Paulo Pereira

Paulo Pereira

Auto-generated profile, based on publicly available information

Paulo Pereira

Departamento de Desporto e Saúde, Escola de Saúde e Desenvolvimento Humano, Universidade de Évora, Évora, Portugal

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 June 2017 in Journal of Sports Sciences
Verified
Journal Article
Closed access
HFHugo Folgado
Hugo Folgado
JBJorge Bravo
Jorge Bravo
PPPaulo Pereira
Paulo Pereira
JSJaime Sampaio
Jaime Sampaio
This study aimed to compare youth football players’ performance during two small-sided games with different pitch orientation: i) 40x30m and ii) 30x40m formats. Twenty under-15 players (age = 14.1 ± 0.5 years) participated in nine GK+4vs4+GK situations in each format, with the duration of six minutes each. Positional data were collected using individual GPS units, and computed for tactical and physical performance indicators. The SSG were video recorded, using notational analysis for collecting technical indicators. A novel method that incorporates time dependent notational information with spatiotemporal data was used to compute multidimensional parameters. Standardised effect sizes and non-clinical magnitude-based inferences were used to compare formats. Results showed that players covered more distance at higher intensities, presented more passes and dribbles and were more synchronised in the longitudinal axis while playing in the 40x30m pitch. In the 30x40m pitch, results showed a lower distance between team centroids, higher number of shots, more lateral passes and a wider team positioning. Multidimensional indicators, as players position and distance to the closest defender while shooting, revealed a more constant distance between attacker and defender in the 40x30m pitch. These results highlight the importance of integrating information from different indicators for a contextually valid information.

5 March 2026 in JMIR mHealth and uHealth
Verified
Journal Article
Open access
EOEduarda Oliosi
Eduarda Oliosi
SFSoraia Daniela Ferreira
Soraia Daniela Ferreira
AGAna Paula Giordano
Ana Paula Giordano
GVGuilherme Viveiros
Guilherme Viveiros
Jose ParracaJose Parraca
Jose Parraca
SASalomé Azevedo
Salomé Azevedo
Background: Artificial intelligence (AI)–driven pose estimation (PE) offers a scalable and cost-effective solution to track exercises in mobile health apps. However, occlusion, influenced by camera angle and distance, can reduce detection accuracy and repetition counting precision. The influence of smartphone positioning on these performance metrics remains underexplored in controlled studies. Objective: The study aimed to examine how smartphone camera angle (front, side, and diagonal) and distance (90 cm, 180 cm, 200 cm, and 360 cm) affect detection performance and repetition counting accuracy during push-ups and squats using AI-based PE. Methods: In this cross-sectional, within-subject study, 44 healthy university students (9 [20.5%] female participants; mean age 20.3 y, SD 0.4 y; mean BMI 23.2, SD 0.6 kg/m²) were assigned to perform either squats or push-ups. Each participant completed their assigned exercise across 12 predefined smartphone camera configurations, yielding approximately 264 squat trials (n=22) and 264 push-up trials (n=22). Each trial consisted of an average of 5 repetitions, totaling approximately 1320 repetitions per exercise. PE performance was assessed using binary classification accuracy, detection rate, and mean absolute error (MAE) for repetition counting. Generalized linear mixed-effects models evaluated classification odds, linear mixed-effects models analyzed MAE, and Tukey-adjusted post hoc tests followed significant effects. Results: The mean detection rate was 61.1% (SD 48.8%) for push-ups and 61.5% (SD 48.7%) for squats, with MAEs of 1.08 (SD 1.78) and 1.11 (SD 1.82) repetitions, respectively. Push-ups were most accurately detected from diagonal views at 90 to 180 cm (up to 85.7% detection; MAE=0.28) and least accurately from the front at 360 cm (20%; MAE=2.70). Squats performed best from a diagonal view at 200 cm (95.5%; MAE=0.05) and worst from the side at 90 cm (0%; MAE=5). Generalized linear mixed models showed that for push-ups, the front 90 cm and diagonal 360 cm views significantly reduced classification odds compared to the side 90 cm view ( P =.03 and P =.04, respectively), whereas for squats, diagonal and front views significantly outperformed side views across all distances ( P <.001). Post hoc tests confirmed that for push-ups, diagonal close or mid-range views had significantly lower MAEs than far front views, and for squats, diagonal and front views at 180 to 200 cm achieved the highest accuracy and lowest MAEs ( P <.05). Conclusions: AI-based PE effectiveness for exercise tracking is significantly affected by smartphone positioning. Diagonal and frontal views at mid-range distances (180‐200 cm) provided the highest detection accuracy and counting precision. These findings offer actionable guidance for developers, clinicians, coaches, and users optimizing mobile health exercise monitoring.

14 August 2025 in JMIR Preprints
Verified
Preprint
Open access
EOEduarda Oliosi
Eduarda Oliosi
SFSoraia Daniela Ferreira
Soraia Daniela Ferreira
AGAna Paula Giordano
Ana Paula Giordano
GVGuilherme Viveiros
Guilherme Viveiros
Jose ParracaJose Parraca
Jose Parraca
SASalomé Azevedo
Salomé Azevedo
BACKGROUND Artificial Intelligence (AI)-driven pose estimation offers a scalable and cost-effective solution to track exercises in mobile health (mHealth) applications. However, occlusion, influenced by camera angle and distance, can reduce detection accuracy and repetition counting precision. The influence of smartphone positioning on these performance metrics remains underexplored in controlled studies. OBJECTIVE To examine how smartphone camera angle (front, side, and diagonal) and distance (90 cm, 180 cm, 200 cm, and 360 cm) affect detection performance and repetition counting accuracy during push-ups and squats using AI-based pose estimation. METHODS In this cross-sectional, within-subject study, 44 healthy university students (nine female [20.5%]; mean age 20.3 ± 0.4 years; mean BMI 23.2 ± 0.6 kg/m²) were assigned to perform either squats or push-ups. Each participant completed their assigned exercise across 12 predefined smartphone camera configurations, yielding ~264 squat trials (n=22) and 264 push-up trials (n=22). Each trial averaged five repetitions, totaling ~1,320 repetitions per exercise. Pose estimation performance was assessed using binary classification accuracy, detection rate, and mean absolute error (MAE) for repetition counting. Generalized linear mixed-effects models (GLMMs) evaluated classification odds, linear mixed-effects models (LMMs) analyzed MAE, and Tukey-adjusted post hoc tests followed significant effects. RESULTS The mean detection rate was 61.1% (SD 48.8%) for push-ups and 61.5% (SD 48.7%) for squats, with MAEs of 1.08 (SD 1.78) and 1.11 (SD 1.82) repetitions, respectively. Push-ups were most accurately detected from diagonal views at 90–180 cm (up to 85.7% detection; MAE = 0.28) and least accurately from the front at 360 cm (20.0%; MAE = 2.70). Squats performed best from a diagonal view at 200 cm (95.5%; MAE = 0.05) and worst from the side at 90 cm (0.0%; MAE = 5.00). GLMMs showed that for push-ups, the front 90 cm and diagonal 360 cm views significantly reduced classification odds compared to the side 90 cm view (p = 0.032 and p = 0.040, respectively), whereas for squats, diagonal and front views significantly outperformed side views across all distances (p < .001). Post hoc tests confirmed that for push-ups, diagonal close/mid-range views had significantly lower MAEs than far front views, and for squats, diagonal and front views at 180-200 cm achieved the highest accuracy and lowest MAEs (p < .05). CONCLUSIONS AI-based pose estimation effectiveness for exercise tracking is significantly affected by smartphone positioning. Diagonal and frontal views at mid-range distances (180–200 cm) provided the highest detection accuracy and counting precision. These findings offer actionable guidance for developers, clinicians, coaches, and users optimizing mHealth exercise monitoring.