SciTePress - Affiliation Profile

Research.Publish.Connect.

*Please fill out at least one Field. *Value must be an number!

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

*Please fill out at least one Field.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

*Please fill out at least one Field.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

*Please fill out at least one Field.

Name:
Country:
Subject:

Advanced Search Affiliations Search

If you're looking for an exact phrase use quotation marks on text fields.

Proceedings

Proceedings Search *Please fill out at least one Field. *Value must be an number!

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Papers

Papers Search *Please fill out at least one Field.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Authors

Authors Search *Please fill out at least one Field.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Advanced Search

Affiliation

Polytechnic Institute of Lisbon, Portugal

Context (please use complete words only)

Field

Sort by

10 Papers

Bitcoin Fraud Detection: A Study with Dimensionality Reduction and Machine Learning Techniques

Topics: Pattern Recognition; Explainable AI; Machine Learning for Large Datasets; Statistics and Exploratory Data Analysis; Blockchain & Data Security

Authors: Nuno Gomes ¹ and Artur Ferreira ^{2

;

1}

Affiliations: ¹ ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal , ² Instituto de Telecomunicações, Lisboa, Portugal

Digital Object Identifier: 10.5220/0013647400003967

Proceedings of DATA 2025, ISBN: 978-989-758-758-0

Quick Abstract

The use of cryptocurrencies corresponds to a remarkable moment in global financial markets. The nature of cryptocurrency transactions, done between cryptographic addresses, poses many challenges to identify fraudulent activities, since malicious transactions may appear as legitimate. Using data with these transactions, one may learn machine learning models targeted to identify the fraudulent ones. The transaction datasets are typically imbalanced, holding a few illicit examples, which is challenging for machine learning techniques to identify fraudulent transactions. In this paper, we investigate the use of a machine learning pipeline with dimensionality reduction techniques over Bitcoin transaction data. The experimental results show that XGBoost is the best performing method among a large set of competitors. The dimensionality reduction techniques are able to identify adequate subsets suitable for explainability purposes on the classification decision.

Union and Intersection K-Fold Feature Selection

Topics: Feature Selection and Extraction; Machine Learning Methods; Classification and Clustering; Linear Models and Dimensionality Reduction

Authors: Artur Ferreira ^{1

;

2} and Mário Figueiredo ^{3

;

2}

Affiliations: ¹ ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal , ² Instituto de Telecomunicações, Lisboa, Portugal , ³ IST, Instituto Superior Técnico, Universidade de Lisboa, Portugal

Digital Object Identifier: 10.5220/0013282300003905

Proceedings of ICPRAM 2025, ISBN: 978-989-758-730-6

Quick Abstract

Feature selection (FS) is a vast research topic with many techniques proposed over the years. FS techniques may bring many benefits to machine learning algorithms. The combination of FS techniques usually improves the results as compared to the use of one single technique. Recently, the concepts of explainability and interpretability have been proposed in the explainable artificial intelligence (XAI) framework. The recently proposed k-fold feature selection (KFFS) algorithm provides dimensionality reduction and simultaneously yields an output suitable for explainability purposes. In this paper, we extend the KFFS algorithm by performing union and intersection of the individual feature subspaces of two and three feature selection filters. Our experiments performed on 20 datasets show that the union of the feature subsets typically attains better results than the use of individual filters. The intersection also attains adequate results, yielding human manageable (e.g., small) subsets of features, allowing for explainability and interpretability on medical domain data.

A Mutual Information Based Discretization-Selection Technique

Topics: Feature Selection and Extraction; Machine Learning Methods; Classification and Clustering; Linear Models and Dimensionality Reduction

Authors: Artur Ferreira ^{1

;

2} and Mário Figueiredo ^{3

;

2}

Digital Object Identifier: 10.5220/0012467300003654

Proceedings of ICPRAM 2024, ISBN: 978-989-758-684-2

Quick Abstract

In machine learning (ML) and data mining (DM) one often has to resort to data pre-processing techniques to achieve adequate data representations. Among these techniques, we find feature discretization (FD) and feature selection (FS), with many available methods for each one. The use of FD and FS techniques improves the data representation for ML and DM tasks. However, these techniques are usually applied in an independent way, that is, we may use a FD technique but not a FS technique or the opposite case. Using both FD and FS techniques in sequence, may not produce the most adequate results. In this paper, we propose a supervised discretization-selection technique; the discretization step is done in an incremental approach and keeps information regarding the features and the number of bits allocated per feature. Then, we apply a selection criterion based upon the discretization bins, yielding a discretized and dimensionality reduced dataset. We evaluate our technique on different types of data and in most cases the discretized and reduced version of the data is the most suited version, achieving better classification performance, as compared to the use of the original features.

Prediction of Alzheimer Disease on the DARWIN Dataset with Dimensionality Reduction and Explainability Techniques

Topics: XAI using Machine Learning; Metrics for Explanations; Healthcare and Biomedical Sciences; Evaluation of Explainability; Model Accuracy and Interpretability; Model-Specific vs Model-Agnostic Methods for Explainability

Authors: Alexandre Moreira ¹ , Artur Ferreira ^{1

;

2} and Nuno Leite ¹

Affiliations: ¹ ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal , ² Instituto de Telecomunicações, Lisboa, Portugal

Digital Object Identifier: 10.5220/0013017400003886

Proceedings of EXPLAINS 2024, ISBN: 978-989-758-720-7

Quick Abstract

The progressive degeneration of nerve cells causes neurodegenerative diseases. For instance, Alzheimer and Parkinson diseases progressively decrease the cognitive abilities and the motor skills of an individual. Without the knowledge for a cure, we aim to slow down their impact by resorting to rehabilitative therapies and medicines. Thus, early diagnosis plays a key role to delay the progression of these diseases. The analysis of handwriting dynamics for specific tasks is found to be an effective tool to provide early diagnosis of these diseases. Recently, the Diagnosis AlzheimeR WIth haNdwriting (DARWIN) dataset was introduced. It contains records of handwriting samples from 174 participants (diagnosed as having Alzheimer’s or not), performing 25 specific handwriting tasks, including dictation, graphics, and copies. In this paper, we explore the use of the DARWIN dataset with dimensionality reduction, explainability, and classification techniques. We identify the most relevant and decisive handwriting features for predicting Alzheimer. From the original set of 450 features with different groups, we found small subsets of features showing that the time spent to perform the in-air movements are the most decisive type of features for predicting Alzheimer.

Building a Dataset for Trip Style Assessment Based on Real Trip Data

Topics: Data Mining; Pattern Recognition; Data Science; Data Fusion; Feature Selection

Authors: Luís Loureiro ^{1

;

2} , Artur Ferreira ^{1

;

3} and André Lourenço ^{1

;

2}

Affiliations: ¹ ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal , ² CardioID Technologies, Portugal , ³ Instituto de Telecomunicações, Lisboa, Portugal

Digital Object Identifier: 10.5220/0012079400003541

Proceedings of DATA 2023, ISBN: 978-989-758-664-4

Quick Abstract

In most countries, to have permission to drive vehicles on public roads one must have insurance against civil liability for vehicles. In many cases, the insurance fees depend on the age of the driver, the number of years one holds a driving license, and the driving history. The usual assumption taken by insurance companies that younger drivers are always more risky than others are not always correct, penalizing young good drivers. In this paper, we follow a pay-as-you-drive approach based on trip behavior data of different drivers. First, we build a dataset from real trip data. Then, we apply a two-stage clustering approach to the dataset to identify trip profiles. The experimental results show that we can cluster and identify distinct trip profiles in which many trips have a non-aggressive style, some have an aggressive style and only a few are risky style trips. Our solution finds application in fair insurance fee calculation or fleet management tasks, for instance.

Estimating Electric Vehicle Driving Range with Machine Learning

Topics: Ensemble Methods; Feature Selection and Extraction; Industry Related Applications; Machine Learning Methods

Authors: David Albuquerque ^{1

;

2} , Artur Ferreira ^{1

;

2} and David Coutinho ^{1

;

2}

Affiliations: ¹ ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal , ² Instituto de Telecomunicações, Lisboa, Portugal

Digital Object Identifier: 10.5220/0011672100003411

Proceedings of ICPRAM 2023, ISBN: 978-989-758-626-2

Quick Abstract

In the past years, we have witnessed an increase on the use of electric vehicles (EV), which are now widely accepted as reliable and eco-friendly means of transportation. When choosing an EV, usually one of the key parameters of choice for the consumer is its driving range (DR) capability. The DR depends on many factors that should be addressed when predicting its value. In some cases, the existing heuristic techniques for DR estimation provide values with large variation, which may cause driver anxiety. In this paper, we explore the use of machine learning (ML) techniques to estimate the DR. From publicly available data, we build a dataset with EV data suitable to estimate the DR. Then, we resort to regression techniques on models learned on the dataset, evaluated with standard metrics. The experimental results show that regression techniques perform adequate and smooth estimation of the DR value on both short and long trips, avoiding the need to use the previous heuristic techniques, thus minimizing the drivers anxiety and allowing better trip planning.

Leveraging Explainability with K-Fold Feature Selection

Topics: Feature Selection and Extraction; Bioinformatics and Systems Biology; Machine Learning Methods; Classification and Clustering; Linear Models and Dimensionality Reduction

Authors: Artur Ferreira ^{1

;

2

;

3} and Mário Figueiredo ^{3

;

2

;

1}

Digital Object Identifier: 10.5220/0011744400003411

Proceedings of ICPRAM 2023, ISBN: 978-989-758-626-2

Quick Abstract

Learning with high-dimensional (HD) data poses many challenges, since the large number of features often yields redundancy and irrelevance issues, which may decrease the performance of machine learning (ML) methods. Often, when learning with HD data, one resorts to feature selection (FS) approaches to avoid the curse of dimensionality. The use of FS may improve the results, but its use by itself does not lead to explainability, in the sense of identifying the small subset of core features that most influence the prediction of the ML model, which can still be seen as a black-box. In this paper, we propose k-fold feature selection (KFFS), which is a FS approach to shed some light into that black-box, by resorting to the k-fold data partition procedure and one generic unsupervised or supervised FS filter. KFFS finds small and decisive subsets of features for a classification task, at the expense of increased computation time. On HD data, KFFS finds small subsets of features, with dimensionality small enough to be analyzed by human experts (e.g, a medical doctor in a cancer detection problem). It also provides classification models with lower error rate and fewer features than those provided by the use of the individual supervised FS filter.

Union k-Fold Feature Selection on Microarray Data

Topics: Decision Support Systems; Pattern Recognition; Support Vector Machines; Feature Selection

Authors: Artur Ferreira ^{1

;

2} and Mário Figueiredo ^{1

;

3}

Affiliations: ¹ Instituto de Telecomunicações, Lisboa, Portugal , ² ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politecnico de Lisboa, Portugal , ³ IST, Instituto Superior Tecnico, Universidade de Lisboa, Portugal

Digital Object Identifier: 10.5220/0012135800003541

Proceedings of DATA 2023, ISBN: 978-989-758-664-4

Quick Abstract

Cancer detection from microarray data is an important problem to be handled by machine learning techniques. This type of data poses many challenges to machine learning techniques, namely because it usually has large number of features (genes) and small number of instances (patients). Moreover, it is important to characterize which genes are the most important for a given classification task, providing explainability on the classification. In this paper, we propose a feature selection approach for microarray data, which is an extension of the recently proposed k-fold feature selection algorithm. We propose performing the union of the feature subspaces found independently by two feature selection filters, which have been proven to be adequate for this type of data, individually. The experimental results show that the union of the subsets of features found by each filter, in some cases, produces better results than the use of each individual filter, yielding human manageable subsets of features.

A Step Towards the Explainability of Microarray Data for Cancer Diagnosis with Machine Learning Techniques

Topics: Feature Selection and Extraction; Machine Learning Methods; Classification and Clustering; Linear Models and Dimensionality Reduction

Authors: Adara S. R. Nogueira ¹ , Artur J. Ferreira ^{2

;

1} and Mário A. T. Figueiredo ^{2

;

3}

Digital Object Identifier: 10.5220/0010980100003122

Proceedings of ICPRAM 2022, ISBN: 978-989-758-549-4

Quick Abstract

Detecting diseases, such as cancer, from from gene expression data has assumed great importance and is a very active area of research. Today, many gene expression datasets are publicly available, which consist of microarray data with information on the activation (or not) of thousands of genes, in sets of patients that have (or not) a certain disease. These datasets consist of high-dimensional feature vectors (very large numbers of genes), which raises difficulties for human analysis and interpretation with the goal of identifying the most relevant genes for detecting the presence of a particular disease. In this paper, we propose to take a step towards the explainability of these disease detection methods, by applying feature discretization and feature selection techniques. We accurately classify microarray data, while substantially reducing and identifying subsets of relevant genes. These small subsets of genes are thus easier to interpret by human experts, thus potentially providing valuable information about which genes are involved in a given disease.

On the Improvement of Feature Selection Techniques: The Fitness Filter

Topics: Feature Selection and Extraction; Machine Learning Methods; Classification and Clustering; Data Mining and Algorithms for Big Data

Authors: Artur J. Ferreira ^{1

;

2} and Mário A. T. Figueiredo ^{1

;

3}

Affiliations: ¹ Instituto de Telecomunicações, Lisboa, Portugal , ² ISEL, Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal , ³ IST, Instituto Superior Técnico, Universidade de Lisboa, Portugal

Digital Object Identifier: 10.5220/0010396303650372

Proceedings of ICPRAM 2021, ISBN: 978-989-758-486-2

Quick Abstract

The need for feature selection (FS) techniques is central in many machine learning and pattern recognition problems. FS is a vast research field and therefore we now have many FS techniques proposed in the literature, applied in the context of quite different problems. Some of these FS techniques follow the relevance-redundancy (RR) framework to select the best subset of features. In this paper, we propose a supervised filter FS technique, named as fitness filter, that follows the RR framework and uses data discretization. This technique can be used directly on low or medium dimensional data or it can be applied as a post-processing technique to other FS techniques. Specifically, when used as a post-processing technique, it further reduces the dimensionality of the feature space found by common FS techniques and often improves the classification accuracy.