Application of machine learning techniques to analyse student interactions and improve the collaboration process

In e-learning environments that use the collaboration strategy, providing participants with a set of communication services may not be enough to ensure collaborative learning. It is thus necessary to analyse collaboration regularly and frequently. Using machine learning techniques is recommended when analysing environments where there are a large number of participants or where they control the collaboration process. This research studied two approaches that use machine learning techniques to analyse student collaboration in a long-term collaborative learning experience during the academic years 2006–2007, 2007–2008 and 2008–2009. The aims were to analyse collaboration during the collaboration process and that it should be domain independent. Accordingly, the intention was to be able to carry out the analysis regularly and frequently in different collaborative environments. One of the two approaches classifies students according to their collaboration using unsupervised machine learning techniques, clustering, while the other approach constructs metrics that provide information on collaboration using supervised learning techniques, decision trees. The research results suggest that collaboration can be analysed in this way, thus achieving the aims set out with two different machine learning techniques.     

Constructing and Utilizing a Model of User Preferences in Collaborative Consultation Dialogues

A natural language collaborative consultation system must take user preferences into account. A model of user preferences allows a system to appropriately evaluate alternatives using criteria of importance to the user. Additionally, decision research suggests both that an accurate model of user preferences could enable the system to improve a user's decision-making by ensuring that all important alternatives are considered, and that such a model of user preferences must be built dynamically by observing the user's actions during the decision-making process. This paper presents two strategies: one for dynamically recognizing user preferences during the course of a collaborative planning dialogue and the other for exploiting the model of user preferences to detect suboptimal solutions and suggest better alternatives. Our recognition strategy utilizes not only the utterances themselves but also characteristics of the dialogue in developing a model of user preferences. Our generation strategy takes into account both the strength of a preference and the closeness of a potential match in evaluating actions in the user's plan and suggesting better alternatives. By modeling and utilizing user preferences, our system is able to fulfill its role as a collaborative agent.     

基于动态任务空间的协同学习管理模型与实现

在协同学习支撑环境以及协同学习系统中,学生和老师都需要一些协同和控制手段去协调共同的学习活动。为此,提出了一种新的协同学习环境下的协同学习管理模型。它通过对协同学习任务的分解和学习资源的合理化配置搭建共享的任务空间。文中分析了动态任务空间的组成元素,给出了动态任务空间模型的形式化定义,介绍了模型管理工具的设计与实现,总结了模型在协同学习系统中应用的特点。     

Integrating new information and communication technologies in a group decision support system

We view group decision making as a collaborative process, where decision makers can establish a common belief on the dimensions of the problem by following a series of well-defined communicative actions. Having first defined these actions, this paper reports on the exploitation of recent advances in information and communication technology, which can be used to: (i) remove the communication impediments among spatially dispersed decision makers; (ii) efficiently elicit and represent the domain of knowledge; (iii) develop efficient mechanisms to structure and consistently maintain the decision analysis; and (iv) automate the decision making process itself. Automation concerns coherence and consistency checking, detection of contradictions, truth maintenance, and information retrieval techniques.     

Using a wiki to evaluate individual contribution to a collaborative learning project

Abstract   One critical issue arising in the educational use of collaborative learning concerns the teacher's difficulty in evaluating the contribution and participation of each student in group-work. This article aims to illustrate and discuss a methodology that enables evaluation of the collaborative learning process based on co-writing in a wiki environment. After considering the effectiveness of co-writing as a strategy of collaborative learning, the article will highlight issues regarding methods for evaluating each student's contribution to the collaborative process and to the group's overall action. A solution will be proposed to address the problem. It is based upon the elaboration of information traced automatically by wiki, employing survey grids and formulae developed ad hoc to calculate participation and contribution indexes. These tools will be illustrated together with their application in two university courses. Results demonstrate the added value given by the proposed approach to the evaluation process of co-writing. However, these findings also highlight critical issues and some possible remedies for the lack of specific wiki functions to automatically extract information required for quantitative analysis of the actions taken by members of the learning group.     

Improving human robot collaboration through Force/Torque based learning for object manipulation

Human–Robot Collaboration (HRC) is a term used to describe tasks in which robots and humans work together to achieve a goal. Unlike traditional industrial robots, collaborative robots need to be adaptive; able to alter their approach to better suit the situation and the needs of the human partner. As traditional programming techniques can struggle with the complexity required, an emerging approach is to learn a skill by observing human demonstration and imitating the motions; commonly known as Learning from Demonstration (LfD). In this work, we present a LfD methodology that combines an ensemble machine learning algorithm (i.e. Random Forest (RF)) with stochastic regression, using haptic information captured from human demonstration. The capabilities of the proposed method are evaluated using two collaborative tasks; co-manipulation of an object (where the human provides the guidance but the robot handles the objects weight) and collaborative assembly of simple interlocking parts. The proposed method is shown to be capable of imitation learning; interpreting human actions and producing equivalent robot motion across a diverse range of initial and final conditions. After verifying that ensemble machine learning can be utilised for real robotics problems, we propose a further extension utilising Weighted Random Forest (WRF) that attaches weights to each tree based on its performance. It is then shown that the WRF approach outperforms RF in HRC tasks.     

Belief-Driven Manipulator Visual Servoing for Less Controlled Environments

This paper presents the architecture of a feedforward manipulator control strategy based on a belief function that may be appropriate for less controlled environments. In this architecture, the belief about the environmental state, as described by a probability density function, is maintained by a recursive Bayesian estimation process. A likelihood is derived from each observation regardless of whether the targeted features of the environmental state have been detected or not. This provides continuously evolving information to the controller and allows an inaccurate belief to evolve into an accurate belief. Control actions are determined by maximizing objective functions using non-linear optimization. Forward models are used to transform control actions to a predicted state so that objective functions may be expressed in task space. The first set of examples numerically investigates the validity of the proposed strategy by demonstrating control in a two dimensional scenario. Then a more realistic application is presented where a robotic manipulator executes a searching and tracking task using an eye-in-hand vision sensor.     

Conflict resolution in collaborative planning dialogs

In a collaborative planning environment in which the agents are autonomous and heterogeneous, it is inevitable that discrepancies in the agents' beliefs result in conflicts during the planning process. In such cases, it is important that the agents engage in collaborative negotiation to resolve the detected conflicts in order to determine what should constitute their shared plan of actions and shared beliefs. This paper presents a plan-based model for conflict detection and resolution in collaborative planning dialogs. Our model specifies how a collaborative system should detect conflicts that arise between the system and its user during the planning process. If the detected conflicts warrant resolution, our model initiates collaborative negotiation in an attempt to resolve the conflicts in the agent's beliefs. In addition, when multiple conflicts arise, our model identifies and addresses the most effective aspect in its pursuit of conflict resolution. Furthermore, by capturing the collaborative planning process in a recursive Propose–Evaluate–Modify cycle of actions, our model is capable of handling embedded negotiation during conflict resolution.     

Maintenance strategy for leased equipment

In case of leasing, the user rents equipment for a predetermined time. During this period, all maintenance actions are performed by the lessor. The aim of this research paper consists in determining an optimal maintenance policy for ensuring a minimum reliability, required by the customer. Two strategies are proposed: the first consists in performing preventive actions whenever the system reliability reaches a predefined reliability threshold. These actions are characterized by a reduction of the system age. The objective is therefore to determine the effectiveness factor of the optimal maintenance minimizing maintenance costs. For the second strategy, “improving” actions replace corrective actions during an interval to be determined to minimize maintenance costs. The first strategy will be solved using a numerical procedure and the second strategy uses an algorithm of discrete event simulation.     

ComPLuS model: A new insight in pupils’ collaborative talk, actions and balance during a computer-mediated music task

This exploratory work describes and analyses the collaborative interactions that emerge during computer-based music composition in the primary school. The study draws on socio-cultural theories of learning, originated within Vygotsky’s theoretical context, and proposes a new model, namely Computer-mediated Praxis and Logos under Synergy (ComPLuS). In this model, peers’ dialogue is categorised into five types; disputational, cumulative, exploratory, operational, and reflective, with each one corresponding to different types of spoken contributions. Moreover, peers’ actions are categorised as individual or joint and are used to evaluate the effect of computer mediation on the collaborative activity and its balance within a pair. The potential and effectiveness of the realisation of the ComPLuS model in practice, as far as peers’ collaboration is concerned, are evaluated from its trialling in an experimental case-study, in which a group of 11-yr old pupils worked in pairs to compose short melodies using computers at the computer room of their school. Emphasis was placed upon the types of social modes of thinking with regard to pupils’ spoken contributions and talk types during their conversation; pupils’ actions when manipulating software, and the balance of talk and action between the pair members. Their ongoing peer-to-peer communication and actions formed the research data. A mixed (qualitative and quantitative) analysis revealed that peers usually adopted cumulative and exploratory talk. Moreover, the action type which dominated their work was based on a consensual decision. Nevertheless, it was found that lead on collaborative talk does not mean lead on joint action and does not always sustain a balance in peers’ collaboration. Experimentation with the music software, in conjunction with pupils’ musical background, facilitated their joint action, exploratory and reflective talk. However, audio feedback provided by the software did not seem to affect peers’ talk types. These results suggest that the ComPLuS model captures the characteristics of peers’ collaborative interactions during their shared discussions and actions, and can lead to a better understanding of the nature of computer-supported collaborative creativity in primary music education.     

From Predefined Consistency to User-Centered Emergent Consistency in Real-Time Collaborative Editing Systems

In this paper, we introduce a basic conceptual model of real-time collaborative editing systems which differentiates the coordination aspect of actions (which do not exist in single-user systems) from the application-dependent semantic aspect of actions (i.e., those actions that happen in single-user systems). Based on this model, a new taxonomy is provided to analyze the existing consistency-maintenance mechanisms and highlight potential new mechanisms. Furthermore, a new user-centered consistency model is proposed, which focuses on dynamic consistency that is negotiable among end users rather than static consistency that is automatically determined by the system. In the mean time, some challenging research issues in real-time collaborative editing systems are outlined     

Risky business or sharing the load? - Social flow in collaborative mobile learning

Mobile learning has been built upon the premise that we can transform traditional classroom or computer-based learning activities into a more ubiquitous and connected form of learning. Tentative outcomes from this assertion have been witnessed in many collaborative learning activities, but few analytic observations on what triggers this collaboration have so far been made. However Social Flow, a concept framework that extends Csikszentmihalyi’s flow theory, may help us to partially explain the triggering mechanism of collaborative mobile learning. Our case study in this article, where learners together explore a built environment as part of a simulated security guard training programme, describes how the concept of social flow in a collaborative learning space might sketch out what triggers an optimal learning experience in collaboration and what can be additionally achieved in a collaborative learning experience. In this learning context, collaborative mobile learning might be seen to prompt more knowledge generation and extra learning tasks by fostering greater motivation than other learning environments.     

Fully Distributed Nash Equilibrium Seeking for High-Order Players With Actuator Limitations

This paper explores the problem of distributed Nash equilibrium seeking in games, where players have limited knowledge on other players’ actions. In particular, the involved players are considered to be high-order integrators with their control inputs constrained within a pre-specified region. A linear transformation for players’ dynamics is firstly utilized to facilitate the design of bounded control inputs incorporating multiple saturation functions. By introducing consensus protocols with adaptive and time-varying gains, the unknown actions for players are distributively estimated. Then, a fully distributed Nash equilibrium seeking strategy is exploited, showcasing its remarkable properties: 1) ensuring the boundedness of control inputs; 2) avoiding any global information/parameters; and 3) allowing the graph to be directed. Based on Lyapunov stability analysis, it is theoretically proved that the proposed distributed control strategy can lead all the players’ actions to the Nash equilibrium. Finally, an illustrative example is given to validate effectiveness of the proposed method.      

GARUSO: a gamification approach for involving stakeholders outside organizational reach in requirements engineering

Stakeholder participation is a key success factor of Requirements Engineering (RE). Typically, the techniques used for identifying and involving stakeholders in RE assume that stakeholders can be identified among the members of the organizations involved when a software system is ordered, developed or maintained—and that these stakeholders can be told or even mandated to contribute. However, these assumptions no longer hold for many of today’s software systems where significant stakeholders (in particular, end-users and people affected by a system) are outside organizational reach: They are neither known nor can they easily be identified in the involved organizations nor can they be told to participate in RE activities. We have developed the GARUSO approach to address this problem. It uses a strategy for identifying stakeholders outside organizational reach and a social media platform that applies gamification for motivating these stakeholders to participate in RE activities. In this article, we describe the GARUSO approach and report on its empirical evaluation. We found that the identification strategy attracted a crowd of stakeholders outside organizational reach to the GARUSO platform and motivated them to participate voluntarily in collaborative RE activities. From our findings, we derived a first set of design principles on how to involve stakeholders outside organizational reach in RE. Our work expands the body of knowledge on crowd RE regarding stakeholders outside organizational reach.

     

分布式集群协同仿真研究

分布式集群协同仿真是指地域上分布、系统上异构的多个节点群为实现某一复杂的仿真目的而进行互连并进行内容级的互操作的一种复杂、大型、综合的协同仿真。其中每一个节点为一个仿真系统(或仿真器)或控制系统或服务器,多个节点互连形成为节点群构成具有明确仿真目标的综合仿真系统,井且这些节点群综合仿真系统种类多样(虚拟仿真系统、实物仿真系统、构造仿真系统等)、具有层次结构(如军事上战略仿真、战役仿真、战术仿真、装备仿真等)、地理上,“域分布(WAN或INTERNT环境)而且它们之间的连接关系较为复杂(一对一、一对多、多对一、多对多等)。该文提出了“分布式集群协同仿真”与“双时仿真”的概念与构想;研究并设计了分布式集群协同仍真的体系结构;建立了多节点分布集群协同仿真时间管理策略;构建了几类典型协间仿真系统运行控制的算法。分布式集群协同仿真由于具有分布、异构、广域、多粒、层差等特性,因此,分布式集群协同仿真研究既足一个实践课题,同时也是一个理论课题。该文的研究,主要集中在分布集群协同仿真层次的多节点复杂大系统的应刚领域,属实践课题研究。     

Construction of interaction observation systems for collaboration analysis in groupware applications

Interaction observation systems for groupware applications capture and process all the actions performed by users engaged in workgroups. These actions are then stored in log documents that enable the work process carried out by the users to be analyzed and the interaction between users to be studied. This article proposes an approach, based on ontological models, which is devised to help the developer of an observation system for a groupware application to structure and record user actions. In order to achieve this aim, we present a specific ontology that shapes the collaborative work process of the users so as to obtain an XML-based log document that stores all the actions carried out by the users and facilitates the subsequent analysis of the system usage and users’ behavior. This approach has been used to improve communication and collaboration capabilities in the COLLECE groupware application.     

SBD策略在多智能体协作中的应用研究

多智能体系统是分布式人工智能的主要学科之一。该文针对多智能体协作问题，提出了SBE)策略，并将其成功地应用于RoboCup仿真球队。SBD策略能够有效地瓦解对手有组织的协作，对于提高球队的整体对抗能力起到了明显作用。采用SBD策略的中南大学云麓队(CSU-Yunlu)，在2003年中国机器人大赛RoboCup仿真组比赛中荣获二等奖。     

Trace retrieval for business process operational support

Operational support assists users while process instances are being executed, by making predictions about the instance completion, or recommending suitable actions, resources or routing decisions, on the basis of the already completed instances, stored as execution traces in the event log.In this paper, we propose a case-based retrieval approach to business process management operational support, where log traces are exploited as cases. Once past traces have been retrieved, classical statistical techniques can be applied to them, to support prediction and recommendation. The framework enables the user to submit queries able to express complex patterns exhibited by the current process instance. Such queries can be composed by several simple patterns (i.e., single actions, or direct sequences of actions), separated by delays (i.e., actions we do not care about). Delays can also be imprecise (i.e., the number of actions can be given as a range). The tool also relies on a tree structure, adopted as an index for a quick retrieval from the available event log.Our approach is highly innovative with respect to the existing literature panorama, since it is the first work that exploits case-based retrieval techniques in the operational support context; moreover, the possibility of retrieving traces by querying complex patterns and the indexing strategy are major departures also with respect to other existing trace retrieval tools proposed in the case based reasoning area.Thanks to its characteristics and methodological solutions, the tool implements operational support tasks in a flexible and efficient way, as demonstrated by our experimental results.