A multi-output two-stage locally regularized model construction method using the extreme learning machine

This paper investigates the construction of linear-in-the-parameters (LITP) models for multi-output regression problems. Most existing stepwise forward algorithms choose the regressor terms one by one, each time maximizing the model error reduction ratio. The drawback is that such procedures cannot guarantee a sparse model, especially under highly noisy learning conditions. The main objective of this paper is to improve the sparsity and generalization capability of a model for multi-output regression problems, while reducing the computational complexity. This is achieved by proposing a novel multi-output two-stage locally regularized model construction (MTLRMC) method using the extreme learning machine (ELM). In this new algorithm, the nonlinear parameters in each term, such as the width of the Gaussian function and the power of a polynomial term, are firstly determined by the ELM. An initial multi-output LITP model is then generated according to the termination criteria in the first stage. The significance of each selected regressor is checked and the insignificant ones are replaced at the second stage. The proposed method can produce an optimized compact model by using the regularized parameters. Further, to reduce the computational complexity, a proper regression context is used to allow fast implementation of the proposed method. Simulation results confirm the effectiveness of the proposed technique. © 2013 Elsevier B.V.

Agent-Based Modeling of Deshopping Behaviour: A Single Shop Model with Multiple Deshoppers

Deshopping is rapidly turning into a modern day scourge for the retailers worldwide due to its prevalence and regularity. The presence of flexible return policies have made retail return management a real challenging issue for both the present and the future. In this study, we propose and develop a multi-agent simulation model for deshopper behavior in a single shop context. The background, theoretical underpinning, logical and computational model, experiment design and simulation results are reported and discussed in the paper.

Information Exchange and Fusion in Dynamic and Heterogeneous Distributed Environments

Context awareness, dynamic reconfiguration at runtime and heterogeneity are key characteristics of future distributed systems, particularly in ubiquitous and mobile computing scenarios. The main contributions of this dissertation are theoretical as well as architectural concepts facilitating information exchange and fusion in heterogeneous and dynamic distributed environments. Our main focus is on bridging the heterogeneity issues and, at the same time, considering uncertain, imprecise and unreliable sensor information in information fusion and reasoning approaches. A domain ontology is used to establish a common vocabulary for the exchanged information. We thereby explicitly support different representations for the same kind of information and provide Inter-Representation Operations that convert between them. Special account is taken of the conversion of associated meta-data that express uncertainty and impreciseness. The Unscented Transformation, for example, is applied to propagate Gaussian normal distributions across highly non-linear Inter-Representation Operations. Uncertain sensor information is fused using the Dempster-Shafer Theory of Evidence as it allows explicit modelling of partial and complete ignorance. We also show how to incorporate the Dempster-Shafer Theory of Evidence into probabilistic reasoning schemes such as Hidden Markov Models in order to be able to consider the uncertainty of sensor information when deriving high-level information from low-level data. For all these concepts we provide architectural support as a guideline for developers of innovative information exchange and fusion infrastructures that are particularly targeted at heterogeneous dynamic environments. Two case studies serve as proof of concept. The first case study focuses on heterogeneous autonomous robots that have to spontaneously form a cooperative team in order to achieve a common goal. The second case study is concerned with an approach for user activity recognition which serves as baseline for a context-aware adaptive application. Both case studies demonstrate the viability and strengths of the proposed solution and emphasize that the Dempster-Shafer Theory of Evidence should be preferred to pure probability theory in applications involving non-linear Inter-Representation Operations.

The prediction of seasonal and inter-annual climate variations and their impacts on the water resources in the eastern seaboard of Thailand

The research of this thesis dissertation covers developments and applications of short-and long-term climate predictions. The short-term prediction emphasizes monthly and seasonal climate, i.e. forecasting from up to the next month over a season to up to a year or so. The long-term predictions pertain to the analysis of inter-annual- and decadal climate variations over the whole 21st century. These two climate prediction methods are validated and applied in the study area, namely, Khlong Yai (KY) water basin located in the eastern seaboard of Thailand which is a major industrial zone of the country and which has been suffering from severe drought and water shortage in recent years. Since water resources are essential for the further industrial development in this region, a thorough analysis of the potential climate change with its subsequent impact on the water supply in the area is at the heart of this thesis research. The short-term forecast of the next-season climate, such as temperatures and rainfall, offers a potential general guideline for water management and reservoir operation. To that avail, statistical models based on autoregressive techniques, i.e., AR-, ARIMA- and ARIMAex-, which includes additional external regressors, and multiple linear regression- (MLR) models, are developed and applied in the study region. Teleconnections between ocean states and the local climate are investigated and used as extra external predictors in the ARIMAex- and the MLR-model and shown to enhance the accuracy of the short-term predictions significantly. However, as the ocean state – local climate teleconnective relationships provide only a one- to four-month ahead lead time, the ocean state indices can support only a one-season-ahead forecast. Hence, GCM- climate predictors are also suggested as an additional predictor-set for a more reliable and somewhat longer short-term forecast. For the preparation of “pre-warning” information for up-coming possible future climate change with potential adverse hydrological impacts in the study region, the long-term climate prediction methodology is applied. The latter is based on the downscaling of climate predictions from several single- and multi-domain GCMs, using the two well-known downscaling methods SDSM and LARS-WG and a newly developed MLR-downscaling technique that allows the incorporation of a multitude of monthly or daily climate predictors from one- or several (multi-domain) parent GCMs. The numerous downscaling experiments indicate that the MLR- method is more accurate than SDSM and LARS-WG in predicting the recent past 20th-century (1971-2000) long-term monthly climate in the region. The MLR-model is, consequently, then employed to downscale 21st-century GCM- climate predictions under SRES-scenarios A1B, A2 and B1. However, since the hydrological watershed model requires daily-scale climate input data, a new stochastic daily climate generator is developed to rescale monthly observed or predicted climate series to daily series, while adhering to the statistical and geospatial distributional attributes of observed (past) daily climate series in the calibration phase. Employing this daily climate generator, 30 realizations of future daily climate series from downscaled monthly GCM-climate predictor sets are produced and used as input in the SWAT- distributed watershed model, to simulate future streamflow and other hydrological water budget components in the study region in a multi-realization manner. In addition to a general examination of the future changes of the hydrological regime in the KY-basin, potential future changes of the water budgets of three main reservoirs in the basin are analysed, as these are a major source of water supply in the study region. The results of the long-term 21st-century downscaled climate predictions provide evidence that, compared with the past 20th-reference period, the future climate in the study area will be more extreme, particularly, for SRES A1B. Thus, the temperatures will be higher and exhibit larger fluctuations. Although the future intensity of the rainfall is nearly constant, its spatial distribution across the region is partially changing. There is further evidence that the sequential rainfall occurrence will be decreased, so that short periods of high intensities will be followed by longer dry spells. This change in the sequential rainfall pattern will also lead to seasonal reductions of the streamflow and seasonal changes (decreases) of the water storage in the reservoirs. In any case, these predicted future climate changes with their hydrological impacts should encourage water planner and policy makers to develop adaptation strategies to properly handle the future water supply in this area, following the guidelines suggested in this study.

Capturing temporality and intentionality in information systems

Information modelling is a topic that has been researched a great deal, but still many questions around it have not been solved. An information model is essential in the design of a database which is the core of an information system. Currently most of databases only deal with information that represents facts, or asserted information. The ability of capturing semantic aspect has to be improved, and yet other types, such as temporal and intentional information, should be considered. Semantic Analysis, a method of information modelling, has offered a way to handle various aspects of information. It employs the domain knowledge and communication acts as sources of information modelling. It lends itself to a uniform structure whereby semantic, temporal and intentional information can be captured, which builds a sound foundation for building a semantic temporal database.

Multi-agent model for robotic assembly system

In this paper, a multi-agent based model for a robotic assembly system is presented. Firstly, an organization model is used to construct the multi-agent model. Secondly, a dynamic self-organizing method is then put forward for the multi-agent robotic system to bid and contract the operations. Thirdly, a real multi-agent robotic system is built and assembly experiments are carried out. Finally, the experimental results confirm that the present multi-agent robotic system has flexibility, adaptation and stability.

Using information flow model to specify the Kanban-controlled shopfloor control system

The implementation of Kanban-based production control systems may be difficult in make-to-order environments such as job shops. The flexible manufacturing approach constitutes a promising solution to adapt the Kanban method to such environments. This paper presents an information flow modelling approach for specifying the operational planning and control functions of the Kanban-controlled shopfloor control system (KSCS) in a flexible manufacturing environment. By decomposing the KSCS control functionalities, we have created the system information flow model through the data flow diagrams of Structured Systems Analysis Methodology. The data flow diagrams serve effective system specifications for communicating the system operations to participants of different disciplines as well as the system model for the design and development of KSCS.

A maturity model of enterprise business intelligence

The implementation of an enterprise-level business intelligence initiative is a large-scale and complex undertaking, involving significant expenditure and multiple stakeholders over a lengthy period. It is therefore imperative to have systematic guidelines for business intelligence stakeholders in referring business intelligence maturity levels. Draw upon the prudent concepts of the Capability Maturity Model, this research proposes a multi-dimensional maturity model with distinct maturity levels for managing enterprise business intelligence initiatives. The maturity model, named Enterprise Business Intelligence Maturiy (EBIM), consists of five core maturity levels and four key dimensions, namely information quality, master data management, warehousing architecture, and analytics. It can be used to assist enterprises in benchmarking their business intelligence maturity level and identifying the critical areas to attain higher level of maturity.

Collaborating differently on different topics: a multi-relational approach to multi-task learning

Multi-task learning offers a way to benefit from synergy of multiple related prediction tasks via their joint modeling. Current multi-task techniques model related tasks jointly, assuming that the tasks share the same relationship across features uniformly. This assumption is seldom true as tasks may be related across some features but not others. Addressing this problem, we propose a new multi-task learning model that learns separate task relationships along different features. This added flexibility allows our model to have a finer and differential level of control in joint modeling of tasks along different features. We formulate the model as an optimization problem and provide an efficient, iterative solution. We illustrate the behavior of the proposed model using a synthetic dataset where we induce varied feature-dependent task relationships: positive relationship, negative relationship, no relationship. Using four real datasets, we evaluate the effectiveness of the proposed model for many multi-task regression and classification problems, and demonstrate its superiority over other state-of-the-art multi-task learning models

A new transfer learning framework with application to model-agnostic multi-task learning

Learning from small number of examples is a challenging problem in machine learning. An effective way to improve the performance is through exploiting knowledge from other related tasks. Multi-task learning (MTL) is one such useful paradigm that aims to improve the performance through jointly modeling multiple related tasks. Although there exist numerous classification or regression models in machine learning literature, most of the MTL models are built around ridge or logistic regression. There exist some limited works, which propose multi-task extension of techniques such as support vector machine, Gaussian processes. However, all these MTL models are tied to specific classification or regression algorithms and there is no single MTL algorithm that can be used at a meta level for any given learning algorithm. Addressing this problem, we propose a generic, model-agnostic joint modeling framework that can take any classification or regression algorithm of a practitioner’s choice (standard or custom-built) and build its MTL variant. The key observation that drives our framework is that due to small number of examples, the estimates of task parameters are usually poor, and we show that this leads to an under-estimation of task relatedness between any two tasks with high probability. We derive an algorithm that brings the tasks closer to their true relatedness by improving the estimates of task parameters. This is achieved by appropriate sharing of data across tasks. We provide the detail theoretical underpinning of the algorithm. Through our experiments with both synthetic and real datasets, we demonstrate that the multi-task variants of several classifiers/regressors (logistic regression, support vector machine, K-nearest neighbor, Random Forest, ridge regression, support vector regression) convincingly outperform their single-task counterparts. We also show that the proposed model performs comparable or better than many state-of-the-art MTL and transfer learning baselines.

Computational methods for the analysis of protein structure and function

The vast majority of known proteins have not yet been experimentally characterized and little is known about their function. The design and implementation of computational tools can provide insight into the function of proteins based on their sequence, their structure, their evolutionary history and their association with other proteins. Knowledge of the three-dimensional (3D) structure of a protein can lead to a deep understanding of its mode of action and interaction, but currently the structures of <1% of sequences have been experimentally solved. For this reason, it became urgent to develop new methods that are able to computationally extract relevant information from protein sequence and structure. The starting point of my work has been the study of the properties of contacts between protein residues, since they constrain protein folding and characterize different protein structures. Prediction of residue contacts in proteins is an interesting problem whose solution may be useful in protein folding recognition and de novo design. The prediction of these contacts requires the study of the protein inter-residue distances related to the specific type of amino acid pair that are encoded in the so-called contact map. An interesting new way of analyzing those structures came out when network studies were introduced, with pivotal papers demonstrating that protein contact networks also exhibit small-world behavior. In order to highlight constraints for the prediction of protein contact maps and for applications in the field of protein structure prediction and/or reconstruction from experimentally determined contact maps, I studied to which extent the characteristic path length and clustering coefficient of the protein contacts network are values that reveal characteristic features of protein contact maps. Provided that residue contacts are known for a protein sequence, the major features of its 3D structure could be deduced by combining this knowledge with correctly predicted motifs of secondary structure. In the second part of my work I focused on a particular protein structural motif, the coiled-coil, known to mediate a variety of fundamental biological interactions. Coiled-coils are found in a variety of structural forms and in a wide range of proteins including, for example, small units such as leucine zippers that drive the dimerization of many transcription factors or more complex structures such as the family of viral proteins responsible for virus-host membrane fusion. The coiled-coil structural motif is estimated to account for 5-10% of the protein sequences in the various genomes. Given their biological importance, in my work I introduced a Hidden Markov Model (HMM) that exploits the evolutionary information derived from multiple sequence alignments, to predict coiled-coil regions and to discriminate coiled-coil sequences. The results indicate that the new HMM outperforms all the existing programs and can be adopted for the coiled-coil prediction and for large-scale genome annotation. Genome annotation is a key issue in modern computational biology, being the starting point towards the understanding of the complex processes involved in biological networks. The rapid growth in the number of protein sequences and structures available poses new fundamental problems that still deserve an interpretation. Nevertheless, these data are at the basis of the design of new strategies for tackling problems such as the prediction of protein structure and function. Experimental determination of the functions of all these proteins would be a hugely time-consuming and costly task and, in most instances, has not been carried out. As an example, currently, approximately only 20% of annotated proteins in the Homo sapiens genome have been experimentally characterized. A commonly adopted procedure for annotating protein sequences relies on the "inheritance through homology" based on the notion that similar sequences share similar functions and structures. This procedure consists in the assignment of sequences to a specific group of functionally related sequences which had been grouped through clustering techniques. The clustering procedure is based on suitable similarity rules, since predicting protein structure and function from sequence largely depends on the value of sequence identity. However, additional levels of complexity are due to multi-domain proteins, to proteins that share common domains but that do not necessarily share the same function, to the finding that different combinations of shared domains can lead to different biological roles. In the last part of this study I developed and validate a system that contributes to sequence annotation by taking advantage of a validated transfer through inheritance procedure of the molecular functions and of the structural templates. After a cross-genome comparison with the BLAST program, clusters were built on the basis of two stringent constraints on sequence identity and coverage of the alignment. The adopted measure explicity answers to the problem of multi-domain proteins annotation and allows a fine grain division of the whole set of proteomes used, that ensures cluster homogeneity in terms of sequence length. A high level of coverage of structure templates on the length of protein sequences within clusters ensures that multi-domain proteins when present can be templates for sequences of similar length. This annotation procedure includes the possibility of reliably transferring statistically validated functions and structures to sequences considering information available in the present data bases of molecular functions and structures.

Sicurezza di rete, analisi del traffico e monitoraggio.

Il lavoro è stato suddiviso in tre macro-aree. Una prima riguardante un'analisi teorica di come funzionano le intrusioni, di quali software vengono utilizzati per compierle, e di come proteggersi (usando i dispositivi che in termine generico si possono riconoscere come i firewall). Una seconda macro-area che analizza un'intrusione avvenuta dall'esterno verso dei server sensibili di una rete LAN. Questa analisi viene condotta sui file catturati dalle due interfacce di rete configurate in modalità promiscua su una sonda presente nella LAN. Le interfacce sono due per potersi interfacciare a due segmenti di LAN aventi due maschere di sotto-rete differenti. L'attacco viene analizzato mediante vari software. Si può infatti definire una terza parte del lavoro, la parte dove vengono analizzati i file catturati dalle due interfacce con i software che prima si occupano di analizzare i dati di contenuto completo, come Wireshark, poi dei software che si occupano di analizzare i dati di sessione che sono stati trattati con Argus, e infine i dati di tipo statistico che sono stati trattati con Ntop. Il penultimo capitolo, quello prima delle conclusioni, invece tratta l'installazione di Nagios, e la sua configurazione per il monitoraggio attraverso plugin dello spazio di disco rimanente su una macchina agent remota, e sui servizi MySql e DNS. Ovviamente Nagios può essere configurato per monitorare ogni tipo di servizio offerto sulla rete.

High-Speed Laser Processing of Thin Single and Multi-Layer Films

Theoretical models are developed for the continuous-wave and pulsed laser incision and cut of thin single and multi-layer films. A one-dimensional steady-state model establishes the theoretical foundations of the problem by combining a power-balance integral with heat flow in the direction of laser motion. In this approach, classical modelling methods for laser processing are extended by introducing multi-layer optical absorption and thermal properties. The calculation domain is consequently divided in correspondence with the progressive removal of individual layers. A second, time-domain numerical model for the short-pulse laser ablation of metals accounts for changes in optical and thermal properties during a single laser pulse. With sufficient fluence, the target surface is heated towards its critical temperature and homogeneous boiling or "phase explosion" takes place. Improvements are seen over previous works with the more accurate calculation of optical absorption and shielding of the incident beam by the ablation products. A third, general time-domain numerical laser processing model combines ablation depth and energy absorption data from the short-pulse model with two-dimensional heat flow in an arbitrary multi-layer structure. Layer removal is the result of both progressive short-pulse ablation and classical vaporisation due to long-term heating of the sample. At low velocity, pulsed laser exposure of multi-layer films comprising aluminium-plastic and aluminium-paper are found to be characterised by short-pulse ablation of the metallic layer and vaporisation or degradation of the others due to thermal conduction from the former. At high velocity, all layers of the two films are ultimately removed by vaporisation or degradation as the average beam power is increased to achieve a complete cut. The transition velocity between the two characteristic removal types is shown to be a function of the pulse repetition rate. An experimental investigation validates the simulation results and provides new laser processing data for some typical packaging materials.

A Model-Based Monitoring Architecture for Heterogeneous Enterprise Services and Information Systems

Runtime management of distributed information systems is a complex and costly activity. One of the main challenges that must be addressed is obtaining a complete and updated view of all the managed runtime resources. This article presents a monitoring architecture for heterogeneous and distributed information systems. It is composed of two elements: an information model and an agent infrastructure. The model negates the complexity and variability of these systems and enables the abstraction over non-relevant details. The infrastructure uses this information model to monitor and manage the modeled environment, performing and detecting changes in execution time. The agents infrastructure is further detailed and its components and the relationships between them are explained. Moreover, the proposal is validated through a set of agents that instrument the JEE Glassfish application server, paying special attention to support distributed configuration scenarios.