32 documents found, page 1 of 4
Intelligent Data Engineering and Automated Learning – IDEAL 2024
Nogueira, VitorThis two-volume set, LNCS 15346 and LNCS 15347, constitutes the proceedings of the 25th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2024, held in Valencia, Spain, during November 20–22, 2024. The 86 full papers and 6 short papers presented in this book were carefully reviewed and selected from 130 submissions. IDEAL 2024 is focusing on Big Data Analytics and Privacy, M...
Parameter Efficient Fine-Tunning of LLMs: Application to Machine Translation fr...
Santos, Daniel; Nogueira, Vitor; Quaresma, PauloFine-tuning Large Language Models (LLMs) for specific tasks, such as machine translation, is a computationally expensive process that often requires substantial hardware resources. Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA) and Quantized Low-Rank Adaptation (QLoRA), offer a resource-efficient alternative by significantly reducing the number of trainable parameters and mem...
Are Small Language Models Enough for Biomedical QA Tasks?
Lamar-Leon, Javier; Nogueira, Vitor; Quaresma, PauloThis paper presents a specialized fine-tuning approach for the Mistral-7B Large Language Model (LLM) tailored for biomedical applications. We employ Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method, to adapt the model to the intricacies of biomedical language and domain-specific knowledge. By integrating LoRA, we aim to preserve the general language understanding capabilities of Mistral-7B w...
Describing Land Cover Changes via Multi-Temporal Remote Sensing Image Captionin...
Lamar-Leon, Javier; Nogueira, Vitor; Salgueiro, Pedro; Quaresma, PauloDescribing land cover changes from multi-temporal remote sensing imagery requires capturing both visual transformations and their semantic meaning in natural language. Existing methods often struggle to balance visual accuracy with descriptive coherence. We propose MVLT-LoRA-CC (Multi-modal Vision Language Transformer with Low-Rank Adaptation for Change Captioning), a framework that integrates a Vision Transfor...
Plagiarism: Report
Lamar-Leon, Javier; Quaresma, Paulo; Nogueira, VitorPlagiarism detection is essential for maintaining academic integrity, ensuring that scholarly works are original and properly cited. With the rise of online resources and AI writing tools, the risk of plagiarism has increased, making detection crucial in the academic process. Detection methods can be monolingual or cross-lingual and are classified as intrinsic or extrinsic, utilizing various techniques such as ...
Mobile Digital Forensics: Report
Lamar-Leon, Javier; Quaresma, Paulo; Nogueira, VitorIn today's digital age, mobile devices are essential to daily life, serving as primary tools for communication, information storage, and data exchange. With the widespread use of smartphones, there has been a significant rise in cybercrimes, increasing the demand for effective digital forensic tools and techniques to extract, analyze, and present evidence from these devices. Mobile device forensic tools are cru...
Factors That Influence the Type of Road Traffic Accidents: A Case Study in a Di...
Infante, Paulo; Jacinto, Gonçalo; Afonso, Anabela; Rego, Leonor; Nogueira, Pedro; Silva, Marcelo; Nogueira, Vitor; Saias, José; Quaresma, PauloRoad traffic accidents (RTAs) are a problem with repercussions in several dimensions: social, economic, health, justice, and security. Data science plays an important role in its explanation and prediction. One of the main objectives of RTA data analysis is to identify the main factors associated with a RTA. The present study aims to contribute to the identification of the determinants for the type of RTA: coll...
Generating a European Portuguese BERT Based Model Using Content from Arquivo.pt...
Miquelina, Nuno; Quaresma, Paulo; Nogueira, VitorBuilding a language model from free available internet information takes several steps and challenges. This new model aims to be a BERT-based language model for Portuguese-European, with no specific context. The corpus was built using a web page archive infrastructure provided by Arquivo.pt and restricted to .pt domains. This paper will describe the overall process of building the corpus and training a BERT model.
Comparison of Statistical and Machine Learning Models on Road Traffic Accident ...
infante, paulo; Jacinto, Gonçalo; Afonso, Anabela; Rego, Leonor; Nogueira, Vitor; Quaresma, Paulo; Saias, José; Santos, Daniel; Nogueira, PedroPortugal has the sixth highest road fatality rate among European Union members. This is a problem of different dimensions with serious consequences in people’s lives. This study analyses daily data from police and government authorities on road traffic accidents that occurred between 2016 and 2019 in a district of Portugal. This paper looks for the determinants that contribute to the existence of victims in roa...
Some determinants for road accidents severity in the district of Setúbal
Infante, Paulo; Afonso, Anabela; Jacinto, Gonçalo; Rego, Leonor; Nogueira, Pedro; Silva, Marcelo; Nogueira, Vitor; Saias, José; Quaresma, PauloIn Portugal, the district of Setúbal is among those with the higher number of road accidents with fatal injuries but with fewer accidents. This work analyzes data from road accidents that occurred in the area under the jurisdiction of the Territorial Command of Setúbal, belonging to the Guarda Nacional Republicana, the Portuguese Gendarmerie. A spatial analysis of the accidents was carried out, using the Getis–...