An integrated system for human action recognition from video using hidden Markov model

In this paper, we present an integrated system for real-time automatic detection of human actions from video. The proposed approach uses the boundary of humans as the main feature for recognizing actions. Background subtraction is performed using Gaussian mixture model. Then, features are extracted from silhouettes and Vector Quantization is used to map features into symbols (bag of words approach). Finally, actions are detected using the Hidden Markov Model. The proposed system was validated using a newly collected real- world dataset. The obtained results show that the system is capable of achieving robust human detection, in both indoor and outdoor environments. Moreover, promising classification results were achieved when detecting two basic human actions: walking and sitting.

Earthwork optimization system for sustainable highway construction

In highway construction, earthworks refer to the tasks of excavation, transportation, spreading and compaction of geomaterial (e.g. soil, rockfill and soil-rockfill mixture). Whereas relying heavily on machinery and repetitive processes, these tasks are highly susceptible to optimization. In this context Artificial Intelligent techniques, such as Data Mining and modern optimization can be applied for earthworks. A survey of these applications shows that they focus on the optimization of specific objectives and/or construction phases being possible to identify the capabilities and limitations of the analyzed techniques. Thus, according to the pinpointed drawbacks of these techniques, this paper describes a novel intelligent earthwork optimization system, capable of integrating DM, modern optimization and GIS technologies in order to optimize the earthwork processes throughout all phases of design and construction work. This integration system allows significant savings in time, cost and gas emissions contributing for a more sustainable construction.

Clustering-based approach for categorizing pregnant women in obstetrics and maternity care

When a pregnant woman is guided to a hospital for obstetrics purposes, many outcomes are possible, depending on her current conditions. An improved understanding of these conditions could provide a more direct medical approach by categorizing the different types of patients, enabling a faster response to risk situations, and therefore increasing the quality of services. In this case study, the characteristics of the patients admitted in the maternity care unit of Centro Hospitalar of Porto are acknowledged, allowing categorizing the patient women through clustering techniques. The main goal is to predict the patients’ route through the maternity care, adapting the services according to their conditions, providing the best clinical decisions and a cost-effective treatment to patients. The models developed presented very interesting results, being the best clustering evaluation index: 0.65. The evaluation of the clustering algorithms proved the viability of using clustering based data mining models to characterize pregnant patients, identifying which conditions can be used as an alert to prevent the occurrence of medical complications.

Predicting plateau pressure in intensive medicine for ventilated patients

Barotrauma is identified as one of the leading diseases in Ventilated Patients. This type of problem is most common in the Intensive Care Units. In order to prevent this problem the use of Data Mining (DM) can be useful for predicting their occurrence. The main goal is to predict the occurence of Barotrauma in order to support the health professionals taking necessary precautions. In a first step intensivists identified the Plateau Pressure values as a possible cause of Barotrauma. Through this study DM models (classification) where induced for predicting the Plateau Pressure class (>=30 cm

Intelligent decision support to predict patient barotrauma risk in intensive care units

The occurrence of Barotrauma is identified as a major concern for health professionals, since it can be fatal for patients. In order to support the decision process and to predict the risk of occurring barotrauma Data Mining models were induced. Based on this principle, the present study addresses the Data Mining process aiming to provide hourly probability of a patient has Barotrauma. The process of discovering implicit knowledge in data collected from Intensive Care Units patientswas achieved through the standard process Cross Industry Standard Process for Data Mining. With the goal of making predictions according to the classification approach they several DM techniques were selected: Decision Trees, Naive Bayes and Support Vector Machine. The study was focused on identifying the validity and viability to predict a composite variable. To predict the Barotrauma two classes were created: “risk” and “no risk”. Such target come from combining two variables: Plateau Pressure and PCO2. The best models presented a sensitivity between 96.19% and 100%. In terms of accuracy the values varied between 87.5% and 100%. This study and the achieved results demonstrated the feasibility of predicting the risk of a patient having Barotrauma by presenting the probability associated.

Sistema de predição de avarias em máquinas de unidades fabris globalmente dispersas

Tese de Doutoramento Ramo Engenharia Industrial e de Sistemas

Análise de dados e aplicação de modelos estatísticos para apoio à decisão de contratação na Petróleo Brasileiro

Dissertação de mestrado em Engenharia Industrial

Exploração de séries temporais em processos de previsão de vendas

Dissertação de mestrado em Engenharia de Sistemas

Sistema inteligente para análise do posicionamento de árbitros de futebol

Dissertação de mestrado em Sistemas de Informação

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Given the limitations of different types of remote sensing images, automated land-cover classifications of the Amazon várzea may yield poor accuracy indexes. One way to improve accuracy is through the combination of images from different sensors, by either image fusion or multi-sensor classifications. Therefore, the objective of this study was to determine which classification method is more efficient in improving land cover classification accuracies for the Amazon várzea and similar wetland environments - (a) synthetically fused optical and SAR images or (b) multi-sensor classification of paired SAR and optical images. Land cover classifications based on images from a single sensor (Landsat TM or Radarsat-2) are compared with multi-sensor and image fusion classifications. Object-based image analyses (OBIA) and the J.48 data-mining algorithm were used for automated classification, and classification accuracies were assessed using the kappa index of agreement and the recently proposed allocation and quantity disagreement measures. Overall, optical-based classifications had better accuracy than SAR-based classifications. Once both datasets were combined using the multi-sensor approach, there was a 2% decrease in allocation disagreement, as the method was able to overcome part of the limitations present in both images. Accuracy decreased when image fusion methods were used, however. We therefore concluded that the multi-sensor classification method is more appropriate for classifying land cover in the Amazon várzea.

Sistema de apoio à decisão clínica: quality of life system

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

Pervasive patient timeline

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

Apoio à decisão na análise inteligente de reclamações

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

Pervasive business intelligence: a marketing intelligence framework proposal

Doctoral Thesis in Information Systems and Technologies Area of Information Systems and Technology

Automatically estimating iSAX parameters

The Symbolic Aggregate Approximation (iSAX) is widely used in time series data mining. Its popularity arises from the fact that it largely reduces time series size, it is symbolic, allows lower bounding and is space efficient. However, it requires setting two parameters: the symbolic length and alphabet size, which limits the applicability of the technique. The optimal parameter values are highly application dependent. Typically, they are either set to a fixed value or experimentally probed for the best configuration. In this work we propose an approach to automatically estimate iSAX’s parameters. The approach – AutoiSAX – not only discovers the best parameter setting for each time series in the database, but also finds the alphabet size for each iSAX symbol within the same word. It is based on simple and intuitive ideas from time series complexity and statistics. The technique can be smoothly embedded in existing data mining tasks as an efficient sub-routine. We analyze its impact in visualization interpretability, classification accuracy and motif mining. Our contribution aims to make iSAX a more general approach as it evolves towards a parameter-free method.