Normalização automática de descrições de hotéis

As descrições de produtos turísticos na área da hotelaria, aviação, rent-a-car e pacotes de férias baseiam-se sobretudo em descrições textuais em língua natural muito heterogénea com estilos, apresentações e conteúdos muito diferentes entre si. Uma vez que o sector do turismo é bastante dinâmico e que os seus produtos e ofertas estão constantemente em alteração, o tratamento manual de normalização de toda essa informação não é possível. Neste trabalho construiu-se um protótipo que permite a classificação e extracção automática de informação a partir de descrições de produtos de turismo. Inicialmente a informação é classificada quanto ao tipo. Seguidamente são extraídos os elementos relevantes de cada tipo e gerados objectos facilmente computáveis. Sobre os objectos extraídos, o protótipo com recurso a modelos de textos e imagens gera automaticamente descrições normalizadas e orientadas a um determinado mercado. Esta versatilidade permite um novo conjunto de serviços na promoção e venda dos produtos que seria impossível implementar com a informação original. Este protótipo, embora possa ser aplicado a outros domínios, foi avaliado na normalização da descrição de hotéis. As frases descritivas do hotel são classificadas consoante o seu tipo (Local, Serviços e/ou Equipamento) através de um algoritmo de aprendizagem automática que obtém valores médios de cobertura de 96% e precisão de 72%. A cobertura foi considerada a medida mais importante uma vez que a sua maximização permite que não se percam frases para processamentos posteriores. Este trabalho permitiu também a construção e população de uma base de dados de hotéis que possibilita a pesquisa de hotéis pelas suas características. Esta funcionalidade não seria possível utilizando os conteúdos originais. ABSTRACT: The description of tourism products, like hotel, aviation, rent-a-car and holiday packages, is strongly supported on natural language expressions. Due to the extent of tourism offers and considering the high dynamics in the tourism sector, manual data management is not a reliable or scalable solution. Offer descriptions - in the order of thousands - are structured in different ways, possibly comprising different languages, complementing and/or overlap one another. This work aims at creating a prototype for the automatic classification and extraction of relevant knowledge from tourism-related text expressions. Captured knowledge is represented in a normalized/standard format to enable new services based on this information in order to promote and sale tourism products that would be impossible to implement with the raw information. Although it could be applied to other areas, this prototype was evaluated in the normalization of hotel descriptions. Hotels descriptive sentences are classified according their type (Location, Services and/or Equipment) using a machine learning algorithm. The built setting obtained an average recall of 96% and precision of 72%. Recall considered the most important measure of performance since its maximization allows that sentences were not lost in further processes. As a side product a database of hotels was built and populated with search facilities on its characteristics. This ability would not be possible using the original contents.

Information Usefulness To Support Dialogue Management in Healthcare

The main objective of the framework we are proposing is to help the physician obtain information about the patient's condition in order to reach the \emph{correct} diagnosis as soon as possible. In our proposal, the number of interactions between the physician and the patient is reduced to a strict minimum on the one hand and, on the other hand, it is made possible to increase the number of questions to be asked if the uncertainty about the diagnosis persists. These advantages are due to the fact that (i) we implement a reasoning component that allows us to predict a symptom from another symptom without explicitly asking the patient, (ii) we consider non-binary values for the weights associated with the symptoms, we introduce a dataset filtering process in order to choose which partition should be used with respect to some particular characteristics of the patient, and, in addition, (iv) it was added new functionality to the framework: the ability to detect further future risks of a patient already knowing his pathology. The experimental results we obtained are very encouraging

Developing a radiomic based machine learning model to identify patients with resected non-small-cell lung cancer at high risk of relapse

Background There is a wide variation of recurrence risk of Non-small-cell lung cancer (NSCLC) within the same Tumor Node Metastasis (TNM) stage, suggesting that other parameters are involved in determining this probability. Radiomics allows extraction of quantitative information from images that can be used for clinical purposes. The primary objective of this study is to develop a radiomic prognostic model that predicts a 3 year disease free-survival (DFS) of resected Early Stage (ES) NSCLC patients. Material and Methods 56 pre-surgery non contrast Computed Tomography (CT) scans were retrieved from the PACS of our institution and anonymized. Then they were automatically segmented with an open access deep learning pipeline and reviewed by an experienced radiologist to obtain 3D masks of the NSCLC. Images and masks underwent to resampling normalization and discretization. From the masks hundreds Radiomic Features (RF) were extracted using Py-Radiomics. Hence, RF were reduced to select the most representative features. The remaining RF were used in combination with Clinical parameters to build a DFS prediction model using Leave-one-out cross-validation (LOOCV) with Random Forest. Results and Conclusion A poor agreement between the radiologist and the automatic segmentation algorithm (DICE score of 0.37) was found. Therefore, another experienced radiologist manually segmented the lesions and only stable and reproducible RF were kept. 50 RF demonstrated a high correlation with the DFS but only one was confirmed when clinicopathological covariates were added: Busyness a Neighbouring Gray Tone Difference Matrix (HR 9.610). 16 clinical variables (which comprised TNM) were used to build the LOOCV model demonstrating a higher Area Under the Curve (AUC) when RF were included in the analysis (0.67 vs 0.60) but the difference was not statistically significant (p=0,5147).

Anelli booleani, reticoli booleani e algebre di Boole

Presentazione di anelli booleani, reticoli booleani e algebre di Boole e spiegazione di come e perché sia possibile che lo studio di ciascuna di esse sia equivalente allo studio delle altre due. Trattazione dell'esempio dell'insieme delle parti di un insieme arbitrario, rappresentazione di esso sia come anello booleano che come reticolo booleano e algebra di Boole e descrizione della sua importanza mediante il teorema di Stone (formulato per ciascuna struttura booleana). Rappresentazione dei reticoli distributivi e degli ideali d'ordine di un insieme parzialmente ordinato, per giungere al teorema di Birkhoff.

Quality controls for the Mu2e electromagnetic calorimeter and R&D studies for the muon capture rate determination

According to the SM, while Lepton Flavour Violation is allowed in the neutral sector, Charged Lepton Flavour Violation (CLFV) processes are forbidden. The Mu2e Experiment at Fermilab will search for the CLFV process of neutrinoless conversion of a muon into an electron within the field of an Al nucleus. The Mu2e detectors and its state-of-the-art superconducting magnetic system are presented, with special focus put to the electromagnetic crystal calorimeter. The calorimeter is composed by two annular disks, each one hosting pure CsI crystals read-out by custom silicon photomultipliers (SiPMs). The SiPMs are amplified by custom electronics (FEE) and are glued to copper holders in group of 2 SiPMs and 2 FEE boards thus forming a crystal Readout Unit. These Readout Units are being tested at the Quality Control (QC) Station, whose design, realization and operations are presented in this work. The QC Station allows to determine the gain, the response and the photon detection efficiency of each unit and to evaluate the dependence of these parameters from the supply voltage and temperature. The station is powered by two remotely-controlled power supplies and monitored thanks to a Slow Control system which is also illustrated in this work. In this thesis, we also demonstrated that the calorimeter can perform its own measurement of the Mu2e normalization factor, i.e. the counting of the 1.8 MeV photon line produced in nuclear muon captures. A specific calorimeter sub-system called CAPHRI, composed by four LYSO crystals with SiPM readout, has been designed and tested. We simulated the capability of this system on performing this task showing that it can get a faster and more reliable measurement of the muon capture rates with respect to the current Mu2e detector dedicated to this measurement. The characterization of energy resolution and response uniformity of the four procured LYSO crystals are llustrated.

Graph-based User Scheduling for MIMO LEO-based Satellite Communication Systems

The study of the user scheduling problem in a Low Earth Orbit (LEO) Multi-User MIMO system is the objective of this thesis. With the application of cutting-edge digital beamforming algorithms, a LEO satellite with an antenna array and a large number of antenna elements can provide service to many user terminals (UTs) in full frequency reuse (FFR) schemes. Since the number of UTs on-ground are many more than the transmit antennas on the satellite, user scheduling is necessary. Scheduling can be accomplished by grouping users into different clusters: users within the same cluster are multiplexed and served together via Space Division Multiple Access (SDMA), i.e., digital beamforming or Multi-User MIMO techniques; the different clusters of users are then served on different time slots via Time Division Multiple Access (TDMA). The design of an optimal user grouping strategy is known to be an NP-complete problem which can be solved only through exhaustive search. In this thesis, we provide a graph-based user scheduling and feed space beamforming architecture for the downlink with the aim of reducing user inter-beam interference. The main idea is based on clustering users whose pairwise great-circle distance is as large as possible. First, we create a graph where the users represent the vertices, whereas an edge in the graph between 2 users exists if their great-circle distance is above a certain threshold. In the second step, we develop a low complex greedy user clustering technique and we iteratively search for the maximum clique in the graph, i.e., the largest fully connected subgraph in the graph. Finally, by using the 3 aforementioned power normalization techniques, a Minimum Mean Square Error (MMSE) beamforming matrix is deployed on a cluster basis. The suggested scheduling system is compared with a position-based scheduler, which generates a beam lattice on the ground and randomly selects one user per beam to form a cluster.