EDUCA: A web 2.0 authoring tool for developing adaptive and intelligent tutoring systems using a Kohonen network

This paper presents a Web 2.0 Learning Environment, for a systematic creation of adaptive and intelligent tutoring systems. Authoring contents is made by a community of users including teachers and students. The tutoring systems adapt the contents according to the best learning style using self-organizing maps (SOMs). The SOM was trained for classifying Felder–Silverman learning styles. The most important advantage of these unsupervised neural networks is that they do not require an external teacher for presenting a training set. The approach was implemented under an authoring tool that allows the production of personalized learning material to be used under collaborative and mobile learning environments. The tutoring systems together with the neural network can also be exported to mobile devices. We present different results to the approach working under the authoring tool.     

A fuzzy model to evaluate the suitability of installing an enterprise resource planning system

The use of enterprise resource planning (ERP) as a foundation for the integration of the complete range of business processes and functions, is clearly useful and economically profitable in most very large organizations which manage a great deal of data in their information systems. However, the decision of installing an ERP system in all the companies is not always so clear, it will depend on the size, future profits and other features of the company. Therefore, different parameters (features, aspects) will be evaluated to make a decision about the suitability of the ERP system. These parameters might have different nature or the knowledge about them could be vague or imprecise. Thus, this implies that it would be suitable that the evaluation process can manage heterogeneous information. In this paper we shall present a fuzzy evaluation model to evaluate the suitability of an ERP system based on a multi-expert decision-making (ME-DM) process that is able to deal with heterogeneous information.     

Air management in a diesel engine using fuzzy control techniques

Air management for diesel engines is a major challenge from the control point of view because of the highly nonlinear behavior of this system. For this reason, linear control techniques are unable to provide the required performance, and nonlinear controllers are used instead. This article discusses two fundamental steps when designing a control system. Firstly, a methodology to identify Takagi–Sugeno (T–S) structures using experimental data is proposed. Secondly, the design of a fuzzy controller in PDC structure (Parallel Distributed Compensation) is presented. The parameters of this controller are obtained from a LMI (Linear Matrix Inequalities) minimization problem.     

MOE prediction in Abies pinsapo Boiss. timber: Application of an artificial neural network using non-destructive testing

Determining the modulus of elasticity of wood by applying an artificial neural network using the physical properties and non-destructive testing can be a useful method in assessments of the timber structure in old constructions. The modulus of elasticity of Abies pinsapo Boiss. timber was predicted in this study through the parameters of density, width, thickness, moisture content, ultrasonic wave propagation velocity and visual grading of the test pieces. A feedforward multilayer perceptron network was designed for this purpose, achieving 75.0% success in the testing or unknown group.     

A study on the use of statistical tests for experimentation with neural networks: Analysis of parametric test conditions and non-parametric tests

In this paper, we focus on the experimental analysis on the performance in artificial neural networks with the use of statistical tests on the classification task. Particularly, we have studied whether the sample of results from multiple trials obtained by conventional artificial neural networks and support vector machines checks the necessary conditions for being analyzed through parametrical tests. The study is conducted by considering three possibilities on classification experiments: random variation in the selection of test data, the selection of training data and internal randomness in the learning algorithm.The results obtained state that the fulfillment of these conditions are problem-dependent and indefinite, which justifies the need of using non-parametric statistics in the experimental analysis.     

Boosting k-nearest neighbor classifier by means of input space projection

The k-nearest neighbors classifier is one of the most widely used methods of classification due to several interesting features, such as good generalization and easy implementation. Although simple, it is usually able to match, and even beat, more sophisticated and complex methods. However, no successful method has been reported so far to apply boosting to k-NN. As boosting methods have proved very effective in improving the generalization capabilities of many classification algorithms, proposing an appropriate application of boosting to k-nearest neighbors is of great interest.Ensemble methods rely on the instability of the classifiers to improve their performance, as k-NN is fairly stable with respect to resampling, these methods fail in their attempt to improve the performance of k-NN classifier. On the other hand, k-NN is very sensitive to input selection. In this way, ensembles based on subspace methods are able to improve the performance of single k-NN classifiers. In this paper we make use of the sensitivity of k-NN to input space for developing two methods for boosting k-NN. The two approaches modify the view of the data that each classifier receives so that the accurate classification of difficult instances is favored.The two approaches are compared with the classifier alone and bagging and random subspace methods with a marked and significant improvement of the generalization error. The comparison is performed using a large test set of 45 problems from the UCI Machine Learning Repository. A further study on noise tolerance shows that the proposed methods are less affected by class label noise than the standard methods.     

Multi-objective Swarm Intelligence schedulers for online scientific Clouds

Cloud Computing is a promising paradigm for parallel computing. However, as Cloud-based services become more dynamic, resource provisioning in Clouds becomes more challenging. The paradigm, with its promise of virtually infinite resources, seems to suit well in solving resource greedy scientific computing problems. In a Cloud, an appropriate number of Virtual Machines (VM) is created and allocated in physical resources for executing jobs. This work focuses on the Infrastructure as a Service (IaaS) model where custom VMs are launched in appropriate hosts available in a Cloud to execute scientific experiments coming from multiple users. Finding optimal solutions to allocate VMs to physical resources is an NP-complete problem, and therefore many heuristics have been developed. In this work, we describe and evaluate two Cloud schedulers based on Swarm Intelligence (SI) techniques, particularly Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). The main performance metrics to study are the number of serviced users by the Cloud and the total number of created VMs in online (non-batch) scheduling scenarios. We also perform a sensitivity analysis by varying the specific-parameter values of each algorithm to evaluate the impact on the performance of the two objective metrics. The intra-Cloud network traffic is also measured. Simulated experiments performed using CloudSim and job data from real scientific problems show that the use of SI-based techniques succeeds in balancing the studied metrics compared to Genetic Algorithms.     

Resilient overlay network for real-time interactive multimedia sessions in corporate networks

Real-time interactive multimedia communications are becoming increasingly useful for education, business, e-commerce and e-government, providing an enriched user experience in teleconferencing, e-meetings, distance training and product demonstrations. Large corporations are usually located at several sites, so real-time multipoint sessions within corporations are especially difficult. IP multicast is available or feasible within each site of an organization. Thus, corporate networks can be considered as various multicast-capable networks interconnected through a wide area network without multicast connectivity. This paper proposes a resilient self-managed overlay network to support real-time multipoint interactive sessions within corporate networks. The proposed overlay takes advantage of the configuration of corporate networks to self-organize and provide an efficient media delivery service, making use of multicast communications wherever available. Various self-healing techniques are implemented allowing for the continuity of ongoing sessions in spite of network disruptions and entity failures. Extensive simulations and tests have been carried out to assess the performance and resilience of the overlay facing several types of disruptions.     

Online classifier adaptation for cost-sensitive learning

In this paper, we propose the problem of online cost-sensitive classifier adaptation and the first algorithm to solve it. We assume that we have a base classifier for a cost-sensitive classification problem, but it is trained with respect to a cost setting different to the desired one. Moreover, we also have some training data samples streaming to the algorithm one by one. The problem is to adapt the given base classifier to the desired cost setting using the steaming training samples online. To solve this problem, we propose to learn a new classifier by adding an adaptation function to the base classifier, and update the adaptation function parameter according to the streaming data samples. Given an input data sample and the cost of misclassifying it, we update the adaptation function parameter by minimizing cost-weighted hinge loss and respecting previous learned parameter simultaneously. The proposed algorithm is compared to both online and off-line cost-sensitive algorithms on two cost-sensitive classification problems, and the experiments show that it not only outperforms them on classification performances, but also requires significantly less running time.

     

A novel model for arc territory design: promoting Eulerian districts

The problem of district design for the implementation of arc routing activities is addressed. The aim is to partition a road network into a given number of sectors to facilitate the organization of the operations to be implemented within the region. This problem arises in numerous applications such as postal delivery, meter readings, winter gritting, road maintenance, and municipal solid waste collection. An integer linear programming model is proposed where a novel set of node parity constraints to favor Eulerian districts is introduced. Series of instances were solved to assess the impact of these parity constraints on the objective function and deadhead distance. Networks with up to 401 nodes and 764 edges were successfully solved. The model is useful at a tactical level as it can be used to promote workload balance, compactness, deadhead distance reduction and parity in districts.