Plataforma de apoio à decisão nos cuidados de ginecologia e obstetrícia

Dissertação de mestrado integrado em Engenharia Biomédica (área de especialização em Informática Médica)

Categorização do consumo de energia em sistemas de povoamento de Data Warehouses

Os recursos computacionais exigidos durante o processamento de grandes volumes de dados durante um processo de povoamento de um data warehouse faz com que a necessidade da procura de novas implementações tenha também em atenção a eficiência energética dos diversos componentes processuais que integram um qualquer sistema de povoamento. A lacuna de técnicas ou metodologias para categorizar e avaliar o consumo de energia em sistemas de povoamento de data warehouses é claramente notória. O acesso a esse tipo de informação possibilitaria a construção de sistemas de povoamento de data warehouses com níveis de consumo de energia mais baixos e, portanto, mais eficientes. Partindo da adaptação de técnicas aplicadas a sistemas de gestão de base de dados para a obtenção dos consumos energéticos da execução de interrogações, desenhámos e implementámos uma nova técnica que nos permite obter os consumos de energia para um qualquer processo de povoamento de um data warehouse, através da avaliação do consumo de cada um dos componentes utilizados na sua implementação utilizando uma ferramenta convencional. Neste artigo apresentamos a forma como fazemos tal avaliação, utilizando na demonstração da viabilidade da nossa proposta um processo de povoamento bastante típico em data warehouses – substituição encadeada de chaves operacionais -, que foi implementado através da ferramenta Kettle.

A relational algebra approach to ETL modeling

The MAP-i Doctoral Programme in Informatics, of the Universities of Minho, Aveiro and Porto

Forecasting human entrances at a commercial store using facial recognition data

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

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.

A clinical recommendation system to maternity care

Nowadays in healthcare, the Clinical Decision Support Systems are used in order to help health professionals to take an evidence-based decision. An example is the Clinical Recommendation Systems. In this sense, it was developed and implemented in Centro Hospitalar do Porto a pre-triage system in order to group the patients on two levels (urgent or outpatient). However, although this system is calibrated and specific to the urgency of obstetrics and gynaecology, it does not meet all clinical requirements by the general department of the Portuguese HealthCare (Direção Geral de Saúde). The main requirement is the need of having priority triage system characterized by five levels. Thus some studies have been conducted with the aim of presenting a methodology able to evolve the pre-triage system on a Clinical Recommendation System with five levels. After some tests (using data mining and simulation techniques), it has been validated the possibility of transformation the pre-triage system in a Clinical Recommendation System in the obstetric context. This paper presents an overview of the Clinical Recommendation System for obstetric triage, the model developed and the main results achieved.

A Real-Time intelligent system for tracking patient condition

Hospitals have multiple data sources, such as embedded systems, monitors and sensors. The number of data available is increasing and the information are used not only to care the patient but also to assist the decision processes. The introduction of intelligent environments in health care institutions has been adopted due their ability to provide useful information for health professionals, either in helping to identify prognosis or also to understand patient condition. Behind of this concept arises this Intelligent System to track patient condition (e.g. critic events) in health care. This system has the great advantage of being adaptable to the environment and user needs. The system is focused in identifying critic events from data streaming (e.g. vital signs and ventilation) which is particularly valuable for understanding the patient’s condition. This work aims to demonstrate the process of creating an intelligent system capable of operating in a real environment using streaming data provided by ventilators and vital signs monitors. Its development is important to the physician because becomes possible crossing multiple variables in real-time by analyzing if a value is critic or not and if their variation has or not clinical importance.

Combining data mining and evolutionary computation for multi-criteria optimization of earthworks

Earthworks tasks aim at levelling the ground surface at a target construction area and precede any kind of structural construction (e.g., road and railway construction). It is comprised of sequential tasks, such as excavation, transportation, spreading and compaction, and it is strongly based on heavy mechanical equipment and repetitive processes. Under this context, it is essential to optimize the usage of all available resources under two key criteria: the costs and duration of earthwork projects. In this paper, we present an integrated system that uses two artificial intelligence based techniques: data mining and evolutionary multi-objective optimization. The former is used to build data-driven models capable of providing realistic estimates of resource productivity, while the latter is used to optimize resource allocation considering the two main earthwork objectives (duration and cost). Experiments held using real-world data, from a construction site, have shown that the proposed system is competitive when compared with current manual earthwork design.

A geographic opportunistic forwarding strategy for vehicular named data networking

Studies in Computational Intelligence, 616

Task clustering on ETL systems – A pattern-oriented approach

Usually, data warehousing populating processes are data-oriented workflows composed by dozens of granular tasks that are responsible for the integration of data coming from different data sources. Specific subset of these tasks can be grouped on a collection together with their relationships in order to form higher- level constructs. Increasing task granularity allows for the generalization of processes, simplifying their views and providing methods to carry out expertise to new applications. Well-proven practices can be used to describe general solutions that use basic skeletons configured and instantiated according to a set of specific integration requirements. Patterns can be applied to ETL processes aiming to simplify not only a possible conceptual representation but also to reduce the gap that often exists between two design perspectives. In this paper, we demonstrate the feasibility and effectiveness of an ETL pattern-based approach using task clustering, analyzing a real world ETL scenario through the definitions of two commonly used clusters of tasks: a data lookup cluster and a data conciliation and integration cluster.

Using a domain-specific language to enrich ETL schemas

Today it is easy to find a lot of tools to define data migration schemas among different types of information systems. Data migration processes use to be implemented on a very diverse range of applications, ranging from conventional operational systems to data warehousing platforms. The implementation of a data migration process often involves a serious planning, considering the development of conceptual migration schemas at early stages. Such schemas help architects and engineers to plan and discuss the most adequate way to migrate data between two different systems. In this paper we present and discuss a way for enriching data migration conceptual schemas in BPMN using a domain-specific language, demonstrating how to convert such enriched schemas to a first correspondent physical representation (a skeleton) in a conventional ETL implementation tool like Kettle.

Automatic generation of ETL physical systems from BPMN conceptual models

ETL conceptual modeling is a very important activity in any data warehousing system project implementation. Owning a high-level system representation allowing for a clear identification of the main parts of a data warehousing system is clearly a great advantage, especially in early stages of design and development. However, the effort to model conceptually an ETL system rarely is properly rewarded. Translating ETL conceptual models directly into something that saves work and time on the concrete implementation of the system process it would be, in fact, a great help. In this paper we present and discuss a hybrid approach to this problem, combining the simplicity of interpretation and power of expression of BPMN on ETL systems conceptualization with the use of ETL patterns to produce automatically an ETL skeleton, a first prototype system, which has the ability to be executed in a commercial ETL tool like Kettle.

Using relational algebra on the specification of real world ETL processes

Modeling Extract-Transform-Load (ETL) processes of a Data Warehousing System has always been a challenge. The heterogeneity of the sources, the quality of the data obtained and the conciliation process are some of the issues that must be addressed in the design phase of this critical component. Commercial ETL tools often provide proprietary diagrammatic components and modeling languages that are not standard, thus not providing the ideal separation between a modeling platform and an execution platform. This separation in conjunction with the use of standard notations and languages is critical in a system that tends to evolve through time and which cannot be undermined by a normally expensive tool that becomes an unsatisfactory component. In this paper we demonstrate the application of Relational Algebra as a modeling language of an ETL system as an effort to standardize operations and provide a basis for uncommon ETL execution platforms.

Poker learner: modelação de jogadores através de data mining

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

Concise server-wide causality management for eventually consistent data stores

Large scale distributed data stores rely on optimistic replication to scale and remain highly available in the face of net work partitions. Managing data without coordination results in eventually consistent data stores that allow for concurrent data updates. These systems often use anti-entropy mechanisms (like Merkle Trees) to detect and repair divergent data versions across nodes. However, in practice hash-based data structures are too expensive for large amounts of data and create too many false conflicts. Another aspect of eventual consistency is detecting write conflicts. Logical clocks are often used to track data causality, necessary to detect causally concurrent writes on the same key. However, there is a nonnegligible metadata overhead per key, which also keeps growing with time, proportional with the node churn rate. Another challenge is deleting keys while respecting causality: while the values can be deleted, perkey metadata cannot be permanently removed without coordination. Weintroduceanewcausalitymanagementframeworkforeventuallyconsistentdatastores,thatleveragesnodelogicalclocks(BitmappedVersion Vectors) and a new key logical clock (Dotted Causal Container) to provides advantages on multiple fronts: 1) a new efficient and lightweight anti-entropy mechanism; 2) greatly reduced per-key causality metadata size; 3) accurate key deletes without permanent metadata.