An Extended Event Reasoning Framework for Decision Support under Uncertainty

To provide in-time reactions to a large volume of surveil- lance data, uncertainty-enabled event reasoning frameworks for CCTV and sensor based intelligent surveillance system have been integrated to model and infer events of interest. However, most of the existing works do not consider decision making under uncertainty which is important for surveillance operators. In this paper, we extend an event reasoning framework for decision support, which enables our framework to predict, rank and alarm threats from multiple heterogeneous sources.

STARTEC: Novel processing technologies in the development of a decision support tool to ensure safe and nutritious Ready-To-Eat foods

Ready-to-eat (RTE) foods can be readily consumed with minimum or without any further preparation; their processing is complex—involving thorough decontamination processes— due to their composition of mixed ingredients. Compared with conventional preservation technologies, novel processing technologies can enhance the safety and quality of these complex products by reducing the risk of pathogens and/ or by preserving related health-promoting compounds. These novel technologies can be divided into two categories: thermal and non-thermal. As a non-thermal treatment, High Pressure Processing is a very promising novel methodology that can be used even in the already packaged RTE foods. A new “volumetric” microwave heating technology is an interesting cooking and decontamination method directly applied to foods. Cold Plasma technology is a potential substitute of chlorine washing in fresh vegetable decontamination. Ohmic heating is a heating method applicable to viscous products but also to meat products. Producers of RTE foods have to deal with challenging decisions starting from the ingredients suppliers to the distribution chain. They have to take into account not only the cost factor but also the benefits and food products’ safety and quality. Novel processing technologies can be a valuable yet large investment for several SME food manufacturers, but they need support data to be able to make adequate decisions. Within the FP7 Cooperation funded by the European Commission, the STARTEC project aims to develop an IT decision supporting tool to help food business operators in their risk assessment and future decision making when producing RTE foods with or without novel preservation technologies.

A decision support system for managing irrigation in agriculture

In this paper, an automatic Smart Irrigation Decision Support System, SIDSS, is proposed to manage irrigation in agriculture. Our system estimates the weekly irrigations needs of a plantation, on the basis of both soil measurements and climatic variables gathered by several autonomous nodes deployed in field. This enables a closed loop control scheme to adapt the decision support system to local perturbations and estimation errors. Two machine learning techniques, PLSR and ANFIS, are proposed as reasoning engine of our SIDSS. Our approach is validated on three commercial plantations of citrus trees located in the South-East of Spain. Performance is tested against decisions taken by a human expert.

A streamlined life-cycle assessment and decision tool for used tyres recycling

In order to achieve progress towards sustainable resource management, it is essential to evaluate options for the reuse and recycling of secondary raw materials, in order to provide a robust evidence base for decision makers. This paper presents the research undertaken in the development of a web-based decision-support tool (the used tyres resource efficiency tool) to compare three processing routes for used tyres compared to their existing primary alternatives. Primary data on the energy and material flows for the three routes, and their alternatives were collected and analysed. The methodology used was a streamlined life-cycle assessment (sLCA) approach. Processes included were: car tyre baling against aggregate gabions; car tyre retreading against new car tyres; and car tyre shred used in landfill engineering against primary aggregates. The outputs of the assessment, and web-based tool, were estimates of raw materials used, carbon dioxide emissions and costs. The paper discusses the benefits of carrying out a streamlined LCA and using the outputs of this analysis to develop a decision-support tool. The strengths and weakness of this approach are discussed and future research priorities identified which could facilitate the use of life cycle approaches by designers and practitioners.

Interventions to improve the appropriate use of polypharmacy for older people

Background
Inappropriate polypharmacy is a particular concern in older people and is associated with negative health outcomes. Choosing the best interventions to improve appropriate polypharmacy is a priority, hence interest in appropriate polypharmacy, where many medicines may be used to achieve better clinical outcomes for patients, is growing.

Objectives
This review sought to determine which interventions, alone or in combination, are effective in improving the appropriate use of polypharmacy and reducing medication-related problems in older people.

Search methods
In November 2013, for this first update, a range of literature databases including MEDLINE and EMBASE were searched, and handsearching of reference lists was performed. Search terms included 'polypharmacy', 'medication appropriateness' and 'inappropriate prescribing'.

Selection criteria
A range of study designs were eligible. Eligible studies described interventions affecting prescribing aimed at improving appropriate polypharmacy in people 65 years of age and older in which a validated measure of appropriateness was used (e.g. Beers criteria, Medication Appropriateness Index (MAI)).

Data collection and analysis
Two review authors independently reviewed abstracts of eligible studies, extracted data and assessed risk of bias of included studies. Study-specific estimates were pooled, and a random-effects model was used to yield summary estimates of effect and 95% confidence intervals (CIs). The GRADE (Grades of Recommendation, Assessment, Development and Evaluation) approach was used to assess the overall quality of evidence for each pooled outcome.

Main results
Two studies were added to this review to bring the total number of included studies to 12. One intervention consisted of computerised decision support; 11 complex, multi-faceted pharmaceutical approaches to interventions were provided in a variety of settings. Interventions were delivered by healthcare professionals, such as prescribers and pharmacists. Appropriateness of prescribing was measured using validated tools, including the MAI score post intervention (eight studies), Beers criteria (four studies), STOPP criteria (two studies) and START criteria (one study). Interventions included in this review resulted in a reduction in inappropriate medication usage. Based on the GRADE approach, the overall quality of evidence for all pooled outcomes ranged from very low to low. A greater reduction in MAI scores between baseline and follow-up was seen in the intervention group when compared with the control group (four studies; mean difference -6.78, 95% CI -12.34 to -1.22). Postintervention pooled data showed a lower summated MAI score (five studies; mean difference -3.88, 95% CI -5.40 to -2.35) and fewer Beers drugs per participant (two studies; mean difference -0.1, 95% CI -0.28 to 0.09) in the intervention group compared with the control group. Evidence of the effects of interventions on hospital admissions (five studies) and of medication-related problems (six studies) was conflicting.

Authors' conclusions
It is unclear whether interventions to improve appropriate polypharmacy, such as pharmaceutical care, resulted in clinically significant improvement; however, they appear beneficial in terms of reducing inappropriate prescribing.

Étude des impacts écologiques du dynamisme spatio-temporel des habitats naturels sur la faune menacée du Complexe Zones Humides Mahavavy-Kinkony, Madagascar.

This study of the Mahavavy-Kinkony Wetland Complex (MKWC) assesses the impacts of habitat change on the resident globally threatened fauna. Located in Boeny Region, northwest Madagascar, the Complex encompasses a range of habitats including freshwater lakes, rivers, marshes, mangrove forests, and deciduous forest. Spatial modelling and analysis tools were used to (i) identify the important habitats for selected, threatened fauna, (ii) assess their change from 1950 to 2005, (iii) detect the causes of change, (iv) simulate changes to 2050 and (v) evaluate the impacts of change. The approach for prioritising potential habitats for threatened species used ecological science techniques assisted by the decision support software Marxan. Nineteen species were analysed: nine birds, three primates, three fish, three bats and one reptile. Based on knowledge of local land use, supervised classification of Landsat images from 2005 was used to classify the land use of the Complex. Simulations of land use change to 2050 were carried out based on the Land Change Modeler module in Idrisi Andes with the neural network algorithm. Changes in land use at site level have occurred over time but they are not significant. However, reductions in the extent of reed marshes at Lake Kinkony and forests at Tsiombikibo and Marofandroboka directly threaten the species that depend on these habitats. Long term change monitoring is recommended for the Mahavavy Delta, in order to evaluate the predictions through time. The future change of Andohaomby forest is of great concern and conservation actions are recommended as a high priority. Abnormal physicochemical properties were detected in lake Kinkony due to erosion of the four watersheds to the south, therefore an anti-erosion management plan is required for these watersheds. Among the species of global conservation concern, Sakalava rail (Amaurornis olivieri), Crowned sifaka (Propithecus coronatus) and dambabe (Paretroplus dambabe) are estimated the most affected, but at the site level Decken’s sifaka (Propithecus deckeni), kotsovato (Paretroplus kieneri) and Madagascan big-headed turtle (Erymnochelys madagascariensis) are also threatened. Local enforcement of national legislation on hunting means that MKWC is among the sites where the flying fox (Pteropus rufus) and Madagascan rousette (Rousettus madagascariensis) are well protected. Ecological restoration, ecological research and actions to reduce anthropogenic pressures are recommended.

An Adaptive Machine Learning Decision System for Flexible Predictive Maintenance

Process monitoring and Predictive Maintenance (PdM) are gaining increasing attention in most manufacturing environments as a means of reducing maintenance related costs and downtime. This is especially true in industries that are data intensive such as semiconductor manufacturing. In this paper an adaptive PdM based flexible maintenance scheduling decision support system, which pays particular attention to associated opportunity and risk costs, is presented. The proposed system, which employs Machine Learning and regularized regression methods, exploits new information as it becomes available from newly processed components to refine remaining useful life estimates and associated costs and risks. The system has been validated on a real industrial dataset related to an Ion Beam Etching process for semiconductor manufacturing.

THE SAAF STUDY: evaluation of the Safeguarding Children Assessment and Analysis Framework (SAAF), compared with management as usual, for improving outcomes for children and young people who have experienced, or are at risk of, maltreatment: study protocol for a randomised controlled trial

Background: Serious case reviews and research studies have indicated weaknesses in risk assessments conducted by child protection social workers. Social workers are adept at gathering information but struggle with analysis and assessment of risk. The Department for Education wants to know if the use of a structured decision-making tool can improve child protection assessments of risk.

Methods/design: This multi-site, cluster-randomised trial will assess the effectiveness of the Safeguarding Children Assessment and Analysis Framework (SAAF). This structured decision-making tool aims to improve social workers' assessments of harm, of future risk and parents' capacity to change. The comparison is management as usual.

Inclusion criteria: Children's Services Departments (CSDs) in England willing to make relevant teams available to be randomised, and willing to meet the trial's training and data collection requirements.

Exclusion criteria: CSDs where there were concerns about performance; where a major organisational restructuring was planned or under way; or where other risk assessment tools were in use.

Six CSDs are participating in this study. Social workers in the experimental arm will receive 2 days training in SAAF together with a range of support materials, and access to limited telephone consultation post-training. The primary outcome is child maltreatment. This will be assessed using data collected nationally on two key performance indicators: the first is the number of children in a year who have been subject to a second Child Protection Plan (CPP); the second is the number of re-referrals of children because of related concerns about maltreatment. Secondary outcomes are: i) the quality of assessments judged against a schedule of quality criteria and ii) the relationship between the three assessments required by the structured decision-making tool (level of harm, risk of (re) abuse and prospects for successful intervention).

Discussion: This is the first study to examine the effectiveness of SAAF. It will contribute to a very limited literature on the contribution that structured decision-making tools can make to improving risk assessment and case planning in child protection and on what is involved in their effective implementation.

Interventions to improve the appropriate use of polypharmacy in older people: a Cochrane systematic review

Objective: To summarise the findings of an updated Cochrane review of interventions aimed at improving the appropriate use of polypharmacy in older people. Design: Cochrane systematic review. Multiple electronic databases were searched including MEDLINE, EMBASE and the Cochrane Central Register of Controlled Trials (from inception to November 2013). Hand searching of references was also performed. Randomised controlled trials (RCTs), controlled clinical trials, controlled before-and-after studies and interrupted time series analyses reporting on interventions targeting appropriate polypharmacy in older people in any healthcare setting were included if they used a validated measure of prescribing appropriateness. Evidence quality was assessed using the Cochrane risk of bias tool and GRADE (Grades of Recommendation, Assessment, Development and Evaluation).
Setting: All healthcare settings. 
Participants: Older people (≥65 years) with ≥1 long-term condition who were receiving polypharmacy (≥4 regular medicines).
Primary and secondary outcome measures: Primary outcomes were the change in prevalence of appropriate polypharmacy and hospital admissions. Medication-related problems (eg, adverse drug reactions), medication adherence and quality of life were included as secondary outcomes.
Results: 12 studies were included: 8 RCTs, 2 cluster RCTs and 2 controlled before-and-after studies. 1 study involved computerised decision support and 11 comprised pharmaceutical care approaches across various settings. Appropriateness was measured using validated tools, including the Medication Appropriateness Index, Beers’ criteria and Screening Tool of Older Person’s Prescriptions (STOPP)/ Screening Tool to Alert doctors to Right Treatment (START). The interventions demonstrated a reduction in inappropriate prescribing. Evidence of effect on hospital admissions and medication-related problems was conflicting. No differences in health-related quality of life were reported.
Conclusions: The included interventions demonstrated improvements in appropriate polypharmacy based on reductions in inappropriate prescribing. However, it remains unclear if interventions resulted in clinically significant improvements (eg, in terms of hospital admissions). Future intervention studies would benefit from available guidance on intervention development, evaluation and reporting to facilitate replication in clinical practice.

Towards Utilizing Model-Driven Engineering of Composite Applications for Business Performance Analysis

Composite Applications on top of SAPs implementation of SOA (Enterprise SOA) enable the extension of already existing business logic. In this paper we show, based on a case study, how Model-Driven Engineering concepts are applied in the development of such Composite Applications. Our Case Study extends a back-end business process which is required for the specific needs of a demo company selling wine. We use this to describe how the business centric models specifying the modified business behaviour of our case study can be utilized for business performance analysis where most of the actions are performed by humans. In particular, we apply a refined version of Model-Driven Performance Engineering that we proposed in our previous work and motivate which business domain specifics have to be taken into account for business performance analysis. We additionally motivate the need for performance related decision support for domain experts, who generally lack performance related skills. Such a support should offer visual guidance about what should be changed in the design and resource mapping to get improved results with respect to modification constraints and performance objectives, or objectives for time.

PROSTATIC INTRAEPITHELIAL NEOPLASIA (PIN) - PERFORMANCE OF BAYESIAN BELIEF NETWORK FOR DIAGNOSIS AND GRADING

Prostatic intraepithelial neoplasia (PIN) diagnosis and grading are affected by uncertainties which arise from the fact that almost all knowledge of PIN histopathology is expressed in concepts, descriptive linguistic terms, and words. A Bayesian belief network (BBN) was therefore used to reduce the problem of uncertainty in diagnostic clue assessment, while still considering the dependences between elements in the reasoning sequence. A shallow network was used with an open-tree topology, with eight first-level descendant nodes for the diagnostic clues (evidence nodes), each independently linked by a conditional probability matrix to a root node containing the diagnostic alternatives (decision node). One of the evidence nodes was based on the tissue architecture and the others were based on cell features. The system was designed to be interactive, in that the histopathologist entered evidence into the network in the form of likelihood ratios for outcomes at each evidence node. The efficiency of the network was tested on a series of 110 prostate specimens, subdivided as follows: 22 cases of non-neoplastic prostate or benign prostatic tissue (NP), 22 PINs of low grade (PINlow), 22 PINs of high grade (PINhigh), 22 prostatic adenocarcinomas with cribriform pattern (PACcri), and 22 prostatic adenocarcinomas with large acinar pattern (PAClgac). The results obtained in the benign and malignant categories showed that the belief for the diagnostic alternatives is very high, the values being in general more than 0.8 and often close to 1.0. When considering the PIN lesions, the network classified and graded most of the cases with high certainty. However, there were some cases which showed values less than 0.8 (13 cases out of 44), thus indicating that there are situations in which the feature changes are intermediate between contiguous categories or grades. Discrepancy between morphological grading and the BBN results was observed in four out of 44 PIN cases: one PINlow was classified as PINhigh and three PINhigh were classified as PINlow. In conclusion, the network can grade PlN lesions and differentiate them from other prostate lesions with certainty. In particular, it offers a descriptive classifier which is readily implemented and which allows the use of linguistic, fuzzy variables.

Soil Moisture Deficit as a predictor of the trend in soil water status of grass fields

Nutrient loss from agricultural land following organic fertilizer spreading can lead to eutrophication and poor water quality. The risk of pollution is partly related to the soil water status during and after spreading. In response to these issues, a decision support system (DSS) for nutrient management has been developed to predict when soil and weather conditions are suitable for slurry spreading. At the core of the DSS, the Hybrid Soil Moisture Deficit (HSMD) model estimates soil water status relative to field capacity (FC) for three soil classes (well, moderately and poorly drained) and has potential to predict the occurrence of a transport vector when the soil is wetter than FC. Three years of field observation of volumetric water content was used to validate HSMD model predictions of water status and to ensure correct use and interpretation of the drainage classes. Point HSMD model predictions were validated with respect to the temporal and spatial variations in volumetric water content and soil strength properties. It was found that the HSMD model predictions were well related to topsoil water content through time, but a new class intermediate between poor and moderate, perhaps ‘imperfectly drained’, was needed. With correct allocations of a field into a drainage class, the HSMD model predictions reflect field scale trends in water status and therefore the model is suitable for use at the core of a DSS.

Towards utilizing Model-Driven Engineering of Composite Applications for business performance analysis

Composite Applications on top of SAPs implementation of SOA (Enterprise SOA) enable the extension of already existing business logic. In this paper we show, based on a case study, how Model-Driven Engineering concepts are applied in the development of such Composite Applications. Our Case Study extends a back-end business process which is required for the specific needs of a demo company selling wine. We use this to describe how the business centric models specifying the modified business behaviour of our case study can be utilized for business performance analysis where most of the actions are performed by humans. In particular, we apply a refined version of Model-Driven Performance Engineering that we proposed in our previous work and motivate which business domain specifics have to be taken into account for business performance analysis. We additionally motivate the need for performance related decision support for domain experts, who generally lack performance related skills. Such a support should offer visual guidance about what should be changed in the design and resource mapping to get improved results with respect to modification constraints and performance objectives, or objectives for time.