In-depth behavior understanding and use: The behavior informatics approach

The in-depth analysis of human behavior has been increasingly recognized as a crucial means for disclosing interior driving forces, causes and impact on businesses in handling many challenging issues such as behavior modeling and analysis in virtual organizations, web community analysis, counter-terrorism and stopping crime. The modeling and analysis of behaviors in virtual organizations is an open area. Traditional behavior modeling mainly relies on qualitative methods from behavioral science and social science perspectives. On the other hand, so-called behavior analysis is actually based on human demographic and business usage data, such as churn prediction in the telecommunication industry, in which behavior-oriented elements are hidden in routinely collected transactional data. As a result, it is ineffective or even impossible to deeply scrutinize native behavior intention, lifecycle and impact on complex problems and business issues. In this paper, we propose the approach of behavior informatics (BI), in order to support explicit and quantitative behavior involvement through a conversion from source data to behavioral data, and further conduct genuine analysis of behavior patterns and impacts. BI consists of key components including behavior representation, behavioral data construction, behavior impact analysis, behavior pattern analysis, behavior simulation, and behavior presentation and behavior use. We discuss the concepts of behavior and an abstract behavioral model, as well as the research tasks, process and theoretical underpinnings of BI. Two real-world case studies are demonstrated to illustrate the use of BI in dealing with complex enterprise problems, namely analyzing exceptional market microstructure behavior for market surveillance and mining for high impact behavior patterns in social security data for governmental debt prevention. Substantial experiments have shown that BI has the potential to greatly complement the existing empirical and specific means by finding deeper and more informative patterns leading to greater in-depth behavior understanding. BI creates new directions and means to enhance the quantitative, formal and systematic modeling and analysis of behaviors in both physical and virtual organizations.     

Smooth Intervention Model of Individual Interactive Behavior

User feature extraction and identity authentication methods based on interactive behavior are an important method of identity recognition. However, for high-frequency users, the interactive behavior patterns and operating habits are relatively stable, which are easily imitated by fraudsters and make the existing models have a higher misjudgment. The key to solving the above problems is to make the users'' behavior change smoothly and distinguishably. This study proposes a smooth intervention model based on an individual interactive behavior system to handle it. Firstly, according to the users'' historical web behavior log, the change trend of users'' interactive behavior is obtained from multiple dimensions. Then, combined with the stability and deviation of the behavior, the Time-Domain Drift Algorithm (TDDA) is proposed to determine the behavior guidance time of each user. Finally, an intervention model for interactive behavior reconstruction systems is proposed, which superimposes behavior trigger factors on non-critical paths in the system to guide users to generate new interactive behavior habits. Experiments prove that the method proposed in this study could guide the user behavior to change smoothly and produce sufficient distinction to significantly advance the model accuracy in the scenario of behavior camouflage anomaly detection.     

个体交互行为的平滑干预模型

基于交互行为的用户特征提取和身份认证方法是一种重要的身份识别方式,但高频用户的交互行为模式和操作习惯相对稳定,易被欺诈者模仿,使得现有模型对此类欺诈行为的误判较高.如何使得用户行为主动平滑变化且可区分,成为解决上述问题的关键.针对此问题,提出一种基于个体交互行为系统平滑干预模型:首先,根据用户历史交互行为日志从多个维度...     

Identification of trusted interactive behavior based on mouse behavior considering web User's emotions

Under existing network security technology, it is still possible for hackers to impersonate legitimate users and invade a system for malicious destruction. Therefore, this study constructs a user's unique mouse behavior pattern to identify a trusted interaction behavior in a real environment and quantify the effects of different emotions on mouse behavior and the accuracy of the user's trusted interaction behavior identification. First, mouse data was collected for 8 user's trusted interactions on an academic study website (AML). These data were used to construct the basic trusted interaction model by a big data analysis method called a random forest. Second, in a repeated measurement experiment, 18 participants completed tasks on the AML under different emotions, and the emotions' impact on the mouse behavior and accuracy of the user's trusted interaction identification was analyzed. In the results, the accuracy of the trusted interaction behavior identification based on mouse behavior reached 91.82%, and the error rate was lower than 8.18%. Significant differences were observed in horizontal velocity, velocity, and traveled distance under different emotions. However, there was no significant difference in the accuracy of a user's trusted interaction behavior identification under different emotions. Based on these results, the trusted interaction behavior of web users can be accurately identified based on the user's mouse behavior pattern. The user's mouse behavior differs under different emotions, but there is no significant difference on the identification of the user's trusted interaction behavior. The findings help to provide another protection layer for network information security.     

大数据背景下教育数据挖掘在学生在线学习行为分析中的应用研究

本文基于我院自行开发并已广泛投入使用的计算机基础信息化导学平台中的日志数据。首先对平台中学员登陆情况、资源浏览情况相关的数据进行收集预处理;接下来对学员的登陆行为、和资源浏览情况进行统计分析;在此基础上,采用决策树算法分析得到了对影响学员登陆行为及资源浏览行为的影响因素。依据分析结果,可使教育教学工作者基于学习者的学习情况来实现教学内容组织、构建教学模式等。     

A hybrid of sequential rules and collaborative filtering for product recommendation

Customers’ purchase behavior may vary over time. Traditional collaborative filtering (CF) methods make recommendations to a target customer based on the purchase behavior of customers whose preferences are similar to those of the target customer; however, the methods do not consider how the customers’ purchase behavior may vary over time. In contrast, the sequential rule-based recommendation method analyzes customers’ purchase behavior over time to extract sequential rules in the form: purchase behavior in previous periods ⇒ purchase behavior in the current period. If a target customer’s purchase behavior history is similar to the conditional part of the rule, then his/her purchase behavior in the current period is deemed to be the consequent part of the rule. Although the sequential rule method considers the sequence of customers’ purchase behavior over time, it does not utilize the target customer’s purchase data for the current period. To resolve the above problems, this work proposes a novel hybrid recommendation method that combines the segmentation-based sequential rule method with the segmentation-based KNN-CF method. The proposed method uses customers’ RFM (Recency, Frequency, and Monetary) values to cluster customers into groups with similar RFM values. For each group of customers, sequential rules are extracted from the purchase sequences of that group to make recommendations. Meanwhile, the segmentation-based KNN-CF method provides recommendations based on the target customer’s purchase data for the current period. Then, the results of the two methods are combined to make final recommendations. Experiment results show that the hybrid method outperforms traditional CF methods.     

结合行为树与Q-learning优化UT2004中agent行为决策

针对FPS游戏UT2004中的NPC（Non-Player-Character,即非玩家角色）的行为决策不够灵活多变,不够智能等问题,结合行为树与Q-learning强化学习算法,提出了一种预处理与在线学习结合的方式优化NPC行为决策的方法。通过在行为树上的强化学习,NPC行为决策更为灵活、智能,即human-like。实验结果表明了该方法的有效性与可行性。     

Deciding whether to look after them,to like it,or leave it: A multidimensional analysis of predictors of positive and negative bystander behavior in cyberbullying among adolescents

BackgroundPositive bystander behavior in cyberbullying among adolescents may effectively mitigate cyberbullying and its harm for the victim. Limited, scattered, and sometimes only qualitative research is available on predictors of positive (e.g. defending, comforting or reporting) and negative (e.g. passive bystanding, joining, reinforcing) bystander behavior in cyberbullying. A multidimensional model and multilevel analysis were therefore applied in this study.MethodsA sample of 1979 adolescents in 7th -9th grade, in 16 schools and 158 classes participated in the study. Analyses were performed in MLwiN 2.32.ResultsAnalyses confirmed the multifaceted nature of bystander behavior and behavioral intention. No school level effects, and only limited class effects were found. Strongest individual predictors of positive bystander behavior were a positive intention, and friendship with the victim. Intention for positive bystander behavior was most predicted by positive outcome expectations of their actions for the victim. Negative bystander behavior was most predicted by intentions for negative behavior, and moral disengagement attitudes. Intentions to act as a negative bystander were most predicted by positive attitudes towards passive bystanding and a lack of skills (social, empathic, coping). Moral disengagement at classroom level also predicted positive behavior and behavioral intentions, and negative behavioral intentions, but not negative behavior. Information days for pupils on cyberbullying was a significant school-level predictor of the intention to act as a positive bystander.ConclusionsFuture research and interventions should take the multidimensional nature of cyberbullying bystander behavior into account. Implications for research and practice are discussed.     

ASTM E1989-98 - The New Instrument Control Standard

The new ASTM E1989-98 Laboratory Equipment Control Interface Specification (LECIS) is a robust standard definition of equipment behavior while under remote control. The goal of the standardization effort is to facilitate “plug-and-play” integration of laboratory automation with standard hardware behavior and software interfaces. The LECIS standardizes laboratory equipment behavior and a message passing scheme between the controller and equipment that synchronizes this behavior. Commercial adoption of this new standard is well under way.     

Cellular Homeostasis,Epigenesis and Replication in Randomly Aggregated Macromolecular Systems

Abstract

Proto-organisms probably were randomly aggregated nets of chemical reactions. The hypothesis that contemporary organisms are also randomly constructed molecular automata is examined by modeling the gene as a binary (on-off) device and studying the behavior of large, randomly constructed nets of these binary “genes.” The results suggest that, if each “gene” is directly affected by two or three other “genes,” then such random nets: behave with great order and stability; undergo behavior cycles whose length predicts cell replication time as a function of the number of genes per cell; possess different modes of behavior whose number per net predicts roughly the number of cell types in an organism as a function of its number of genes; and under the stimulus of noise are capable of differentiating directly from any mode of behavior to at most a few other modes of behavior. Cellular differentiation is modeled as a Markov chain among the modes of behavior of a genetic net. The possibility of a general theory of metabolic behavior is suggested. Analytic approaches to the behavior of switching nets are discussed in Appendix 1, and some implications of the results for the origin of self replicating macromolecular systems is discussed in Appendix 6.     

Risk management: moving beyond process

Software risk management is more than just another process; it is a fundamental change in the way uncertainty and decision making are viewed. More specifically, effective risk management requires obtaining functional behavior, not just following a process or having diverse sources of information. Functional behavior is often labeled the absence of dysfunctional behavior, yet eliminating dysfunctional behavior doesn't automatically result in the desired behavior. Rockwell found that they needed to go a step further and devise a plan to “coach” functional behavior. The author describes a plan to elicit the behavior “communicate risk more effectively” which Rockwell identified as a common thread among many functional behaviors. After implementing this plan we noted several improvements, including fewer surprises and crises, even on our most risky programs. Reviews are now more robust, providing more accurate pictures of each program's situation: past, present, and future. It is also easier to identify whether a program is controlling its fate or simply reacting to the world around it     

严肃游戏中虚拟角色行为建模综述

严肃游戏是计算机游戏一个新的发展方向,可以提供形象互动的模拟教学环境,已经广泛应用于科学教育、康复医疗、应急管理、军事训练等领域。虚拟角色是严肃游戏中模拟具有生命特征的图形实体,行为可信的虚拟角色能够提升用户使用严肃游戏的体验感。严肃游戏中的图形渲染技术已经逐步成熟,而虚拟角色行为建模的研究尚在初级阶段。可信的虚拟角色必须能够具有感知、情绪和行为能力。本文分别从游戏剧情与行为、行为建模方法、行为学习和行为建模评价等4个方面来分析虚拟角色行为建模研究。分析了有限状态机和行为树的特点,讨论了虚拟角色的行为学习方法。指出了强化学习的关键要素,探讨了深度强化学习的应用途径。综合已有研究,归纳了虚拟角色行为框架,该框架主要包括感觉输入、知觉分析、行为决策和动作4大模块。从情感计算的融入、游戏剧情和场景设计、智能手机平台和多通道交互4个角度讨论需要进一步研究的问题。虚拟角色的行为建模需要综合地考虑游戏剧情、机器学习和人机交互技术,构建具有自主感知、情绪、行为、学习能力、多通道交互的虚拟角色能够极大地提升严肃游戏的感染力,更好地体现寓教于乐。     

Spontaneous behavior for cooperation through interaction: An emotionally intelligent robot system

This paper deals withspontaneous behavior for cooperation through interaction in a distributed autonomous robot system. Though a human gives the robots evaluation functions for the relation of cooperation among robots, each robot decides its behavior depending on its environment, its experience, and the behavior of other robots. The robot acquires a model of the behavior of the other robots through learning. Inspired by biological systems, the robot's behaviors are interpreted as emotional by an observer of the system. In psychology, the emotions have been considered to play important roles for generation of motivation and behavior selection. In this paper, the robot's behaviors are interpreted as follows: each robot feels frustration when its behavior decision does not fit its environment. Then, it changes its behavior to change its situation actively and spontaneously. The results show potential of intelligent behavior by emotions. This work was presented, in part, at the International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1996     

面向决策可托管应用的行为提取与分析方法

游戏平台为优化游戏体验常提供决策AI托管功能,这导致平台在对用户进行画像时面临数据质量低的问题。日志中混合了托管AI和玩家自主作出的决策行为,有时还存在行为缺失的情况。提出一种面向决策可托管应用的行为提取与分析方法,通过基于启发式规则的行为特征提取方法从日志中提取玩家自主行为。最后使用多种画像方法在原始数据集和精简数据集上分别进行分析并比较其结果,得出该方法可在大幅度缩减数据量的同时较好地保留玩家的行为特征信息。     

基于大数据聚合的电力用户行为实时云监测方法

为提升电力用户行为监测效果及准确性,判断电力用户异常行为,提出一种基于大数据聚合的电力用户行为实时云监测方法。该方法将基础设施及终端等获取的电力用户行为大数据储存至数据层的关系数据库内,处理层调用数据层存储电力用户行为大数据,采用大数据处理技术,通过数据降维、清洗以及标准化处理后,提升电力用户行为大数据质量;应用层采用改进流数据聚类算法,通过用户及簇典型曲线提取、曲线相似度度量,实现用户用电行为异常监测,并通过显示层云展现监测结果。实验结果证明,该方法的数据聚类质量高,可以有效获取电力用户行为监测结果,判断电力用户是否存在异常行为,具备较高监测准确性。     

基于情绪和兴趣的用户访问行为预测

微博用户行为预测旨在研究用户的行为习惯,本文主要从用户属性、用户兴趣和用户情绪三个方面,对影响微博用户行为的因素进行研究分析,提取影响用户行为的特征,训练预测模型. 实验中还将情感和兴趣特征在预测模型中的作用进行了对比,结果显示预测模型在转发行为预测的平均准确率能够达到82.56%,在评论行为预测的平均准确率能够达到84.59%,在点赞行为预测的平均准确率能够达到79.35%,表明了用户兴趣和情感特征对于微博用户行为预测结果提升中的有效性.     

基于图模型理论的决策者组合行为冲突分析

依据现有4种基本稳定性能够获取冲突均衡解,但该过程通常假设决策者具有相同的行为模式.为了研究各个决策者行为模式的差异性对冲突演化分析与求解的影响,提出一种决策者组合行为冲突分析方法.首先,基于冲突分析图模型4种稳定性概念,通过预见力和风险态度两项指标识别不同决策者的行为模式;其次,定义规范化的组合均衡解概念,以此反映决策者不同行为模式对冲突决策的影响;接着,给出基于矩阵行为模式分析函数的组合均衡求解方法,以此提高均衡解的计算效率;最后,运用新方法解决企业员工体面劳动保障制度实施冲突问题.研究表明,所提出方法能够较好地提高冲突分析图模型理论的战略解析能力和决策水平.     

“What’s coming next?” Epistemic curiosity and lurking behavior in online communities

Prior research has repeatedly found that lurkers, the passive members of online communities, dominate such communities in terms of membership. Yet lurking in online communities reflects a phenomenon largely neglected by contemporary information systems theory and research. This study starts by reviewing existing literature on lurking behavior in online communities and identifies an unexplored opportunity related to the nature and origins of lurkers’ behavior, the individual propensity to de-lurk, and the dynamic interplay between lurking and de-lurking behavior. A theoretical process-based framework linking epistemic curiosity to lurking and de-lurking behavior in online communities is presented. This framework links prior academic work on epistemic curiosity as personality trait and emotional–motivational state to lurkers’ contribution behavior in online communities. The article concludes by proposing that the psychology of curiosity in general holds great promise for research on online communities in information systems.     

A pilot study of cooperative programming learning behavior and its relationship with students' learning performance

In this study we proposed a web-based programming assisted system for cooperation (WPASC) and we also designed one learning activity for facilitating students' cooperative programming learning. The aim of this study was to investigate cooperative programming learning behavior of students and its relationship with learning performance. Students' opinions and perceptions toward learning activity and the WPASC were also investigated. The results of this study revealed that most of students perceived that learning activity and the WPASC were useful for cooperative programming learning. Students' learning behavior during cooperative programming learning activity was classified into six different categories and we found that learning behavior has relationship with learning performance. Students from completely independent, self-improving using assistance, confident after enlightenment and imitating categories performed well due to their effective and motivated learning behavior. However, students from performing poorly without assistance and plagiarizing categories performed the worse; the former could not get assistance at all and the later had no learning motivation. The results also showed that students' learning behavior may have increasing, decreasing and no transition during problems solving. Therefore, performing poorly without assistance and plagiarizing learning behavior and decreasing transition or no transition in learning behavior should be identified right after completing a programming problem. Then the instructor should intervene into learning behavior in order to change it into more effective for learning. Besides, more incentives need to be given for increasing students' learning motivation and posting solutions and feedback by students at the early stage of a problem solving period.