Rising interest in the field of Intelligent Transportation Systems combined with the increased availability of collected data allows the study of different methods for prevention of traffic congestion in cities. A common need in all of these methods is the use of traffic predictions for supporting planning and operation of the traffic lights and traffic management schemes. This paper focuses on comparing the forecasting effectiveness of three machine learning models, namely Random Forests, Support Vector Regression, and Multilayer Perceptron—in addition to Multiple Linear Regression—using probe data collected from the road network of Thessaloniki, Greece. The comparison was conducted with multiple tests clustered in three types of scenarios. The first scenario tests the algorithms on specific randomly selected dates on different randomly selected roads. The second scenario tests the algorithms on randomly selected roads over eight consecutive 15 min intervals; the third scenario tests the algorithms on random roads for the duration of a whole day. The experimental results show that while the Support Vector Regression model performs best at stable conditions with minor variations, the Multilayer Perceptron model adapts better to circumstances with greater variations, in addition to having the most near-zero errors.

Background: Angiographic detection of thrombus in STEMI is associated with adverse outcomes. However, routine thrombus aspiration failed to demonstrate the anticipated benefit. Hence, management of high coronary thrombus burden remains challenging. We sought to assess for the first time extracted thrombotic material characteristics utilizing micro-computed tomography (micro-CT).Methods: One hundred thirteen STEMI patients undergoing thrombus aspiration were enrolled. Micro-CT was undertaken to quantify retrieved thrombus volume, surface, and density. Correlation of these indices with angiographic and electrocardiographic outcomes was performed.Results: Mean aspirated thrombus volume, surface, and density (±standard deviation) were 15.71 ± 20.10 mm³, 302.89 ± 692.54 mm², and 3139.04 ± 901.88 Hounsfield units, respectively. Aspirated volume and surface were significantly higher (p < 0.001) in patients with higher angiographic thrombus burden. After multivariable analysis, independent predictors for thrombus volume were reference vessel diameter (RVD) (p = 0.011), right coronary artery (RCA) (p = 0.039), and smoking (p = 0.027), whereas RVD (p = 0.018) and RCA (p = 0.019) were predictive for thrombus surface. Thrombus volume and surface were independently associated with distal embolization (p = 0.007 and p = 0.028, respectively), no-reflow phenomenon (p = 0.002 and p = 0.006, respectively), and angiographically evident residual thrombus (p = 0.007 and p = 0.002, respectively). Higher thrombus density was correlated with worse pre-procedural TIMI flow (p < 0.001). Patients with higher aspirated volume and surface developed less ST resolution (p = 0.042 and p = 0.023, respectively).Conclusions: Angiographic outcomes linked with worse prognosis were more frequent among patients with larger extracted thrombus. Despite retrieving larger thrombus load in these patients, current thrombectomy devices fail to deal with thrombotic material adequately. Further studies of novel thrombus aspiration technologies are warranted to improve patient outcomes.Clinical Trial Registration: QUEST-STEMI trial ClinicalTrials.gov number: NCT03429608 Date of registration: February 12, 2018. The study was prospectively registered.

Red Flags in fiscal projects are warning signs that may indicate underlying problems with their implementation. In this paper, we present how National Strategic Reference Framework Open Data can be used to take full advantage of semantic web technologies and data mining techniques to build a knowledge-based system that identifies Red Flags. We collected the data from the Open Data API provided by the Greek Ministry of Economy and Finance. Data modeling consist of two ontologies; the Vocabulary of Fiscal Projects, describing the fiscal projects and the National Strategic Reference Framework Greece Vocabulary, illustrating the Greek National Strategic Reference Framework data. We transformed the data into RDF triples and uploaded them onto an OpenLink Virtuoso Server, so that we could retrieve them via SPARQL queries. Performance indicators were defined to assess the state of the project and Density-Based Spatial Clustering of Applications with Noise, (DBSCAN) was used to identify Red Flags. User’s demands is that rejected projects should raise Red Flags, to avoid project failure and assist the auditor to organize the monitoring process efficiently, by avoiding to examine most of the non-problematic projects. We performed a use case scenario in which an auditor has to examine NSRF projects, approximately 12 months before the end of the programming period. The system retrieved the fiscal information, calculated the performance indicators and identified the Red Flags. The last update of the projects status after the end of the programming period was retrieved and extracted the number of rejected projects, to test whether the user requirements are satisfied. Rejected projects consist of 3.8% of the total projects. The results of the use case scenario show that RedFlags platform is more likely to identify project failures and not raise Red Flags on not rejected projects. Therefore, the RedFlags platform using open data, assists the auditor to organize the monitoring process better.

Today, there is a growing need within citizens, journalists and many public bodies to explore and search for valuable information and knowledge in budget data, that are widely published by governments and municipalities across Europe. A significant element of these fiscal datasets are code lists, which serve not only for the coding and the simplicity of representation of budget concepts, but can also act as linking entities between budget datasets of different countries, bodies, years and structure, in order to facilitate their comparison. To this end, we made an extensive survey of code lists that refer or are related to fiscal or other concepts that are included in budget datasets, recording totally 239 international and national classifications. We selected some of these classifications to represent them semantically with SKOS and then we examined their linking possibilities. While manual and automated methods are insufficient for linking large code lists, tools using semi-automated methods, like Alignment seem to be more suitable for this specific task.

Data Mining and Knowledge discovery in Databases (KDD) is the process that includes data selection, pre-processing, transformation, data mining, evaluation and interpretation of the solutions from the observed results in order to discover useful knowledge from a collection of data. Semantic web and Open Linked Data can provide a higher level quality in Data Mining tasks using additional and linked information from various sources. There are many data models and different approaches that have been proposed in this area combining different aspects of Open Linked Data and Data Mining processes. OpenBudgets.eu meets this concept by modelling Open Budget data from Municipalities of Europe. This paper presents KDD process using the data model of OpenBudgets.eu in order to extract new knowledge from the budget and transaction data of Municipalities of Athens and Thessaloniki. We explored through descriptive statistics the budget phase amounts of the administrative units in Athens and Thessaloniki since 2011 and we observed that both Municipalities tried to reduce their expenditures in these years. The distributions of the expenditure amounts of services and the other descriptive measures and visualizations are provided in order to understand the structure of the expenditures of these Municipalities. Finally using cluster analysis, we built a model that categorizes what expenditure amounts an administrative unit in Athens and Thessaloniki will execute.