However, throughout the history of research on emotions, memory and experience have been emphasized to have a major influence on the emotional process. In this paper, we propose a new computational model of emotions that can be incorporated into intelligent agents and other complex, interactive programs. The model uses a fuzzy-logic representation to map events and observations to emotional states. The model also includes several inductive learning algorithms for learning patterns of events, associations among objects, and expectations. We demonstrate empirically through a computer simulation of a pet that the adaptive components of the model are crucial to users' assessments of the believability of the agent's interactions.     

Toward incorporating emotions with rationality into a communicative virtual agent

This paper addresses the problem of human–computer interactions when the computer can interpret and express a kind of human-like behavior, offering natural communication. A conceptual framework for incorporating emotions with rationality is proposed. A model of affective social interactions is described. The model utilizes the SAIBA framework, which distinguishes among several stages of processing of information. The SAIBA framework is extended, and a model is realized in human behavior detection, human behavior interpretation, intention planning, attention tracking behavior planning, and behavior realization components. Two models of incorporating emotions with rationality into a virtual artifact are presented. The first one uses an implicit implementation of emotions. The second one has an explicit realization of a three-layered model of emotions, which is highly interconnected with other components of the system. Details of the model with implicit implementation of emotional behavior are shown as well as evaluation methodology and results. Discussions about the extended model of an agent are given in the final part of the paper.     

Information technology customer aggression: The importance of an organizational climate of support

Information technology personnel are often ill prepared to react in a positive fashion to the aggressive communications from their customers, the users. Being able to regulate the emotions spiked by aggressive customer behavior is important to the long term health and retention of IT employees. Surface acting responses, the ability to display false emotions to mask strong emotions, is common, but not better for the long term health of the individual or organization. Deep acting responses, where emotional responses are modified to encourage expected behavior, are the better response and can be promoted with an organizational climate of support. A model derived from emotion response theory demonstrates these relationships hold for IT employees, who tend to be more introverted than most employees and often react differently to aggressive communication from customers. The model is verified with a sample of IT employees in Taiwan companies. Organizations should provide a climate of support for IT personnel and train them on how to respond appropriately to customer aggression through emotion regulation strategies in a direction that promotes better relationships.     

Psychologically inspired anticipation and dynamic response for impacts to the head and upper body

We present a psychology-inspired approach for generating a character' s anticipation of and response to an impending head or upper body impact. Protective anticipatory movement is built upon several actions that have been identified in the psychology literature as response mechanisms in monkeys and in humans. These actions are parameterized by a model of the approaching object (the threat) and are defined as procedural rules. We present a hybrid forward and inverse kinematic blending technique to guide the character to the pose that results from these rules while maintaining properties of a balanced posture as well as characteristics of the behavior just prior to the interaction. In our case, these characteristics are determined by a motion capture sequence. We combine our anticipation model with a physically-based dynamic response to produce animations where a character anticipates an impact before collision and reacts to the contact, physically, after the collision. We present a variety of examples including threats that vary in approach direction, size and speed.     

Identification of aggressive driving behavior of online car-hailing drivers based on association classification

With the rapid development of online car-hailing, the related crashes have become a key issue with public concern. Identifying and predicting aggressive driving behaviors is critical to reduce traffic crashes. In this study, we propose a method to recognize aggressive driving behavior based on association classification, with multisource features being employed, including driver emotion, vehicle kinematic characteristics, and road environment. The model performs best in a 10-fold cross-test when the minimum support and minimum confidence are set as 0.01 and 0.8, respectively. Besides, we also compare the performance of aggressive driving behavior recognition classifiers constructed using association classification with other rule-based classification methods, including ID3, C4.5, CART, and Random Forest. The results show that association classification performs better than other classification competitors. Thirty-six if–then rules generated by the association classification are used to analyze the influencing factors and associated mechanisms of aggressive driving behavior. It is found that aggressive driving behavior is highly correlated with driver anger and disgust emotions. Aggressive driving behavior is more likely to occur when no passengers are in the car than the case with passengers. Driver entertainment behavior and passenger interference also affect driving behavior. Moreover, drivers are prone to aggressive driving when making a U-turn. This research not only proposed a new identification method for aggressive driving behavior but also provided a comprehensive understanding of the associated influencing factors which thus benefit the further research and development of safety assistance driving devices.     

Emotional Dynamics and Coping Mechanisms to Generate Human-Like Agent Behaviors

Emotion mechanisms represent an important moderating factor of human behavior. Thus, they are necessary to produce realistic behavioral simulations. This work addresses this challenging issue by incorporating emotional processes into an agent model. We intend to show the potential of emotions and coping mechanisms to produce fast and human-like emotional behaviors, particularly, in emergency situations. We focus on the interplay of emotions and goals and its impact on agent behavior. Emotions constitute heuristics to agent decision making. They induce emotion-specific goals that orient agent goal adoption mechanisms and fasten its behavior selection.     

Microconsistency in Simple Empirical Agent-Based Financial Models

Models with small numbers of agents have recently been simplified for direct empirical estimation. Parameters are estimated at the macro level to get a best fit to the data. However, little analysis is done at the micro level to examine the choices made by agents for forecasting rules. This paper explores one of these recent models from the standpoint of micro agent behavior. It is shown that at the fitted forecasting rules, agents would prefer deviating to other nearby rules. The simple two type model is then compared with several multi-type models allowing for agents to use a broader set of rules. This can impact the dynamics of the generated time series, but it also may not if one takes the parameter estimates of the original model as an exogenous restriction on a reasonable support for the forecasting rules. This result emphasizes that these models may be imposing some hidden micro assumptions about agent behavior.

     

Emotion space model for classifying opinions in stock message board

The online stock message is known to have impacts on the trend of the stock market. Understanding investor opinions in stock message boards is important, and the automatic classification of the investors’ opinions is one of the key methods for the issue. Traditional opinion classification methods mainly use terms and their frequency, part of speech, rule of opinions and sentiment shifters. But semantic information is ignored in term selection, and it is also hard to find the complete rules. In this paper, based on the classification of human emotions proposed by Ekman, we extend the traditional positive–negative analysis to the six important emotion states to build an extremely low dimensional emotion space model (ESM). It enables the prediction of investors’ emotions in public. Specifically, we use lexical semantic extension and correlation analysis methods to extend the scale of emotion words, which can capture more words with strong emotions for ad hoc domain, like network emotion symbols. We apply our ESM on messages of a famous stock message board TheLion. We also compare our model with traditional methods information gain and mutual information. The results show that ESM is not parameter sensitive. Besides, ESM is efficient for modeling sentiment classifying and can achieve higher classification accuracy than traditional ones.     

Emotions and temperament of robots: Behavioral aspects

An approach to the control of robots behavior based on the emotion and temperament mechanism is proposed. It is shown that these psychological features can be simulated fairly simply. The proposed emotion-based architecture of the robot control system leans upon the Simonov informational theory of emotions, while the specific features of temperament are reduced to a two-parameter model of the excitation-inhibition type. Experiments performed with mobile robots are described. These experiments demonstrate a set of various types of robots’ behavior: melancholic, choleric, sanguine, and phlegmatic. All these types were implemented using the so-called temperament controller, which determines a balance between the excitation and inhibition parameters of the robot control system. An FSM-based model of temperament is also proposed that makes it possible to describe the behavior of an individual. Using this model, it is shown that, for performing certain collective behavior tasks, it is useful to have in the group individuals with different behavior so that this behavior also depends on the individual emotions and temperament of robots.     

一种新的网络故障检测方法

文章提出了一种基于粗糙集和径向基函数思想的网络层故障检测算法——RSMNBP。这种新的方法提供网络层状态数据的采集、分析、存储和响应功能,具有简化样本、适应性强、容错性高等特点,能有效处理网络层故障诊断中噪声和不相容的信息。由于检测问题的实质是一种映射,该方法用一种前馈型网络来逼近这种映射关系,实现对故障的有效分类。同时,RSMNBP的网络结构可以随着网络层中各种服务和应用的变化而构造。仿真表明,利用该方法实现的系统与同类的其他方法相比,提高了检测准确率和诊断速度。     

Human emotion recognition and analysis in response to audio music using brain signals

Human emotion recognition using brain signals is an active research topic in the field of affective computing. Music is considered as a powerful tool for arousing emotions in human beings. This study recognized happy, sad, love and anger emotions in response to audio music tracks from electronic, rap, metal, rock and hiphop genres. Participants were asked to listen to audio music tracks of 1 min for each genre in a noise free environment. The main objectives of this study were to determine the effect of different genres of music on human emotions and indicating age group that is more responsive to music. Thirty men and women of three different age groups (15–25 years, 26–35 years and 36–50 years) underwent through the experiment that also included self reported emotional state after listening to each type of music. Features from three different domains i.e., time, frequency and wavelet were extracted from recorded EEG signals, which were further used by the classifier to recognize human emotions. It has been evident from results that MLP gives best accuracy to recognize human emotion in response to audio music tracks using hybrid features of brain signals. It is also observed that rock and rap genres generated happy and sad emotions respectively in subjects under study. The brain signals of age group (26–35 years) gave best emotion recognition accuracy in accordance to the self reported emotions.     

Why Machines Cannot Feel

For a long time, emotions have been ignored in the attempt to model intelligent behavior. However, within the last years, evidence has come from neuroscience that emotions are an important facet of intelligent behavior being involved into cognitive problem solving, decision making, the establishment of social behavior, and even conscious experience. Also in research communities like software agents and robotics, an increasing number of researchers start to believe that computational models of emotions will be needed to design intelligent systems. Nevertheless, modeling emotions in technical terms poses many difficulties and has often been accounted as just not feasible. In this article, there are identified the main problems, which occur when attempting to implement emotions into machines. By pointing out these problems, it is aimed to avoid repeating mistakes committed when modeling computational models of emotions in order to speed up future development in this area. The identified issues are not derived from abstract reflections about this topic but from the actual attempt to implement emotions into a technical system based on neuroscientific research findings. It is argued that besides focusing on the cognitive aspects of emotions, a consideration of the bodily aspects of emotions—their grounding into a visceral body—is of crucial importance, especially when a system shall be able to learn correlations between environmental objects and events and their “emotional meaning”.     

Characterization and analysis of sales data for the semiconductor market: An expert system approach

Chip purchasing policies of the Original Equipment Manufacturers (OEMs) of laptop computers are characterized by similarity measures and probabilistic rules. Our main goal is to build an expert system for predicting purchasing behavior in the semiconductor market. The probabilistic rules and similarity measures are extracted from data of products bought by the OEMs in the semiconductor market over twenty quarters. We present the data collected and different qualitative data mining approaches to analyze and extract rules from the data that best characterize the purchasing behavior of the OEMs. Our analysis of the similar product selection shows that there are two main groups of OEMs buying similar products. Using our probabilistic rules, we obtain an average score of approximately 95% reconstructing quarterly data for a one year window.     

情绪主导型群体事件的情绪演化模型与仿真

大规模群体负面情绪的形成与蔓延是引发情绪主导型群体事件的根本原因。考虑在社会关系网络中的个体是有限理性的情形下,对群体情绪形成原因进行分析,归纳了群体情绪感染规则与蔓延机制,并依此构建了群体情绪感染模型,利用多主体仿真平台Netlogo对群体负面情绪的演化过程进行仿真实验,考察不同情景下群体负面情绪的演变情况,结果表明普通民众的理性程度,个体间的情感关系,意见领袖的干预、占比、干预时间、情绪感染阈值等都对群体负面情绪有影响。最后,对情绪主导型群体突发事件的预防与对策给出了合理建议。     

On the Relative Soundness of the Free Algebra Model for Public Key Encryption

Formal systems for cryptographic protocol analysis typically model cryptosystems in terms of free algebras. Modeling the behavior of a cryptosystem in terms of rewrite rules is more expressive, however, and there are some attacks that can only be discovered when rewrite rules are used. But free algebras are more efficient, and appear to be sound for “most” protocols. In [J. Millen, “On the freedom of decryption”, Information Processing Letters 86 (6) (June 2003) 329–333] Millen formalizes this intuition for shared key cryptography and provides conditions under which it holds; that is, conditions under which security for a free algebra version of the protocol implies security of the version using rewrite rules. Moreover, these conditions fit well with accepted best practice for protocol design. However, he left public key cryptography as an open problem. In this paper, we show how Millen's approach can be extended to public key cryptography, giving conditions under which security for the free algebra model implies security for the rewrite rule model. As in the case for shared key cryptography, our conditions correspond to standard best practice for protocol design.     

Combining rough decisions for intelligent text mining using Dempster’s rule

An important issue in text mining is how to make use of multiple pieces knowledge discovered to improve future decisions. In this paper, we propose a new approach to combining multiple sets of rules for text categorization using Dempster’s rule of combination. We develop a boosting-like technique for generating multiple sets of rules based on rough set theory and model classification decisions from multiple sets of rules as pieces of evidence which can be combined by Dempster’s rule of combination. We apply these methods to 10 of the 20-newsgroups—a benchmark data collection (Baker and McCallum 1998), individually and in combination. Our experimental results show that the performance of the best combination of the multiple sets of rules on the 10 groups of the benchmark data is statistically significant and better than that of the best single set of rules. The comparative analysis between the Dempster–Shafer and the majority voting (MV) methods along with an overfitting study confirm the advantage and the robustness of our approach.     

Predicting employee information security policy compliance on a daily basis: The interplay of security-related stress,emotions, and neutralization

We conceptualized security-related stress (SRS) and proposed a theoretical model linking SRS, discrete emotions, coping response, and information security policy (ISP) compliance. We used an experience sampling design, wherein 138 professionals completed surveys. We observed that SRS had a positive association with frustration and fatigue, and these negative emotions were associated with neutralization of ISP violations. Additionally, frustration and fatigue make employees more likely to follow through on their rationalizations of ISP violations by decreased ISP compliance. Our findings provide evidence that neutralization is not a completely stable phenomenon but can vary within individuals from one time point to another.     

Learning goal hierarchies from structured observations and expert annotations

We describe a relational learning by observation framework that automatically creates cognitive agent programs that model expert task performance in complex dynamic domains. Our framework uses observed behavior and goal annotations of an expert as the primary input, interprets them in the context of background knowledge, and returns an agent program that behaves similar to the expert. We map the problem of creating an agent program on to multiple learning problems that can be represented in a “supervised concept learning’’ setting. The acquired procedural knowledge is partitioned into a hierarchy of goals and represented with first order rules. Using an inductive logic programming (ILP) learning component allows our framework to naturally combine structured behavior observations, parametric and hierarchical goal annotations, and complex background knowledge. To deal with the large domains we consider, we have developed an efficient mechanism for storing and retrieving structured behavior data. We have tested our approach using artificially created examples and behavior observation traces generated by AI agents. We evaluate the learned rules by comparing them to hand-coded rules. Editor: Rui Camacho     

Mining Customer Value: From Association Rules to Direct Marketing

Direct marketing is a modern business activity with an aim to maximize the profit generated from marketing to a selected group of customers. A key to direct marketing is to select a subset of customers so as to maximize the profit return while minimizing the cost. Achieving this goal is difficult due to the extremely imbalanced data and the inverse correlation between the probability that a customer responds and the dollar amount generated by a response. We present a solution to this problem based on a creative use of association rules. Association rule mining searches for all rules above an interestingness threshold, as opposed to some rules in a heuristic-based search. Promising association rules are then selected based on the observed value of the customers they summarize. Selected association rules are used to build a model for predicting the value of a future customer. On the challenging KDD-CUP-98 dataset, this approach generates 41% more profit than the KDD-CUP winner and 35% more profit than the best result published thereafter, with 57.7% recall on responders and 78.0% recall on non-responders. The average profit per mail is 3.3 times that of the KDD-CUP winner.