Complex Symbolic Sequence Encodings for Predictive Monitoring of Business Processes

This paper addresses the problem of predicting the outcome of an ongoing case of a business process based on event logs. In this setting, the outcome of a case may refer for example to the achievement of a performance objective or the fulfillment of a compliance rule upon completion of the case. Given a log consisting of traces of completed cases, given a trace of an ongoing case, and given two or more possible out- comes (e.g., a positive and a negative outcome), the paper addresses the problem of determining the most likely outcome for the case in question. Previous approaches to this problem are largely based on simple symbolic sequence classification, meaning that they extract features from traces seen as sequences of event labels, and use these features to construct a classifier for runtime prediction. In doing so, these approaches ignore the data payload associated to each event. This paper approaches the problem from a different angle by treating traces as complex symbolic sequences, that is, sequences of events each carrying a data payload. In this context, the paper outlines different feature encodings of complex symbolic sequences and compares their predictive accuracy on real-life business process event logs.

Predictive models for water sources with high susceptibility for bromine-containing disinfection by-product formation: Implications for water treatment

This study examines a matrix of synthetic water samples designed to include conditions that favour brominated disinfection by-product (Br-DBP) formation, in order to provide predictive models suitable for high Br-DBP forming waters such as salinity-impacted waters. Br-DBPs are known to be more toxic than their chlorinated analogues, in general, and their formation may be favoured by routine water treatment practices such as coagulation/flocculation under specific conditions; therefore, circumstances surrounding their formation must be understood. The chosen factors were bromide concentration, mineral alkalinity, bromide to dissolved organic carbon (Br/DOC) ratio and Suwannee River natural organic matter concentration. The relationships between these parameters and DBP formation were evaluated by response surface modelling of data generated using a face-centred central composite experimental design. Predictive models for ten brominated and/or chlorinated DBPs are presented, as well as models for total trihalomethanes (tTHMs) and total dihaloacetonitriles (tDHANs), and bromide substitution factors for the THMs and DHANs classes. The relationships described revealed that increasing alkalinity and increasing Br/DOC ratio were associated with increasing bromination of THMs and DHANs, suggesting that DOC lowering treatment methods that do not also remove bromide such as enhanced coagulation may create optimal conditions for Br-DBP formation in waters in which bromide is present.

Bayesian predictive modeling and comparison of oil samples

Statistical comparison of oil samples is an integral part of oil spill identification, which deals with the process of linking an oil spill with its source of origin. In current practice, a frequentist hypothesis test is often used to evaluate evidence in support of a match between a spill and a source sample. As frequentist tests are only able to evaluate evidence against a hypothesis but not in support of it, we argue that this leads to unsound statistical reasoning. Moreover, currently only verbal conclusions on a very coarse scale can be made about the match between two samples, whereas a finer quantitative assessment would often be preferred. To address these issues, we propose a Bayesian predictive approach for evaluating the similarity between the chemical compositions of two oil samples. We derive the underlying statistical model from some basic assumptions on modeling assays in analytical chemistry, and to further facilitate and improve numerical evaluations, we develop analytical expressions for the key elements of Bayesian inference for this model. The approach is illustrated with both simulated and real data and is shown to have appealing properties in comparison with both standard frequentist and Bayesian approaches

The ovarian response to controlled stimulation in IVF cycles may be predictive of the age at menopause

STUDY QUESTION Can the number of oocytes retrieved in IVF cycles be predictive of the age at menopause? SUMMARY ANSWER The number of retrieved oocytes can be used as an indirect assessment of the extent of ovarian reserve to provide information on the duration of the reproductive life span in women of different ages. WHAT IS KNOWN ALREADY Menopause is determined by the exhaustion of the ovarian follicular pool. Ovarian reserve is the main factor influencing ovarian response in IVF cycles. As a consequence the response to ovarian stimulation with the administration of gonadotrophins in IVF treatment may be informative about the age at menopause. STUDY DESIGN, SIZE, DURATION In the present cross-sectional study, participants were 1585 infertile women from an IVF clinic and 2635 menopausal women from a more general population. PARTICIPANTS/MATERIALS, SETTING, METHODS For all infertile women, the response to ovarian stimulation with gonadotrophins was recorded. For menopausal women, relevant demographic characteristics were available for the analysis. MAIN RESULTS AND THE ROLE OF CHANCE A cubic function described the relationship between mean numbers of oocytes and age, with all terms being statistically significant. From the estimated residual distribution of the actual number of oocytes about this mean, a distribution of the age when there would be no oocytes retrieved following ovarian stimulation was derived. This was compared with the distribution of the age at menopause from the menopausal women, showing that menopause occurred about a year later. LIMITATIONS, REASONS FOR CAUTION The retrieved oocyte data were from infertile women, while the menopausal ages were from a more general population. WIDER IMPLICATIONS OF THE FINDINGS In the present study, we have shown some similarity between the distributions of the age when no retrieved oocytes can be expected after ovarian stimulation and the age at menopause. For a given age, the lower the ovarian reserve, the lower the number of retrieved oocytes would be and the earlier the age that menopause would occur.

Minimizing overprocessing waste in business processes via predictive activity ordering

Overprocessing waste occurs in a business process when effort is spent in a way that does not add value to the customer nor to the business. Previous studies have identied a recurrent overprocessing pattern in business processes with so-called "knockout checks", meaning activities that classify a case into "accepted" or "rejected", such that if the case is accepted it proceeds forward, while if rejected, it is cancelled and all work performed in the case is considered unnecessary. Thus, when a knockout check rejects a case, the effort spent in other (previous) checks becomes overprocessing waste. Traditional process redesign methods propose to order knockout checks according to their mean effort and rejection rate. This paper presents a more fine-grained approach where knockout checks are ordered at runtime based on predictive machine learning models. Experiments on two real-life processes show that this predictive approach outperforms traditional methods while incurring minimal runtime overhead.

Complex symbolic sequence clustering and multiple classifiers for predictive process monitoring

This paper addresses the following predictive business process monitoring problem: Given the execution trace of an ongoing case,and given a set of traces of historical (completed) cases, predict the most likely outcome of the ongoing case. In this context, a trace refers to a sequence of events with corresponding payloads, where a payload consists of a set of attribute-value pairs. Meanwhile, an outcome refers to a label associated to completed cases, like, for example, a label indicating that a given case completed “on time” (with respect to a given desired duration) or “late”, or a label indicating that a given case led to a customer complaint or not. The paper tackles this problem via a two-phased approach. In the first phase, prefixes of historical cases are encoded using complex symbolic sequences and clustered. In the second phase, a classifier is built for each of the clusters. To predict the outcome of an ongoing case at runtime given its (uncompleted) trace, we select the closest cluster(s) to the trace in question and apply the respective classifier(s), taking into account the Euclidean distance of the trace from the center of the clusters. We consider two families of clustering algorithms – hierarchical clustering and k-medoids – and use random forests for classification. The approach was evaluated on four real-life datasets.

Autonomous UAVs wildlife detection using thermal imaging, predictive navigation and computer vision

There is an increased interest on the use of Unmanned Aerial Vehicles (UAVs) for wildlife and feral animal monitoring around the world. This paper describes a novel system which uses a predictive dynamic application that places the UAV ahead of a user, with a low cost thermal camera, a small onboard computer that identifies heat signatures of a target animal from a predetermined altitude and transmits that target’s GPS coordinates. A map is generated and various data sets and graphs are displayed using a GUI designed for easy use. The paper describes the hardware and software architecture and the probabilistic model for downward facing camera for the detection of an animal. Behavioral dynamics of target movement for the design of a Kalman filter and Markov model based prediction algorithm are used to place the UAV ahead of the user. Geometrical concepts and Haversine formula are applied to the maximum likelihood case in order to make a prediction regarding a future state of the user, thus delivering a new way point for autonomous navigation. Results show that the system is capable of autonomously locating animals from a predetermined height and generate a map showing the location of the animals ahead of the user.

A data fusion approach of multiple maintenance data sources for real-world reliability modelling

A central tenet in the theory of reliability modelling is the quantification of the probability of asset failure. In general, reliability depends on asset age and the maintenance policy applied. Usually, failure and maintenance times are the primary inputs to reliability models. However, for many organisations, different aspects of these data are often recorded in different databases (e.g. work order notifications, event logs, condition monitoring data, and process control data). These recorded data cannot be interpreted individually, since they typically do not have all the information necessary to ascertain failure and preventive maintenance times. This paper presents a methodology for the extraction of failure and preventive maintenance times using commonly-available, real-world data sources. A text-mining approach is employed to extract keywords indicative of the source of the maintenance event. Using these keywords, a Naïve Bayes classifier is then applied to attribute each machine stoppage to one of two classes: failure or preventive. The accuracy of the algorithm is assessed and the classified failure time data are then presented. The applicability of the methodology is demonstrated on a maintenance data set from an Australian electricity company.

Predictive technology and natural hazards: Risk for Australian planning authorities?

Purpose The object of this paper is to examine whether the improvements in technology that enhance community understanding of the frequency and severity of natural hazards also increased the risk of potential liability of planning authorities in negligence. In Australia, the National Strategy imposes a resilience based approach to disaster management and stresses that responsible land use planning can reduce or prevent the impact of natural hazards upon communities. Design/methodology/approach This paper analyses how the principles of negligence allocate responsibility for loss suffered by a landowner in a hazard prone area between the landowner and local government. Findings The analysis in this paper concludes that despite being able to establish a causal link between the loss suffered by a landowner and the approval of a local authority to build in a hazard prone area, it would be in the rarest of circumstances a negligence action may be proven. Research limitations/implications The focus of this paper is on planning policies and land development, not on the negligent provision of advice or information by the local authority. Practical implications This paper identifies the issues a landowner may face when seeking compensation from a local authority for loss suffered due to the occurrence of a natural hazard known or predicted to be possible in the area. Originality/value The paper establishes that as risk managers, local authorities must place reliance upon scientific modelling and predictive technology when determining planning processes in order to fulfil their responsibilities under the National Strategy and to limit any possible liability in negligence.

Predicting the temporal response of seagrass meadows to dredging using Dynamic Bayesian Networks

Predicting temporal responses of ecosystems to disturbances associated with industrial activities is critical for their management and conservation. However, prediction of ecosystem responses is challenging due to the complexity and potential non-linearities stemming from interactions between system components and multiple environmental drivers. Prediction is particularly difficult for marine ecosystems due to their often highly variable and complex natures and large uncertainties surrounding their dynamic responses. Consequently, current management of such systems often rely on expert judgement and/or complex quantitative models that consider only a subset of the relevant ecological processes. Hence there exists an urgent need for the development of whole-of-systems predictive models to support decision and policy makers in managing complex marine systems in the context of industry based disturbances. This paper presents Dynamic Bayesian Networks (DBNs) for predicting the temporal response of a marine ecosystem to anthropogenic disturbances. The DBN provides a visual representation of the problem domain in terms of factors (parts of the ecosystem) and their relationships. These relationships are quantified via Conditional Probability Tables (CPTs), which estimate the variability and uncertainty in the distribution of each factor. The combination of qualitative visual and quantitative elements in a DBN facilitates the integration of a wide array of data, published and expert knowledge and other models. Such multiple sources are often essential as one single source of information is rarely sufficient to cover the diverse range of factors relevant to a management task. Here, a DBN model is developed for tropical, annual Halophila and temperate, persistent Amphibolis seagrass meadows to inform dredging management and help meet environmental guidelines. Specifically, the impacts of capital (e.g. new port development) and maintenance (e.g. maintaining channel depths in established ports) dredging is evaluated with respect to the risk of permanent loss, defined as no recovery within 5 years (Environmental Protection Agency guidelines). The model is developed using expert knowledge, existing literature, statistical models of environmental light, and experimental data. The model is then demonstrated in a case study through the analysis of a variety of dredging, environmental and seagrass ecosystem recovery scenarios. In spatial zones significantly affected by dredging, such as the zone of moderate impact, shoot density has a very high probability of being driven to zero by capital dredging due to the duration of such dredging. Here, fast growing Halophila species can recover, however, the probability of recovery depends on the presence of seed banks. On the other hand, slow growing Amphibolis meadows have a high probability of suffering permanent loss. However, in the maintenance dredging scenario, due to the shorter duration of dredging, Amphibolis is better able to resist the impacts of dredging. For both types of seagrass meadows, the probability of loss was strongly dependent on the biological and ecological status of the meadow, as well as environmental conditions post-dredging. The ability to predict the ecosystem response under cumulative, non-linear interactions across a complex ecosystem highlights the utility of DBNs for decision support and environmental management.

The usefulness of fair values in improving the predictive ability of earnings: Evidence from international banks

One of the objectives of general-purpose financial reporting is to provide information about the financial position, financial performance and cash flows of an entity that is useful to a wide range of users in making economic decisions. The current focus on potentially increased relevance of fair value accounting weighed against issues of reliability has failed to consider the potential impact on the predictive ability of accounting. Based on a sample of international (non-U.S.) banks from 24 countries during 2009-2012, we test the usefulness of fair values in improving the predictive ability of earnings. First, we find that the increasing use of fair values on balance-sheet financial instruments enhances the ability of current earnings to predict future earnings and cash flows. Second, we provide evidence that the fair value hierarchy classification choices affect the ability of earnings to predict future cash flows and future earnings. More precisely, we find that the non-discretionary fair value component (Level 1 assets) improves the predictability of current earnings whereas the discretionary fair value components (Level 2 and Level 3 assets) weaken the predictive power of earnings. Third, we find a consistent and strong association between factors reflecting country-wide institutional structures and predictive power of fair values based on discretionary measurement inputs (Level 2 and Level 3 assets and liabilities). Our study is timely and relevant. The findings have important implications for standard setters and contribute to the debate on the use of fair value accounting.

Ship collision avoidance and COLREGS compliance using simulation-based control behavior selection with predictive hazard assessment

This paper describes a concept for a collision avoidance system for ships, which is based on model predictive control. A finite set of alternative control behaviors are generated by varying two parameters: offsets to the guidance course angle commanded to the autopilot and changes to the propulsion command ranging from nominal speed to full reverse. Using simulated predictions of the trajectories of the obstacles and ship, compliance with the Convention on the International Regulations for Preventing Collisions at Sea and collision hazards associated with each of the alternative control behaviors are evaluated on a finite prediction horizon, and the optimal control behavior is selected. Robustness to sensing error, predicted obstacle behavior, and environmental conditions can be ensured by evaluating multiple scenarios for each control behavior. The method is conceptually and computationally simple and yet quite versatile as it can account for the dynamics of the ship, the dynamics of the steering and propulsion system, forces due to wind and ocean current, and any number of obstacles. Simulations show that the method is effective and can manage complex scenarios with multiple dynamic obstacles and uncertainty associated with sensors and predictions.

Safety of Repair, Maintenance, Minor Alteration, and Addition (RMAA) Works: A New Focus of Construction Safety

"Safety of RMAA works is an almost uncharted topic of rising importance internationally. Small construction contractors are particularly dependant on RMAA work, especially during times of recession, and they undertake more risks on these jobs than large companies do. This book is based on unique international research and consultancy projects which detail, investigate, and suggest solutions to the specific challenges of safety in RMAA works, based on case studies. Starting with an overview of safety in the wider construction industries of developed countries, the first half of this book also provides a comprehensive summary of relevant rules, regulations, and the resulting safety performances. The systems in the UK, US and Hong Kong are described and contrasted, giving the reader an understanding of how different regulatory approaches have yielded a variety of results. From this solid introduction, specific problems observed in RMAA work are examined through case studies, with reference to the underlying cultural and demographic factors, and a variety of practical engineering and management solutions are explored. This important and practical international work is essential reading for postgraduate students of health and safety in construction, construction project management, or construction in developing countries, as well as policy-makers and construction project managers."--Publisher website