Les réseaux de télécommunication doivent être fiables et robustes pour garantir la haute disponibilité des services. Les opérateurs cherchent actuellement à automatiser autant que possible les opérations complexes de gestion des réseaux, telles que le diagnostic de pannes.Dans cette thèse nous nous sommes intéressés au diagnostic automatique de pannes dans les réseaux d'accès optiques de l'opérateur Orange. L'outil de diagnostic utilisé jusqu'à présent, nommé DELC, est un système expert à base de règles de décision. Ce système est performant mais difficile à maintenir en raison, en particulier, du très grand volume d'informations à analyser. Il est également impossible de disposer d'une règle pour chaque configuration possible de panne, de sorte que certaines pannes ne sont actuellement pas diagnostiquées.Dans cette thèse nous avons proposé une nouvelle approche. Dans notre approche, le diagnostic des causes racines des anomalies et alarmes observées s'appuie sur une modélisation probabiliste, de type réseau bayésien, des relations de dépendance entre les différentes alarmes, compteurs, pannes intermédiaires et causes racines au niveau des différents équipements de réseau. Ce modèle probabiliste a été conçu de manière modulaire, de façon à pouvoir évoluer en cas de modification de l'architecture physique du réseau.Le diagnostic des causes racines des anomalies est effectué par inférence, dans le réseau bayésien, de l'état des noeuds non observés au vu des observations (compteurs, alarmes intermédiaires, etc...) récoltées sur le réseau de l'opérateur. La structure du réseau bayésien, ainsi que l'ordre de grandeur des paramètres probabilistes de ce modèle, ont été déterminés en intégrant dans le modèle les connaissances des experts spécialistes du diagnostic sur ce segment de réseau. L'analyse de milliers de cas de diagnostic de pannes a ensuite permis de calibrer finement les paramètres probabilistes du modèle grâce à un algorithme EM (Expectation Maximization).Les performances de l'outil développé, nommé PANDA, ont été évaluées sur deux mois de diagnostic de panne dans le réseau GPON-FTTH d'Orange en juillet-août 2015. Dans la plupart des cas, le nouveau système, PANDA, et le système en production, DELC, font un diagnostic identique. Cependant un certain nombre de cas sont non diagnostiqués par DELC mais ils sont correctement diagnostiqués par PANDA. Les cas pour lesquels les deux systèmes émettent des diagnostics différents ont été évalués manuellement, ce qui a permis de démontrer dans chacun de ces cas la pertinence des décisions prises par PANDA. / Telecommunication networks must be reliable and robust to ensure high availability of services. Operators are currently searching to automate as much as possible, complex network management operations such as fault diagnosis.In this thesis we are focused on self-diagnosis of failures in the optical access networks of the operator Orange. The diagnostic tool used up to now, called DELC, is an expert system based on decision rules. This system is efficient but difficult to maintain due in particular to the very large volume of information to analyze. It is also impossible to have a rule for each possible fault configuration, so that some faults are currently not diagnosed.We proposed in this thesis a new approach. In our approach, the diagnosis of the root causes of malfunctions and alarms is based on a Bayesian network probabilistic model of dependency relationships between the different alarms, counters, intermediate faults and root causes at the level of the various network component. This probabilistic model has been designed in a modular way, so as to be able to evolve in case of modification of the physical architecture of the network. Self-diagnosis of the root causes of malfunctions and alarms is made by inference in the Bayesian network model of the state of the nodes not observed in view of observations (counters, alarms, etc.) collected on the operator's network. The structure of the Bayesian network, as well as the order of magnitude of the probabilistic parameters of this model, were determined by integrating in the model the expert knowledge of the diagnostic experts on this segment of the network. The analysis of thousands of cases of fault diagnosis allowed to fine-tune the probabilistic parameters of the model thanks to an Expectation Maximization algorithm. The performance of the developed probabilistic tool, named PANDA, was evaluated over two months of fault diagnosis in Orange's GPON-FTTH network in July-August 2015. In most cases, the new system, PANDA, and the system in production, DELC, make an identical diagnosis. However, a number of cases are not diagnosed by DELC but are correctly diagnosed by PANDA. The cases for which self-diagnosis results of the two systems are different were evaluated manually, which made it possible to demonstrate in each of these cases the relevance of the decisions taken by PANDA.

This thesis proposes and discusses a statistical model for interpreting forensic DNA mixtures. We develop methods for estimation of model parameters and assessing the uncertainty of the estimated quantities. Further, we discuss how to interpret the mixture in terms of predicting the set of contributors. We emphasise the importance of challenging any interpretation of a particular mixture, and for this purpose we develop a set of diagnostic tools that can be used in assessing the adequacy of the model to the data at hand as well as in a systematic validation of the model on experimental data. An important feature of this work is that all methodology is developed entirely within the framework of the adopted model, ensuring a transparent and consistent analysis. To overcome the challenge that lies in handling the large state space for DNA profiles, we propose a representation of a genotype that exhibits a Markov structure. Further, we develop methods for efficient and exact computation in a Bayesian network. An implementation of the model and methodology is available through the R package DNAmixtures.

This paper concerns about key business process in the production companies, namely, the new product development. The object of this thesis has been to create a tool to estimate the risk of the new product development. To reach this goal, current tools used to deciding the risk must have been explored. As the best tool, appropriate for assessing the risk of new product development has proved the Bayesian Network. This paper explains the construction of the Bayesian network and shows the way how to generate the probabilities in the network to be accurate for the risk estimation. Based on this theoretical knowledge has been built an information system, which estimates the risk of the new products and administer the risks.

No description available.

Dans un réseau bayésien, une observation sur une variable signifie en général que cette variable est instanciée. Ceci signifie que l’observateur peut affirmer avec certitude que la variable est dans l’état signalé. Cette thèse porte sur d’autres types d’observations, souvent appelées observations incertaines, qui ne peuvent pas être représentées par la simple affectation de la variable. Cette thèse clarifie et étudie les différents concepts d’observations incertaines et propose différentes applications des observations incertaines dans les réseaux bayésiens.Nous commençons par dresser un état des lieux sur les observations incertaines dans les réseaux bayésiens dans la littérature et dans les logiciels, en termes de terminologie, de définition, de spécification et de propagation. Il en ressort que le vocabulaire n'est pas clairement établi et que les définitions proposées couvrent parfois des notions différentes.Nous identifions trois types d’observations incertaines dans les réseaux bayésiens et nous proposons la terminologie suivante : observation de vraisemblance, observation probabiliste fixe et observation probabiliste non-fixe. Nous exposons ensuite la façon dont ces observations peuvent être traitées et propagées.Enfin, nous donnons plusieurs exemples d’utilisation des observations probabilistes fixes dans les réseaux bayésiens. Le premier exemple concerne la propagation d'observations sur une sous-population, appliquée aux systèmes d'information géographique. Le second exemple concerne une organisation de plusieurs agents équipés d'un réseau bayésien local et qui doivent collaborer pour résoudre un problème. Le troisième exemple concerne la prise en compte d'observations sur des variables continues dans un RB discret. Pour cela, l'algorithme BN-IPFP-1 a été implémenté et utilisé sur des données médicales de l'hôpital Bourguiba de Sfax. / In a Bayesian network, evidence on a variable usually signifies that this variable is instantiated, meaning that the observer can affirm with certainty that the variable is in the signaled state. This thesis focuses on other types of evidence, often called uncertain evidence, which cannot be represented by the simple assignment of the variables. This thesis clarifies and studies different concepts of uncertain evidence in a Bayesian network and offers various applications of uncertain evidence in Bayesian networks.Firstly, we present a review of uncertain evidence in Bayesian networks in terms of terminology, definition, specification and propagation. It shows that the vocabulary is not clear and that some terms are used to represent different concepts.We identify three types of uncertain evidence in Bayesian networks and we propose the followingterminology: likelihood evidence, fixed probabilistic evidence and not-fixed probabilistic evidence. We define them and describe updating algorithms for the propagation of uncertain evidence. Finally, we propose several examples of the use of fixed probabilistic evidence in Bayesian networks. The first example concerns evidence on a subpopulation applied in the context of a geographical information system. The second example is an organization of agent encapsulated Bayesian networks that have to collaborate together to solve a problem. The third example concerns the transformation of evidence on continuous variables into fixed probabilistic evidence. The algorithm BN-IPFP-1 has been implemented and used on medical data from CHU Habib Bourguiba in Sfax.

Gescannte und vektorisierte technische Zeichnungen werden automatisch unter Nutzung eines Netzes von Modellen in eine hochwertige Datenstruktur migriert. Die Modelle beschreiben die Inhalte der Zeichnungen hierarchisch und deklarativ. Modelle für einzelne Bestandteile der Zeichnungen können paarweise unabhängig entwickelt werden. Dadurch werden auch sehr komplexe Zeichnungsklassen wie Elektroleitungsnetze oder Gebäudepläne zugänglich. Die Modelle verwendet der neue, sogenannte Y-Algorithmus: Hypothesen über die Deutung lokaler Zeichnungsinhalte werden hierarchisch generiert. Treten bei der Nutzung konkurrierender Modelle Konflikte auf, werden diese protokolliert. Mittels des Konfliktbegriffes können konsistente Interpretationen einer kompletten Zeichnung abstrakt definiert und während der Analyse einer konkreten Zeichnung bestimmt werden. Ein wahrscheinlichkeitsbasiertes Gütemaß bewertet jede dieser alternativen, globalen Interpretationen. Das Suchen einer bzgl. dieses Maßes optimalen Interpretation ist ein NP-hartes Problem. Ein Branch and Bound-Algorithmus stellt die adäquate Lösung dar.

This thesis tackles the problem of predicting the collision risk for vehicles driving in complex traffic scenes for a few seconds into the future. The method is based on previous research using dynamic Bayesian networks to represent the state of the system. Common risk prediction methods are often categorized into three different groups depending on their abstraction level. The most complex of these are interaction-aware models which take driver interactions into account. These models often suffer from high computational complexity which is a key limitation in practical use. The model studied in this work takes interactions between drivers into account by considering driver intentions and the traffic rules in the scene. The state of the traffic scene used in the model contains the physical state of vehicles, the intentions of drivers and the expected behaviour of drivers according to the traffic rules. To allow for real-time risk assessment, an approximate inference of the state given the noisy sensor measurements is done using sequential importance resampling. Two different measures of risk are studied. The first is based on driver intentions not matching the expected maneuver, which in turn could lead to a dangerous situation. The second measure is based on a trajectory prediction step and uses the two measures time to collision (TTC) and time to critical collision probability (TTCCP). The implemented model can be applied in complex traffic scenarios with numerous participants. In this work, we focus on intersection and roundabout scenarios. The model is tested on simulated and real data from these scenarios. %Simulations of these scenarios is used to test the model. In these qualitative tests, the model was able to correctly identify collisions a few seconds before they occur and is also able to avoid false positives by detecting the vehicles that will give way. / Detta arbete behandlar problemet att förutsäga kollisionsrisken för fordon som kör i komplexa trafikscenarier för några sekunder i framtiden. Metoden är baserad på tidigare forskning där dynamiska Bayesianska nätverk används för att representera systemets tillstånd. Vanliga riskprognosmetoder kategoriseras ofta i tre olika grupper beroende på deras abstraktionsnivå. De mest komplexa av dessa är interaktionsmedvetna modeller som tar hänsyn till förarnas interaktioner. Dessa modeller lider ofta av hög beräkningskomplexitet, vilket är en svår begränsning när det kommer till praktisk användning. Modellen som studeras i detta arbete tar hänsyn till interaktioner mellan förare genom att beakta förarnas avsikter och trafikreglerna i scenen. Tillståndet i trafikscenen som används i modellen innehåller fordonets fysiska tillstånd, förarnas avsikter och förarnas förväntade beteende enligt trafikreglerna. För att möjliggöra riskbedömning i realtid görs en approximativ inferens av tillståndet givet den brusiga sensordatan med hjälp av sekventiell vägd simulering. Två olika mått på risk studeras. Det första är baserat på förarnas avsikter, närmare bestämt att ta reda på om de inte överensstämmer med den förväntade manövern, vilket då skulle kunna leda till en farlig situation. Det andra riskmåttet är baserat på ett prediktionssteg som använder sig av time to collision (TTC) och time to critical collision probability (TTCCP). Den implementerade modellen kan tillämpas i komplexa trafikscenarier med många fordon. I detta arbete fokuserar vi på scerarier i korsningar och rondeller. Modellen testas på simulerad och verklig data från dessa scenarier. I dessa kvalitativa tester kunde modellen korrekt identifiera kollisioner några få sekunder innan de inträffade. Den kunde också undvika falsklarm genom att lista ut vilka fordon som kommer att lämna företräde.

Invasive alien plants have widespread ecological and socioeconomic impacts throughout many parts of the world, including Swaziland where the government declared them a national disaster. Control of these species requires knowledge on the invasion ecology of each species including how they interact with the invaded environment. Species distribution models are vital for providing solutions to such problems including the prediction of their niche and distribution. Various modelling approaches are used for species distribution modelling albeit with limitations resulting from statistical assumptions, implementation and interpretation of outputs. This study explores the usefulness of Bayesian networks (BNs) due their ability to model stochastic, nonlinear inter-causal relationships and uncertainty. Data-driven BNs were used to explore patterns and processes influencing the spatial distribution of 16 priority invasive alien plants in Swaziland. Various BN structure learning algorithms were applied within the Weka software to build models from a set of 170 variables incorporating climatic, anthropogenic, topo-edaphic and landscape factors. While all the BN models produced accurate predictions of alien plant invasion, the globally scored networks, particularly the hill climbing algorithms, performed relatively well. However, when considering the probabilistic outputs, the constraint-based Inferred Causation algorithm which attempts to generate a causal BN structure, performed relatively better. The learned BNs reveal that the main pathways of alien plants into new areas are ruderal areas such as road verges and riverbanks whilst humans and human activity are key driving factors and the main dispersal mechanism. However, the distribution of most of the species is constrained by climate particularly tolerance to very low temperatures and precipitation seasonality. Biotic interactions and/or associations among the species are also prevalent. The findings suggest that most of the species will proliferate by extending their range resulting in the whole country being at risk of further invasion. The ability of BNs to express uncertain, rather complex conditional and probabilistic dependencies and to combine multisource data makes them an attractive technique for species distribution modeling, especially as joint invasive species distribution models (JiSDM). Suggestions for further research are provided including the need for rigorous invasive species monitoring, data stewardship and testing more BN learning algorithms. / Environmental Sciences / D. Phil. (Environmental Science)

Saltmarshes provide a diverse range of ecosystem services and are protected under a number of international designations. Nevertheless they are generally declining in extent in the United Kingdom and North West Europe. The drivers of this decline are complex and poorly understood. When considering mitigation and management for future ecosystem service provision it will be important to understand why, where, and to what extent decline is likely to occur. Few studies have attempted to forecast saltmarsh morphodynamics at a system level over decadal time scales. There is no synthesis of existing knowledge available for specific site predictions nor is there a formalised framework for individual site assessment and management. This project evaluates the extent to which machine learning model approaches (boosted regression trees, neural networks and Bayesian networks) can facilitate synthesis of information and prediction of decadal-scale morphological tendencies of saltmarshes. Importantly, data-driven predictions are independent of the assumptions underlying physically-based models, and therefore offer an additional opportunity to crossvalidate between two paradigms. Marsh margins and interiors are both considered but are treated separately since they are regarded as being sensitive to different process suites. The study therefore identifies factors likely to control morphological trajectories and develops geospatial methodologies to derive proxy measures relating to controls or processes. These metrics are developed at a high spatial density in the order of tens of metres allowing for the resolution of fine-scale behavioural differences. Conventional statistical approaches, as have been previously adopted, are applied to the dataset to assess consistency with previous findings, with some agreement being found. The data are subsequently used to train and compare three types of machine learning model. Boosted regression trees outperform the other two methods in this context. The resulting models are able to explain more than 95% of the variance in marginal changes and 91% for internal dynamics. Models are selected based on validation performance and are then queried with realistic future scenarios which represent altered input conditions that may arise as a consequence of future environmental change. Responses to these scenarios are evaluated, suggesting system sensitivity to all scenarios tested and offering a high degree of spatial detail in responses. While mechanistic interpretation of some responses is challenging, process-based justifications are offered for many of the observed behaviours, providing confidence that the results are realistic. The work demonstrates a potentially powerful alternative (and complement) to current morphodynamic models that can be applied over large areas with relative ease, compared to numerical implementations. Powerful analyses with broad scope are now available to the field of coastal geomorphology through the combination of spatial data streams and machine learning. Such methods are shown to be of great potential value in support of applied management and monitoring interventions.

For railways, risk analysis is carried out to identify hazardous situations and their consequences. Until recently, classical methods such as Fault Tree Analysis (FTA) and Event Tree Analysis (ETA) were applied in modelling the linear and logically deterministic aspects of railway risks, safety and reliability. However, it has been proven that modern railway systems are rather complex, involving multi-dependencies between system variables and uncertainties about these dependencies. For train derailment accidents, for instance, high train speed is a common cause of failure; slip and failure of brake applications are disjoint events; failure dependency exists between the train protection and warning system and driver errors; driver errors are time dependent and there is functional uncertainty in derailment conditions. Failing to incorporate these aspects of a complex system leads to wrong estimations of the risks and safety, and, consequently, to wrong management decisions. Furthermore, a complex railway system integrates various technologies and is operated in an environment where the behaviour and failure modes of the system are difficult to model using probabilistic techniques. Modelling and quantification of the railway risk and safety problems that involve dependencies and uncertainties such as mentioned above are complex tasks. Importance measures are useful in the ranking of components, which are significant with respect to the risk, safety and reliability of a railway system. The computation of importance measures using FTA has limitation for complex railways. ALARP (As Low as Reasonably Possible) risk acceptance criteria are widely accepted as ’\'best practice’’ in the railways. According to the ALARP approach, a tolerable region exists between the regions of intolerable and negligible risks. In the tolerable region, risk is undertaken only if a benefit is desired. In this case, one needs to have additional criteria to identify the socio-economic benefits of adopting a safety measure for railway facilities. The Life Quality Index (LQI) is a rational way of establishing a relation between the financial resources utilized to improve the safety of an engineering system and the potential fatalities that can be avoided by safety improvement. This thesis shows the application of the LQI approach to quantifying the social benefits of a number of safety management plans for a railway facility. We apply Bayesian Networks and influence diagrams, which are extensions of Bayesian Networks, to model and assess the life safety risks associated with railways. Bayesian Networks are directed acyclic probabilistic graphical models that handle the joint distribution of random variables in a compact and flexible way. In influence diagrams, problems of probabilistic inference and decision making – based on utility functions – can be combined and optimized, especially, for systems with many dependencies and uncertainties. The optimal decision, which maximizes the total benefits to society, is obtained. In this thesis, the application of Bayesian Networks to the railway industry is investigated for the purpose of improving modelling and the analysis of risk, safety and reliability in railways. One example application and two real world applications are presented to show the usefulness and suitability of the Bayesian Networks for the quantitative risk assessment and risk-based decision support in reference to railways.:ACKNOWLEDGEMENTS IV ABSTRACT VI ZUSAMMENFASSUNG VIII LIST OF FIGURES XIV LIST OF TABLES XVI CHAPTER 1: Introduction 1 1.1 Need to model and quantify the causes and consequences of hazards on railways 1 1.2 State-of-the art techniques in the railway 2 1.3 Goals and scope of work 4 1.4 Existing work 6 1.5 Outline of the thesis 7 CHAPTER 2: Methods for safety and risk analysis 10 2.1 Introduction 10 2.1.1 Simplified risk analysis 12 2.1.2 Standard risk analysis 12 2.1.3 Model-based risk analysis 12 2.2 Risk Matrix 14 2.2.1 Determine the possible consequences 14 2.2.2 Likelihood of occurrence 15 2.2.3 Risk scoring matrix 15 2.3 Failure Modes & Effect Analysis – FMEA 16 2.3.1 Example application of FMEA 17 2.4 Fault Tree Analysis – FTA 19 2.5 Reliability Block Diagram – RBD 22 2.6 Event Tree Analysis – ETA 24 2.7 Safety Risk Model – SRM 25 2.8 Markov Model – MM 27 2.9 Quantification of expected values 31 2.9.1 Bayesian Analysis – BA 35 2.9.2 Hazard Function – HF 39 2.9.3 Monte Carlo (MC) Simulation 42 2.10 Summary 46 CHAPTER 3: Introduction to Bayesian Networks 48 3.1 Terminology in Bayesian Networks 48 3.2 Construction of Bayesian Networks 49 3.3 Conditional independence in Bayesian Networks 51 3.4 Joint probability distribution in Bayesian Networks 52 3.5 Probabilistic Inference in Bayesian Networks 53 3.6 Probabilistic inference by enumeration 54 3.7 Probabilistic inference by variable elimination 55 3.8 Approximate inference for Bayesian Networks 57 3.9 Dynamic Bayesian Networks 58 3.10 Influence diagrams (IDs) 60 CHAPTER 4: Risk acceptance criteria and safety targets 62 4.1 Introduction 62 4.2 ALARP (As Low As Reasonably Possible) criteria 62 4.3 MEM (Minimum Endogenous Mortality) criterion 63 4.4 MGS (Mindestens Gleiche Sicherheit) criteria 64 4.5 Safety Integrity Levels (SILs) 65 4.6 Importance Measures (IMs) 66 4.7 Life Quality Index (LQI) 68 4.8 Summary 72 CHAPTER 5: Application of Bayesian Networks to complex railways: A study on derailment accidents 73 5.1 Introduction 73 5.2 Fault Tree Analysis for train derailment due to SPAD 74 5.2.1 Computation of importance measures using FTA 75 5.3 Event Tree Analysis (ETA) 78 5.4 Mapping Fault Tree and Event Tree based risk model to Bayesian Networks 79 5.4.1 Computation of importance measures using Bayesian Networks 81 5.5 Risk quantification 82 5.6 Advanced aspects of example application 83 5.6.1 Advanced aspect 1: Common cause failures 83 5.6.2 Advanced aspect 2: Disjoint events 84 5.6.3 Advanced aspect 3: Multistate system and components 84 5.6.4 Advanced aspect 4: Failure dependency 85 5.6.5 Advanced aspect 5: Time dependencies 85 5.6.6 Advanced aspect 6: Functional uncertainty and factual knowledge 85 5.6.7 Advanced aspect 7: Uncertainty in expert knowledge 86 5.6.8 Advanced aspect 8: Simplifications and dependencies in Event Tree Analysis 86 5.7 Implementation of the advanced aspects of the train derailment model using Bayesian Networks. 88 5.8 Results and discussions 92 5.9 Summary 93 CHAPTER 6: Bayesian Networks for risk-informed safety requirements for platform screen doors in railways 94 6.1 Introduction 94 6.2 Components of the risk-informed safety requirement process for Platform Screen Door system in a mega city 97 6.2.1 Define objective and methodology 97 6.2.2 Familiarization of system and information gathering 97 6.2.3 Hazard identification and hazard classification 97 6.2.4 Hazard scenario analysis 98 6.2.5 Probability of occurrence and failure data 99 6.2.6 Quantification of the risks 105 6.2.6.1. Tolerable risks 105 6.2.6.2. Risk exposure 105 6.2.6.3. Risk assessment 106 6.3 Summary 107 CHAPTER 7: Influence diagrams based decision support for railway level crossings 108 7.1 Introduction 108 7.2 Level crossing accidents in railways 109 7.3 A case study of railway level crossing 110 7.4 Characteristics of the railway level crossing under investigation 111 7.5 Life quality index applied to railway level crossing risk problem 115 7.6 Summary 119 CHAPTER 8: Conclusions and outlook 120 8.1 Summary and important contributions 120 8.2 Originality of the work 122 8.3 Outlook 122 BIBLIOGRAPHY 124 APPENDIX 1 131