A multi-agent recommender system for supporting device adaptivity in e-Commerce

Traditional recommender systems for e-Commerce support the customers’ activities providing them with useful suggestions about available products in Web stores. To this purpose, in an agent-based context, each customer is often associated with a customer agent that interacts with the site agent associated with the visited e-Commerce Web site. In presence of a high number of interactions between customers and Web sites, the generation of recommendations can be a heavy task for both these agents. Moreover, customers can navigate on the Web by using different devices having different characteristics that may influence customer’s preferences. In this paper we propose a new multi-agent system, called ARSEC, where each device exploited by a customer is associated with a device agent that autonomously monitors his/her behaviour. Furthermore, each customer is associated with a customer agent that collects in a global profile the information provided by his/her device agents and each e-Commerce Web site is associated with a seller agent. Based on the similarity existing among the global profiles the customers are partitioned in clusters, each one managed by a counsellor agent. Recommendations are generated in ARSEC as result of the collaboration between the seller agent and some counsellor agents associated with the customer. The usage of the device agents leads to generating recommendations taking into account the device currently used, while the fully decentralized architecture introduces a strong reduction of the time costs. Some experimental results are presented to show the significant advantages obtained by ARSEC in terms of recommendation effectiveness with respect to other well-known agent-based recommenders.     

Learning adaptivity in support of flipped learning: An ontological problem‐solving approach

In recent years, flipped learning has received tremendous attention from educational practitioners and researchers. However, this study argues that existing e‐learning systems mainly serve for learning management and content delivery purposes, although they lack support for flipped learning. As an innovative educational approach, flipped learning requires more pedagogical elements, such as integrated instructional design and adaptive content delivery, to achieve effective direct instruction. This study aims to create a learning adaptivity design to support effective learning in the flipped individual learning space in which the teacher is absent. Because teaching involves various pedagogical and content knowledge sources, we propose a conceptual model of teaching as a function of the knowledge triad of Guideline (G), Teaching Activity (T), and Material (M). To realize this conceptualization, an ontological problem‐solving approach is used for knowledge‐based systems development to integrate the relevant knowledge sources. The knowledge model is created using the Protégé platform to develop OWL‐based domain ontology, task ontology, and SWRL‐based semantic rules to enable inference in the GTM triad for learning adaptivity. The case illustration shows that the knowledge‐based system prototype can adaptively guide student learning in the flipped individual learning space with the knowledge sources integrated.     

Trust ontologies for e‐service environments

In this article, we introduce trust ontologies. An ontology represents a set of concepts that are commonly shared and agreed to by all parties in a particular domain. Here, we introduce generic and specific trust ontologies. These ontologies include the following: an agent trust ontology and trustworthiness; agents include sellers, service providers, Web sites, brokers, shops, suppliers, buyers, or reviewers. A services trust ontology and trustworthiness assists in measuring the quality of service that agents provide in the service‐oriented environment such as sales, orders, track and trace, warehousing, logistics, education, governance, advertising, entertainment, trading, online databases, virtual community services, security, information services, opinions, and e‐reviews. A goods or products trust ontology and trustworthiness is useful for measuring the quality of products such as commercial products, information products, entertainment products, or second‐hand products. We present a trust ontology that is suitable for all types of agents that exist in the service‐oriented environment. As agent trust is measured through the quality of goods and services, we introduce two additional distinct concepts of service trust ontology and product trust ontology. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 519–545, 2007.     

Dynamic intermittent Q‐learning–based model‐free suboptimal co‐design of ‐stabilization

This paper proposes an intermittent model‐free learning algorithm for linear time‐invariant systems, where the control policy and transmission decisions are co‐designed simultaneously while also being subjected to worst‐case disturbances. The control policy is designed by introducing an internal dynamical system to further reduce the transmission rate and provide bandwidth flexibility in cyber‐physical systems. Moreover, a Q‐learning algorithm with two actors and a single critic structure is developed to learn the optimal parameters of a Q‐function. It is shown by using an impulsive system approach that the closed‐loop system has an asymptotically stable equilibrium and that no Zeno behavior occurs. Furthermore, a qualitative performance analysis of the model‐free dynamic intermittent framework is given and shows the degree of suboptimality concerning the optimal continuous updated controller. Finally, a numerical simulation of an unknown system is carried out to highlight the efficacy of the proposed framework.     

Stop talking and type: comparing virtual and face‐to‐face mentoring in an epistemic game

Research has shown that computer games and other virtual environments can support significant learning gains because they allow young people to explore complex concepts in simulated form. However, in complex problem‐solving domains, complex thinking is learned not only by taking action, but also with the aid of mentors who provide guidance in the form of questions, instructions, advice, feedback and encouragement. In this study, we examine one context of such mentoring to understand the impact of replacing face‐to‐face interactions between mentors and students with virtual, chat‐based interactions. We use pre‐ and post‐measures of learning and a post‐measure of engagement, as well as epistemic network analysis (ENA), a novel quantitative method, to examine student and mentor discourse. Our results suggest that mentoring via online chat can be as effective as mentoring face‐to‐face in appropriately structured contexts more generally – and that ENA may be a useful tool for assessing student and mentor discourse in the context of learning interactions.     

Solvability conditions and design for synchronization of discrete‐time multiagent systems

This paper provides solvability conditions for state synchronization with homogeneous discrete‐time multiagent systems with a directed and weighted communication network under partial‐ or full‐state coupling. Our solvability conditions reveal that the synchronization problem is solvable for all possible, a priori given, set of graphs associated with a communication network only under the condition that the agents are at most weakly unstable (ie, agents have all eigenvalues in the closed unit disc). However, if an upper bound on the eigenvalues inside the unit disc of the row stochastic matrices associated with any graph in a given set of graphs is known, then one can achieve synchronization for a class of unstable agents. We provide protocol design for at most weakly unstable agents based on a direct eigenstructure assignment method and a standard H₂ discrete‐time algebraic Riccati equation. We also provide protocol design for strictly unstable agents (ie, agents have at least one eigenvalue outside the unit disc) based on the standard H₂ discrete‐time algebraic Riccati equation.     

Finite‐Time Consensus Problem for Second‐Order Multi‐Agent Systems Under Switching Topologies

This paper investigates the finite‐time consensus problem for multi‐agent systems with second‐order individual dynamics under switching topologies. A distributed continuous‐time protocol is designed to guarantee finite‐time consensus for homogeneous agents without predetermined leaders, i.e., it ensures agents asymptotically converge to an average consensus within finite time, even if the interaction topology among them is time‐varying but stepwise jointly‐connected. In particular, it introduces a distributed continuous‐time protocol to reach consensus in finite time and reduce the chattering together. Finally, the simulation results are also given to validate the proposed approach.     

Using U‐Pace instruction to improve the academic performance of economically disadvantaged undergraduates

This study was undertaken to evaluate whether the student success associated with the U‐Pace instructional approach, which integrates mastery‐based learning with proactive instructor support in an online learning environment, would replicate for both economically disadvantaged students and students who are not economically disadvantaged. Undergraduates were enrolled in U‐Pace (intervention) or comparison sections of a gateway course at two universities with different learning management systems. Course content was held constant. At both universities, intervention students earned a significantly greater percentage of objectively determined final grades of A or B. This academic success was found for both economically disadvantaged intervention students and intervention students who were not economically disadvantaged. Improvement from the beginning to the end of the semester in intervention students' rate of mastering concepts was found at University 1, but not at University 2. The assessment of learning conducted at University 1, independent of final course grades, showed that intervention students scored significantly higher on the proctored cumulative exam than comparison students. Findings suggest that the U‐Pace instructional intervention holds promise for increasing the success of undergraduates regardless of economic status.     

A NEW E‐LEARNING ACHIEVEMENT EVALUATION MODEL BASED ON ROUGH SET AND SIMILARITY FILTER

The trend of utilizing information and Internet technologies as teaching and learning tools is rapidly expanding into education. E‐learning is one of the most popular learning environments in the information era. The Internet enables students to learn without limitations of space and time. Furthermore, the learners can repeatedly review the context of a course without the barrier of distance. Recently, student‐centered instruction has become the primary trend in education, and the e‐learning system, which is considered with regard to of personalization and adaptability, is more and more popular. By means of e‐learning systems, teachers can adjust the learning schedule instantly for each learner according to a student's achievements and build more adaptive learning environments. Sometimes, teachers give biased assessments of students’ achievements under uncontrollable conditions (i.e., tiredness, preference) and are in dire need of overcoming this predicament. To solve the drawback mentioned, a new model to evaluate learning achievements based on rough set and similarity filter is proposed. The proposed model includes four facets: (1) select important features (attributes) to enhance classification performance by feature selection methods; (2) utilize minimal entropy principle approach (MEPA) to fuzzify the quantitative data; (3) select linguistic values for each feature and delete inconsistent data using the similarity threshold (similarity filter); and (4) generate rules based on rough set theory (RST). The practical e‐learning achievement data sets are collected by an e‐learning online examination system from a university in Taiwan. To verify our model, the performances of the proposed model are compared with the listing models. Results of this study demonstrate that the proposed model outperforms the listing models.     

Improving the effectiveness of English vocabulary review by integrating ARCS with mobile game‐based learning

Memorizing English vocabulary is often considered uninteresting, and a lack of motivation exists during learning activities. Moreover, most vocabulary practice systems automatically select words from articles and do not provide integrated model methods for students. Therefore, this study constructed a mobile game‐based English vocabulary practice system, which imitates the popular block elimination game and combines test items of article, difficulty, and teacher model in accordance with curriculum objectives and demands. The participants were first‐year students and classified into traditional group (Group T) and game‐based group (Group G), and learning effectiveness and motivation were analysed in this study. According to statistical analysis results, students who used the game‐based vocabulary practice system, which could captivate their attention and interest, had higher learning effectiveness and provided positive feedback of learning motivation. Furthermore, English teachers could select teaching materials that are consistent with the features, knowledge, and cultural background of learners to improve the relevance dimension of learning motivation.     

MASHA: A multi-agent system handling user and device adaptivity of Web sites

A user that navigates on the Web using different devices should be characterized by a global profile, which represents his behaviour when using all these devices. Then, the user’s profile could be usefully exploited when interacting with a site agent that is able to provide useful recommendations on the basis of the user’s interests, on one hand, and to adapt the site presentation to the device currently exploited by the user, on the other hand. However, it is not suitable to construct such a global profile by a software running on the exploited device since this device (e.g., a mobile phone or a palmtop) may have limited resources. Therefore, in this paper, we propose a multi-agent architecture, called MASHA, handling user and device adaptivity of Web sites, in which each device is provided with a client agent that autonomously collects information about the user’s behaviour associated to just that device. However, the user profile contained in this client is continuously updated with information coming from a unique server agent, associated with the user. Such information is collected by the server agent from the different devices exploited by the user, and represents a global user profile. The third component of this architecture, called adapter agent, is capable to generate a personalized representation of the Web site, containing some useful recommendations derived by both an analysis of the user profile and the suggestions coming from other users exploiting the same device.     

ADAPTIVE RANKS CLONE AND k‐NEAREST NEIGHBOR LIST–BASED IMMUNE MULTI‐OBJECTIVE OPTIMIZATION

Artificial immune systems (AIS) are computational systems inspired by the principles and processes of the vertebrate immune system. The AIS‐based algorithms typically exploit the immune system's characteristics of learning and adaptability to solve some complicated problems. Although, several AIS‐based algorithms have proposed to solve multi‐objective optimization problems (MOPs), little focus have been placed on the issues that adaptively use the online discovered solutions. Here, we proposed an adaptive selection scheme and an adaptive ranks clone scheme by the online discovered solutions in different ranks. Accordingly, the dynamic information of the online antibody population is efficiently exploited, which is beneficial to the search process. Furthermore, it has been widely approved that one‐off deletion could not obtain excellent diversity in the final population; therefore, a k‐nearest neighbor list (where k is the number of objectives) is established and maintained to eliminate the solutions in the archive population. The k‐nearest neighbors of each antibody are founded and stored in a list memory. Once an antibody with minimal product of k‐nearest neighbors is deleted, the neighborhood relations of the remaining antibodies in the list memory are updated. Finally, the proposed algorithm is tested on 10 well‐known and frequently used multi‐objective problems and two many‐objective problems with 4, 6, and 8 objectives. Compared with five other state‐of‐the‐art multi‐objective algorithms, namely NSGA‐II, SPEA2, IBEA, HYPE, and NNIA, our method achieves comparable results in terms of convergence, diversity metrics, and computational time.     

Adaptive iterative learning control for coordination of second‐order multi‐agent systems

In this paper, an efficient framework is proposed to the consensus and formation control of distributed multi‐agent systems with second‐order dynamics and unknown time‐varying parameters, by means of an adaptive iterative learning control approach. Under the assumption that the acceleration of the leader is unknown to any follower agents, a new adaptive auxiliary control and the distributed adaptive iterative learning protocols are designed. Then, all follower agents track the leader uniformly on [0,T] for consensus problem and keep the desired distance from the leader and achieve velocity consensus uniformly on [0,T] for the formation problem, respectively. The distributed multi‐agent coordinations performance is analyzed based on the Lyapunov stability theory. Finally, simulation examples are given to illustrate the effectiveness of the proposed protocols in this paper.Copyright © 2013 John Wiley & Sons, Ltd.     

A highly modular and extensible architecture for an integrated IMS‐based authoring system: the <e‐Aula> experience

The <e‐Aula> platform is a new experimental e‐learning environment that adheres closely to IMS Global Learning Consortium, Inc. e‐learning standards in order to facilitate their applicability in different learning scenarios. <e‐Aula> is equipped with an integrated modular and extensible architecture for the authoring of IMS‐compliant learning materials focused on the IMS manifest. This manifest‐driven architecture facilitates maintenance and promotes the evolution of the authoring system in <e‐Aula>, both of which are mandatory requirements in the successful production and maintenance of content for many different specialized learning domains. In this paper, we describe this authoring system, its manifest‐driven architecture and its implementation using well‐known and robust Java‐based Web technologies. Copyright © 2006 John Wiley & Sons, Ltd.     

Short answers to deep questions: supporting teachers in large‐class settings

In large class settings, individualized student–teacher interaction is difficult. However, teaching interactions (e.g., formative feedback) are central to encouraging deep approaches to learning. While there has been progress in automatic short‐answer grading, analysing student responses to support formative feedback at scale is arguably some way from being widely applied in practice. However, analysing student written responses can provide insights into student conceptions, thus directly informing teacher actions. Indeed, we argue that analysing student responses to provide feedback directly to teachers is as worthy a goal as providing individualized feedback to students and is achievable given the current state‐of‐the‐art in natural language processing. In this paper, we analyse student written responses to short‐answer questions posed in the context of a large first year health sciences course. Each question was designed to elicit deep responses. Our qualitative analysis illustrates the variability in student responses and reveals multiple relationships between these responses, course materials and the questions posed. Such information can be invaluable for teacher praxis. We conclude with a conceptual ‘dashboard’ that categorizes student responses and reveals relationships between responses, course resources and the questions. Such a dashboard could provide timely, actionable insights for teachers and help foster deep learning approaches for students.     

r‐consensus control for higher‐order multi‐agent systems with digraph

This paper studies a consensus problem for lth (l ≥ 2) order multi‐agent systems with digraph, namely, for a fixed r (0 ≤ r ≤ l ? 1), the rth derivative of the states x_i of agents are convergent to a constant value and, for every k (0 ≤ k ≤ l ? 1), are convergent to zeros. A new concept of r‐consensus is introduced and new consensus protocols are proposed for solving such an r‐consensus problem. A sufficient and necessary condition for r‐consensus is obtained. As special cases, criteria for third‐order systems are given, in which the exact relationship between feedback gains is established. Finally, an illustrative example is given to demonstrate the effectiveness of these protocols.     

Memory effects of all‐solution‐processed oxide thin‐film transistors using ZnO nanoparticles

Abstract— Non‐volatile memory effects of an all‐solution‐processed oxide thin‐film transistor (TFT) with ZnO nanoparticles (NPs) as the charge‐trapping layer are reported. The device was fabricated by using a soluble MgInZnO active channel on a ZrHfO^x gate dielectric. ZnO NPs were used as the charge‐trapping site at the gate‐insulator—channel interface, and Al was used for source and drain electrodes. Transfer characteristics of the device showed a large clockwise hysteresis, which can be used to demonstrate its memory function due to electron trapping in the ZnO NP charge‐trapping layer. This memory effect has the potential to be utilized as a memory application on displays and disposable electronics.     

High‐order internal model‐based iterative learning control design for nonlinear distributed parameter systems

This article deals with the problem of iterative learning control algorithm for a class of nonlinear parabolic distributed parameter systems (DPSs) with iteration‐varying desired trajectories. Here, the variation of the desired trajectories in the iteration domain is described by a high‐order internal model. According to the characteristics of the systems, the high‐order internal model‐based P‐type learning algorithm is constructed for such nonlinear DPSs, and furthermore, the corresponding convergence theorem of the presented algorithm is established. It is shown that the output trajectory can converge to the desired trajectory in the sense of (L²,λ) ‐norm along the iteration axis within arbitrarily small error. Finally, a simulation example is given to illustrate the effectiveness of the proposed method.     

Mean‐field games for multiagent systems with multiplicative noises

This paper studies mean‐field games for multiagent systems with control‐dependent multiplicative noises. For the general systems with nonuniform agents, we obtain a set of decentralized strategies by solving an auxiliary limiting optimal control problem subject to consistent mean‐field approximations. The set of decentralized strategies is further shown to be an ε‐Nash equilibrium. For the integrator multiagent systems, we design a set of ε‐Nash strategies by exploiting the convexity property of the limiting problem. It is shown that under the mild conditions, all the agents achieve mean‐square consensus.     

Squared‐down passivity–based state synchronization of homogeneous continuous‐time multiagent systems via static protocol in the presence of time‐varying topology

This paper studies state synchronization of homogeneous multiagent systems (MAS) via a static protocol with partial‐state coupling in the presence of a time‐varying communication topology, which includes general time‐varying graphs as well as switching graphs. If the agents are squared‐down passive or squared‐down passifiable (via static output feedback or static input feedforward), then a static protocol can be designed for balanced, time‐varying graphs. Moreover, this static protocol works for arbitrary switching directed graphs if the agents are squared‐down minimum phase with relative degree one. The static protocol is designed for each agent such that state synchronization is achieved without requiring exact knowledge about the time‐varying network.