Towards a pervasive data mining engine: architecture overview

Current data mining engines are difficult to use, requiring optimizations by data mining experts in order to provide optimal results. To solve this problem a new concept was devised, by maintaining the functionality of current data mining tools and adding pervasive characteristics such as invisibility and ubiquity which focus on their users, providing better ease of use and usefulness, by providing autonomous and intelligent data mining processes. This article introduces an architecture to implement a data mining engine, composed by four major components: database; Middleware (control); Middleware (processing); and interface. These components are interlinked but provide independent scaling, allowing for a system that adapts to the user’s needs. A prototype has been developed in order to test the architecture. The results are very promising and showed their functionality and the need for further improvements.

Predicting triage waiting time in maternity emergency care by means of data mining

Healthcare organizations often benefit from information technologies as well as embedded decision support systems, which improve the quality of services and help preventing complications and adverse events. In Centro Materno Infantil do Norte (CMIN), the maternal and perinatal care unit of Centro Hospitalar of Oporto (CHP), an intelligent pre-triage system is implemented, aiming to prioritize patients in need of gynaecology and obstetrics care in two classes: urgent and consultation. The system is designed to evade emergency problems such as incorrect triage outcomes and extensive triage waiting times. The current study intends to improve the triage system, and therefore, optimize the patient workflow through the emergency room, by predicting the triage waiting time comprised between the patient triage and their medical admission. For this purpose, data mining (DM) techniques are induced in selected information provided by the information technologies implemented in CMIN. The DM models achieved accuracy values of approximately 94% with a five range target distribution, which not only allow obtaining confident prediction models, but also identify the variables that stand as direct inducers to the triage waiting times.

Predicting pre-triage waiting time in a maternity emergency room through data mining

An unsuitable patient flow as well as prolonged waiting lists in the emergency room of a maternity unit, regarding gynecology and obstetrics care, can affect the mother and child’s health, leading to adverse events and consequences regarding their safety and satisfaction. Predicting the patients’ waiting time in the emergency room is a means to avoid this problem. This study aims to predict the pre-triage waiting time in the emergency care of gynecology and obstetrics of Centro Materno Infantil do Norte (CMIN), the maternal and perinatal care unit of Centro Hospitalar of Oporto, situated in the north of Portugal. Data mining techniques were induced using information collected from the information systems and technologies available in CMIN. The models developed presented good results reaching accuracy and specificity values of approximately 74% and 94%, respectively. Additionally, the number of patients and triage professionals working in the emergency room, as well as some temporal variables were identified as direct enhancers to the pre-triage waiting time. The imp lementation of the attained knowledge in the decision support system and business intelligence platform, deployed in CMIN, leads to the optimization of the patient flow through the emergency room and improving the quality of services.

Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.

Development of composite auxetic structures for civil engineering applications

Tese de Doutoramento em Engenharia Têxtil

Ingeniería de glicanos: diseño de inmunógenos y ligandos de lectinas. Glycan engineering: design of immunogens and ligand of lectins.

La ingeniería de glicanos es un área de investigación emergente, la que posee múltiples aplicaciones en medicina. Mediante esta herramienta se intentará reducir la flexibilidad de las uniones glicosídicas de antígenos tumorales, como la del antígeno T (Galbeta3GalNAcalfa-Ser/Thr). Aquí se realizarán las menores alteraciones posibles en la topología de glicanos que generen la mejor respuesta inmune hacia el antígeno de interés. Por otra parte, se buscará ligandos de alta afinidad que interaccionen con lectinas involucradas en diseminación de metástasis. Mediante ensayos teóricos de Docking se tratará de hallar modificaciones topológicas de glicanos que potencialmente tengan propiedades anti-adhesivas para células tumorales. Este proyecto constará de tres etapas: una teórica, utilizando programas de cálculos para ensayos de Docking y mínimos energéticos de glicanos. Otra de síntesis, generando los glicoconjugados sugeridos en la etapa anterior. En la última, se verificará si estos glicanos rediseñados adquirieron las propiedades biológicas deseadas. Así se determinará si generan una respuesta inmune que reconozca antígenos y células tumorales. También, se analizarán las propiedades anti-adhesivas de los glicanos utilizando diferentes modelos experimentales. Finalmente, se determinará si los inmunógenos producidos y/o glicoconjugados rediseñados poseen efecto en el desarrollo tumoral y sobrevida animal.

Los entornos virtuales como herramienta sustituta del laboratorio "real" y como complemento de la enseñanza de Química a alumnos de Ingeniería. Virtual environments as substitute tools for the "conventional" laboratories and as a complement for Chemistry teaching to Engineering students.

El presente proyecto se plantea el siguiente problema de investigación:¿Cuál es la eficacia de los entornos virtuales de enseñanza para optimizar los aprendizajes de Química? Se sostiene la hipótesis de que los entornos virtuales de enseñanza, empleados como mediación instrumental, son eficaces para optimizar los aprendizajes de química, particularmente facilitando la vinculación y reversibilidad entre "mundo micro y macroscópico"; capacidad que usualmente sólo se atribuye al trabajo experimental de laboratorio. Los objetivos propuestos son: Determinar la eficacia de entornos virtuales de enseñanza, como mediaciones instrumentales, para optimizar los aprendizajes de química en estudiantes de ingeniería. Implementar un entrono virtual de enseñanza de química, diseñado como mediación instrumental y destinado a estudiantes de dos carreras de ingeniería del IUA. Evaluar el desarrollo y los resultados de la innovación introducida. Comparar los resultados de la innovación con los resultados de la enseñanza usual. Derivar conclusiones acerca de la eficacia de la innovación propuesta. Socializar el conocimiento producido en ámbitos científico-tecnológicos reconocidos. Se generará un aula virtual en plataforma Educativa y utilidzando el laboratorio de computación de la institución se buscará desarrollar laboratorios virtuales donde se propondrán actividades de simulación de trabajo experimental. Los resultados esperados son: - Un Aula Virtual que cumpla funciones análogas a las de un laboratorio experimental. - Información válida y confiable acerca de la eficacia de la misma como medio para optimizar los aprendizajes de química. - Publicaciones en ámbitos científico-tecnológicos reconocidos que sometan a juicio público la innovación y la investigación efectuadas. La importancia del proyecto radica principalmente en poner a prueba la eficacia de los entornos virtuales para optimizar los aprendizajes de química, analogando tareas usualmente limitadas al trabajo experimental de laboratorio. Su pertinencia apunta a un replanteo del curriculo de los cursos de Química para estudiantes de Ingeniería.

Investigation into the potential for establishing a self-sustainable wetland ecosystem over pyritic mine tailings

Research was conducted to investigate the potential for ecologically engineering a sustainable wetland ecosystem over pyritic mine tailings to prevent the generation of acid mine drainage. Ecological engineering is technology with the primary goal being the creation of self-sustainable ecological systems. Work involved the design and construction of a pilot-scale wetland system comprising three wetland cells, each covering 100 m2. Approximately forty tonnes of pyritic mine tailings were deposited on the base of the first cell above a synthetic liner, covered with peat, flooded and planted with emergent wetland macrophytes Typha latifolia, Phragmites australis, and Juncus effusus. The second cell was constructed as a conventional free water surface wetland, planted identically, and used as a reference wetland/experimental control. Wetland monitoring to determine long-term sustainability focused on indicators of ecosystem health including ecological, hydrological, physico-chemical, geochemical, and biotic metrics. An integrated assessment was conducted that involved field ecology in addition to ecological risk assessment. The objective of the field ecology study was to use vegetative parameters as ecological indicators for documenting wetlands success or degradation. The goal of the risk assessment was to determine if heavy-metal contamination of the wetland sediments occurred through metal mobilisation from the underlying tailings, and to evaluate if subsequent water column chemistry and biotic metal concentrations were significantly correlated with adverse wetland ecosystem impacts. Data were used to assess heavy metal bioavailability within the system as a function of metal speciation in the wetland sediments. Results indicate hydrology is the most important variable in the design and establishment of the tailings wetland and suggest a wetland cover is an ecologically viable alternative for pyritic tailings which are feasible to flood. Ecological data indicate that in terms of species richness and diversity, the tailings-wetland was exhibiting the ecological characteristics of natural wetlands within two years. Ata indicate that pH and conductivity in the tailings-wetland were not adversely impacted by the acid-generating potential or sulphate concentration of the tailings substrate and its porewater. Similarly, no enhanced seasonal impacts from sulphate or metals in the water column, nor adverse impacts on the final water quality of the outflows, were detected. Mean total metal concentrations in the sediments of the tailings-wetland indicate no significant adverse mobilisation of metals into the peat substrate from the tailings. Correlation analyses indicate a general increase in sediment metal concentration in this wetland with increasing water depth and pH, and a corresponding decrease in the metal concentrations of the water column. Sediment extractions also showed enrichment of Cd, Fe, Pb and Zn in the oxidisable fraction (including sulphides and organic matter) of the tailings-wetland sediments. These data suggest that adsorption and coprecipitation of metals is occurring from the water column of the tailings wetland with organic material at increasing depths under reducing conditions. The long-term control of metal bioavailability in the tailings wetland will likely be related to the presence and continual build-up of organic carbon binding sites in the developing wetland above the tailings. Metal speciation including free-metal ion concentration and the impact of physico-chemical parameters particularly pH and organic matter, were investigated to assess ecotoxicological risk. Results indicate that potentially bioavailable metals (the sum of the exchangeable and reducible fractions) within the tailings wetland are similar to values cited for natural wetlands. Estimated free-metal ion concentrations calculated from geochemical regression models indicate lower free-metal ion concentrations of Cd in the tailings wetland than natural wetlands and slightly higher free-metal ion concentrations of Pb and Zn. Increased concentrations of metals in roots, rhizomes and stems of emergent macrophytes did not occur in the tailings wetland. Even though a substantial number of Typha latifolia plants were found rooting directly into tailings, elevated metals were not found in these plant tissues. Phragmites also did not exhibit elevated metal concentrations in any plant tissues. Typha and Phragmites populations appear to be exhibiting metal-tolerant behaviour. The chemistry of the water column and sediments in Silvermines wetland were also investigated and were much more indicative of a wetland system impacted by heavy metal contamination than the tailings-wetland. Mean Dc, Fe, Mn, Pb and Zn concentrations in the water column and sediments of Silvermines wetlands were substantially higher than in the pilot wetlands and closely approximate concentrations in these matrices contaminated with metals from mining. In addition, mean sulphate concentration in Silvermines wetland was substantially higher and is closer to sulphate concentrations in waters associated with mining. Potentially bioavailable metals were substantially elevated in Silvermines wetland in comparison to the pilot wetlands and higher than those calculated for natural rive sediments. However, Fe oxy-hydroxide concentrations in Silvermines sediments are also much higher than in the pilot wetlands and this significantly impacts the concentration of free-metal ions in the sediment porewater. The free-metal ion concentrations for Pb and Zn indicate that Silvermines wetland is retaining metals and acting as a treatment wetland for drainage emanating from Silvermines tailings dam.

Data mining with graphical models

Data Mining, Learning from data, graphical models, possibility theory

SQL based frequent pattern mining

Data mining, frequent pattern mining, database mining, mining algorithms in SQL

Spatial data mining in precision agriculture

Magdeburg, Univ., Fak. für Informatik, Diss., 2012

Online-Data-Mining auf Datenströmen : Methoden zur Clusteranalyse und Klassifikation

Online Data Mining, Data Streams, Classification, Clustering

Data mining in diagnostic charts and treatment outcome prediction for vision restoration therapy

Data Mining, Vision Restoration, Treatment outcome prediction, Self-Organising-Map

On the stepwise and disciplined engineering of adaptive service-oriented applications

Magdeburg, Univ., Fak. für Informatik, Habil.-Schr., 2010