A behavior-based scheme using reinforcement learning for autonomous underwater vehicles

This paper presents a hybrid behavior-based scheme using reinforcement learning for high-level control of autonomous underwater vehicles (AUVs). Two main features of the presented approach are hybrid behavior coordination and semi on-line neural-Q_learning (SONQL). Hybrid behavior coordination takes advantages of robustness and modularity in the competitive approach as well as efficient trajectories in the cooperative approach. SONQL, a new continuous approach of the Q_learning algorithm with a multilayer neural network is used to learn behavior state/action mapping online. Experimental results show the feasibility of the presented approach for AUVs

Adaptive intelligent agent approach to guide the web navigation on the PLAN-G distance learning platform

Hypermedia systems based on the Web for open distance education are becoming increasinglypopular as tools for user-driven access learning information. Adaptive hypermedia is a new direction in research within the area of user-adaptive systems, to increase its functionality by making it personalized [Eklu 961. This paper sketches a general agents architecture to include navigationaladaptability and user-friendly processes which would guide and accompany the student during hislher learning on the PLAN-G hypermedia system (New Generation Telematics Platform to Support Open and Distance Learning), with the aid of computer networks and specifically WWW technology [Marz 98-1] [Marz 98-2]. The PLAN-G actual prototype is successfully used with some informatics courses (the current version has no agents yet). The propased multi-agent system, contains two different types of adaptive autonomous software agents: Personal Digital Agents {Interface), to interacl directly with the student when necessary; and Information Agents (Intermediaries), to filtrate and discover information to learn and to adapt navigation space to a specific student

Engaging students in an e-learning experience : how to manage information resources through wikis and web blogs

The purpose of this paper is to describe the collaboration between librarians and scholars, from a virtual university, in order to facilitate collaborative learning on how to manage information resources. The personal information behaviour of e-learning students when managing information resources for academic, professional and daily life purposes was studied from 24 semi-structured face-to-face interviews. The results of the content analysis of the interview' transcriptions, highlighted that in the workplace and daily life contexts, competent information behaviour is always linked to a proactive attitude, that is to say, that participants seek for information without some extrinsic reward or avoiding punishment. In the academic context, it was observed a low level of information literacy and it seems to be related with a prevalent uninvolved attitude.

Adaption of Courses and Learning Environment to the User Context in dotLRN

The explosive growth of Internet during the last years has been reflected in the ever-increasing amount of the diversity and heterogeneity of user preferences, types and features of devices and access networks. Usually the heterogeneity in the context of the users which request Web contents is not taken into account by the servers that deliver them implying that these contents will not always suit their needs. In the particular case of e-learning platforms this issue is especially critical due to the fact that it puts at stake the knowledge acquired by their users. In the following paper we present a system that aims to provide the dotLRN e-learning platform with the capability to adapt to its users context. By integrating dotLRN with a multi-agent hypermedia system, online courses being undertaken by students as well as their learning environment are adapted in real time

Trajectòries d'èxit de joves immigrants a l'ensenyament superior i al món professional

L’educació dels immigrants és un tema prioritari a les agendes polítiques de molts països de la OCDE. En molts casos, els governs s’han preocupat especialment de la seva integració al món del treball però creix l’interès en els seus resultats al sistema educatiu i en la revisió de les polítiques adreçades a respondre a les seves necessitats educatives i formatives. La majoria d’aquests estudis es situen a l’esfera de l’educació infantil, primària, secundaria i formació professional, per això resulta pràcticament impossible trobar estudis que analitzin el baix percentatge d’accés d’estudiants immigrants extracomunitaris a la universitat (al voltant de 3,3% en el cas de Catalunya); que contribueixin a entendre els factors que configuren les trajectòries d’èxit escolar i d’integració laboral dels estudiants immigrants que accedeixen i completen els estudis universitaris; que puguin donar pautes per desenvolupar polítiques educatives que millorin els resultats d’aprenentatge dels estudiants immigrants; i que puguin servir com a mirall i incentiu per a altres persones immigrants i, perquè no, també del país. Aquest projecte ha estudiat el conjunt d’elements que condicionen l’accés dels joves immigrants als estudis universitaris, i a l’estatus laboral que els hauria de possibilitar la seva formació universitària. L’estudi ha consistit en una metaanàlisi dels documents existents sobre el tema i en la realització de 8 narratives biogràfiques; quatre de persones cursant diferents estudis a les universitats catalanes i quatre que ja s’han incorporat al món del professional. Aquestes narratives venen acompanyades de 8 vídeos que exploren noves maneres de visibilització d’aquesta població i es transformen en una pràctica d’autoria. Aquest material visual pot servir com a recurs educatiu, en la mida que pugui ser un mirall i un incentiu per a altres persones immigrants i del país. Finalment, presenta un seguit de recomanacions per als responsables de les polítiques i dels centres educatius.

Strong minimax lower bounds for learning

Minimax lower bounds for concept learning state, for example, thatfor each sample size $n$ and learning rule $g_n$, there exists a distributionof the observation $X$ and a concept $C$ to be learnt such that the expectederror of $g_n$ is at least a constant times $V/n$, where $V$ is the VC dimensionof the concept class. However, these bounds do not tell anything about therate of decrease of the error for a {\sl fixed} distribution--concept pair.\\In this paper we investigate minimax lower bounds in such a--stronger--sense.We show that for several natural $k$--parameter concept classes, includingthe class of linear halfspaces, the class of balls, the class of polyhedrawith a certain number of faces, and a class of neural networks, for any{\sl sequence} of learning rules $\{g_n\}$, there exists a fixed distributionof $X$ and a fixed concept $C$ such that the expected error is larger thana constant times $k/n$ for {\sl infinitely many n}. We also obtain suchstrong minimax lower bounds for the tail distribution of the probabilityof error, which extend the corresponding minimax lower bounds.

Memòria del projecte: Trajectòries d'èxit de joves immigrants a l'ensenyament superior i al món professional

[cat] L'educació dels immigrants és un tema prioritari a les agendes polítiques de molts països de la OCDE. En molts casos, els governs s'han preocupat especialment de la seva integració al món del treball però creix l'interès en els seus resultats al sistema educatiu i en la revisió de les polítiques adreçades a respondre a les seves necessitats educatives i formatives. La majoria d'aquests estudis es situen a l'esfera de l'educació infantil, primària, secundaria i formació professional, per això resulta pràcticament impossible trobar informes que analitzin el baix percentatge d'accés d'estudiants immigrants extracomunitaris a la universitat (al voltant de 3,3% en el cas de Catalunya); que contribueixin a entendre els factors que configuren les trajectòries d'èxit escolar i d'integració laboral dels estudiants immigrants que accedeixen i completen els estudis universitaris; que puguin donar pautes per desenvolupar polítiques educatives que millorin els resultats d'aprenentatge dels estudiants immigrants; i que puguin servir com a mirall i incentiu per a altres persones immigrants i, perquè no, també del país. Aquest projecte ha estudiat el conjunt d'elements que condicionen l'accés dels joves immigrants als estudis universitaris, i a l'estatus laboral que els hi hauria de possibilitar la seva formació universitària.L'estudi ha consistit en una metaanàlisi dels documents existents sobre el tema i en la realització de 8 narratives biogràfiques; quatre de persones cursant diferents estudis a les universitats catalanes i quatre que ja s'han incorporat al món del professional. Aquestes narratives venen acompanyades de 8 vídeos que exploren noves maneres de visibilització d'aquesta població i es transformen en una pràctica d'autoria. Aquest material visual pot servir com a recurs educatiu, en la mida que pugui ser un mirall i un incentiu per a altres persones immigrants i del país.Finalment, presenta un seguit de recomanacions per als responsables de les polítiques i dels centres educatius.

Cambios en el uso y la concepción de las TIC, implementando el Mobile Learning.

This research analyses the actual use and conception of the ICT mobility that a life long learning group of students have. The students have participated in a Mobile Learning experience along an online postgraduate course, which was designed under a traditional e-learning perspective. The students received a tablet PC (iPad) in order to work at the course and also to use it in their personal and professional life. A complete and original pre-test / post-test questionnaire was applied before and after the course. This instrument was scientifically validated. Thru the questionnaire, uses tendency and students perceptions were studied. Frequencies, purposes, habits of use and valuation, as well as the device"s integration into their personal, social and professional life were studied. The analysis intents to apply the 'Social Technographics Profile" by Bernoff (2010) to classify, by profile groups, the users of the actual Internet. Finally a reflexion of the reasons and limits of the theory, in this study, and also the relation to reality is presented. The Inter-coding reliability and validity shows the possibility of applying the instrument on wider samples in order to get a closer look to the uses and actual conceptions of the ubiquitous ICTs.

Neural networks complemented with genetic algorithms and fuzzy systems for predicting nitrogenous effluent variables in wastewater treatment plants

This work focuses on the prediction of the two main nitrogenous variables that describe the water quality at the effluent of a Wastewater Treatment Plant. We have developed two kind of Neural Networks architectures based on considering only one output or, in the other hand, the usual five effluent variables that define the water quality: suspended solids, biochemical organic matter, chemical organic matter, total nitrogen and total Kjedhal nitrogen. Two learning techniques based on a classical adaptative gradient and a Kalman filter have been implemented. In order to try to improve generalization and performance we have selected variables by means genetic algorithms and fuzzy systems. The training, testing and validation sets show that the final networks are able to learn enough well the simulated available data specially for the total nitrogen

Quality of Learners' Time and Learning Performance Beyond Quantitative Time-on-Task

Peer-reviewed

Extending Learning Objects by Means of Social Networking

Learning objects have been the promise of providing people with high quality learning resources. Initiatives such as MIT Open-CourseWare, MERLOT and others have shown the real possibilities of creating and sharing knowledge through Internet. Thousands of educational resources are available through learning object repositories. We indeed live in an age of content abundance, and content can be considered as infrastructure for building adaptive and personalized learning paths, promoting both formal and informal learning. Nevertheless, although most educational institutions are adopting a more open approach, publishing huge amounts of educational resources, the reality is that these resources are barely used in other educational contexts. This paradox can be partly explained by the dificulties in adapting such resources with respect to language, e-learning standards and specifications and, finally, granularity. Furthermore, if we want our learners to use and take advantage of learning object repositories, we need to provide them with additional services than just browsing and searching for resources. Social networks can be a first step towards creating an open social community of learning around a topic or a subject. In this paper we discuss and analyze the process of using a learning object repository and building a social network on the top of it, with respect to the information architecture needed to capture and store the interaction between learners and resources in form of learning object metadata.

Promoting the Creation, Share and Use of OERs through Open Repositories and Social Networks

In this paper we discuss and analyze the process of using a learning object repository and building a social network on the top of it, including aspects related to open source technologies, promoting the use of the repository by means of social networks and helping learners to develop their own learning paths.

Engaging students in an e-learning experience : how to manage information resources through wikis and web blogs

The purpose of this paper is to describe the collaboration between librarians and scholars, from a virtual university, in order to facilitate collaborative learning on how to manage information resources. The personal information behaviour of e-learning students when managing information resources for academic, professional and daily life purposes was studied from 24 semi-structured face-to-face interviews. The results of the content analysis of the interview' transcriptions, highlighted that in the workplace and daily life contexts, competent information behaviour is always linked to a proactive attitude, that is to say, that participants seek for information without some extrinsic reward or avoiding punishment. In the academic context, it was observed a low level of information literacy and it seems to be related with a prevalent uninvolved attitude.

Integrating defeasible argumentation with fuzzy ART neural networks for pattern classification

Many classification systems rely on clustering techniques in which a collection of training examples is provided as an input, and a number of clusters c1,...cm modelling some concept C results as an output, such that every cluster ci is labelled as positive or negative. Given a new, unlabelled instance enew, the above classification is used to determine to which particular cluster ci this new instance belongs. In such a setting clusters can overlap, and a new unlabelled instance can be assigned to more than one cluster with conflicting labels. In the literature, such a case is usually solved non-deterministically by making a random choice. This paper presents a novel, hybrid approach to solve this situation by combining a neural network for classification along with a defeasible argumentation framework which models preference criteria for performing clustering.

Time patterns and perceptions of online learning success factors

Online learning provides the opportunity to work on academic tasks at any time at the same time as doing other activities, such as using in web 2.0 tools. This study identifies factors that contribute to success in online learning from the students¿ perspective and their relationship with time patterns. A survey of learning outputs was used to find relationships between students¿ satisfaction, knowledge acquisition and knowledge transfer with time for working on academic tasks. In this study, 199 students from a university in Mexico completed the survey. Findings suggest that knowledge transfer has a significant association with the number of hours online per day, hours spent on social networks and the use made of e-learning during working hours. Learner satisfaction has a strong relationship with the time in years a learner has been using the Internet and the number of hours devoted to the course per week. The findings of this research will be helpful for faculty and instructional designers for implementing learning strategies.