Efficient solutions to factored MDPs with imprecise transition probabilities

When modeling real-world decision-theoretic planning problems in the Markov Decision Process (MDP) framework, it is often impossible to obtain a completely accurate estimate of transition probabilities. For example, natural uncertainty arises in the transition specification due to elicitation of MOP transition models from an expert or estimation from data, or non-stationary transition distributions arising from insufficient state knowledge. In the interest of obtaining the most robust policy under transition uncertainty, the Markov Decision Process with Imprecise Transition Probabilities (MDP-IPs) has been introduced to model such scenarios. Unfortunately, while various solution algorithms exist for MDP-IPs, they often require external calls to optimization routines and thus can be extremely time-consuming in practice. To address this deficiency, we introduce the factored MDP-IP and propose efficient dynamic programming methods to exploit its structure. Noting that the key computational bottleneck in the solution of factored MDP-IPs is the need to repeatedly solve nonlinear constrained optimization problems, we show how to target approximation techniques to drastically reduce the computational overhead of the nonlinear solver while producing bounded, approximately optimal solutions. Our results show up to two orders of magnitude speedup in comparison to traditional ""flat"" dynamic programming approaches and up to an order of magnitude speedup over the extension of factored MDP approximate value iteration techniques to MDP-IPs while producing the lowest error of any approximation algorithm evaluated. (C) 2011 Elsevier B.V. All rights reserved.

Diagnostic tools in beta regression with varying dispersion

We consider the issue of performing residual and local influence analyses in beta regression models with varying dispersion, which are useful for modelling random variables that assume values in the standard unit interval. In such models, both the mean and the dispersion depend upon independent variables. We derive the appropriate matrices for assessing local influence on the parameter estimates under different perturbation schemes. An application using real data is presented and discussed.

Framtagning av prototyp för att läsa och dokumentera kundspecifikationer

To increase the quality in their products ABB is working towards a cleared order concept. That means that all customer specified options are to be known before they start with order calculations and construction. As it is today they use paper checklists to achieve this. One order may have several reactors, and for a reactor there can be several different alternatives. For each alternative a new checklist must be filled out.As of today all reading of the customer specification and checklist fill in with is done by hand by different persons, and sometimes the same data is read more than one time. All data is also manually inserted into the calculation tools.To decrease the risk that data is left out or gets distorted they want to have a tool to aid with the reading of the specification and the documentation of that work. Already read data can be copied over to another alternative so that it not must be read one more time. The read data are to be stored in a database so that it easily can be per automation inserted into the different design tools.

Techno-economic Appraisal of Concentrating Solar Power Systems (CSP)

The diffusion of Concentrating Solar Power Systems (CSP) systems is currently taking place at a much slower pace than photovoltaic (PV) power systems. This is mainly because of the higher present cost of the solar thermal power plants, but also for the time that is needed in order to build them. Though economic attractiveness of different Concentrating technologies varies, still PV power dominates the market. The price of CSP is expected to drop significantly in the near future and wide spread installation of them will follow. The main aim of this project is the creation of different relevant case studies on solar thermal power generation and a comparison betwwen them. The purpose of this detailed comparison is the techno-economic appraisal of a number of CSP systems and the understanding of their behaviour under various boundary conditions. The CSP technologies which will be examined are the Parabolic Trough, the Molten Salt Power Tower, the Linear Fresnel Mirrors and the Dish Stirling. These systems will be appropriatly sized and simulated. All of the simulations aim in the optimization of the particular system. This includes two main issues. The first is the achievement of the lowest possible levelized cost of electricity and the second is the maximization of the annual energy output (kWh). The project also aims in the specification of these factors which affect more the results and more specifically, in what they contribute to the cost reduction or the power generation. Also, photovoltaic systems will be simulated under same boundary conditions to facolitate a comparison between the PV and the CSP systems. Last but not leats, there will be a determination of the system which performs better in each case study.

Common Features in Vector Nonlinear Time Series Models

This thesis consists of four manuscripts in the area of nonlinear time series econometrics on topics of testing, modeling and forecasting nonlinear common features. The aim of this thesis is to develop new econometric contributions for hypothesis testing and forecasting in these area. Both stationary and nonstationary time series are concerned. A definition of common features is proposed in an appropriate way to each class. Based on the definition, a vector nonlinear time series model with common features is set up for testing for common features. The proposed models are available for forecasting as well after being well specified. The first paper addresses a testing procedure on nonstationary time series. A class of nonlinear cointegration, smooth-transition (ST) cointegration, is examined. The ST cointegration nests the previously developed linear and threshold cointegration. An Ftypetest for examining the ST cointegration is derived when stationary transition variables are imposed rather than nonstationary variables. Later ones drive the test standard, while the former ones make the test nonstandard. This has important implications for empirical work. It is crucial to distinguish between the cases with stationary and nonstationary transition variables so that the correct test can be used. The second and the fourth papers develop testing approaches for stationary time series. In particular, the vector ST autoregressive (VSTAR) model is extended to allow for common nonlinear features (CNFs). These two papers propose a modeling procedure and derive tests for the presence of CNFs. Including model specification using the testing contributions above, the third paper considers forecasting with vector nonlinear time series models and extends the procedures available for univariate nonlinear models. The VSTAR model with CNFs and the ST cointegration model in the previous papers are exemplified in detail,and thereafter illustrated within two corresponding macroeconomic data sets.

Personlighetsbedömning i samband med rekrytering : En studie om bemanningsbranschens personlighetsbedömning vid en rekrytering

Att medarbetare är av existentiell betydelse för en organisations överlevnad är sedan länge känt. Därmed är rekrytering en av de viktigaste funktionerna inom HR för att attrahera rätt kompetens till organisationen då en misslyckad rekrytering vanligen leder till bortkastad tid och dyra rekryteringsprocesser. Något som kommit att få allt större betydelse vid urvalet och bedömningen av nya medarbetare är kandidaters personlighet. Forskning visar att personlighetsdrag spelar en stor roll när det kommer till framtida arbetsprestationer och förmågan att göra rätt bedömningar av människor är därför central. Teorier om synen på personlighet, kompetens, kompetensbaserad rekrytering och urval samt bedömningsmetoder och personlighetsbedömning används för att analysera studiens resultat. Denna kvalitativa studies övergripande syfte var att öka förståelsen för hur rekryterare bedömer en kandidats personlighet vid en rekryteringsprocess inom bemanningsföretag. Bemanningsföretag är företag som ständigt arbetar med rekrytering och uthyrning av personal, varför ett proaktivt bemanningsarbete krävs för att skapa en konkurrensfördel på marknaden. Inför denna fallstudie kontaktades tre av den svenska bemanningsbranschens största aktörer varav två rekryterare på vardera företag deltog i semistrukturerade intervjuer. Personlighet ansågs generellt som något viktigt som samtliga rekryterare lade stor vikt vid under hela processens gång, från utformandet av kravprofilen till avslutande bedömning. Bedömningen skedde genom såväl test som intervju och referenstagning. Samtliga poängterade vikten av att alltid göra en helhetsbedömning av kandidaten och att det därmed var svårt att vikta exempelvis formella kompetenser mot personliga egenskaper. Resultatet visar att bemanningsbranschens arbete med personlighetsbedömning vid rekrytering utgår ifrån strukturerade bedömningsmetoder. Deras gedigna och proaktiva arbete med rekrytering lever upp till påståendet om att personalen är en organisations viktigaste resurs och vikten av att förstå innebörden av personlighetens betydelse i uttrycket ”rätt person på rätt plats”.

Describing Web Service Architectures through Design-by-Contract

Architectural description languages (ADLs) are used to specify a high-level, compositional view of a software application, specifying how a system is to be composed from coarse-grain components. ADLs usually come equipped with a formal dynamic semantics, facilitating specification and analysis of distributed and event-based systems. In this paper, we describe the TrustME, an ADL framework that provides both a process and a structural view of web service-based systems. We use Petri-net descriptions to give a dynamic view of business workflow for web service collaboration. We adapt the approach of Schmidt to define a form of Meyer's design-by-contract for configuring workflow architectures. This serves as a configuration-level means of constructing safer, more robust systems.

An Architectural Description Language for Enterprise Computing

Architectural description languages (ADLs) are used to specify high-level, compositional view of a software application. ADLs usually come equipped with a rigourous state-transition style semantics, facilitating specification and analysis of distributed and event-based systems. However, enterprise system architectures built upon newer middleware (implementations of Java’s EJB specification, or Microsoft’s COM+/ .NET) require additional expressive power from an ADL. The TrustME ADL is designed to meet this need. In this paper, we describe several aspects of TrustME that facilitate specification and anlysis of middleware-based architectures for the enterprise.

Trust-By-Contract: Modelling, Analysing and Predicting Behaviour in Software Architectures

Architecture description languages (ADLs) are used to specify high-level, compositional views of a software application. ADL research focuses on software composed of prefabricated parts, so-called software components. ADLs usually come equipped with rigorous state-transition style semantics, facilitating verification and analysis of specifications. Consequently, ADLs are well suited to configuring distributed and event-based systems. However, additional expressive power is required for the description of enterprise software architectures – in particular, those built upon newer middleware, such as implementations of Java’s EJB specification, or Microsoft’s COM+/.NET. The enterprise requires distributed software solutions that are scalable, business-oriented and mission-critical. We can make progress toward attaining these qualities at various stages of the software development process. In particular, progress at the architectural level can be leveraged through use of an ADL that incorporates trust and dependability analysis. Also, current industry approaches to enterprise development do not address several important architectural design issues. The TrustME ADL is designed to meet these requirements, through combining approaches to software architecture specification with rigorous design-by-contract ideas. In this paper, we focus on several aspects of TrustME that facilitate specification and analysis of middleware-based architectures for trusted enterprise computing systems.

A Compositional Semantics of UML-RSDS

This paper provides a semantics for the UML-RSDS (Reactive System Development Support) subset of UML, using the real-time action logic (RAL) formalism. We show how this semantics can be used to resolve some ambiguities and omissions in UML semantics, and to support reasoning about specifications using the B formal method and tools. We use `semantic profiles' to provide precise semantics for different semantic variation points of UML. We also show how RAL can be used to give a semantics to notations for real-time specification in UML. Unlike other approaches to UML semantics, which concentrate on the class diagram notation, our semantic representation has behaviour as a central element, and can be used to define semantics for use cases, state machines and interactions, in addition to class diagrams.

Towards Qualitative Approaches to Bayesian Evidential Reasoning

A crucial aspect of evidential reasoning in crime investigation involves comparing the support that evidence provides for alternative hypotheses. Recent work in forensic statistics has shown how Bayesian Networks (BNs) can be employed for this purpose. However, the specification of BNs requires conditional probability tables describing the uncertain processes under evaluation. When these processes are poorly understood, it is necessary to rely on subjective probabilities provided by experts. Accurate probabilities of this type are normally hard to acquire from experts. Recent work in qualitative reasoning has developed methods to perform probabilistic reasoning using coarser representations. However, the latter types of approaches are too imprecise to compare the likelihood of alternative hypotheses. This paper examines this shortcoming of the qualitative approaches when applied to the aforementioned problem, and identifies and integrates techniques to refine them.

On Qualitative Probabilities for Legal Reasoning about Evidence

A crucial aspect of evidential reasoning in crime investigation involves comparing the support that evidence provides for alternative hypotheses. Recent work in forensic statistics has shown how Bayesian Networks (BNs) can be employed for this purpose. However, the specification of BNs requires conditional probability tables describing the uncertain processes under evaluation. When these processes are poorly understood, it is necessary to rely on subjective probabilities provided by experts. Accurate probabilities of this type are normally hard to acquire from experts. Recent work in qualitative reasoning has developed methods to perform probabilistic reasoning using coarser representations. However, the latter types of approaches are too imprecise to compare the likelihood of alternative hypotheses. This paper examines this shortcoming of the qualitative approaches when applied to the aforementioned problem, and identifies and integrates techniques to refine them.

Reasoning about Requirements Evolution Using Clustered Belief Revision

During the development of system requirements, software system specifications are often inconsistent. Inconsistencies may arise for different reasons, for example, when multiple conflicting viewpoints are embodied in the specification, or when the specification itself is at a transient stage of evolution. These inconsistencies cannot always be resolved immediately. As a result, we argue that a formal framework for the analysis of evolving specifications should be able to tolerate inconsistency by allowing reasoning in the presence of inconsistency without trivialisation, and circumvent inconsistency by enabling impact analyses of potential changes to be carried out. This paper shows how clustered belief revision can help in this process. Clustered belief revision allows for the grouping of requirements with similar functionality into clusters and the assignment of priorities between them. By analysing the result of a cluster, an engineer can either choose to rectify problems in the specification or to postpone the changes until more information becomes available.

From SMART to agent systems development

n order for agent-oriented software engineering to prove effective it must use principled notions of agents and enabling specification and reasoning, while still considering routes to practical implementation. This paper deals with the issue of individual agent specification and construction, departing from the conceptual basis provided by the smart agent framework. smart offers a descriptive specification of an agent architecture but omits consideration of issues relating to construction and control. In response, we introduce two new views to complement smart: a behavioural specification and a structural specification which, together, determine the components that make up an agent, and how they operate. In this way, we move from abstract agent system specification to practical implementation. These three aspects are combined to create an agent construction model, actsmart, which is then used to define the AgentSpeak(L) architecture in order to illustrate the application of actsmart.

QoS-aware model driven architecture through the UML and CIM

The specification of Quality of Service (QoS) constraints over software design requires measures that ensure such requirements are met by the delivered product. Achieving this goal is non-trivial, as it involves, at least, identifying how QoS constraint specifications should be checked at the runtime. In this paper we present an implementation of a Model Driven Architecture (MDA) based framework for the runtime monitoring of QoS properties. We incorporate the UML2 superstructure and the UML profile for Quality of Service to provide abstract descriptions of component-and-connector systems. We then define transformations that refine the UML2 models to conform with the Distributed Management Taskforce (DMTF) Common Information Model (CIM) (Distributed Management Task Force Inc. 2006), a schema standard for management and instrumentation of hardware and software. Finally, we provide a mapping the CIM metamodel to a .NET-based metamodel for implementation of the monitoring infrastructure utilising various .NET features including the Windows Management Instrumentation (WMI) interface.