A carregar...
Projeto de investigação
Not Available
Financiador
Autores
Publicações
Generic FPGA Pre-Processing Image Library for Industrial Vision Systems
Publication . Ferreira, Diogo; Moutinho , Filipe; Matos-Carvalho , João P.; Guedes , Magno; Deusdado , Pedro; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; DEE - Departamento de Engenharia Electrotécnica e de Computadores; CTS - Centro de Tecnologia e Sistemas; MDPI - Multidisciplinary Digital Publishing Institute
Currently, there is a demand for an increase in the diversity and quality of new products reaching the consumer market. This fact imposes new challenges for different industrial sectors, including processes that integrate machine vision. Hardware acceleration and improvements in processing efficiency are becoming crucial for vision-based algorithms to follow the complexity growth of future industrial systems. This article presents a generic library of pre-processing filters for execution in field-programmable gate arrays (FPGAs) to reduce the overall image processing time in vision systems. An experimental setup based on the Zybo Z7 Pcam 5C Demo project was developed and used to validate the filters described in VHDL (VHSIC hardware description language). Finally, a comparison of the execution times using GPU and CPU platforms was performed as well as an evaluation of the integration of the current work in an industrial application. The results showed a decrease in the pre-processing time from milliseconds to nanoseconds when using FPGAs.
Text clustering with large language model embeddings
Publication . Petukhova, Alina; Matos-Carvalho, João P.; Fachada, Nuno; CTS - Centro de Tecnologia e Sistemas; UNINOVA-Instituto de Desenvolvimento de Novas Tecnologias; KeAi Communications Co.
Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms. This study argues that recent advancements in large language models (LLMs) have the potential to enhance this task. The research investigates how different textual embeddings, particularly those utilised in LLMs, and various clustering algorithms influence the clustering of text datasets. A series of experiments were conducted to evaluate the impact of embeddings on clustering results, the role of dimensionality reduction through summarisation, and the adjustment of model size. The findings indicate that LLM embeddings are superior at capturing subtleties in structured language. OpenAI's GPT-3.5 Turbo model yields better results in three out of five clustering metrics across most tested datasets. Most LLM embeddings show improvements in cluster purity and provide a more informative silhouette score, reflecting a refined structural understanding of text data compared to traditional methods. Among the more lightweight models, BERT demonstrates leading performance. Additionally, it was observed that increasing model dimensionality and employing summarisation techniques do not consistently enhance clustering efficiency, suggesting that these strategies require careful consideration for practical application. These results highlight a complex balance between the need for refined text representation and computational feasibility in text clustering applications. This study extends traditional text clustering frameworks by integrating embeddings from LLMs, offering improved methodologies and suggesting new avenues for future research in various types of textual analysis.
LSTM-Based Trajectory and Phase-Shift Prediction for RSMA Networks Assisted by AIRS
Publication . Sousa Lima, Brena Kelly; Matos-Carvalho, João Pedro; Dinis, Rui; da Costa, Daniel Benevides; Beko, Marko; Oliveira, Rodolfo; CTS - Centro de Tecnologia e Sistemas; DEE - Departamento de Engenharia Electrotécnica e de Computadores; Institute of Electrical and Electronics Engineers (IEEE)
This paper investigates rate-splitting multiple access (RSMA) networks with multiusers assisted by aerial intelligent reflecting surfaces (AIRS). To improve the sum-rate of the system, the UAV’s trajectory and phase-shift vectors are optimized, in which the mobility scenarios with static and dynamic users are explored. In particular, long short-term memory (LSTM)-based frameworks for predicting the UAV’s trajectory and the phase-shift of the reflecting elements of AIRS are proposed. For more insight, a third model is created by combining information from the static and dynamic scenarios. Furthermore, to improve the transmit beamforming at the BS, an algorithm based on alternating optimization (AO) under the assumptions of imperfect successive interference cancelation (SIC) is presented. Training progress and testing results are provided to demonstrate the efficiency of the proposed models. In addition, numerical simulations are presented to verify the performance gains in terms of sum-rate. The simulation results show that the UAV performs better in trajectory prediction and phase-shift when different investigated scenarios are not combined.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
CEEC INST 2018
Número da atribuição
CEECINST/00147/2018/CP1498/CT0015