Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About

About

Miguel Velhote Correia is Associate Professor at the Faculty of Engineering of the University of Porto (FEUP), where he taughts since 1998. He graduated in Electrical and Computer Engineering at FEUP in 1990. He also obtained his Master's and Doctorate at FEUP in 1995 and 2001, in the areas of Industrial Automation and Computer Vision, respectively. Since March 2008, he has been a senior researcher at INESC-Tecnologia e Ciência, responsible for the Bioinstrumentation Laboratory of the Research Center for Biomedical Engineering. He is also a member of the Order of Engineers. In 2007 he was co-founder and technical consultant until 2017 of Kinematix Sense S.A, a start-up electronic devices company from the University of Porto and INESC-TEC. Between 1993 and 2007, he was a researcher at the Instituto de Engenharia Biomédica and, previously, at the Centro CIM do Porto at FEUP. His main research interests are in Electronics and Biomedical Instrumentation, Wearable Systems, Computer Vision, Signal and Image Processing, focusing on the measurement and analysis of human movement, perception, action and performance. Since 1990 he has participated in more than two dozen funded research projects, supervised 10 PhD students and 50 MSc students, and co-authored more than 150 articles published in scientific journals and international conference proceedings.

Interest
Topics
Details

Details

  • Name

    Miguel Velhote Correia
  • Role

    Senior Researcher
  • Since

    01st March 2008
  • Nationality

    Portugal
  • Contacts

    +351222094106
    miguel.velhote.correia@inesctec.pt
008
Publications

2023

Lower Limb Joint Load Comparison from Subject Specific Musculoskeletal Model Simulation and Direct Measurements on Different Subject with Instrumented Implant During Normal and Abnormal Gait

Authors
Rodrigues, C; Correia, M; Abrantes, J; Rodrigues, M; Nadal, J;

Publication
COMPUTER METHODS, IMAGING AND VISUALIZATION IN BIOMECHANICS AND BIOMEDICAL ENGINEERING II

Abstract
This study presents lower limb joint load comparison from subject specific musculoskeletal model simulation (MSK-MS) and direct measurements from instrumented implants on post-operative (PO) patients. A case study was considered for MSK-MS gait analysis of a 40-year-old healthy male with 70 kg and 1.86 m height. Reflective adhesive markers were applied on skin surface of selected anatomical points at right and left lower limbs. Orthostatic and dynamic acquisition on normal gait (NG), stiff-knee gait (SKG) and slow running (SR) was performed from ground reaction forces with two force plates at 2 kHz and trajectories of skin markers with eight-camera system at 100 Hz. Subject specific MSK-MS was performed using AnyGait and morphed Twente Lower Extremity Model (TLEM), matching the size and joint morphology of the stick-figure model. Over-determinate kinematic analysiswas performed, and motion equations solved with hard and soft constraints. Representative MSK-MS gait cycles were selected at NG, SKG and SR lower limb joint vertical force components at the hip, the knee, and the ankle normalized to body weight (JFz/BW). Internal joint direct measurements of four PO patients', 61-83 years, average weight 808 N and 1.71 m height, with telemetric Hip I (4-channel), Hip II (8-channel) and knee (9-channel) instrumented implants were selected from Orthoload database with comparable gait to NG, SKG and SR. Statistical measurements presented similar mean JFz/BW at right/left hip, knee, ankle MSK-MS and asymmetric peak values with dominant NG, SKG and SR different variances (p < 0.05). Direct JFz/BW measures contrasted NG with similar hip and knee mean and variance from SKG and SR with different mean and variance. Peak JFz/BW direct measurements presented higher hip and knee values on SR and NG than SKG, with higher values at the knee than the hip on NG and SKG, and the opposite on SR. Direct JFz/BW measurements presented at the hip and the knee lower values than their corresponding MSK-MS on NG, SKG and SR.

2023

Detection of Intermittent Claudication from Smartphone Inertial Data in Community Walks Using Machine Learning Classifiers

Authors
Pinto, B; Correia, MV; Paredes, H; Silva, I;

Publication
SENSORS

Abstract
Peripheral arterial disease (PAD) causes blockage of the arteries, altering the blood flow to the lower limbs. This blockage can cause the individual with PAD to feel severe pain in the lower limbs. The main contribution of this research is the discovery of a solution that allows the automatic detection of the onset of claudication based on data analysis from patients' smartphones. For the data-collection procedure, 40 patients were asked to walk with a smartphone on a thirty-meter path, back and forth, for six minutes. Each patient conducted the test twice on two different days. Several machine learning models were compared to detect the onset of claudication on two different datasets. The results suggest that we can identify the onset of claudication using inertial sensors with a best case accuracy of 92.25% for the Extreme Gradient Boosting model.

2023

Minding your steps: a cross-sectional pilot study using foot-worn inertial sensors and dual-task gait analysis to assess the cognitive status of older adults with mobility limitations

Authors
Guimaraes, V; Sousa, I; de Bruin, ED; Pais, J; Correia, MV;

Publication
BMC GERIATRICS

Abstract
BackgroundCognitive impairment is a critical aspect of our aging society. Yet, it receives inadequate intervention due to delayed or missed detection. Dual-task gait analysis is currently considered a solution to improve the early detection of cognitive impairment in clinical settings. Recently, our group proposed a new approach for the gait analysis resorting to inertial sensors placed on the shoes. This pilot study aimed to investigate the potential of this system to capture and differentiate gait performance in the presence of cognitive impairment based on single- and dual-task gait assessments.MethodsWe analyzed demographic and medical data, cognitive tests scores, physical tests scores, and gait metrics acquired from 29 older adults with mobility limitations. Gait metrics were extracted using the newly developed gait analysis approach and recorded in single- and dual-task conditions. Participants were stratified into two groups based on their Montreal Cognitive Assessment (MoCA) global cognitive scores. Statistical analysis was performed to assess differences between groups, discrimination ability, and association of gait metrics with cognitive performance.ResultsThe addition of the cognitive task influenced gait performance of both groups, but the effect was higher in the group with cognitive impairment. Multiple dual-task costs, dual-task variability, and dual-task asymmetry metrics presented significant differences between groups. Also, several of these metrics provided acceptable discrimination ability and had a significant association with MoCA scores. The dual-task effect on gait speed explained the highest percentage of the variance in MoCA scores. None of the single-task gait metrics presented significant differences between groups.ConclusionsOur preliminary results show that the newly developed gait analysis solution based on foot-worn inertial sensors is a pertinent tool to evaluate gait metrics affected by the cognitive status of older adults relying on single- and dual-task gait assessments. Further evaluation with a larger and more diverse group is required to establish system feasibility and reliability in clinical practice.

2023

Towards Industrially Feasible Invisible Electrocardiography (ECG) in Sanitary Facilities

Authors
Silva, AD; Correia, MV; Costa, A; da Silva, HP;

Publication
2023 IEEE 7TH PORTUGUESE MEETING ON BIOENGINEERING, ENBENG

Abstract
Previous work from our team, has proposed a novel approach to invisible electrocardiography (ECG) in sanitary facilities using polymeric electrodes, leading to the creation of a proof-of-concept system integrated in a toilet seat. However, for this approach to be industrially feasible, further optimization is needed, in particular in what concerns electrode materials compatible with injection moulding processes. In this paper we explore the use of different types of conductive materials as electrodes, aiming at industrial-scale production of a toilet seat capable of recording ECG data, without the need for bodyworn devices. In addition, the effect of cleaning agents applied to the materials over time. Our approach has been evaluated comparatively with a gold standard device, for a population of 15 healthy subjects. While some of the materials did not allow adequate signal acquisition in all users, one electrically conductive compound showed the best results as per heart rate and ECG waveform morphology analysis. For the best performing compound we were able to acquire signals in 100% of the sessions, with an average heart rate deviation between the reference and experimental systems of -3.67 +/- 5.05 beats per minute (BPM). In terms of ECG waveform morphology, the best cases showed a Pearson correlation coefficient of 0.99.

2023

Sagittal Lower Limb Joint Angular Phase-Plane Analysis at Long, Short and No-Countermovement

Authors
Rodrigues, C; Correia, M; Abrantes, J; Rodrigues, M; Nadal, J;

Publication
2023 IEEE 7TH PORTUGUESE MEETING ON BIOENGINEERING, ENBENG

Abstract
This study presents non-invasive subject specific analysis using innovative tools from dynamic systems theory and image processing for sagittal plane anatomical marker tracking and digital filtering for detection of normalized phase differences of lower limb joint angular displacement and angular velocity coordination during long and short countermovement (CM) and muscle stretch-shortening cycle. Applied metrics captured at low-dimensional level (one variable - the phase) differences of CM neuromuscular control of lower limb joint coordination with greater dissimilarity between long and short CM, whereas no CM condition shares higher phase coordination at the hip, knee, ankle.

Supervised
thesis

2022

Towards Personalized In-Silico Mathematical Models and Tools for Brain Networks Simulations and Study of Optimal Therapeutic Approaches for Refractory Epilepsy

Author
Elodie Múrias Lopes

Institution
UP-FEUP

2022

Multimodal Cervical Cancer Diagnosis: Deep Learning for Automatic Decision Support

Author
Tomé Mendes Albuquerque

Institution
UP-FEUP

2022

Dispositivo Intraoral para Determinação de Parâmetros Vitais em Pacientes com Síndrome da Apneia Obstrutiva do Sono

Author
Beatriz Isabel Saloio Guedes

Institution
UP-FEUP

2022

Prototype of a mandibular advancement device with microsensors for sleep apnea syndrome and snoring

Author
Helena Patrícia Campos da Silva

Institution
UP-FEUP

2022

bio-signal analysis for neuromuscular control assessment: application to the stretch-shortening cycle in the human locomotion system

Author
Carlos Manuel Barbosa Rodrigues

Institution
UP-FEUP