Learning relational probabilistic action models for online planning with decision forests

Probabilistic relational models (PRMs) extend Bayesian networks (BNs) to a relational data mining context. Even though a panoply of works have focused, separately, on Bayesian networks and relational databases random generation, no work has been identified for PRMs on that track. This paper provides an algorithmic approach allowing to generate random PRMs from scratch to cover the absence of generation process. The proposed method allows to generate PRMs as well as synthetic relational data from a randomly generated relational schema and a random set of probabilistic dependencies. This can be of interest for machine learning researchers to evaluate their proposals in a common framework, as for databases designers to evaluate the effectiveness of the components of a database management system.

A Personalized Recommender System from Probabilistic Relational Model and Users’ Preferences

Probabilistic prediction model of steel to concrete bond failure under high temperature by machine learning

Fluid diffusivity inversion and injection-induced microseismicity provide useful means of evaluating unconventional reservoirs. When taking into consideration geomechanics, linear poroelasticity equations provide the key connection between diffusion and microseismicity. This work explores microseismicity generation from a probabilistic point of view, embedding uncertainty assessment in its quantification. Bayesian framework serves as the base for probabilistic analysis. The primary objective of this work is to develop a new microseismicity probabilistic model framework that can be used for uncertainty quantification in data analysis as well as to provide forward modeling of microseismicity. Results are tested against real data of Horn Rives shales in Western Canada, and show good prediction of the number of actual microseismicity occurrences against time. The novel probabilistic model is derived from Directed Graphic Model using a statistical learning framework. Stochastic Poisson process combined with a specific rate model is integrated to generate a likelihood function. Both, parameter inference and microseismic event forecast are assisted by Bayesian theorem. The model has an intrinsic statistical learning root, which specifically uses observed microseismic data to update model parameters and then is applied for microseismicity prediction. The model is extended to take into account basic geomechanical principles. Dieterich (1994) relative seismicity rate model is integrated into the aforemantioned probabilistic model. We use a synthetic case to demonstrate how the probabilistic model can be connected with stress and pressure information from geomechanical calculations. The novelty of this study is the development of a probabilistic microseismic prediction model which obeys rate-and-state law based relative seismicity rate constitutive equations. The model inherently considers time dependence of nucleation and fault geomechanics. It can be used for planning purposes in the pre-hydraulic fracturing stage.

Capturing word meaning is one of the challenges of natural language processing (NLP). Formal models of meaning, such as networks of words or concepts, are knowledge repositories used in a variety of applications. To be effectively used, these networks have to be large or, at least, adapted to specific domains. Learning word meaning from texts is then an active area of research. Lexico-syntactic pattern methods are one of the possible solutions. Yet, these models do not use structural properties of target semantic relations, e.g. transitivity, during learning. In this paper, we propose a novel lexico-syntactic pattern probabilistic method for learning taxonomies that explicitly models transitivity and naturally exploits vector space model techniques for reducing space dimensions. We define two probabilistic models: the direct probabilistic model and the induced probabilistic model. The first is directly estimated on observations over text collections. The second uses transitivity on the direct probabilistic model to induce probabilities of derived events. Within our probabilistic model, we also propose a novel way of using singular value decomposition as unsupervised method for feature selection in estimating direct probabilities. We empirically show that the induced probabilistic taxonomy learning model outperforms state-of-the-art probabilistic models and our unsupervised feature selection method improves performance.

A Unified Recommendation Framework Based on Probabilistic Relational Models

Probabilistic relational models (PRMs) extend Bayesian networks to multi-relational domains and represent the dependencies between attributes within a table and across multiple tables. This paper presents a method of integrating and learning with concept hierarchies with PRMs, in order to retrieve richer object and relational information from multi-relational databases. A concept hierarchy defines a partially ordered sequence of mappings from a set of concepts to their higher-level correspondences. Natural concept hierarchies are often associated with some attributes in databases and can be used to discover knowledge. We first introduce concept hierarchies to PRMs by using background knowledge. A score-based search algorithm is then investigated for learning with concept hierarchies in PRMs parameter estimation procedure. The method can learn the most appropriate concepts from the data and use them to update the parameters. Experimental results on both real and synthetic data are discussed.KeywordsMinimum Description LengthConcept HierarchyStatistical Relational LearningProbabilistic Relational ModelAggregate RuleThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The reactive evaluation approach and the predictive approach for modeling and analyzing breaks in deteriorating water distribution systems have been tried. Descriptive statistical studies have been used to analyse pipe failure. Predictive models are classified into three basic categories: aggregate type models, regression type models, and probabilistic predictive models. The Proportional Hazards Model is a probabilistic predictive model, and is applied to predict failure probabilities in deteriorating water pipes. This methodology possesses high flexibility for adapting to particular system characteristics. Economic studies have been performed to determine an optimum replacement time for breaking mains. Once the total cost (direct and social) is known, the next questions to be answered are which pipes should be replaced and when they should be replaced.

Most asset deterioration tools are designed for a specific application, as a consequence, a small change of the specification may result in a complete change of the tool. Inspired by the model-based approach of separating problem specification from analysis technique, we propose a model-based asset deterioration assessment framework using probabilistic relational models. The probabilistic relational models express abstract probabilistic dependency covers a range of deterioration modelling assumptions. An expert in the domain of asset deterioration can then use his knowledge of the factors that affect deterioration to customise the abstract models to a specific application, without requiring a detailed understanding the underlying computational framework. We illustrate the use of the framework with multiple variants of deterioration models.

The probabilistic predictive modelling (PPM) approach in human-in-the-loop (HITL) related aerospace problems enables one to predict, quantify, assure and even specify the probability of the outcome of an aerospace mission or a situation when the performance of a never-perfect human, never-100%-reliable instrumentation (equipment), never absolutely predictable response of the object of control (aero or spacecraft), uncertain and often harsh environment, as well as the interaction (interfaces) of these uncertainties, contribute jointly to the likelihood of such an outcome. The objective of this paper is to generate thinking on how to advance the state-of-the-art in today's aerospace human psychology and particularly, on how to quantify, by both modelling and experimentation, the HITL related effort when the HF and equipment/instrumentation performance contribute jointly to the outcome (success and safety) of an aerospace mission or an extraordinary situation.

This paper proposes the use of Probabilistic Relational Models (PRM) for analyzing dependencies between Information Security Governance (ISG) components and its impact on process capability of mitigating information security vulnerabilities. Using the PRM enables inference between different ISG components expressed in probabilities, and also inference on the process capability. A concrete PRM which exemplifies how to assess the capability of the access control process is further presented, and thus showing how the PRM can be adapted to fit the analysis of a specific process in an organizational environment.

Trivariate analysis of soil ranking-correlated characteristics and its application to probabilistic stability assessments in geotechnical engineering problems

There is growing interest in the field of digital soil mapping (DSM) to quantify the underlying uncertainty of point predictions through different probabilistic prediction models. Uncertainty in DSM is often described in the format of a prediction interval (PI). Yet, PIs or uncertainty estimates in general are only of value for end users if they have good quality, i.e. when they are reliable. Reliability refers to the consistency between predicted conditional probabilities and observed frequencies of independent validation data. Ideally, PIs are also sharp, which refers to the concentration of probabilistic information, i.e. the narrowness of conditional probability distributions. The prediction interval coverage probability (PICP) is currently used in DSM to assess the reliability of PIs but it is ignorant to a potential one-sided bias of its bounding quantiles. Therefore, we propose to complement the current validation procedure with new metrics suggested in the broader probabilistic literature. This includes metrics that do not only evaluate uncertainty estimates in PI format but also quantiles or full conditional probability distributions. The newly proposed metrics are the quantile coverage probability (QCP), the probability integral transform (PIT) and so-called proper scoring rules for relative comparisons. Examples of scoring rules are the continuous ranked probability score (CRPS), which can be decomposed into a reliability part (RELI) and the interval score (IS). Sharpness can be evaluated through the prediction interval width (PIW). We illustrated the use of the various metrics in a case-study using soil pH data from The Land Use and Coverage Area Frame Survey (LUCAS). Thereby, uncertainty estimates of five different models were compared: Kriging with external drift (KED), quantile regression forest (QRF), quantile regression post-processing of a random forest (QRPP RF), quantile regression neural network (QRNN) and a reference null-model (NM).  KED, NM and QRPP RF showed very good reliability according to QCP, PICP, PIT and RELI. QRF was slightly pessimistic in the centre and QRNN very overoptimistic at the edges of the conditional probability distributions. Despite this, QRF performed best according to mean CRPS and mean IS because it produced fewer outliers at the edges. As expected, NM had the lowest sharpness, i.e. the largest PIW values. Sharpness of the other models was overall similar but QRNN had sharper predictions at the edges and QRF was less sharp in the centre of the conditional probability distributions. Lastly, we also generated PIW maps to indicate the spatial uncertainty of the five prediction models. The spatial variability of PIW was larger for QRF, QRNN and QRPP RF in comparison to KED. Whereas with NM, PIW was completely uniform. 

A machine learning approach to predicting bicycle demand during the COVID-19 pandemic

Probabilistic Prediction Model for the Chloride Diffusion Coefficient of Concrete under Tensile and Compressive Stresses