Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre

Sobre

Davide Carneiro é Professor Coordenador na Escola Superior de Tecnologia e Gestão do Instituto Politécnico do Porto. É também investigador integrado no Centro de Inovação e Investigação em Ciências Empresariais e Sistemas de Informação, da mesma instituição, e membro colaborador do INESC TEC. Tem o grau de Doutor com Menção Europeia atribuído conjuntamente pelas Universidades de Minho, Aveiro e Porto em 2013, através do Programa Doutoral MAP-i. Desenvolve investigação científica em áreas de aplicação da Inteligência Artificial e das Ciências dos Dados, incluindo na Resolução Alternativa de Conflitos, Interação Homem-Computador e Deteção de Fraude. Interessa-se ainda por problemas relacionados com meta-learning e explicabilidade, e como estes podem ser utilizados no contexto de problemas reais. Nos últimos anos participou em vários projetos de investigação financiados nas áreas de Inteligência Artificial, Inteligência Ambiente, Resolução Alternativa de Conflitos e Deteção de Fraude. Foi coordenador científico do projeto Neurat (NORTE-01-0247-FEDER-039900) e é coordenador institucional do projeto europeu EJUST ODR Scheme (JUST-2021-EJUSTICE, 101046468). A nível nacional é Investigador Principal dos projetos CEDEs - Continuously Evolving Distributed Ensembles (EXPL/CCI-COM/0706/2021) e xAIDMLS (CPCA-IAC/AV/475278/2022), financiados pela FCT. É ainda atualmente investigador nos projetos europeus FACILITATE-AI e PRIVATEER.

É autor de mais de 150 publicações científicas nas suas áreas de investigação, incluindo a autoria de um livro de cariz científico, três livros sob a forma editada, e mais de 140 capítulos de livro, publicações em revistas internacionais indexadas, e artigos em atas de conferências. Em paralelo, dedica-se ainda fortemente à orientação científica de Estudantes, envolvendo-os sempre que possível em tarefas práticas integradas nos projetos de investigação em que participa.

Davide é co-fundador e CRO da AnyBrain, uma startup portuguesa no campo da Interação Homem Computador. A empresa desenvolve software para a deteção de fadiga em ambientes de escritório, (https://performetric.net/), para a análise de performance em eSports (https://performetric.gg/), e para identificação de jogadores e deteção de fraude em eSports (https://anybrain.gg/).

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Davide Rua Carneiro
  • Cargo

    Investigador Sénior
  • Desde

    01 agosto 2022
002
Publicações

2024

Supervised and unsupervised techniques in textile quality inspections

Autores
Ferreira, M; Carneiro, R; Guimarães, M; Oliveira, V;

Publicação
Procedia Computer Science

Abstract
Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data. © 2024 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)

2023

Data-Driven Production Planning Approach Based on Suppliers and Subcontractors Analysis: The Case of the Footwear Cluster

Autores
Ferreira, R; Sousa, C; Carneiro, D; Cardeiro, C;

Publicação
Procedia Computer Science

Abstract

2023

Real-Time Algorithm Recommendation Using Meta-Learning

Autores
Palumbo, G; Guimaraes, M; Carneiro, D; Novais, P; Alves, V;

Publicação
AMBIENT INTELLIGENCE-SOFTWARE AND APPLICATIONS-13TH INTERNATIONAL SYMPOSIUM ON AMBIENT INTELLIGENCE

Abstract
As the field of Machine Learning evolves, the number of available learning algorithms and their parameters continues to grow. On the one hand, this is positive as it allows for the finding of potentially more accurate models. On the other hand, however, it also makes the process of finding the right model more complex, given the number of possible configurations. Traditionally, data scientists rely on trial-and-error or brute force procedures, which are costly, or on their own intuition or expertise, which is hard to acquire. In this paper we propose an approach for algorithm recommendation based on meta-learning. The approach can be used in real-time to predict the best n algorithms (based on a selected performance metric) and their configuration, for a given ML problem. We evaluate it through cross-validation, and by comparing it against an Auto ML approach, in terms of accuracy and time. Results show that the proposed approach recommends algorithms that are similar to those of traditional approaches, in terms of performance, in just a fraction of the time.

2023

Algorithm Recommendation and Performance Prediction Using Meta-Learning

Autores
Palumbo, G; Carneiro, D; Guimares, M; Alves, V; Novais, P;

Publicação
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS

Abstract
In the last years, the number of machine learning algorithms and their parameters has increased significantly. On the one hand, this increases the chances of finding better models. On the other hand, it increases the complexity of the task of training a model, as the search space expands significantly. As the size of datasets also grows, traditional approaches based on extensive search start to become prohibitively expensive in terms of computational resources and time, especially in data streaming scenarios. This paper describes an approach based on meta-learning that tackles two main challenges. The first is to predict key performance indicators of machine learning models. The second is to recommend the best algorithm/configuration for training a model for a given machine learning problem. When compared to a state-of-the-art method (AutoML), the proposed approach is up to 130x faster and only 4% worse in terms of average model quality. Hence, it is especially suited for scenarios in which models need to be updated regularly, such as in streaming scenarios with big data, in which some accuracy can be traded for a much shorter model training time.

2023

Comparison of Supervised Learning Algorithms for Quality Assessment of Wearable Electrocardiograms With Paroxysmal Atrial Fibrillation

Autores
Huerta, A; Martinez, A; Carneiro, D; Bertomeu González, V; Rieta, JJ; Alcaraz, R;

Publicação
IEEE ACCESS

Abstract
Emerging wearable technology able to monitor electrocardiogram (ECG) continuously for long periods of time without disrupting the patient's daily life represents a great opportunity to improve suboptimal current diagnosis of paroxysmal atrial fibrillation (AF). However, its integration into clinical practice is still limited because the acquired ECG recording is often strongly contaminated by transient noise, thus leading to numerous false alarms of AF and requiring manual interpretation of extensive amounts of ECG data. To improve this situation, automated selection of ECG segments with sufficient quality for precise diagnosis has been widely proposed, and numerous algorithms for such ECG quality assessment can be found. Although most have reported successful performance on ECG signals acquired from healthy subjects, only a recent algorithm based on a well-known pre-trained convolutional neural network (CNN), such as AlexNet, has maintained a similar efficiency in the context of paroxysmal AF. Hence, having in mind the latest major advances in the development of neural networks, the main goal of this work was to compare the most recent pre-trained CNN models in terms of classification performance between high- and low-quality ECG excerpts and computational time. In global values, all reported a similar classification performance, which was significantly superior than the one provided by previous methods based on combining hand-crafted ECG features with conventional machine learning classifiers. Nonetheless, shallow networks (such as AlexNet) trended to detect better high-quality ECG excerpts and deep CNN models to identify better noisy ECG segments. The networks with a moderate depth of about 20 layers presented the best balanced performance on both groups of ECG excerpts. Indeed, GoogLeNet (with a depth of 22 layers) obtained very close values of sensitivity and specificity about 87%. It also maintained a misclassification rate of AF episodes similar to AlexNet and an acceptable computation time, thus constituting the best alternative for quality assessment of wearable, long-term ECG recordings acquired from patients with paroxysmal AF.