Marluce Rodrigues Pereira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marluce Rodrigues Pereira has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- André Pimenta Freire
Federal University of Lavras
3 shared publications - André de Lima Salgado
Federal University of Lavras
1 shared publication - Breno Carvalho Pedroso
UFLA
1 shared publication - Denilson Alves Pereira
UFLA
1 shared publication - Elias J. Miranda
UFAL
1 shared publication - Fábio Aparecido Cândido Da Silva
UFLA
1 shared publication
Latest Publications
- 12 September 2025
- Published by Springer Nature
- p. 275-279
Participatory Design of Mobile Application for Cycling: An Experience Report
- 12 September 2025
- Published by Springer Nature
- p. 275-279
Participatory Design of Mobile Application for Cycling: An Experience Report
- Open Access
- 28 May 2025
- Published by Sociedade Brasileira de Computação
- p. 30-33
Controle automatizado de recursos computacionais em cluster com ESP32 e Naive Bayes para melhorar eficiência energética
Este trabalho apresenta uma abordagem para melhorar a eficiência energética de um cluster de baixo custo através do acionamento automático para ligar e desligar as máquinas. A infraestrutura do cluster utilizado para testar a solução inclui quatro máquinas com processadores Intel Celeron e rede cabeada, sistema operacional Alpine Linux e um microcontrolador ESP32 conectado à placa-mãe de cada nó. Um algoritmo Naive Bayes avalia a tendência das atividades de uso de CPU e memória em cada nó, permitindo ao ESP32 decidir ligar ou desligar nós do cluster, garantindo alta disponibilidade. Os resultados foram promissores para o conjunto de máquinas utilizado.
- 28 May 2025
- Published by Sociedade Brasileira de Computação
- p. 30-33
Open AccessControle automatizado de recursos computacionais em cluster com ESP32 e Naive Bayes para melhorar eficiência energética
Este trabalho apresenta uma abordagem para melhorar a eficiência energética de um cluster de baixo custo através do acionamento automático para ligar e desligar as máquinas. A infraestrutura do cluster utilizado para testar a solução inclui quatro máquinas com processadores Intel Celeron e rede cabeada, sistema operacional Alpine Linux e um microcontrolador ESP32 conectado à placa-mãe de cada nó. Um algoritmo Naive Bayes avalia a tendência das atividades de uso de CPU e memória em cada nó, permitindo ao ESP32 decidir ligar ou desligar nós do cluster, garantindo alta disponibilidade. Os resultados foram promissores para o conjunto de máquinas utilizado.
- Open Access
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 260-269
Performance evaluation of LLMs in the Text-to-SQL task in Portuguese
Context: The rising need for consulting data in industry and academic contexts has fueled Text-to-SQL development, where natural language queries are translated into SQL, making data access easier. Problem: Most research focuses on English Text-to-SQL, leaving Portuguese—a language spoken by over 260 million people— underrepresented, creating challenges for organizations reliant on accurate data retrieval in Portuguese. Solution: This study evaluates the effectiveness of various Large Language Models (LLMs) on Portuguese Text-to-SQL tasks using a validated translation of the Spider benchmark. IS Theory: This research applies Task-Technology Fit (TTF) Theory to assess how well LLMs meet the needs of Portuguese Text-to-SQL tasks. TTF evaluates the match between LLM capabilities and task requirements, including language understanding, schema recognition, and SQL generation. Proper alignment is key for effective data retrieval, particularly for Portuguese-language applications in organizational decisionmaking. Method: A comparative analysis of seven LLMs—tested on both Portuguese and English Spider benchmarks—was performed. Exact Match (EM) and Execution Accuracy (EX) metrics measured performance, and a zero-shot prompting approach maintained consistency. Results Summary: Larger LLMs and specialized code models excelled, showing less performance variance between Portuguese and English tasks. Generalist models, however, produced verbose outputs, which may limit practical use in production systems. Contributions and Impact on IS: This research establishes baseline Portuguese Text-to-SQL metrics and insights into language adaptability in LLMs, offering guidance for organizations seeking Portuguese-language data solutions. By bridging language gaps, it advances data-driven practices and fosters growth in Portuguese-speaking regions.
- 19 May 2025
- Published by Sociedade Brasileira de Computação
- p. 260-269
Open AccessPerformance evaluation of LLMs in the Text-to-SQL task in Portuguese
Context: The rising need for consulting data in industry and academic contexts has fueled Text-to-SQL development, where natural language queries are translated into SQL, making data access easier. Problem: Most research focuses on English Text-to-SQL, leaving Portuguese—a language spoken by over 260 million people— underrepresented, creating challenges for organizations reliant on accurate data retrieval in Portuguese. Solution: This study evaluates the effectiveness of various Large Language Models (LLMs) on Portuguese Text-to-SQL tasks using a validated translation of the Spider benchmark. IS Theory: This research applies Task-Technology Fit (TTF) Theory to assess how well LLMs meet the needs of Portuguese Text-to-SQL tasks. TTF evaluates the match between LLM capabilities and task requirements, including language understanding, schema recognition, and SQL generation. Proper alignment is key for effective data retrieval, particularly for Portuguese-language applications in organizational decisionmaking. Method: A comparative analysis of seven LLMs—tested on both Portuguese and English Spider benchmarks—was performed. Exact Match (EM) and Execution Accuracy (EX) metrics measured performance, and a zero-shot prompting approach maintained consistency. Results Summary: Larger LLMs and specialized code models excelled, showing less performance variance between Portuguese and English tasks. Generalist models, however, produced verbose outputs, which may limit practical use in production systems. Contributions and Impact on IS: This research establishes baseline Portuguese Text-to-SQL metrics and insights into language adaptability in LLMs, offering guidance for organizations seeking Portuguese-language data solutions. By bridging language gaps, it advances data-driven practices and fosters growth in Portuguese-speaking regions.
- Open Access
- 14 October 2024
- Published by Sociedade Brasileira de Computação
- p. 28-36
Acceptance and Usability of Complex Medical Systems: A Study with Radiology Professionals
The increasing demand for imaging tests has made radiology information systems crucial in medical practice, especially those based on web technology. These systems include Picture Archiving and Communication System (PACS), Radiology Information Systems (RIS), and Hospital Information System (HIS), generate and manipulate images through specialized software. To operate this complex software, require attention to detail and image manipulation techniques for accurate diagnoses. Usability issues in medical image manipulation software, given the process of adapting to new software and complex tasks, can result in inaccurate diagnoses with clinical impact. This is a qualitative study, which is based on the work routines of radiology professionals, focusing on issues of cognitive learning, interaction, and usability with radiology software. Moderate usability tests with radiology technicians were conducted to identify the difficulties and challenges they encounter while using medical image manipulation software. The analysis identified 64 problems grouped into 20 categories and organized under Visual Presentation, Content, Information Architecture, and Interactivity. The paper emphasizes violated heuristics and describes how these problem categories impact users in their medical activities and their influence on the clinical process. The obtained results provide insights to enhance usability practices and recommendations, aiming to support the development systems used in radiology practice.
- 14 October 2024
- Published by Sociedade Brasileira de Computação
- p. 28-36
Open AccessAcceptance and Usability of Complex Medical Systems: A Study with Radiology Professionals
The increasing demand for imaging tests has made radiology information systems crucial in medical practice, especially those based on web technology. These systems include Picture Archiving and Communication System (PACS), Radiology Information Systems (RIS), and Hospital Information System (HIS), generate and manipulate images through specialized software. To operate this complex software, require attention to detail and image manipulation techniques for accurate diagnoses. Usability issues in medical image manipulation software, given the process of adapting to new software and complex tasks, can result in inaccurate diagnoses with clinical impact. This is a qualitative study, which is based on the work routines of radiology professionals, focusing on issues of cognitive learning, interaction, and usability with radiology software. Moderate usability tests with radiology technicians were conducted to identify the difficulties and challenges they encounter while using medical image manipulation software. The analysis identified 64 problems grouped into 20 categories and organized under Visual Presentation, Content, Information Architecture, and Interactivity. The paper emphasizes violated heuristics and describes how these problem categories impact users in their medical activities and their influence on the clinical process. The obtained results provide insights to enhance usability practices and recommendations, aiming to support the development systems used in radiology practice.
- Open Access
- 14 October 2024
- Published by Sociedade Brasileira de Computação
- p. 124-132
Elderly Fall Monitoring in Smart Homes Using Wearable Device
The constant progress of technology, especially in the area of health, brings numerous benefits, one of which is the increase in human life expectancy. However, problems that occur recurrently among the elderly age group are now on the radar of studies that also seek to improve the quality of life of these people. The number of cases of falls among elderly people is worrying, even more so as this is a portion of the population that tends to live alone. In the context of smart homes, several solutions have emerged for monitoring elderly people to increase safety and provide faster assistance, if necessary. One of these solutions is the use of wearable devices responsible for identifying the person’s movements. This work presents the study and development of a wearable device capable of detecting falls and, if they occur, automatically notifying the necessary people through alert messages via the Telegram application so that they can help the person who has suffered a fall. In this work, a Wi-Fi network, MQTT protocol, accelerometer and gyroscope inertial sensors and an ESP32 board programmed using the Arduino IDE were used. Preliminary tests indicated good performance in recognizing falls, based on tilt angle analysis, gyroscope readings and accelerometer readings. The proof of concept and preliminary tests carried out demonstrate the potential for using low-cost technologies for wearable resources for application in smart homes and monitoring the health of elderly people.
- 14 October 2024
- Published by Sociedade Brasileira de Computação
- p. 124-132
Open AccessElderly Fall Monitoring in Smart Homes Using Wearable Device
The constant progress of technology, especially in the area of health, brings numerous benefits, one of which is the increase in human life expectancy. However, problems that occur recurrently among the elderly age group are now on the radar of studies that also seek to improve the quality of life of these people. The number of cases of falls among elderly people is worrying, even more so as this is a portion of the population that tends to live alone. In the context of smart homes, several solutions have emerged for monitoring elderly people to increase safety and provide faster assistance, if necessary. One of these solutions is the use of wearable devices responsible for identifying the person’s movements. This work presents the study and development of a wearable device capable of detecting falls and, if they occur, automatically notifying the necessary people through alert messages via the Telegram application so that they can help the person who has suffered a fall. In this work, a Wi-Fi network, MQTT protocol, accelerometer and gyroscope inertial sensors and an ESP32 board programmed using the Arduino IDE were used. Preliminary tests indicated good performance in recognizing falls, based on tilt angle analysis, gyroscope readings and accelerometer readings. The proof of concept and preliminary tests carried out demonstrate the potential for using low-cost technologies for wearable resources for application in smart homes and monitoring the health of elderly people.