Ana 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
Ana Pereira has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Francisco Nunes
Fraunhofer Portugal AICOS, Porto, Portugal
3 shared publications Inês Sousa
Fraunhofer Portugal AICOS, Porto, Portugal
3 shared publications- Duarte Folgado
Fraunhofer Portugal AICOS
2 shared publications Ricardo Peixoto
Fraunhofer Portugal AICOS, Porto, Portugal
2 shared publications- Vânia Guimarães
Fraunhofer Portugal AICOS, Porto, Portugal
2 shared publications Alberto Carvalho
Fraunhofer Portugal AICOS, Porto, Portugal
1 shared publication
Latest Publications
- Open Access
- 19 November 2020
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 2 (4) , 579-602
Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems
Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario—an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed.
- 19 November 2020
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 2 (4) , 579-602
Open AccessChallenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems
Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario—an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Position-independent Physical Activity Monitoring: Development and Comparison with Market Devices
The last years have seen great growth in wearable devices for activity monitoring. Fueled by miniaturization and market demand, many devices can accurately estimate physical activity. However, and despite the variety of solutions, existing wearables are tied to classifying activity from a single body position. Once users move their wearable, accuracy is affected. This paper describes the development and validation of a position-independent activity monitoring solution, the GoLiveClip. The performance of GoLiveClip is comparable to position-dependent devices, such as Fitbit Flex 2, Mi Band 2, Garmin Vivoactive HR, and Jawbone Up 24, for activity recognition, step detection, and distance estimation. These results motivate the development of position-independent activity monitoring solutions.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Position-independent Physical Activity Monitoring: Development and Comparison with Market Devices
The last years have seen great growth in wearable devices for activity monitoring. Fueled by miniaturization and market demand, many devices can accurately estimate physical activity. However, and despite the variety of solutions, existing wearables are tied to classifying activity from a single body position. Once users move their wearable, accuracy is affected. This paper describes the development and validation of a position-independent activity monitoring solution, the GoLiveClip. The performance of GoLiveClip is comparable to position-dependent devices, such as Fitbit Flex 2, Mi Band 2, Garmin Vivoactive HR, and Jawbone Up 24, for activity recognition, step detection, and distance estimation. These results motivate the development of position-independent activity monitoring solutions.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Using Inertial Sensors to Evaluate Exercise Correctness in Electromyography-based Home Rehabilitation Systems
Home-based rehabilitation systems can speed up recovery by enabling patients to exercise at home between rehabilitation sessions. However, home-based rehabilitation systems need to monitor and feedback exercises appropriately, as incorrect or imperfect exercises negatively impact the recovery of the patient. This paper describes a methodology for assessing the quality of rehabilitation exercises using inertial sensors, for a system that tracks exercises using surface electromyography sensors. This duality extends the information provided by the electromyography system since it provides a more comprehensive evaluation of posture and movement correctness. The methodology was evaluated with 17 physiotherapy patients, obtaining an average accuracy of 96% in detecting issues in the exercises monitored. The insights of this work are a first step to complement an electromyography-based home system to detect issues in movement and inform patients in real time about the correctness of their exercises.
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Using Inertial Sensors to Evaluate Exercise Correctness in Electromyography-based Home Rehabilitation Systems
Home-based rehabilitation systems can speed up recovery by enabling patients to exercise at home between rehabilitation sessions. However, home-based rehabilitation systems need to monitor and feedback exercises appropriately, as incorrect or imperfect exercises negatively impact the recovery of the patient. This paper describes a methodology for assessing the quality of rehabilitation exercises using inertial sensors, for a system that tracks exercises using surface electromyography sensors. This duality extends the information provided by the electromyography system since it provides a more comprehensive evaluation of posture and movement correctness. The methodology was evaluated with 17 physiotherapy patients, obtaining an average accuracy of 96% in detecting issues in the exercises monitored. The insights of this work are a first step to complement an electromyography-based home system to detect issues in movement and inform patients in real time about the correctness of their exercises.
- Open Access
- 1 January 2019
- Published by INSTICC
- p. 73-82
Physiotherapy Exercises Evaluation using a Combined Approach based on sEMG and Wearable Inertial Sensors
- 1 January 2019
- Published by INSTICC
- p. 73-82
Open AccessPhysiotherapy Exercises Evaluation using a Combined Approach based on sEMG and Wearable Inertial Sensors
- Open Access
- 28 November 2018
- Published by Association for Computing Machinery (ACM)
- p. 202-207
Design and evaluation of an exergame for motor-cognitive training and fall prevention in older adults
- 28 November 2018
- Published by Association for Computing Machinery (ACM)
- p. 202-207
Open AccessDesign and evaluation of an exergame for motor-cognitive training and fall prevention in older adults
- 1 January 2018
- Published by European Alliance for Innovation n.o.
Designing the Smart Badge: A Wearable Device for Hospital Workers
- 1 January 2018
- Published by European Alliance for Innovation n.o.
Designing the Smart Badge: A Wearable Device for Hospital Workers
- Open Access
- 23 May 2017
- Published by Association for Computing Machinery (ACM)
- p. 146-154
Joint angles tracking for rehabilitation at home using inertial sensors
Joint angles are commonly measured in physical rehabilitation to evaluate joint function. Evidences showed that wearable inertial sensors can accurately quantify human motion information, however, the most advanced and accurate methodologies require the execution of complex calibration movements which are unsuitable to inexpert users and inadequate for a home context. This way, four different joint angles estimation methods requiring no calibration movement were developed in order to track the main human body joint angles in real time. IMUs mounted in bracelets were used to restrict sensor positioning on the limbs. For six different exercises, the estimated absolute and relative joint angles were evaluated against the marker-based video tracking software Kinovea ground-truth. Correlation analysis between estimated and ground-truth joint angles indicated a very strong and statistically significant correlation. The average error in estimated joint angles is below 5 degrees for all four methods employed, which may be an acceptable result for the rehabilitation at home scenario.
- 23 May 2017
- Published by Association for Computing Machinery (ACM)
- p. 146-154
Open AccessJoint angles tracking for rehabilitation at home using inertial sensors
Joint angles are commonly measured in physical rehabilitation to evaluate joint function. Evidences showed that wearable inertial sensors can accurately quantify human motion information, however, the most advanced and accurate methodologies require the execution of complex calibration movements which are unsuitable to inexpert users and inadequate for a home context. This way, four different joint angles estimation methods requiring no calibration movement were developed in order to track the main human body joint angles in real time. IMUs mounted in bracelets were used to restrict sensor positioning on the limbs. For six different exercises, the estimated absolute and relative joint angles were evaluated against the marker-based video tracking software Kinovea ground-truth. Correlation analysis between estimated and ground-truth joint angles indicated a very strong and statistically significant correlation. The average error in estimated joint angles is below 5 degrees for all four methods employed, which may be an acceptable result for the rehabilitation at home scenario.