Self-optimization for dynamic scheduling in manufacturing systems

Scheduling is a critical function that is present throughout many industries and applications. A great need exists for developing scheduling approaches that can be applied to a number of different scheduling problems with significant impact on performance of business organizations. A challenge is emerging in the design of scheduling support systems for manufacturing environments where dynamic adaptation and optimization become increasingly important. In this paper, we describe a Self-Optimizing Mechanism for Scheduling System through Nature Inspired Optimization Techniques (NIT).

Case-based reasoning for meta-heuristics self-parameterization in a multi-agent scheduling system

A novel agent-based approach to Meta-Heuristics self-configuration is proposed in this work. Meta-heuristics are examples of algorithms where parameters need to be set up as efficient as possible in order to unsure its performance. This paper presents a learning module for self-parameterization of Meta-heuristics (MHs) in a Multi-Agent System (MAS) for resolution of scheduling problems. The learning is based on Case-based Reasoning (CBR) and two different integration approaches are proposed. A computational study is made for comparing the two CBR integration perspectives. In the end, some conclusions are reached and future work outlined.

Self-organization for scheduling in agile manufacturing

Agility refers to the manufacturing system ability to rapidly adapt to market and environmental changes in efficient and cost-effective ways. This paper addresses the development of self-organization methods to enhance the operations of a scheduling system, by integrating scheduling system, configuration and optimization into a single autonomic process requiring minimal manual intervention to increase productivity and effectiveness while minimizing complexity for users. We intend to conceptualize real manufacturing systems as interacting autonomous entities in order to build future Decision Support Systems (DSS) for Scheduling in agile manufacturing environments.

Case-based reasoning for self-optimizing behavior

In this paper we present a Self-Optimizing module, inspired on Autonomic Computing, acquiring a scheduling system with the ability to automatically select a Meta-heuristic to use in the optimization process, so as its parameterization. Case-based Reasoning was used so the system may be able of learning from the acquired experience, in the resolution of similar problems. From the obtained results we conclude about the benefit of its use.

Adaptation model for PCMAT – Mathematics collaborative learning platform

The aim of this paper is to present an adaptation model for an Adaptive Educational Hypermedia System, PCMAT. The adaptation of the application is based on progressive self-assessment (exercises, tasks, and so on) and applies the constructivist learning theory and the learning styles theory. Our objective is the creation of a better, more adequate adaptation model that takes into account the complexities of different users.

Automatic learning for the classification of chemical reactions and in statistical thermodynamics

This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds. NMR-based classification of photochemical and enzymatic reactions. Photochemical and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen SOMs) and Random Forests (RFs) taking as input the difference between the 1H NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data. A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases was able to correctly classify 75% of an independent test set in terms of the EC number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used. This study was performed with NMR data simulated from the molecular structure by the SPINUS program. In the design of one test set, simulated data was combined with experimental data. The results support the proposal of linking databases of chemical reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions. Genome-scale classification of enzymatic reactions from their reaction equation. The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken, changed, and made during a chemical reaction. The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods should be available to automatically compare metabolic reactions and for the automatic assignment of EC numbers to reactions still not officially classified. In this study, the genome-scale data set of enzymatic reactions available in the KEGG database was encoded by the MOLMAP descriptors, and was submitted to Kohonen SOMs to compare the resulting map with the official EC number classification, to explore the possibility of predicting EC numbers from the reaction equation, and to assess the internal consistency of the EC classification at the class level. A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions. RFs were also used to assign the four levels of the EC hierarchy from the reaction equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases (for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively. In the course of the experiments with metabolic reactions we suggested that the MOLMAP / SOM concept could be extended to the representation of other levels of metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different types of metabolism and pathways that do not share similarities in terms of EC numbers. Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function. The results indicated that for LJ-type potentials, NNs can be trained to generate accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown. The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo, the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes. Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task. The data consisted of energy values, from Density Functional Theory (DFT) calculations, at different distances, for several molecular orientations and three electrode adsorption sites. The results indicate that NNs require a data set large enough to cover well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions. Therefore, they can be used in molecular simulations, particularly for the ethanol/Au (111) interface which is the case studied in the present Thesis. Once properly trained, the networks are able to produce, as output, any required number of energy points for accurate interpolations.

Meta-heuristics self-parameterization in a multi-agent scheduling system using case-based reasoning

This paper proposes a novel agent-based approach to Meta-Heuristics self-configuration. Meta-heuristics are algorithms with parameters which need to be set up as efficient as possible in order to unsure its performance. A learning module for self-parameterization of Meta-heuristics (MH) in a Multi-Agent System (MAS) for resolution of scheduling problems is proposed in this work. The learning module is based on Case-based Reasoning (CBR) and two different integration approaches are proposed. A computational study is made for comparing the two CBR integration perspectives. Finally, some conclusions are reached and future work outlined.

Criação de clusters de clientes de um banco através do self-organizing maps hierárquico: comparação entre HSOM e SOM

Trabalho de Projeto apresentado como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

Machine learning Gaussian short rate

Dissertação para obtenção do Grau de Doutor em Estatística e Gestão do Risco

Learning domain-specific sentiment lexicons with applications to recommender systems

Search is now going beyond looking for factual information, and people wish to search for the opinions of others to help them in their own decision-making. Sentiment expressions or opinion expressions are used by users to express their opinion and embody important pieces of information, particularly in online commerce. The main problem that the present dissertation addresses is how to model text to find meaningful words that express a sentiment. In this context, I investigate the viability of automatically generating a sentiment lexicon for opinion retrieval and sentiment classification applications. For this research objective we propose to capture sentiment words that are derived from online users’ reviews. In this approach, we tackle a major challenge in sentiment analysis which is the detection of words that express subjective preference and domain-specific sentiment words such as jargon. To this aim we present a fully generative method that automatically learns a domain-specific lexicon and is fully independent of external sources. Sentiment lexicons can be applied in a broad set of applications, however popular recommendation algorithms have somehow been disconnected from sentiment analysis. Therefore, we present a study that explores the viability of applying sentiment analysis techniques to infer ratings in a recommendation algorithm. Furthermore, entities’ reputation is intrinsically associated with sentiment words that have a positive or negative relation with those entities. Hence, is provided a study that observes the viability of using a domain-specific lexicon to compute entities reputation. Finally, a recommendation system algorithm is improved with the use of sentiment-based ratings and entities reputation.

Peer interaction and learning opportunities in cohesive and less cohesive L2 classrooms

The present study investigates peer to peer oral interaction in two task based language teaching classrooms, one of which was a self-declared cohesive group, and the other a self- declared less cohesive group, both at B1 level. It studies how learners talk cohesion into being and considers how this talk leads to learning opportunities in these groups. The study was classroom-based and was carried out over the period of an academic year. Research was conducted in the classrooms and the tasks were part of regular class work. The research was framed within a sociocognitive perspective of second language learning and data came from a number of sources, namely questionnaires, interviews and audio recorded talk of dyads, triads and groups of four students completing a total of eight oral tasks. These audio recordings were transcribed and analysed qualitatively for interactions which encouraged a positive social dimension and behaviours which led to learning opportunities, using conversation analysis. In addition, recordings were analysed quantitatively for learning opportunities and quantity and quality of language produced. Results show that learners in both classes exhibited multiple behaviours in interaction which could promote a positive social dimension, although behaviours which could discourage positive affect amongst group members were also found. Analysis of interactions also revealed the many ways in which learners in both the cohesive and less cohesive class created learning opportunities. Further qualitative analysis of these interactions showed that a number of factors including how learners approach a task, the decisions they make at zones of interactional transition and the affective relationship between participants influence the amount of learning opportunities created, as well as the quality and quantity of language produced. The main conclusion of the study is that it is not the cohesive nature of the group as a whole but the nature of the relationship between the individual members of the small group completing the task which influences the effectiveness of oral interaction for learning.This study contributes to our understanding of the way in which learners individualise the learning space and highlights the situated nature of language learning. It shows how individuals interact with each other and the task, and how talk in interaction changes moment-by-moment as learners react to the ‘here and now’ of the classroom environment.

Um modelo para a gestão do conhecimento organizacional no contexto dos serviços partilhados com recurso à utilização do e-Learning

Tese de Doutoramento em Tecnologias e Sistemas de Informação

Learning joint representations for order and timing of perceptual-motor sequences: a dynamic neural field approach

Many of our everyday tasks require the control of the serial order and the timing of component actions. Using the dynamic neural field (DNF) framework, we address the learning of representations that support the performance of precisely time action sequences. In continuation of previous modeling work and robotics implementations, we ask specifically the question how feedback about executed actions might be used by the learning system to fine tune a joint memory representation of the ordinal and the temporal structure which has been initially acquired by observation. The perceptual memory is represented by a self-stabilized, multi-bump activity pattern of neurons encoding instances of a sensory event (e.g., color, position or pitch) which guides sequence learning. The strength of the population representation of each event is a function of elapsed time since sequence onset. We propose and test in simulations a simple learning rule that detects a mismatch between the expected and realized timing of events and adapts the activation strengths in order to compensate for the movement time needed to achieve the desired effect. The simulation results show that the effector-specific memory representation can be robustly recalled. We discuss the impact of the fast, activation-based learning that the DNF framework provides for robotics applications.

Aprendizaje durante la ontogenia temprana: Estudio de la participación del sistema opioide en la modulación de aprendizajes mediados por el etanol. LEARNING AND EARLY ONTOGENY: ANALYSIS OF THE INVOLVEMENT OF OPIOID SYSTEM IN FETAL AND INFANTILE ETHANOL-MEDIATED EXPERIENCIES.

Este plan de trabajos es continuidad de una línea de investigación centrada en evaluar los mecanismos responsables de la adquisición, expresión y persistencia de experiencias con el etanol. A partir de ello, indagar acerca de los efectos de esta experiencia sobre comportamientos de búsqueda y autoadministración de etanol en neonatos e infantes de rata. Se pretende analizar la participación del sistema opiáceo en los mecanismos implicados en una memoria fetal y/o infantil, generada como consecuencia de la exposición etílica. En una primera etapa, nos proponemos establecer de qué manera experiencias prenatales con la droga modulan el patrón de auto-administración de alcohol y otros reforzadores, como sacarosa. En este primer bloque de experimentos realizaremos manipulaciones fetales para determinar con mayor grado de especificidad la posible acción del sistema opiáceo en los mecanismos de adquisición de una memoria etílica prenatal. Se realizarán administraciones de etanol y el antagonista opiáceo, directamente a nivel fetal, y se evaluará esta experiencia en un paradigma de condicionamiento neonatal positivo, mediado por la droga. De acuerdo a la evidencia previa, esperamos que la exposición prenatal con la droga facilite la expresión de conductas de consumo y búsqueda del etanol o hacia las claves que señalizan al psicotrópico, tanto durante la infancia como en el neonato. A su vez, cuando la droga es presentada bajo los efectos de un antagonista opiáceo esperamos que estas conductas muestren un perfil similar a las desplegadas por sujetos controles. El segundo bloque de experimentos ha sido ideado con el objeto de indagar acerca de la posible participación del sistema opiáceo en la modulación de los aspectos reforzantes de la droga, a través de un esquema de auto-administración etílica infantil. Se utilizará un paradigma de condicionamiento instrumental adaptado para ratas infantes que consta de dos instancias, una de adquisición de la conducta instrumental (DPs 14-17) en la cual los animales reciben un pulso de refuerzo, como consecuencia de la ejecución de la conducta operante. En una segunda fase se analiza el patrón de búsqueda del reforzador ya que se registra la respuesta instrumental, sin que ocurra el refuerzo por la misma. Para analizar la participación del sistema opiáceo, durante la fase de adquisición de la conducta operante (DPs 16 y 17) los animales serán re-expuestos a mínimas cantidades del reforzador, bajo los efectos de un antagonista opiáceo, momentos previos al ensayo instrumental correspondiente para cada uno de estos días (Exp. 3). Esperamos que el bloqueo del sistema opiáceo, durante esta re-exposición al etanol, sea suficiente para disminuir el patrón de respuesta instrumental hacia el refuerzo etílico. Un último experimento incorporará un tercer evento de re-exposición al etanol -bajo los efectos del antagonista- previo al ensayo de extinción de la conducta instrumental (DP 18). Este nuevo evento tiene por objeto analizar la participación de este sistema neurobiológico en los mecanismos de búsqueda de etanol. Si el sistema opiáceo participa en la modulación de patrones tanto de búsqueda como consumatorios del reforzamiento por etanol, se espera que la re-exposición a la droga bajo los efectos del antagonista, inhiba estas respuestas tanto durante la sesión de adquisición, como de extinción de la conducta operante. Este proyecto intenta profundizar en el conocimiento de los mecanismos que regulan reconocimiento, aceptación, búsqueda y consumo de etanol, como consecuencia de experiencias tempranas con la droga. A su vez, es importante identificar y estudiar los sistemas neurobiológicos involucrados en estos mecanismos. Es por ello que se intenta determinar el rol que ejerce el sistema opiáceo en la adquisición de estas experiencias etílicas a nivel fetal e infantil, que se conoce promueven la búsqueda y el consumo de la droga. Our work is directed to analyze the involvement of the opioid system in the generation of pre- and early postnatal ethanol-related memories. As a first step, maternal manipulations with ethanol will be done. Infants will be evaluated in a paradigm of infantile self-administration of different reinforcers (ethanol, sucrose or water), employing a model of operant conditioning adapted to infant rats. A second experiment will be conducted in order to analyze if a central administration of ethanol, directly to the fetus, modifies subsequent patterns of neonatal conditioned responses to an artificial nipple, mediated by ethanol reinforcing effects. Fetal presentation of ethanol will be accompanied with the injection of an opioid antagonist in order to analyze the involvement of this system in acquisition processes of a fetal ethanol-mediated memory. A second set of studies will be conducted to analyze appetitive and consummatory behaviors in an infant model of ethanol self-administration. Involvement of opioid system in the acquisition or expression of this experience will be also inquired. Infant rats (PDs14-17) have to display a target behavior (nose-poke) to gain access to 5% sucrose or 3.75% ethanol. On PD18 an extinction session will be included. At PDs16-17, 6-hr before training, pups will be re-exposed to ethanol under opioid antagonism effects (naloxone). In a follow up experiment, a re-exposure trial will be included at PD18. Prior extinction, pups will receive naloxone and will be re-exposed to ethanol. We aim to observe if opioid system is modulating etha¬nol reinforcing effects, in terms of both appetitive and consummatory behaviors.

Baysian Model Averaging, Learning and Model Selection

Agents have two forecasting models, one consistent with the unique rational expectations equilibrium, another that assumes a time-varying parameter structure. When agents use Bayesian updating to choose between models in a self-referential system, we find that learning dynamics lead to selection of one of the two models. However, there are parameter regions for which the non-rational forecasting model is selected in the long-run. A key structural parameter governing outcomes measures the degree of expectations feedback in Muth's model of price determination.