Search

Your search keyword '"Meira, Jorge"' showing total 140 results
Start Over Author "Meira, Jorge" Publication Type Periodicals
140 results on '"Meira, Jorge"'

1. At Your Service: Coffee Beans Recommendation From a Robot Assistant

Author

de Berardinis, Jacopo, Pizzuto, Gabriella, Lanza, Francesco, Chella, Antonio, Meira, Jorge, and Cangelosi, Angelo

Subjects
Computer Science - Information Retrieval, Computer Science - Human-Computer Interaction
Abstract

With advances in the field of machine learning, precisely algorithms for recommendation systems, robot assistants are envisioned to become more present in the hospitality industry. Additionally, the COVID-19 pandemic has also highlighted the need to have more service robots in our everyday lives, to minimise the risk of human to-human transmission. One such example would be coffee shops, which have become intrinsic to our everyday lives. However, serving an excellent cup of coffee is not a trivial feat as a coffee blend typically comprises rich aromas, indulgent and unique flavours and a lingering aftertaste. Our work addresses this by proposing a computational model which recommends optimal coffee beans resulting from the user's preferences. Specifically, given a set of coffee bean properties (objective features), we apply different supervised learning techniques to predict coffee qualities (subjective features). We then consider an unsupervised learning method to analyse the relationship between coffee beans in the subjective feature space. Evaluated on a real coffee beans dataset based on digitised reviews, our results illustrate that the proposed computational model gives up to 92.7 percent recommendation accuracy for coffee beans prediction. From this, we propose how this computational model can be deployed on a service robot to reliably predict customers' coffee bean preferences, starting from the user inputting their coffee preferences to the robot recommending the coffee beans that best meet the user's likings., Comment: Extended version of submission to ACM HAI 2020

Published
2020

3. A Hybrid Model to Classify Physical Activity Profiles

Author

Crista, Vítor, Martinho, Diogo, Meira, Jorge, Carneiro, João, Corchado, Juan, Marreiros, Goreti, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, González-Briones, Alfonso, editor, Almeida, Ana, editor, Fernandez, Alberto, editor, El Bolock, Alia, editor, Durães, Dalila, editor, Jordán, Jaume, editor, and Lopes, Fernando, editor

Published
2022
Full Text
View/download PDF

4. Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations

Author

Glauner, Patrick, Dahringer, Niklas, Puhachov, Oleksandr, Meira, Jorge Augusto, Valtchev, Petko, State, Radu, and Duarte, Diogo

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction
Abstract

Power grids are critical infrastructure assets that face non-technical losses (NTL) such as electricity theft or faulty meters. NTL may range up to 40% of the total electricity distributed in emerging countries. Industrial NTL detection systems are still largely based on expert knowledge when deciding whether to carry out costly on-site inspections of customers. Electricity providers are reluctant to move to large-scale deployments of automated systems that learn NTL profiles from data due to the latter's propensity to suggest a large number of unnecessary inspections. In this paper, we propose a novel system that combines automated statistical decision making with expert knowledge. First, we propose a machine learning framework that classifies customers into NTL or non-NTL using a variety of features derived from the customers' consumption data. The methodology used is specifically tailored to the level of noise in the data. Second, in order to allow human experts to feed their knowledge in the decision loop, we propose a method for visualizing prediction results at various granularity levels in a spatial hologram. Our approach allows domain experts to put the classification results into the context of the data and to incorporate their knowledge for making the final decisions of which customers to inspect. This work has resulted in appreciable results on a real-world data set of 3.6M customers. Our system is being deployed in a commercial NTL detection software., Comment: Proceedings of the 17th IEEE International Conference on Data Mining Workshops (ICDMW 2017)

Published
2017

6. Using Machine Learning to Predict the Users Ratings on TripAdvisor Based on Their Reviews

Author

Carneiro, João, Meira, Jorge, Novais, Paulo, Marreiros, Goreti, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Kotenko, Igor, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Barbosa, Simone Diniz Junqueira, Editorial Board Member, Chen, Phoebe, Editorial Board Member, Cuzzocrea, Alfredo, Editorial Board Member, Du, Xiaoyong, Editorial Board Member, Kara, Orhun, Editorial Board Member, Liu, Ting, Editorial Board Member, Sivalingam, Krishna M., Editorial Board Member, Slezak, Dominik, Editorial Board Member, Washio, Takashi, Editorial Board Member, Yang, Xiaokang, Editorial Board Member, Yuan, Junsong, Editorial Board Member, De La Prieta, Fernando, editor, El Bolock, Alia, editor, Durães, Dalila, editor, Carneiro, João, editor, Lopes, Fernando, editor, and Julian, Vicente, editor

Published
2021
Full Text
View/download PDF

7. The Top 10 Topics in Machine Learning Revisited: A Quantitative Meta-Study

Author

Glauner, Patrick, Du, Manxing, Paraschiv, Victor, Boytsov, Andrey, Andrade, Isabel Lopez, Meira, Jorge, Valtchev, Petko, and State, Radu

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning
Abstract

Which topics of machine learning are most commonly addressed in research? This question was initially answered in 2007 by doing a qualitative survey among distinguished researchers. In our study, we revisit this question from a quantitative perspective. Concretely, we collect 54K abstracts of papers published between 2007 and 2016 in leading machine learning journals and conferences. We then use machine learning in order to determine the top 10 topics in machine learning. We not only include models, but provide a holistic view across optimization, data, features, etc. This quantitative approach allows reducing the bias of surveys. It reveals new and up-to-date insights into what the 10 most prolific topics in machine learning research are. This allows researchers to identify popular topics as well as new and rising topics for their research.

Published
2017

8. Is Big Data Sufficient for a Reliable Detection of Non-Technical Losses?

Author

Glauner, Patrick, Migliosi, Angelo, Meira, Jorge, Valtchev, Petko, State, Radu, and Bettinger, Franck

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence
Abstract

Non-technical losses (NTL) occur during the distribution of electricity in power grids and include, but are not limited to, electricity theft and faulty meters. In emerging countries, they may range up to 40% of the total electricity distributed. In order to detect NTLs, machine learning methods are used that learn irregular consumption patterns from customer data and inspection results. The Big Data paradigm followed in modern machine learning reflects the desire of deriving better conclusions from simply analyzing more data, without the necessity of looking at theory and models. However, the sample of inspected customers may be biased, i.e. it does not represent the population of all customers. As a consequence, machine learning models trained on these inspection results are biased as well and therefore lead to unreliable predictions of whether customers cause NTL or not. In machine learning, this issue is called covariate shift and has not been addressed in the literature on NTL detection yet. In this work, we present a novel framework for quantifying and visualizing covariate shift. We apply it to a commercial data set from Brazil that consists of 3.6M customers and 820K inspection results. We show that some features have a stronger covariate shift than others, making predictions less reliable. In particular, previous inspections were focused on certain neighborhoods or customer classes and that they were not sufficiently spread among the population of customers. This framework is about to be deployed in a commercial product for NTL detection., Comment: Proceedings of the 19th International Conference on Intelligent System Applications to Power Systems (ISAP 2017)

Published
2017

11. Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets

Author

Glauner, Patrick, Meira, Jorge, Dolberg, Lautaro, State, Radu, Bettinger, Franck, Rangoni, Yves, and Duarte, Diogo

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence
Abstract

Electricity theft is a major problem around the world in both developed and developing countries and may range up to 40% of the total electricity distributed. More generally, electricity theft belongs to non-technical losses (NTL), which are losses that occur during the distribution of electricity in power grids. In this paper, we build features from the neighborhood of customers. We first split the area in which the customers are located into grids of different sizes. For each grid cell we then compute the proportion of inspected customers and the proportion of NTL found among the inspected customers. We then analyze the distributions of features generated and show why they are useful to predict NTL. In addition, we compute features from the consumption time series of customers. We also use master data features of customers, such as their customer class and voltage of their connection. We compute these features for a Big Data base of 31M meter readings, 700K customers and 400K inspection results. We then use these features to train four machine learning algorithms that are particularly suitable for Big Data sets because of their parallelizable structure: logistic regression, k-nearest neighbors, linear support vector machine and random forest. Using the neighborhood features instead of only analyzing the time series has resulted in appreciable results for Big Data sets for varying NTL proportions of 1%-90%. This work can therefore be deployed to a wide range of different regions around the world., Comment: Proceedings of the 3rd IEEE/ACM International Conference on Big Data Computing Applications and Technologies (BDCAT 2016)

Published
2016

12. The Challenge of Non-Technical Loss Detection using Artificial Intelligence: A Survey

Author

Glauner, Patrick, Meira, Jorge Augusto, Valtchev, Petko, State, Radu, and Bettinger, Franck

Subjects
Computer Science - Artificial Intelligence
Abstract

Detection of non-technical losses (NTL) which include electricity theft, faulty meters or billing errors has attracted increasing attention from researchers in electrical engineering and computer science. NTLs cause significant harm to the economy, as in some countries they may range up to 40% of the total electricity distributed. The predominant research direction is employing artificial intelligence to predict whether a customer causes NTL. This paper first provides an overview of how NTLs are defined and their impact on economies, which include loss of revenue and profit of electricity providers and decrease of the stability and reliability of electrical power grids. It then surveys the state-of-the-art research efforts in a up-to-date and comprehensive review of algorithms, features and data sets used. It finally identifies the key scientific and engineering challenges in NTL detection and suggests how they could be addressed in the future.

Published
2016
Full Text
View/download PDF

13. Comparative Results with Unsupervised Techniques in Cyber Attack Novelty Detection

Author

Meira, Jorge, Andrade, Rui, Praça, Isabel, Carneiro, João, Marreiros, Goreti, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Novais, Paulo, editor, Jung, Jason J., editor, Villarrubia González, Gabriel, editor, Fernández-Caballero, Antonio, editor, Navarro, Elena, editor, González, Pascual, editor, Carneiro, Davide, editor, Pinto, António, editor, Campbell, Andrew T., editor, and Durães, Dalila, editor

Published
2019
Full Text
View/download PDF

14. Database Processing-in-Memory: A Vision

Author

Kepe, Tiago R., Almeida, Eduardo C., Alves, Marco A. Z., Meira, Jorge A., Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Hartmann, Sven, editor, Küng, Josef, editor, Chakravarthy, Sharma, editor, Anderst-Kotsis, Gabriele, editor, Tjoa, A Min, editor, and Khalil, Ismail, editor

Published
2019
Full Text
View/download PDF

23. 'Overloaded!' — A Model-Based Approach to Database Stress Testing

Author

Meira, Jorge Augusto, de Almeida, Eduardo Cunha, Kim, Dongsun, Filho, Edson Ramiro Lucas, Le Traon, Yves, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Hartmann, Sven, editor, and Ma, Hui, editor

Published
2016
Full Text
View/download PDF

24. Performance evaluation of unsupervised techniques in cyber-attack anomaly detection

Author

Meira, Jorge, Andrade, Rui, Praça, Isabel, Carneiro, João, Bolón-Canedo, Verónica, Alonso-Betanzos, Amparo, and Marreiros, Goreti

Abstract

Cyber security is a critical area in computer systems especially when dealing with sensitive data. At present, it is becoming increasingly important to assure that computer systems are secured from attacks due to modern society dependence from those systems. To prevent these attacks, nowadays most organizations make use of anomaly-based intrusion detection systems (IDS). Usually, IDS contain machine learning algorithms which aid in predicting or detecting anomalous patterns in computer systems. Most of these algorithms are supervised techniques, which contain gaps in the detection of unknown patterns or zero-day exploits, since these are not present in the algorithm learning phase. To address this problem, we present in this paper an empirical study of several unsupervised learning algorithms used in the detection of unknown attacks. In this study we evaluated and compared the performance of different types of anomaly detection techniques in two public available datasets: the NSL-KDD and the ISCX. The aim of this evaluation allows us to understand the behavior of these techniques and understand how they could be fitted in an IDS to fill the mentioned flaw. Also, the present evaluation could be used in the future, as a comparison of results with other unsupervised algorithms applied in the cybersecurity field. The results obtained show that the techniques used are capable of carrying out anomaly detection with an acceptable performance and thus making them suitable candidates for future integration in intrusion detection tools.

Published
2024
Full Text
View/download PDF

25. WAYSIDE MONITORING SYSTEM FOR SAFE RAIL TRANSPORTATION - THE WAY4SAFERAIL PROJECT.

Author

Vale, Cecilia, Ribeiro, Diogo, Mosleh, Araliya, Montenegro, Pedro, Meixedo, Andreia, Marreiros, Goreti, Meira, Jorge, Silva, Ruben, Mohammadi, Mohammadreza, Guedes, António, and Lourenço, Afonso

Subjects
RAILROAD traffic, RAILROAD maintenance & repair, ARTIFICIAL intelligence, RAILROAD safety measures, COST effectiveness
Abstract

Given the critical role of the rail sector in society, railway managers and operators must prioritize traffic and maintenance costs. While current track wayside monitoring systems can detect wheel defects, they do not categorize them by severity or identify risky situations, such as unbalanced loads in railway circulation. The WAY4SAFERAIL project seeks to address this limitation by developing Artificial Intelligence AI-based techniques that improve rail safety by identifying wheel damage conditions and unstable situations caused by unbalanced loads at an early stage. As an initial step in applying AI techniques, this paper presents a part of the research conducted within the WAY4SAFERAIL project, particularly the numerical simulations of wheel defects (wheel flat and polygonal wheel) and unbalanced loads. The proposed methodology demonstrates its reliability and cost-effectiveness for identifying wheel defects and detecting unbalanced train loads. [ABSTRACT FROM AUTHOR]

Published
2023

28. Data-driven predictive maintenance framework for railway systems.

Author

Meira, Jorge, Veloso, Bruno, Bolón-Canedo, Verónica, Marreiros, Goreti, Alonso-Betanzos, Amparo, and Gama, João

Subjects
*ANOMALY detection (Computer security), *BIG data, *INDUSTRY 4.0, *K-nearest neighbor classification, *ELECTRONIC data processing, *MACHINE learning, *RAILROADS
Abstract

The emergence of the Industry 4.0 trend brings automation and data exchange to industrial manufacturing. Using computational systems and IoT devices allows businesses to collect and deal with vast volumes of sensorial and business process data. The growing and proliferation of big data and machine learning technologies enable strategic decisions based on the analyzed data. This study suggests a data-driven predictive maintenance framework for the air production unit (APU) system of a train of Metro do Porto. The proposed method assists in detecting failures and errors in machinery before they reach critical stages. We present an anomaly detection model following an unsupervised approach, combining the Half-Space-trees method with One Class K Nearest Neighbor, adapted to deal with data streams. We evaluate and compare our approach with the Half-Space-Trees method applied without the One Class K Nearest Neighbor combination. Our model produced few type-I errors, significantly increasing the value of precision when compared to the Half-Space-Trees model. Our proposal achieved high anomaly detection performance, predicting most of the catastrophic failures of the APU train system. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

33. Supporting argumentation dialogues in group decision support systems: an approach based on dynamic clustering

Author

Conceição, Luís, Rodrigues, Vasco, Meira, Jorge, Marreiros, Goreti, Novais, Paulo, Universidade do Minho, and Repositório Científico do Instituto Politécnico do Porto

Subjects
Fluid Flow and Transfer Processes, Group decision making, group decision making, dynamic clustering, natural language processing, argumentation, Science & Technology, Process Chemistry and Technology, Natural language processing, Argumentation, General Engineering, General Materials Science, Instrumentation, Computer Science Applications, Dynamic clustering
Abstract

Group decision support systems (GDSSs) have been widely studied over the recent decades. The Web-based group decision support systems appeared to support the group decision-making process by creating the conditions for it to be effective, allowing the management and participation in the process to be carried out from any place and at any time. In GDSS, argumentation is ideal, since it makes it easier to use justifications and explanations in interactions between decision-makers so they can sustain their opinions. Aspect-based sentiment analysis (ABSA) intends to classify opinions at the aspect level and identify the elements of an opinion. Intelligent reports for GDSS provide decision makers with accurate information about each decision-making round. Applying ABSA techniques to group decision making context results in the automatic identification of alternatives and criteria, for instance. This automatic identification is essential to reduce the time decision makers take to step themselves up on group decision support systems and to offer them various insights and knowledge on the discussion they are participating in. In this work, we propose and implement a methodology that uses an unsupervised technique and clustering to group arguments on topics around a specific alternative, for example, or a discussion comparing two alternatives. We experimented with several combinations of word embedding, dimensionality reduction techniques, and different clustering algorithms to achieve the best approach. The best method consisted of applying the KMeans++ clustering technique, using SBERT as a word embedder with UMAP dimensionality reduction. These experiments achieved a silhouette score of 0.63 with eight clusters on the baseball dataset, which wielded good cluster results based on their manual review and word clouds. We obtained a silhouette score of 0.59 with 16 clusters on the car brand dataset, which we used as an approach validation dataset. With the results of this work, intelligent reports for GDSS become even more helpful, since they can dynamically organize the conversations taking place by grouping them on the arguments used., This research was funded by National Funds through the Portuguese FCT—Fundação para a Ciência e a Tecnologia under the R&D Units Project Scope UIDB/00319/2020, UIDB/00760/2020, UIDP/00760/2020, and by the Luís Conceição Ph.D. Grant with the reference SFRH/BD/137150/2018.

Published
2022

40. Estudio sobre las aplicaciones de los Sistemas Multiagentes en la Agricultura

Author

Pérez-Pons, María-Eugenia, Parra Domínguez, Javier, Manuel Corchado, Juan, Meira, Jorge, and Marreiros, Goreti

Subjects
desarrollo económico, technology, economic developmen, tecnología
Abstract

[ES] El intercambio de ideas entre científicos y técnicos, tanto del ámbito académico como empresarial, es fundamental para facilitar el desarrollo de sistemas que puedan satisfacer las demandas de la sociedad actual. La transferencia de tecnología en este campo sigue siendo un reto y, por ello, este tipo de aportaciones se consideran de forma destacada en esta recopilación. Este libro trae debates y publicaciones sobre el desarrollo de técnicas innovadoras de problemas complejos de IoT. El programa técnico se centra tanto en la alta calidad como en la diversidad, con contribuciones en áreas de investigación bien establecidas y en evolución. Específicamente, 10 capítulos fueron presentados a este libro. Los editores alentaron y agradecieron particularmente las contribuciones sobre IA y computación distribuida en aplicaciones de IoT. Los editores agradecen especialmente el apoyo financiero del proyecto “Virtual-Ledgers-Tecnologías DLT/Blockchain y Cripto-IOT sobre organizaciones virtuales de agentes ligeros y su aplicación en la eficiencia en el transporte de última milla”, ID SA267P18, financiado por Junta de Castilla y León y fondos FEDER., [EN] The exchange of ideas between scientists and technicians, from both academic and business areas, is essential in order to ease the development of systems which can meet the demands of today’s society. Technology transfer in this field is still a challenge and, for that reason, this type of contributions are notably considered in this compilation. This book brings in discussions and publications concerning the development of innovative techniques of IoT complex problems. The technical program focuses both on high quality and diversity, with contributions in well-established and evolving areas of research. Specifically, 10 chapters were submitted to this book. The editors particularly encouraged and welcomed contributions on AI and distributed computing in IoT applications. The editors are specially grateful for the funding supporting by the project “Virtual-Ledgers-Tecnologías DLT/Blockchain y Cripto-IOT sobre organizaciones virtuales de agentes ligeros y su aplicación en la eficiencia en el transporte de última milla”, ID SA267P18, financed by regional government of Castilla y León and FEDER funds.

Published
2022

41. Experiencias en el desarrollo de soluciones de mantenimiento predictivo

Author

Alves, Filipe, Meira, Jorge, Marreiros, Goreti, and Leitão, Paulo

Subjects
desarrollo económico, technology, tecnología, economic development
Abstract

[ES] El taller sobre tecnologías de información y comunicación disruptivas para la innovación y la transformación digital, organizado bajo el alcance del proyecto disruptiva, tiene como objetivo discutir los problemas, desafíos y beneficios del uso de tecnologías digitales disruptivas, a saber, Internet de las cosas, Big data, computación en la nube, sistemas multi-agentes, aprendizaje automático, realidad virtual y aumentada, y robótica colaborativa, para apoyar la transformación digital en curso en la sociedad Temas Intelligent Manufacturing Systems Industry 4.0 and digital transformation Internet of Things Cyber-security Collaborative and intelligent robotics Multi-Agent Systems Industrial Cyber-Physical Systems Virtualization and digital twins Predictive maintenance Virtual and augmented reality Big Data and advanced data analytics Edge and cloud computing, [EN] The workshop on Disruptive Information and Communication Technologies for Innovation and Digital transformation, organized under the scope of the Disruptive project, aims to discuss problems, challenges and benefits of using disruptive digital technologies, namely Internet of Things, Big data, cloud computing, multi-agent systems, machine learning, virtual and augmented reality, and collaborative robotics, to support the on-going digital transformation in society Topics Intelligent Manufacturing Systems Industry 4.0 and digital transformation Internet of Things Cyber-security Collaborative and intelligent robotics Multi-Agent Systems Industrial Cyber-Physical Systems Virtualization and digital twins Predictive maintenance Virtual and augmented reality Big Data and advanced data analytics Edge and cloud computing

Published
2022

42. A Recommendation System For Insurance Built With A Multivariate Hawkes Process Based On Customers' Life Events

Author

Lesage, Laurent, Deaconu, Madalina, Lejay, Antoine, Meira, Jorge, Nichil, Geoffrey, State, Radu, Interdisciplinary Centre for Security, Reliability and Trust [Luxembourg] (SnT), Université du Luxembourg (Uni.lu), Processus aléatoires spatio-temporels et leurs applications (PASTA), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut Élie Cartan de Lorraine (IECL), Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Institut Élie Cartan de Lorraine (IECL), Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Foyer Assurances [Leudelange], University of Luxembourg [Luxembourg], The first author also gratefully acknowledges the funding received towards our project (number 13659700) from the Luxembourgish National Research Fund (FNR), INRIA Lorraine, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Insurance, Multivariate Hawkes Process, Recommendation System, Life Events, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

We construct a recommendation system for insurance with a Multivariate Hawkes Process, in order to take into account the influence of life events (e.g. marriage, birth, change of job) on the insurance covering selection from customers. This Multivariate Hawkes Process includes several specific features aiming to compute relevant recommendations to customers from a Luxembourgish insurance company. Some of these features are intent to propose a personalized background intensity for each customer thanks to a Machine Learning model, to use triggering functions suited for insurance data or to overcome flaws in real-world data by adding a specific penalization term in the objective function. Our recommendation system has been backtested over a full year. Observations from model parameters and results from this back-test show that taking into account life events by a Multivariate Hawkes Process allows us to improve significantly the accuracy of recommendations.

Published
2021

44. Influence of intensive near-work on refractive, biometric and topographic changes in last year Portuguese medical students: one-year longitudinal study

Author

Costa, Sónia Torres, Sousa, Sara, Meira, Jorge, Brandão, Elisete, Falcão-Reis, Fernando, and Falcão, Manuel

Abstract

Purpose: To analyze the refractive, biometric and topographic changes in last year Portuguese medical students exposed to high educational demands. Methods: One-year longitudinal cohort study was performed. Data collected consisted in ocular refraction, axial length (AL), keratometry, corneal thickness, macular thickness and volume. Ophthalmological evaluations were performed 6 months before the students’ final exam, one month after the exam and 6 months later. Results: Twenty-five medical students were included. The mean spherical equivalent was -1,57 ± 1,29 D at the 1st visit, -1,73 ± 1,44 D in the 2nd visit and -1,40 ± 1,39 D in the 3rd visit. There were no significant differences in the mean spherical equivalent between the 1st and 2nd visits (p=0,055) and between the 1st and 3rd visits (p=0,331). In the 1st, 2nd and 3rd visits, the AL was 23,91 ± 0,99 mm; 24,01 ± 0,98 mm and 23,94 ±1,03 mm, respectively. The AL increased significantly between the 1st and 2nd visits (p0,05). Conclusions: This study failed to show statistically significant changes in refraction towards myopia in Portuguese medical students after a long period of near-work; nonetheless the small sample size may have contributed to the lack of statistical significance. The refractive values returned to baseline after 6 months., Objetivo: Analisar as alterações refrativas, biométricas e topográficas, em estudantes de medicina Portugueses, no último ano da faculdade, expostos a um elevado nível de exigência académica durante o estudo para o exame de acesso à formação específica. Métodos: Estudo coorte longitudinal com a duração de um ano. Foram obtidos dados relativos à refração ocular, comprimento axial, queratometria, espessura da córnea em diferentes pontos, assim como, espessura e volume da mácula. Os exames oftalmológicos foram realizados 6 meses antes do exame de acesso à formação específica, repetidos 1 mês depois e, por fim, 6 meses após o exame. Resultados: Vinte e cinco estudantes de medicina foram incluídos. Inicialmente, o valor médio do equivalente esférico foi -1,57 ± 1,29 dioptrias (D). Na 2ª visita, foi -1,73 ± 1,44 D e, na 3ª visita, foi -1,40 ± 1,39 D. Não se observaram diferenças estatisticamente significativas no equivalente esférico entre a 1ª e 2ª visitas (p=0,055) e a 1ª e 3ª visitas (p=0,331). Na 1ª, 2ª e 3ª visita o comprimento axial foi 23,91 ± 0,99 mm; 24,01 ± 0,98 mm e 23,94 ±1,03 mm, respetivamente. O aumento do comprimento axial entre a 1ª e a 2ª visitas foi estatisticamente significativo (p

Published
2020

46. Immediate Reactions to Fluorescein and Indocyanine Green in Retinal Angiography: Review of Literature and Proposal for Patient’s Evaluation

Author

Meira, Jorge, Marques, Maria Luís, Falcão-Reis, Fernando, Rebelo Gomes, Eva, and Carneiro, Ângela

Subjects
indocyanine green, genetic structures, fluorescein, hypersensitivity reaction, ophthalmic dyes, Review, adverse reactions, eye diseases, retinal angiography
Abstract

Introduction: Contrast rapid sequence angiography with fluorescein or indocyanine green (ICG) is a diagnostic procedure commonly used in ophthalmology. Adverse reactions to fluorescein and ICG are rare and may be classified as toxic, of hypersensitivity and non-specific. The evaluation and management of a patient with an adverse reaction is a challenge for the majority of ophthalmologists, as is the assessment of risk factors that may contraindicate the procedure. Purpose: We aim to review the concepts underlying adverse reactions to fluorescein and ICG, especially those of hypersensitivity, and present a proposal or the evaluation of the patients in need to perform retinal angiography and for the treatment of immediate reactions to fluorescein and ICG. Methods: The available literature was examined using PubMed-Medline, and using the MeSH terms "fluorescein", "Indocyanine green", "ophthalmic dyes", "retinal angiography", "adverse reactions", and "allergic reaction". Conclusion: This review may help ophthalmologists to identify patients with higher risk of a hypersensitivity reaction and give them tools to recognize patients with suspected hypersensitivity that may benefit from an allergy study. info:eu-repo/semantics/publishedVersion

Published
2020

47. Immediate Reactions to Fluorescein and Indocyanine Green in Retinal Angiography: Review of Literature and Proposal for Patient’s Evaluation

Author

Meira,Jorge, Marques,Maria Luís, Falcão-Reis,Fernando, Rebelo Gomes,Eva, and Carneiro,Ângela

Subjects
Clinical Ophthalmology
Abstract

Jorge Meira, 1,* Maria Luís Marques, 2,* Fernando Falcão-Reis, 1, 3 Eva Rebelo Gomes, 2 Ângela Carneiro 1, 3 1Department of Ophthalmology, Centro Hospitalar Universitário São João, Porto, Portugal; 2Department of Allergy and Clinical Immunology, Centro Hospitalar Universitário do Porto, Porto, Portugal; 3Department of Surgery and Physiology, Faculty of Medicine, University of Porto, Porto, Portugal*These authors contributed equally to this workCorrespondence: Jorge MeiraDepartment of Ophthalmology of São João Hospital, Avenida Prof. Hernâni Monteiro, Porto 4202 – 451, PortugalTel +351225512100Fax +351225513669Email jorgesmeira@gmail.comIntroduction: Contrast rapid sequence angiography with fluorescein or indocyanine green (ICG) is a diagnostic procedure commonly used in ophthalmology. Adverse reactions to fluorescein and ICG are rare and may be classified as toxic, of hypersensitivity and non-specific. The evaluation and management of a patient with an adverse reaction is a challenge for the majority of ophthalmologists, as is the assessment of risk factors that may contraindicate the procedure.Purpose: We aim to review the concepts underlying adverse reactions to fluorescein and ICG, especially those of hypersensitivity, and present a proposal or the evaluation of the patients in need to perform retinal angiography and for the treatment of immediate reactions to fluorescein and ICG.Methods: The available literature was examined using PubMed-Medline, and using the MeSH terms “fluorescein”, “Indocyanine green”, “ophthalmic dyes”, “retinal angiography”, “adverse reactions”, and “allergic reaction”.Conclusion: This review may help ophthalmologists to identify patients with higher risk of a hypersensitivity reaction and give them tools to recognize patients with suspected hypersensitivity that may benefit from an allergy study.Keywords: fluorescein, indocyanine green, ophthalmic dyes, retinal angiography, adverse reactions, hypersensitivity reaction

Published
2020

48. Evaluation of the Results of the Application of the Dexamethasone Implant in the Treatment of Diabetic Macular Edema in Clinical Practice

Author

Meira, Jorge

Subjects
genetic structures, eye diseases
Abstract

OBJETIVOS: Avaliação da eficácia e segurança do implante intravítreo de dexametasona no tratamento do edema macular diabético persistente, na prática clínica. MATERIAL E MÉTODOS: Estudo retrospetivo dos pacientes com edema macular diabético tratados com implante de dexametasona entre dezembro de 2010 e de 2016. A análise da eficácia englobou a acuidade visual e espessura central da retina. A análise de segurança a pressão intraocular e a necessidade de medicação hipotensora. RESULTADOS: Selecionámos 72 pacientes, metade do sexo feminino, com idade média 67.6 anos, já submetidos a tratamento prévio. Após colocação do implante, nos períodos de seguimento de 1-2 meses e 3-4 meses, documentou-se melhoria das médias da acuidade visual de 0.0944 logMAR (p=0.000) e 0.0804 logMAR (p=0.001) e da espessura central da retina de 285.11μm (p=0.000) e 202.056μm (p=0.003). Relativamente à segurança, documentou-se um agravamento médio da pressão intraocular de 1.972mmHg (p=0.000) e 0.946mmHg (p=0.032); 72.2% dos pacientes necessitaram de medicação hipotensora. CONCLUSÃO: O implante de dexametasona promoveu a recuperação da acuidade visual e melhorias significativas da espessura central da retina. Registámos aumentos da pressão intraocular, controlados com medicação hipotensora. Não foi possível documentar o desenvolvimento e/ou progressão de catarata. Este estudo apresenta limitações; estudos com amostras e períodos de seguimento superiores serão importantes para melhor caracterização da eficácia e segurança, Revista Sociedade Portuguesa de Oftalmologia, Vol. 43 N.º 2 (2019)

Published
2019

50. At Your Service

Author

de Berardinis, Jacopo, primary, Pizzuto, Gabriella, additional, Lanza, Francesco, additional, Chella, Antonio, additional, Meira, Jorge, additional, and Cangelosi, Angelo, additional

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results