Search

Since their introduction in 1994, more and more genetically modified (GM) crops are grown worldwide and introduced in food or feed products. In the European Union (EU), the production, trade and marketing of GM products is strictly regulated, but the situation is becoming more complex due to the increasing number and complexity of GM crops, and asynchronic approval procedures with the major GM crop producing countries. Importers and traders are obliged to assess their respective supply chains for the potential presence of authorised and unauthorised GM organisms (GMOs), where wrong decisions may lead to substantial economic losses. This article presents a decision support system SIGMO aimed at guiding producers and traders with the assessment of the likelihood that their products may comprise authorised or unauthorised GM materials. The assessment is based on traceability data about the product (nature and origin of the raw materials, transportation aspects), as well as analytical results of the presence of GMOs in the final product or its ingredients. The approach uses a combination of data-driven and model-driven decision support. SIGMO is composed of (1) a data base providing data about GMO crop species produced and approved in counties worldwide, (2) a multi-attribute model for the assessment of GMO presence in food/feed products, and (3) an on-line user interface. SIGMO helps producers and traders to better comply to valid EU GMO regulations and to better control their products and supply chains in terms of the unintended presence of (unauthorised) GMOs in a cost-effective way. [ABSTRACT FROM AUTHOR]

We provide a continuation of the existing Activity Table Modeling methodology with a modular spreadsheets simulation. The simulation model developed is comprised of 28 modeling elements for the abdominal surgery cycle process. The simulation of a two-week patient flow in an abdominal clinic with 75 beds demonstrates the applicability of the methodology. The simulation does not include macros, thus programming experience is not essential for replication or upgrading the model. Unlike the existing methods, the proposed solution employs a modular approach for modeling the activities that ensures better readability, the possibility of easily upgrading the model with other activities, and its easy extension and connectives with other similar models. We propose a first-in-first-served approach for simulation of servicing multiple patients. The uncertain time duration of the activities is modeled using the function “rand()”. The patients movements from one activity to the next one is tracked with nested “if()” functions, thus allowing easy re-creation of the process without the need of complex programming. [ABSTRACT FROM AUTHOR]

• We developed data-driven and expert-driven computer-based DSS models for medication change of Parkinson's disease patients • The DSS models cover the whole space of input attributes' values, i.e., any combination of motor and non-motor symptoms, and any epidemiologic characterization of a patient • Expert-driven DSS model resembles well the decisions made by physicians and outperforms the data-driven model in terms of accuracy. • The accuracy results indicate that the constructed models are sufficiently adequate and fit for the purpose of making suggestions to DSS users. Parkinson's disease (PD) is a degenerative disorder of the central nervous system for which currently there is no cure. Its treatment requires long-term, interdisciplinary disease management, and usage of typical medications, including levodopa, dopamine agonists, and enzymes, such as MAO-B inhibitors. The key goal of disease management is to prolong patients' independence and keep their quality of life. Due to the different combinations of motor and non-motor symptoms from which PD patients suffer, in addition to existing comorbidities, the change of medications and their combinations is difficult and patient-specific. To help physicians, we developed two decision support models for PD management, which suggest how to change the medication treatment. The models were developed using DEX methodology, which integrates the qualitative multi-criteria decision modelling with rule-based expert systems. The two DEX models differ in the way the decision rules were defined. In the first model, the decision rules are based on the interviews with neurologists (DEX expert model), and in the second model, they are formed from a database of past medication change decisions (DEX data model). We assessed both models on the Parkinson's Progression Markers Initiative (PPMI) and on a questionnaire answered by 17 neurologists from 4 European countries using accuracy measure and the Jaccard index. Both models include 15 sub-models that address possible medication treatment changes based on the given patients' current state. In particular, the models incorporate current state changes in patients' motor symptoms (dyskinesia intensity, dyskinesia duration, OFF duration), mental problems (impulsivity, cognition, hallucinations and paranoia), epidemiologic data (patient's age, activity level) and comorbidities (cardiovascular problems, hypertension and low blood pressure). The highest accuracy of the developed sub-models for 15 medication treatment changes ranges from 69.31 to 99.06 %. Results show that the DEX expert model is superior to the DEX data model. The results indicate that the constructed models are sufficiently adequate and thus fit for the purpose of making "second-opinion" suggestions to decision support users. [ABSTRACT FROM AUTHOR]

Human behaviour in various circumstances mirrors the corresponding brain connectivity patterns, which are suitably represented by functional brain networks. While the objective analysis of these networks by graph theory tools deepened our understanding of brain functions, the multi-brain structures and connections underlying human social behaviour remain largely unexplored. In this study, we analyse the aggregate graph that maps coordination of EEG signals previously recorded during spoken communications in two groups of six listeners and two speakers. Applying an innovative approach based on the algebraic topology of graphs, we analyse higher-order topological complexes consisting of mutually interwoven cliques of a high order to which the identified functional connections organise. Our results reveal that the topological quantifiers provide new suitable measures for differences in the brain activity patterns and inter-brain synchronisation between speakers and listeners. Moreover, the higher topological complexity correlates with the listener’s concentration to the story, confirmed by self-rating, and closeness to the speaker’s brain activity pattern, which is measured by network-to-network distance. The connectivity structures of the frontal and parietal lobe consistently constitute distinct clusters, which extend across the listener’s group. Formally, the topology quantifiers of the multi-brain communities exceed the sum of those of the participating individuals and also reflect the listener’s rated attributes of the speaker and the narrated subject. In the broader context, the presented study exposes the relevance of higher topological structures (besides standard graph measures) for characterising functional brain networks under different stimuli. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new algorithm, called FOCUSED (FOrecast Correction Using Successive prEDictions), for forecast correction of short-term wind speed predictions. We developed FOCUSED with the aim of improving the forecast of bora gusts, which frequently result in high-speed wind situations dangerous for traffic. The motivation arises from occasionally ambiguous results of the currently deployed decision support system, which aids traffic management in strong and gusty wind conditions at the coast of Croatia. The proposed correction algorithm uses characteristics of numerical weather prediction models to iteratively forecast the wind speed multiple times for the same future window. We use these iterative predictions as input features of the FOCUSED algorithm and get the corrected predictions as the output. We compared the proposed algorithm with artificial neural networks, random forests, support vector machines, and linear regression to demonstrate the superiority of the algorithm's performance on a data set comprising five years of real data measurements at the Croatian bridge "Krk" and complementary historical forecasts by ALADIN (Aire Limitée Adaptation dynamique Développement InterNational) numerical weather prediction model. [ABSTRACT FROM AUTHOR]

We address the problem of estimating the time-to-employment of a jobseeker using survival analysis and oblique predictive clustering tree. Unlike standard survival analysis, oblique predictive clustering tree can handle categorical and continuous data and is capable of modelling non-linear dependences. Treating the censored data as missing data opens the possibility to perform survival analysis by using structured output prediction in semi-supervised multi-target regression setting. The effectiveness of this approach is shown on a real dataset from Public Employment Services in Slovenia, comprising time-to-employment records with jobseekers' personal and professional characteristics. The performances are compared with six state-of-the-art AI methods. To the best of our knowledge, this is the first example of using semi-supervised oblique predictive clustering tree for survival analysis. • Estimation of time-to-employment of job seekers through structured output prediction. • The approach is based on Oblique Predictive Clustering Trees (SPYCTs). • Interpretation of the model predictions through the SHAP method. • Validation of the model performed on more than 1000 samples of job seekers data. • The model supports job seekers in finding optimal career solutions. [ABSTRACT FROM AUTHOR]

Mathematical modelling of unemployment dynamics attempts to predict the probability of a job seeker finding a job as a function of time. This is typically achieved by using information in unemployment records. These records are right censored, making survival analysis a suitable approach for parameter estimation. The proposed model uses a deep artificial neural network (ANN) as a non-linear hazard function. Through embedding, high-cardinality categorical features are analysed efficiently. The posterior distribution of the ANN parameters are estimated using a variational Bayes method. The model is evaluated on a time-to-employment data set spanning from 2011 to 2020 provided by the Slovenian public employment service. It is used to determine the employment probability over time for each individual on the record. Similar models could be applied to other questions with multi-dimensional, high-cardinality categorical data including censored records. Such data is often encountered in personal records, for example in medical records. • Variational Bayes approach for parameters estimation of survival models. • Survival analysis is used for evaluating the probability of exit from unemployment. • Profiling can be performed based on survival probability over selected time interval. • Computationally efficient estimation of parameters' posterior distribution. • Hazard function is modelled using a deep neural network. [ABSTRACT FROM AUTHOR]