Sistema de recomendação inteligente para uma plataforma de e-Learning

As plataformas de e-Learning são cada vez mais utilizadas na educação à distância, facto que se encontra diretamente relacionado com a possibilidade de proporcionarem aos seus alunos a valência de poderem assistir a cursos em qualquer lugar. Dentro do âmbito das plataformas de e-Learning encontra-se um grupo especialmente interessante: as plataformas adaptativas, que tendem a substituir o professor (presencial) através de interatividade, variabilidade de conteúdos, automatização e capacidade para resolução de problemas e simulação de comportamentos educacionais. O projeto ADAPT (plataforma adaptativa de e-Learning) consiste na criação de uma destas plataformas, implementando tutoria inteligente, resolução de problemas com base em experiências passadas, algoritmos genéticos e link-mining. É na área de link-mining que surge o desenvolvimento desta dissertação que documenta o desenvolvimento de quatro módulos distintos: O primeiro módulo consiste num motor de busca para sugestão de conteúdos alternativos; o segundo módulo consiste na identificação de mudanças de estilo de aprendizagem; o terceiro módulo consiste numa plataforma de análise de dados que implementa várias técnicas de data mining e estatística para fornecer aos professores/tutores informações importantes que não seriam visíveis sem recurso a este tipo de técnicas; por fim, o último módulo consiste num sistema de recomendações que sugere aos alunos os artigos mais adequados com base nas consultas de alunos com perfis semelhantes. Esta tese documenta o desenvolvimento dos vários protótipos para cada um destes módulos. Os testes efetuados para cada módulo mostram que as metodologias utilizadas são válidas e viáveis.

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

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.

Predicting preterm birth in maternity care by means of data mining

Worldwide, around 9% of the children are born with less than 37 weeks of labour, causing risk to the premature child, whom it is not prepared to develop a number of basic functions that begin soon after the birth. In order to ensure that those risk pregnancies are being properly monitored by the obstetricians in time to avoid those problems, Data Mining (DM) models were induced in this study to predict preterm births in a real environment using data from 3376 patients (women) admitted in the maternal and perinatal care unit of Centro Hospitalar of Oporto. A sensitive metric to predict preterm deliveries was developed, assisting physicians in the decision-making process regarding the patients’ observation. It was possible to obtain promising results, achieving sensitivity and specificity values of 96% and 98%, respectively.

Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables

Lecture Notes in Computer Science, 9273

Pervasive decision support to predict football corners and goals by means of data mining

Football is considered nowadays one of the most popular sports. In the betting world, it has acquired an outstanding position, which moves millions of euros during the period of a single football match. The lack of profitability of football betting users has been stressed as a problem. This lack gave origin to this research proposal, which it is going to analyse the possibility of existing a way to support the users to increase their profits on their bets. Data mining models were induced with the purpose of supporting the gamblers to increase their profits in the medium/long term. Being conscience that the models can fail, the results achieved by four of the seven targets in the models are encouraging and suggest that the system can help to increase the profits. All defined targets have two possible classes to predict, for example, if there are more or less than 7.5 corners in a single game. The data mining models of the targets, more or less than 7.5 corners, 8.5 corners, 1.5 goals and 3.5 goals achieved the pre-defined thresholds. The models were implemented in a prototype, which it is a pervasive decision support system. This system was developed with the purpose to be an interface for any user, both for an expert user as to a user who has no knowledge in football games.

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%.

Mining Events from Multimedia streams, Jon Hare

peaker(s): Jon Hare Organiser: Time: 25/06/2014 11:00-11:50 Location: B32/3077 Abstract The aggregation of items from social media streams, such as Flickr photos and Twitter tweets, into meaningful groups can help users contextualise and effectively consume the torrents of information on the social web. This task is challenging due to the scale of the streams and the inherently multimodal nature of the information being contextualised. In this talk I'll describe some of our recent work on trend and event detection in multimedia data streams. We focus on scalable streaming algorithms that can be applied to multimedia data streams from the web and the social web. The talk will cover two particular aspects of our work: mining Twitter for trending images by detecting near duplicates; and detecting social events in multimedia data with streaming clustering algorithms. I'll will describe in detail our techniques, and explore open questions and areas of potential future work, in both these tasks.

Distributed classification for pocket data mining

Distributed and collaborative data stream mining in a mobile computing environment is referred to as Pocket Data Mining PDM. Large amounts of available data streams to which smart phones can subscribe to or sense, coupled with the increasing computational power of handheld devices motivates the development of PDM as a decision making system. This emerging area of study has shown to be feasible in an earlier study using technological enablers of mobile software agents and stream mining techniques [1]. A typical PDM process would start by having mobile agents roam the network to discover relevant data streams and resources. Then other (mobile) agents encapsulating stream mining techniques visit the relevant nodes in the network in order to build evolving data mining models. Finally, a third type of mobile agents roam the network consulting the mining agents for a final collaborative decision, when required by one or more users. In this paper, we propose the use of distributed Hoeffding trees and Naive Bayes classifers in the PDM framework over vertically partitioned data streams. Mobile policing, health monitoring and stock market analysis are among the possible applications of PDM. An extensive experimental study is reported showing the effectiveness of the collaborative data mining with the two classifers.

OntoSDM: an approach to improve quality on spatial data mining algorithms

The increase in new electronic devices had generated a considerable increase in obtaining spatial data information; hence these data are becoming more and more widely used. As well as for conventional data, spatial data need to be analyzed so interesting information can be retrieved from them. Therefore, data clustering techniques can be used to extract clusters of a set of spatial data. However, current approaches do not consider the implicit semantics that exist between a region and an object’s attributes. This paper presents an approach that enhances spatial data mining process, so they can use the semantic that exists within a region. A framework was developed, OntoSDM, which enables spatial data mining algorithms to communicate with ontologies in order to enhance the algorithm’s result. The experiments demonstrated a semantically improved result, generating more interesting clusters, therefore reducing manual analysis work of an expert.

Link between energy consumption per hour of activity and productivity of labour

The data set shows energy consumption per hour of work (in MJ/hour), and labour productivity (in USD/hour) in the PS economic sector (Energy & Mining + Industry + Construction) for the period 1970-2009 and for the following countries: Germany, Spain, USA, Canada, Italy, UK, France, Japan. The intention is to look at the relationship between energy consumption as a driver of improvements in the productivity of labour. This is of particular relevance for the discussion of reducing working time in the context of the 'degrowth' debate, as it is done in the article to which this data is a suplement.

Data Mining with Enhanced Neural Networks-CMMSE

Abstract This paper presents a new method to extract knowledge from existing data sets, that is, to extract symbolic rules using the weights of an Artificial Neural Network. The method has been applied to a neural network with special architecture named Enhanced Neural Network (ENN). This architecture improves the results that have been obtained with multilayer perceptron (MLP). The relationship among the knowledge stored in the weights, the performance of the network and the new implemented algorithm to acquire rules from the weights is explained. The method itself gives a model to follow in the knowledge acquisition with ENN.

Infer user interests via link structure regularization

Learning user interests from online social networks helps to better understand user behaviors and provides useful guidance to design user-centric applications. Apart from analyzing users' online content, it is also important to consider users' social connections in the social Web. Graph regularization methods have been widely used in various text mining tasks, which can leverage the graph structure information extracted from data. Previously, graph regularization methods operate under the cluster assumption that nearby nodes are more similar and nodes on the same structure (typically referred to as a cluster or a manifold) are likely to be similar. We argue that learning user interests from complex, sparse, and dynamic social networks should be based on the link structure assumption under which node similarities are evaluated based on the local link structures instead of explicit links between two nodes. We propose a regularization framework based on the relation bipartite graph, which can be constructed from any type of relations. Using Twitter as our case study, we evaluate our proposed framework from social networks built from retweet relations. Both quantitative and qualitative experiments show that our proposed method outperforms a few competitive baselines in learning user interests over a set of predefined topics. It also gives superior results compared to the baselines on retweet prediction and topical authority identification. © 2014 ACM.