Predicting and interpreting identification errors in military vehicle training using multidimensional scaling

We compared methods for predicting and understanding the source of confusion errors during military vehicle identification training. Participants completed training to identify main battle tanks. They also completed card-sorting and similarity-rating tasks to express their mental representation of resemblance across the set of training items. We expected participants to selectively attend to a subset of vehicle features during these tasks, and we hypothesised that we could predict identification confusion errors based on the outcomes of the card-sort and similarity-rating tasks. Based on card-sorting results, we were able to predict about 45% of observed identification confusions. Based on multidimensional scaling of the similarity-rating data, we could predict more than 80% of identification confusions. These methods also enabled us to infer the dimensions receiving significant attention from each participant. This understanding of mental representation may be crucial in creating personalised training that directs attention to features that are critical for accurate identification.

Practitioner Summary: Participants completed military vehicle identification training and testing, along with card-sorting and similarity-rating tasks. The data enabled us to predict up to 84% of identification confusion errors and to understand the mental representation underlying these errors. These methods have potential to improve training and reduce identification errors leading to fratricide.     

An intelligent negotiator agent design for bilateral contracts of electrical energy

In this paper, an intelligent agent (using the Fuzzy SARSA learning approach) is proposed to negotiate for bilateral contracts (BC) of electrical energy in Block Forward Markets (BFM or similar market environments). In the BFM energy markets, the buyers (or loads) and the sellers (or generators) submit their bids and offers on a daily basis. The loads and generators could employ intelligent software agents to trade energy in BC markets on their behalves. Since each agent attempts to choose the best bid/offer in the market, conflict of interests might happen. In this work, the trading of energy in BC markets is modeled and solved using Game Theory and Reinforcement Learning (RL) approaches. The Stackelberg equation concept is used for the match making among load and generator agents. Then to overcome the negotiation limited time problems (it is assumed that a limited time is given to each generator–load pairs to negotiate and make an agreement), a Fuzzy SARSA Learning (FSL) method is used. The fuzzy feature of FSL helps the agent cope with continuous characteristics of the environment and also prevents it from the curse of dimensionality. The performance of the FSL (compared to other well-known traditional negotiation techniques, such as time-dependent and imitative techniques) is illustrated through simulation studies. The case study simulation results show that the FSL based agent could achieve more profits compared to the agents using other reviewed techniques in the BC energy market.     

单向通信拓扑领航者动态未知线性多智能体系统的协同迭代学习控制（英文）

This paper considers the cooperative tracking of linear multi-agent systems with a dynamic leader whose input information is unavailable to any followers. Cooperative iterative learning controllers, based on the relative state information of neighboring agents, are proposed for tracking the dynamic leader over directed communication topologies. Stability and convergence of the proposed controllers are established using Lyapunov-Krasovskii functionals. Furthermore, this result is extended to the output feedback case where only the output information of each agent can be obtained. A local observer is constructed to estimate the unmeasurable states. Then, cooperative iterative learning controllers, based on the relative observed states of neighboring agents,are devised. For both cases, it is shown that the multi-agent systems whose communication topologies contain a spanning tree can reach synchronization with the dynamic leader, and meanwhile identify the unknown input of the dynamic leader using distributed iterative learning laws. An illustrative example is provided to verify the proposed control schemes.     

A dynamic analysis of the interplay between asynchronous and synchronous communication in online learning: The impact of motivation

With the increased affordances of synchronous communication tools, more opportunities for online learning to resemble face‐to‐face settings have recently become available. However, synchronous communication does not afford as much time for reflection as asynchronous communication. Therefore, a combination of synchronous and asynchronous communication in e‐learning would seem desirable to optimally support learner engagement and the quality of student learning. It is still an open question though, how to best design online learning with a blend of synchronous and asynchronous communication opportunities over time. Few studies have investigated the relationship between learners' actual use of synchronous and asynchronous communication over time. Therefore, this study addressed that relationship in an online course (N = 110), taking into account student motivation, and employing a dynamic inter‐temporal perspective. In line with our assumptions, we found some support for the expected association between autonomous motivation and engagement in asynchronous and synchronous communication, be it restricted primarily to the first course period. Also, positive relations between engagement in synchronous and asynchronous communication were found, with the strongest influence from using asynchronous to synchronous communication. This study adds to the knowledge base needed to develop guidelines on how synchronous communication can be combined with asynchronous learning.     

Self‐regulation during e‐learning: using behavioural evidence from navigation log files

The current paper examined the relationship between perceived characteristics of the learning environment in an e‐module in relation to test performance among a group of e‐learners. Using structural equation modelling, the relationship between these variables is further explored in terms of the proposed double mediation as outlined by Ning and Downing. These authors initially proposed that motivation and self‐regulation strategies are mediators between the perception of the learning environment and performance. In our replication and extension study, we substituted self‐reported self‐regulation with behavioural indicators of self‐regulation using navigation log files and focused on test‐taking rather than general motivation. We proposed that navigational patterns captured using log files can also help deduce self‐regulation in e‐modules and provide information in the absence of self‐reports. Path analyses provide partial support for our navigational hypotheses and the model. Implications of our results for the use of e‐module data and conclusions based on navigation are discussed.     

Exploring teachers' perceptions on different CSCL script editing tools

Despite the apparent maturity of the learning design field, and the variety of tooling available to support it, adoption among the teacher community (one of its alleged main targets) is still low. There is a lack of research on teachers' perception and use of different technological learning design tools, as existing evaluations are often restricted to a single tool. In order to explore whether there are common factors hampering teacher adoption, and which tool features might appeal to different teachers, more studies involving multiple authoring tools are needed. This paper provides a first step in this direction, describing a mixed methods study performed around a professional development workshop with 18 university teachers from multiple disciplines. This workshop exposed teachers to two different authoring tools (WebCollage and EDIT2), as they learned to create computer-supported collaborative learning (CSCL) designs and implement them. The findings of our interpretive study (which included questionnaires, observations, or group discussion recordings) support the idea that there is no single tool or set of features that are globally perceived as better, although our evidence also highlights certain factors as important for participant teachers – amongst others, the integration of learning designs with the ICT platforms for enactment, as well as with other tools that they already use in their everyday practice.     

Effects of prior knowledge on learning from different compositions of representations in a mobile learning environment

Two experiments examined the effects of prior knowledge on learning from different compositions of multiple representations in a mobile learning environment on plant leaf morphology for primary school students. Experiment 1 compared the learning effects of a mobile learning environment presenting text and photos of plants on a tablet PC, either in combination with or without real plants in the physical environment. Results indicated that there were no interactions between prior knowledge and experimental condition. Students who learned with tablet PCs only outperformed students who additionally learned with real plants on a comprehension and an application test. In addition, high prior knowledge students outperformed low prior knowledge students on both tests. To investigate whether these effects were caused by the specific characteristics of the combination of photos of real plants and real plants, Experiment 2 compared the differential effects of prior knowledge on learning with the combination of texts, photos and real plants to a combination in which the photos were replaced by schematic hand drawings. Results indicated that both low and high prior knowledge students, who learned with the combination of texts, schematic hand drawings and real plants performed better on a comprehension and an application test. High prior knowledge students performed better on both tests. It is concluded that the number and type of representations used is critical for the effectiveness of mobile learning environments.     

An exact algorithm with learning for the graph coloring problem

Given an undirected graph G=(V,E), the Graph Coloring Problem (GCP) consists in assigning a color to each vertex of the graph G in such a way that any two adjacent vertices are assigned different colors, and the number of different colors used is minimized. State-of-the-art algorithms generally deal with the explicit constraints in GCP: any two adjacent vertices should be assigned different colors, but do not specially deal with the implicit constraints between non-adjacent vertices implied by the explicit constraints. In this paper, we propose an exact algorithm with learning for GCP which exploits the implicit constraints using propositional logic. Our algorithm is compared with several exact algorithms among the best in the literature. The experimental results show that our algorithm outperforms other algorithms on many instances. Specifically, our algorithm allows to close the open DIMACS instance 4-Fullins_5.     

Direct measures of digital information processing and communication skills in primary education: Using item response theory for the development and validation of an ICT competence scale

In the past decade, several studies have measured ICT competences from the perspective of ICT self-efficacy. Such indirect measurements tend to have validity problems, as they depend on the pupils' ability to judge their own ICT competences. This study outlines the development of a performance-based digital test and the validation of a direct measure of ICT competence through the use of item response theory (IRT). More specifically, the test and the developed measure focus on primary-school pupils' proficiency in digital information processing and communication. 56 Items were administered to 560 pupils at the end of their primary-school education (age between 10.79 and 13.85 years old). The items were controlled for dimensionality, model-data fit, local item dependence and monotonicity. The final measure contains 27 items that refer to retrieving and processing digital information, and communication with a computer. The results indicate that the instrument is particularly reliable for low and median ability levels. Further refinement and possible future use of the instrument is discussed.