Emanuel Pereira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Emanuel Pereira has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Erick de Andrade Barboza
UFAL
5 shared publications - Francisco Gomes
Design Department, RFIDO IC DESIGN, Belo Horizonte 31330-230, Brazil
2 shared publications - Gabriel Vitorino de Andrade
Computing Institute, Federal University of Alagoas
2 shared publications - Itallo Patrick Castro Alves da Silva
Computing Institute, Federal University of Alagoas
2 shared publications - Sandoval Júnior
Instituto de Computação, Universidade Federal de Alagoas, Maceió 57072-970, Brazil
2 shared publications - Saulo Roberto dos Santos
Computing Institute, Federal University of Alagoas
2 shared publications
Latest Publications
- Open Access
- 11 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 25 (5) , 1-37
Robustness in TinyML: A Systematic Literature Review
TinyML enables the deployment of machine learning models on low-power embedded devices, offering energy-efficient solutions for real-world applications. However, TinyML faces significant challenges due to strict memory, processing, and energy constraints, making the implementation of robust and scalable models particularly difficult. Robustness in this context refers to the ability of models to maintain stable performance under adversarial conditions, sensor noise, and environmental variability, which makes it an essential requirement for reliable deployment in practical scenarios. This study conducts a systematic literature review to examine how robustness is assessed in TinyML, analyzing key factors such as input data types, accessibility of the dataset, real vs. simulated data usage, application domains, evaluated robustness types, hardware constraints, and commonly used performance metrics. The findings show a strong preference for sensor-based inputs, public and real-world datasets, and a focus on noise-related robustness challenges. Memory efficiency stands out as the main hardware constraint, while accuracy is the most used evaluation metric, reflecting the dominance of classification tasks in TinyML research. These insights provide a structured overview of current trends and reveal key gaps in TinyML robustness research, such as the lack of standardized benchmarking frameworks and the need for more advanced adversarial defense mechanisms tailored to low-power environments. They also highlight opportunities for integrating federated and physics-informed learning approaches, promoting the development of more secure, efficient, and resilient embedded machine learning systems.
- 11 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 25 (5) , 1-37
Open AccessRobustness in TinyML: A Systematic Literature Review
TinyML enables the deployment of machine learning models on low-power embedded devices, offering energy-efficient solutions for real-world applications. However, TinyML faces significant challenges due to strict memory, processing, and energy constraints, making the implementation of robust and scalable models particularly difficult. Robustness in this context refers to the ability of models to maintain stable performance under adversarial conditions, sensor noise, and environmental variability, which makes it an essential requirement for reliable deployment in practical scenarios. This study conducts a systematic literature review to examine how robustness is assessed in TinyML, analyzing key factors such as input data types, accessibility of the dataset, real vs. simulated data usage, application domains, evaluated robustness types, hardware constraints, and commonly used performance metrics. The findings show a strong preference for sensor-based inputs, public and real-world datasets, and a focus on noise-related robustness challenges. Memory efficiency stands out as the main hardware constraint, while accuracy is the most used evaluation metric, reflecting the dominance of classification tasks in TinyML research. These insights provide a structured overview of current trends and reveal key gaps in TinyML robustness research, such as the lack of standardized benchmarking frameworks and the need for more advanced adversarial defense mechanisms tailored to low-power environments. They also highlight opportunities for integrating federated and physics-informed learning approaches, promoting the development of more secure, efficient, and resilient embedded machine learning systems.
- 8 February 2026
- Published by Springer Nature
- p. 291-305
From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves
- 8 February 2026
- Published by Springer Nature
- p. 291-305
From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves
- 26 June 2024
- Published by Elsevier in Sustainable Computing: Informatics and Systems
- Vol. 43
An energy efficient TinyML model for a water potability classification problem
- 26 June 2024
- Published by Elsevier in Sustainable Computing: Informatics and Systems
- Vol. 43
An energy efficient TinyML model for a water potability classification problem
- Open Access
- 27 April 2024
- Published by MDPI AG in Technologies
- Vol. 12 (5) , 58
RFID Tags for On-Metal Applications: A Brief Survey
Radio-frequency identification technology finds extensive use in various industrial applications, including those involving metallic surfaces. The integration of radio-frequency identification systems with metal surfaces, such as those found in the automotive sector, presents distinct challenges that can notably affect system efficacy due to metal’s tendency to reflect electromagnetic waves, thus degrading the functionality of conventional radio-frequency identification tags. This highlights the importance of conducting research into academic publications and patents to grasp the current advancements and challenges in this field, aiming to improve the applications of radio-frequency identification tags technology on metal. Consequently, this research undertakes a concise review of both the literature and patents exploring radio-frequency identification technology’s use for on-metal tags, utilizing resources like Google Scholar and Google Patents. The research categorized crucial aspects such as tag flexibility, operating frequency, and geographic origins of the research. Findings highlight China’s prominent role in contributing to metal-focused radio-frequency identification tag research, with a considerable volume of articles and patents. In particular, flexible tags and the Ultra-High Frequency range are dominant in both scholarly and patent documents, reflecting their significance in radio-frequency identification technology applications. The research underscores a vibrant area of development within radio-frequency identification technology, with continued innovation driven by specific industrial needs. Despite the noted advances, the presence of a significant percentage of no longer valid patents suggests substantial opportunities for further research and innovation in radio-frequency identification technology for on-metal applications, especially considering the demand for flexible tags and for solutions in systems that offer specialized characteristics or are tailored for specific uses.
- 27 April 2024
- Published by MDPI AG in Technologies
- Vol. 12 (5) , 58
Open AccessRFID Tags for On-Metal Applications: A Brief Survey
Radio-frequency identification technology finds extensive use in various industrial applications, including those involving metallic surfaces. The integration of radio-frequency identification systems with metal surfaces, such as those found in the automotive sector, presents distinct challenges that can notably affect system efficacy due to metal’s tendency to reflect electromagnetic waves, thus degrading the functionality of conventional radio-frequency identification tags. This highlights the importance of conducting research into academic publications and patents to grasp the current advancements and challenges in this field, aiming to improve the applications of radio-frequency identification tags technology on metal. Consequently, this research undertakes a concise review of both the literature and patents exploring radio-frequency identification technology’s use for on-metal tags, utilizing resources like Google Scholar and Google Patents. The research categorized crucial aspects such as tag flexibility, operating frequency, and geographic origins of the research. Findings highlight China’s prominent role in contributing to metal-focused radio-frequency identification tag research, with a considerable volume of articles and patents. In particular, flexible tags and the Ultra-High Frequency range are dominant in both scholarly and patent documents, reflecting their significance in radio-frequency identification technology applications. The research underscores a vibrant area of development within radio-frequency identification technology, with continued innovation driven by specific industrial needs. Despite the noted advances, the presence of a significant percentage of no longer valid patents suggests substantial opportunities for further research and innovation in radio-frequency identification technology for on-metal applications, especially considering the demand for flexible tags and for solutions in systems that offer specialized characteristics or are tailored for specific uses.
- Top Cited PapersOpen Access
- 21 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Radio Frequency Identification
- Vol. 7, 609-620
RFID Technology for Animal Tracking: A Survey
The application of animal tracking holds significant importance across diverse economic domains, encompassing sectors including livestock husbandry, agricultural practices, and the conservation of wildlife populations. It aims to track and understand animal behavior, movement patterns, and health status. The predominant use of RFID technology is observed within the domains of logistics, localization, and the tracking of goods. Notably, the application of this technology in the field of animal tracking has experienced a significant surge in popularity in recent years. This paper conducts a systematic literature review focused on understanding how RFID technology is being applied in the field of animal tracking. We have conducted a state-of-the-art research regarding animal tracking solutions in the scientific literature and patents. We have analyzed these solutions targeting which animals are being tracked, which problems are addressed, operating frequency, and whether other technologies are combined with RFID for animal tracking purposes. Among the categories of problems addressed, livestock management emerged as the main area, followed by animal tracking and traceability. Mammals, especially cattle, are the most common type of animal monitored. Considering RFID technology, passive UHF tags appeared more often. Moreover, many works also employed cameras and GPS together with RFID. Finally, this work can significantly contribute to this field by systematically presenting a state-of-the-art application of RFID for animal tracking.
- 21 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Radio Frequency Identification
- Vol. 7, 609-620
Top Cited PapersOpen AccessRFID Technology for Animal Tracking: A Survey
The application of animal tracking holds significant importance across diverse economic domains, encompassing sectors including livestock husbandry, agricultural practices, and the conservation of wildlife populations. It aims to track and understand animal behavior, movement patterns, and health status. The predominant use of RFID technology is observed within the domains of logistics, localization, and the tracking of goods. Notably, the application of this technology in the field of animal tracking has experienced a significant surge in popularity in recent years. This paper conducts a systematic literature review focused on understanding how RFID technology is being applied in the field of animal tracking. We have conducted a state-of-the-art research regarding animal tracking solutions in the scientific literature and patents. We have analyzed these solutions targeting which animals are being tracked, which problems are addressed, operating frequency, and whether other technologies are combined with RFID for animal tracking purposes. Among the categories of problems addressed, livestock management emerged as the main area, followed by animal tracking and traceability. Mammals, especially cattle, are the most common type of animal monitored. Considering RFID technology, passive UHF tags appeared more often. Moreover, many works also employed cameras and GPS together with RFID. Finally, this work can significantly contribute to this field by systematically presenting a state-of-the-art application of RFID for animal tracking.
- 7 July 2021
- Published by Springer Nature in Education and Information Technologies
- Vol. 27 (1) , 1183-1212
Brain-imaging techniques in educational technologies: A systematic literature review
- 7 July 2021
- Published by Springer Nature in Education and Information Technologies
- Vol. 27 (1) , 1183-1212
Brain-imaging techniques in educational technologies: A systematic literature review