ISEP – LSA – Artigos
URI permanente para esta coleção:
Navegar
Entradas recentes
- Roaz autonomous surface vehicle design and implementationPublication . Martins, A.; Ferreira, Hugo; Dias, A.; Almeida, C.; Silva, E. P.; Soares Almeida, José MiguelThe design of an Autonomous Surface Vehicle for operation in fiver and estuarine scenarios is presented. Multiple operations with autonomous underwater vehicles and support to AUV missions are one of the main design goals in the ROAZ system. The mechanical design issues are discussed. Hardware, software and implementation status are described along with the control and navigation system architecture. Some preliminary test results concerning a custom developed thruster are presented along with hydrodynamic drag calculations by the use of computer fluid dynamic methods.
- Small fixed wing autonomous aerial vehicle for forest management applicationsPublication . Martins, Alfredo; Almeida, José; Silva, Eduardo; Dias Silva, Hugo Filipe; Bento, Domingos; Figueiredo, André; Santos, FilipeIn this work a forest management infrastructure solution using small autonomous aerial vehicles is proposed. The FALCOS unmanned aerial vehicle developed for remotemonitoring purposes is described. This is a small size UAV with onboard vision processing and autonomous flight capabilities. A set of custom developed navigation sensors was developed for the vehicle. Fire detection is performed through the use of low cost digital cameras and near-infrared sensors. This approach is extended to a radiometric forest inventory and forest fire danger characterization. Test results for navigation and ignition detection in real scenario are presented.
- Real-time vision system for mobile roboticsPublication . Silva, H. M.; Martins, A.; Soares Almeida, José Miguel; Oliveira Lima, Luís Carlos; Silva, E. P.; Patacho, A.This paper describes a real-time vision architecture for mobile robotics. It is integrated in the research program on mobile robotics pursued at the Autonomous Systems Lab ISEP-IPP. The implemented architecture is characterized by: low computational cost, low latency, low power, highly modularity, configurability, adaptability and scalability. A new method using run length encoding (RLE) colour transition allows real-time edge determination at low computational cost. A pipeline structure further reduces latency and allows a paralleled hardware implementation. A dedicated hardware vision sensor was developed in order to take advantage of the proposed architecture. The real-time characteristics and hardware partial implementation, coupled with low energy consumption address typical of autonomous systems applications.
- An explainable machine learning framework for railway predictive maintenance using data streams from the metro operator of PortugalPublication . García-Méndez, Silvia; Arriba-Pérez, Francisco de; Leal, Fátima; Veloso, Bruno; Malheiro, Benedita; Burguillo-Rial, Juan Carlos; BENEDITA CAMPOS NEVES MALHEIRO, MARIAThe public transportation sector generates large volumes of sensor data that, if analyzed adequately, can help anticipate failures and initiate maintenance actions, thereby enhancing quality and productivity. This work contributes to a real-time data-driven predictive maintenance solution for Intelligent Transportation Systems. The proposed method implements a processing pipeline comprised of sample pre-processing, incremental classification with Machine Learning models, and outcome explanation. This novel online processing pipeline has two main highlights: (i) a dedicated sample pre-processing module, which builds statistical and frequency-related features on the fly, and (ii) an explainability module. This work is the first to perform online fault prediction with natural language and visual explainability. The experiments were performed with the MetroPT data set from the metro operator of Porto, Portugal. The results are above 98 % for F-measure and 99 % for accuracy. In the context of railway predictive maintenance, achieving these high values is crucial due to the practical and operational implications of accurate failure prediction. In the specific case of a high F-measure, this ensures that the system maintains an optimal balance between detecting the highest possible number of real faults and minimizing false alarms, which is crucial for maximizing service availability. Furthermore, the accuracy obtained enables reliability, directly impacting cost reduction and increased safety. The analysis demonstrates that the pipeline maintains high performance even in the presence of class imbalance and noise, and its explanations effectively reflect the decision-making process. These findings validate the methodological soundness of the approach and confirm its practical applicability for supporting proactive maintenance decisions in real-world railway operations. Therefore, by identifying the early signs of failure, this pipeline enables decision-makers to understand the underlying problems and act accordingly swiftly.
- Unraveling emotions with pre-trained modelsPublication . Pajón-Sanmartín, Alejandro; Arriba-Pérez, Francisco de; García-Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo-Rial, Juan Carlos; BENEDITA CAMPOS NEVES MALHEIRO, MARIATransformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (LLMs). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose LLMs using simple prompts; (ii) effectiveness of different emotion prompt designs with LLMs; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70 % with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that LLMs require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.
- Identification and explanation of disinformation in wiki data streamsPublication . Arriba-Pérez, Francisco de; García-Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo, Juan C.Social media platforms, increasingly used as news sources for varied data analytics, have transformed how information is generated and disseminated. However, the unverified nature of this content raises concerns about trustworthiness and accuracy, potentially negatively impacting readers’ critical judgment due to disinformation. This work aims to contribute to the automatic data quality validation field, addressing the rapid growth of online content on wiki pages. Our scalable solution includes stream-based data processing with feature engineering, feature analysis and selection, stream-based classification, and real-time explanation of prediction outcomes. The explainability dashboard is designed for the general public, who may need more specialized knowledge to interpret the model’s prediction. Experimental results on two datasets attain approximately 90% values across all evaluation metrics, demonstrating robust and competitive performance compared to works in the literature. In summary, the system assists editors by reducing their effort and time in detecting disinformation.
- Online detection and infographic explanation of spam reviews with data drift adaptationPublication . de Arriba Pérez, Francisco; García Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo, Juan C.Spam reviews are a pervasive problem on online platforms due to its significant impact on reputation. However, research into spam detection in data streams is scarce. Another concern lies in their need for transparency. Consequently, this paper addresses those problems by proposing an online solution for identifying and explaining spam reviews, incorporating data drift adaptation. It integrates (i) incremental profiling, (ii) data drift detection & adaptation, and (iii) identification of spam reviews employing Machine Learning. The explainable mechanism displays a visual and textual prediction explanation in a dashboard. The best results obtained reached up to 87 % spam F-measure.
- Exposing and explaining fake news on-the-flyPublication . de Arriba Pérez, Francisco; García Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo, Juan C.Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless of the reliability of the shared data. Consequently, the latter crowdsourcing model is exposed to manipulation. This work contributes with an explainable and online classification method to recognize fake news in real-time. The proposed method combines both unsupervised and supervised Machine Learning approaches with online created lexica. The profiling is built using creator-, content- and context-based features using Natural Language Processing techniques. The explainable classification mechanism displays in a dashboard the features selected for classification and the prediction confidence. The performance of the proposed solution has been validated with real data sets from Twitter and the results attain 80 % accuracy and macro F-measure. This proposal is the first to jointly provide data stream processing, profiling, classification and explainability. Ultimately, the proposed early detection, isolation and explanation of fake news contribute to increase the quality and trustworthiness of social media contents.
- Interpretable Classification of Wiki-Review StreamsPublication . García-Méndez, Silvia; Leal, Fátima; Malheiro, Benedita; Burguillo-Rial, Juan CarlosWiki articles are created and maintained by a crowd of editors, producing a continuous stream of reviews. Reviews can take the form of additions, reverts, or both. This crowdsourcing model is exposed to manipulation since neither reviews nor editors are automatically screened and purged. To protect articles against vandalism or damage, the stream of reviews can be mined to classify reviews and profile editors in real-time. The goal of this work is to anticipate and explain which reviews to revert. This way, editors are informed why their edits will be reverted. The proposed method employs stream-based processing, updating the profiling and classification models on each incoming event. The profiling uses side and content-based features employing Natural Language Processing, and editor profiles are incrementally updated based on their reviews. Since the proposed method relies on self-explainable classification algorithms, it is possible to understand why a review has been classified as a revert or a non-revert. In addition, this work contributes an algorithm for generating synthetic data for class balancing, making the final classification fairer. The proposed online method was tested with a real data set from Wikivoyage, which was balanced through the aforementioned synthetic data generation. The results attained near-90% values for all evaluation metrics (accuracy, precision, recall, and F-measure).
- Telco customer top‐ups: Stream‐based multi‐target regressionPublication . Alves, Pedro Miguel; Filipe, Ricardo; Malheiro, BeneditaTelecommunication operators compete not only for new clients, but, above all, to maintain current ones. The modelling and prediction of the top-up behaviour of prepaid mobile subscribers allows operators to anticipate customer intentions and implement measures to strengthen customer relationship. This research explores a data set from a Portuguese operator, comprising 30 months of top-up events, to predict the top-up monthly frequency and average value of prepaid subscribers using offline and online multi-target regression algorithms. The offline techniques adopt a monthly sliding window, whereas the online techniques use an event sliding window. Experiments were performed to determine the most promising set of features, analyse the accuracy of the offline and online regressors and the impact of sliding window dimension. The results show that online regression outperforms the offline counterparts. The best accuracy was achieved with adaptive model rules and a sliding window of 500 000 events (approximately 5 months). Finally, the predicted top-up monthly frequency and average value of each subscriber were converted to individual date and value intervals, which can be used by the operator to identify early signs of subscriber disengagement and immediately take pre-emptive measures.