ESTG - Artigos em revistas internacionais
URI permanente para esta coleção:
Navegar
Entradas recentes
- An Annotated Corpus of Crime-Related Portuguese Documents for NLP and Machine Learning ProcessingPublication . Carnaz, Gonçalo; Antunes, Mário; Nogueira, Vitor BeiresCriminal investigations collect and analyze the facts related to a crime, from which the investigators can deduce evidence to be used in court. It is a multidisciplinary and applied science, which includes interviews, interrogations, evidence collection, preservation of the chain of custody, and other methods and techniques of investigation. These techniques produce both digital and paper documents that have to be carefully analyzed to identify correlations and interactions among suspects, places, license plates, and other entities that are mentioned in the investigation. The computerized processing of these documents is a helping hand to the criminal investigation, as it allows the automatic identification of entities and their relations, being some of which difficult to identify manually. There exists a wide set of dedicated tools, but they have a major limitation: they are unable to process criminal reports in the Portuguese language, as an annotated corpus for that purpose does not exist. This paper presents an annotated corpus, composed of a collection of anonymized crime-related documents, which were extracted from official and open sources. The dataset was produced as the result of an exploratory initiative to collect crime-related data from websites and conditioned-access police reports. The dataset was evaluated and a mean precision of 0.808, recall of 0.722, and F1-score of 0.733 were obtained with the classification of the annotated named-entities present in the crime-related documents. This corpus can be employed to benchmark Machine Learning (ML) and Natural Language Processing (NLP) methods and tools to detect and correlate entities in the documents. Some examples are sentence detection, named-entity recognition, and identification of terms related to the criminal domain.
- Aprendizagem Interorganizacional e Capacidade Absortiva: Investigação em Pequenas e Médias EmpresasPublication . Cassol, Alessandra; Tonial, Graciele; Werlang, Nathalia B.Objetivo: Esta pesquisa analisa a influência da aprendizagem interorganizacional (AIO) sobre a capacidade absortiva (Acap), potencial (Pacap) e realizada (Racap), no ambiente de pequenas e médias empresas (PMEs). Originalidade/valor: O estudo contribuiu para o entendimento e a expansão das pesquisas da AIO operacionalizadas por meio dos elementos da Acap. A compreensão desses elementos é fundamental para o desenvolvimento de novas competências das PMEs brasileiras e/ou de países emergentes, imersas em setores dinâmicos e de alta mobilidade tecnológica, para se adaptarem e desenvolverem novas capacidades dinâmicas. Design/metodologia/abordagem: A pesquisa foi realizada por meio de uma survey em uma amostra de 215 PMEs do setor de tecnologia da informação e comunicação (TIC) no estado de Santa Catarina, Brasil. Os dados foram analisados a partir da técnica de modelagem de equações estruturais. Resultados: Os resultados demonstraram que as relações de AIO são capazes de influenciar o desenvolvimento de novas competências e possuem forte influência sobre o desenvolvimento da Acap. A habilidade das organizações em adquirir, assimilar, aplicar e internalizar os conhecimentos disponíveis no setor, por meio de relações interorganizacionais, foi fundamental para a adaptação e sobrevivência.
- Design of tissue engineering scaffolds based on hyperbolic surfaces: Structural numerical evaluationPublication . Almeida, Henrique A.; Bártolo, Paulo J.Tissue engineering represents a new field aiming at developing biological substitutes to restore, maintain, or improve tissue functions. In this approach, scaffolds provide a temporary mechanical and vascular support for tissue regeneration while tissue in-growth is being formed. These scaffolds must be biocompatible, biodegradable, with appropriate porosity, pore structure and distribution, and optimal vascularization with both surface and structural compatibility. The challenge is to establish a proper balance between porosity and mechanical performance of scaffolds.This work investigates the use of two different types of triple periodic minimal surfaces, Schwarz and Schoen, in order to design better biomimetic scaffolds with high surface-to-volume ratio, high porosity and good mechanical properties. The mechanical behaviour of these structures is assessed through the finite element method software Abaqus. The effect of two parametric parameters (thickness and surface radius) is also evaluated regarding its porosity and mechanical behaviour.
- A stochastic approach to optimize Maritime pine (Pinus pinaster Ait.) stand management scheduling under fire risk. An application in PortugalPublication . Ferreira, L.; Constantino, M.; Borges, J. G.The paper discusses research aiming at the development of a management scheduling model for even-aged stands that may take into consideration fuel treatments to address the risk of wildfires. A Stochastic dynamic programming (SDP) approach is proposed to determine the policy (e.g. the fuel treatment and thinning schedules and the rotation age) that produces the maximum expected discounted net revenue. Fuel treatment activities encompass shrub cleanings. Emphasis was on combining a deterministic stand-level growth and yield model with wildfire occurrence and damage models to design a SDP network. SDP stages are defined by age and state variables include both the stand basal area and the number of years since the last fuel treatment. Fire occurrence and damage scenarios are addressed at each stage. Results from an application to Maritime pine (Pinus pinaster Ait.) stand management scheduling in Leiria National Forest, Portugal, are presented. Results suggest that the modeling strategy may help assess the impact of wildfire risk on the optimal stand management schedule. They confirm that the maximum expected discounted net revenues decreases. Further, albeit some timber may be salvaged after the wildfire, rotation age also decreases when the risk of fire is considered. Finally, they provide interesting insights about the role of thinning and fuel treatment policies in mitigating risk.
- Promoting Nerve Regeneration in a Neurotmesis Rat Model Using Poly(DL-lactide-ε-caprolactone) Membranes and Mesenchymal Stem Cells from the Wharton’s Jelly: In Vitro and In Vivo AnalysisPublication . Pereira, T.; Gärtner, A.; Amorim, I.; Almeida, A.; Caseiro, A.R.; Armada-da-Silva, Paulo A. S.; Amado, Sandra; Fregnan, Federica; Varejão, A. S. P.; Santos, J. D.; Bártolo, P. J.; Geuna, S.; Luís, A. L.; Maurício, A. C.In peripheral nerves MSCs can modulate Wallerian degeneration and the overall regenerative response by acting through paracrine mechanisms directly on regenerating axons or upon the nerve-supporting Schwann cells. In the present study, the effect of human MSCs from Wharton’s jelly (HMSCs), differentiated into neuroglial-like cells associated to poly (DL-lactide-ε-caprolactone) membrane, on nerve regeneration, was evaluated in the neurotmesis injury rat sciatic nerve model. Resultsin vitroshowed successful differentiation of HMSCs into neuroglial-like cells, characterized by expression of specific neuroglial markers confirmed by immunocytochemistry and by RT-PCR and qPCR targeting specific genes expressed.In vivotesting evaluated during the healing period of 20 weeks, showed no evident positive effect of HMSCs or neuroglial-like cell enrichment at the sciatic nerve repair site on most of the functional and nerve morphometric predictors of nerve regeneration although the nociception function was almost normal. EPT on the other hand, recovered significantly better after HMSCs enriched membrane employment, to values of residual functional impairment compared to other treated groups. When the neurotmesis injury can be surgically reconstructed with an end-to-end suture or by grafting, the addition of a PLC membrane associated with HMSCs seems to bring significant advantage, especially concerning the motor function recovery.
- Turbomachinery component manufacture by application of electrochemical, electro-physical and photonic processesPublication . Klocke, Fritz; Klink, Andreas; Veselovac, Drazen; Aspinwall, David Keith; Soo, Sein Leung; Schmidt, Michael; Schilp, Johannes; Levy, Gideon; Kruth, Jean-PierreThis paper presents an overview of the current technological and economical capabilities of electrochemical (ECM-based), electro-physical (EDM-based) and photonic (Laser-/EBM-based) additive and removal processes for turbomachinery component manufacture. Starting with the industrial demands and challenges of today, the technologies are reviewed in detail regarding achievable geometrical precision and surface integrity as well as material removal and deposition rates for conventionally difficult-to-cut Ti- and Ni-based alloys and dedicated steels. Past, existing and future areas of technology application of these advanced non-mechanical manufacturing processes are discussed. The paper focusses on the description of shaping processes therefore excludes pure welding or coating applications.
- Enterprise Information SystemsPublication . Varajão, João; Martinho, Ricardo; Soto-Acosta, PedroThis special issue includes original, pertinent and relevant contributions on the technological, organizational and social dimensions of the largely multidisciplinary field of Enterprise Information Systems.
- User-Centered Rating of Well-Being in Older AdultsPublication . Rodrigues, Nuno; Pereira, AntónioPredictions estimate that the future will entail several devices related to IoT (Internet of Things). Most of these will be present in our homes, collecting useful information and triggering informed actions. Much work has been done on collecting data and triggering such devices. However, there is not much work on how to make use of such information to measure the well-being of a person. In the context of older adults, it would be useful to define a means to estimate their well-being, provide them some feedback, and eventually share it with a family member or caregiver. This article emphasizes how to measure well-being through a user-centered Personal Well-being Rating (PWR). Although the proposed rating is idealized as a general equation, our case study is mainly centered on older adults. These are undeniably a group of society that can enrich their lives, by integrating possible solutions implemented considering the PWR. This interpretation opens the door to the development of future interfaces, which can be supported by an explicit way of measuring the well-being of someone inside a home.
- Decision Support System to Diagnosis and Classification of Epilepsy in ChildrenPublication . Rijo, Rui; Silva, Catarina; Pereira, Luis; Gonçalves, Dulce; Agostinho, MargaridaClinical decision support systems play an important role in organizations. They have a tight relation with the information systems. Our goal is to develop a system to support the diagnosis and the classification of epilepsy in children. Around 50 million people in the world have epilepsy. Epilepsy diagnosis can be an extremely complex process, demanding considerable time and effort from physicians and healthcare infrastructures. Exams such as electroencephalograms and magnetic resonances are often used to create a more accurate diagnosis in a short amount of time. After the diagnosis process, physicians classify epilepsy according to the International Classification of Diseases, ninth revision (ICD-9). Physicians need to classify each specific type of epilepsy based on different data, e.g., types of seizures, events and exams' results. The classification process is time consuming and, in some cases, demands for complementary exams. This work presents a text mining approach to support medical decisions relating to epilepsy diagnosis and ICD-9-based classification in children. We put forward a text mining approach using electronically processed medical records, and apply the K-Nearest Neighbor technique as a white-box multiclass classifier approach to classify each instance, mapping it to the corresponding ICD-9-based standard code. Results on real medical records suggest that the proposed framework shows good performance and clear interpretations, albeit the reduced volume of available training data. To overcome this hurdle, in this work we also propose and explore ways of expanding the dataset.
- Registration of Consecutive Frames From Wireless Capsule Endoscopy for 3D Motion EstimationPublication . Oliveira, Marina; Araujo, Helder; Figueiredo, Isabel N.; Pinto, Luís; Curto, Eva; Perdigoto, LuísWireless Capsule Endoscopy (WCE) is a non-invasive medical procedure devised for painless in vivo inspection of the gastrointestinal (GI) tract. It is especially valuable for the examination of the small intestine since it is difficult to reach by traditional endoscopic procedures. The setup includes a camera with an embedded light source and a circuit capable of acquiring and transmitting the video. The main challenge of this technology is the identification of the position and trajectory of the capsule as it travels through the GI tract, which is particularly relevant during the detection of anomalies in the tissue. Given only the information provided by the recorded images, it is possible to estimate the 3D motion of the camera capsule and provide a full trajectory reconstruction. A critical yet difficult step in this process is the image registration between sequential frames. Therefore, being able to determine accurate correspondences between points, regions or features in two consecutive frames is crucial for the computation of the relative rotation and translation of the capsule. This paper comprises a comparative assessment of methodologies to address this problem with a porcine colon dataset obtained with our experimental setup.