scholarly journals Wearable Inertial Measurement Unit to Accelerometer-Based Training Monotony and Strain during a Soccer Season: A within-Group Study for Starters and Non-Starters

2021 ◽  
Vol 18 (15) ◽  
pp. 8007
Author(s):  
Hadi Nobari ◽  
Mustafa Sögüt ◽  
Rafael Oliveira ◽  
Jorge Pérez-Gómez ◽  
Katsuhiko Suzuki ◽  
...  
Keyword(s):  
Inertial Measurement Unit ◽  
Soccer Players ◽  
Measurement Unit ◽  
Arbitrary Unit ◽  
Inertial Measurement ◽  
Professional Soccer ◽  
Weekly Training ◽  
And Training ◽  
Over Time

The purpose of this study was to analyze the intragroup differences in weekly training monotony (TM) and training strain (TS) between starter and non-starter male professional soccer players at accelerometry based variables throughout the periods of a season. TM and TS of different accelerations and decelerations zones for twenty-one players were followed for forty-eight weeks. Regardless of group, players obtained the highest mean TM (starters = 3.3 ± 0.6, non-starters = 2.2 ± 1.1, in arbitrary unit, AU) and TS (starters = 1288.9 ± 265.2, non-starters = 765.4 ± 547.5, AU) scores in the pre-season for accelerations at Zone 1 (<2 m/s2). The results also indicated that both groups exhibited similar TM and TS scores in accelerations at Zones 2 (2 to 4 m/s2) and 3 (>4 m/s2) across the entire season. While the starters showed the highest TM and TS scores at deceleration Zone 1 (<−2 m/s2) in the end-season, the non-starters exhibited the highest scores at the deceleration Zone 1 in pre-season. It seems that in pre-season, coaches applied higher levels of training with greater emphasis on deceleration for non-starters. This tendency was reduced over time for non-starters, while starters presented higher values of deceleration Zone 1. These results highlight the variations in TM and TS across the different periods of a full season according to match starting status among professional soccer players, and the results suggest that non-starter players should receive higher levels of load to compensate for non-participation in matches throughout a soccer season.

Comparisons of new body load and metabolic power average workload indices between starters and non-starters: A full-season study in professional soccer players

2020 ◽  
pp. 175433712097487
Author(s):  
Hadi Nobari ◽  
Gibson Moreira Praça ◽  
Filipe Manuel Clemente ◽  
Jorge Pérez-Gómez ◽  
Jorge Carlos Vivas ◽  
...  
Keyword(s):  
Injury Risk ◽  
Soccer Players ◽  
Metabolic Power ◽  
Early Season ◽  
Professional Soccer ◽  
Weekly Training ◽  
Significant Difference ◽  
Body Load ◽  
Gps Devices ◽  
And Training

The aim of this study was to compare the weekly average training monotony new body load (wTMNBL) and strain (wTSNBL), as well as the weekly average training monotony metabolic power average (wTMMPA) and strain (wTSMPA) between four periods of a season (preseason, early-season, mid-season, and end-season), considering starters and non-starters. Twenty-one professional soccer players (age: 28.27 ± 3.78 years) were monitored throughout a season in the highest level of professional football Premier League in Iran. Data were captured by Global Positioning System (GPS) devices. Independent samples T-tests were applied to analyze the between-group differences for all dependent derived-GPS variables for the full season and its different periods (preseason, early-season, mid-season, and end-season). Based on the amount of time attending in match and training, players were divided into two groups (starters and non-starters) each week. The magnitude of the between-group difference revealed a very large significant greater weekly average TMNBL ( p<0.001, d = −2.42), TSNBL ( p<0.001; d = −2.74), TMMPA ( p<0.001; d =–2.79) and TSMPA ( p<0.001; d = −3.27) for starters when compared to non-starters during the early-season. The findings also revealed a very large significant difference when starters were compared to non-starters during the mid-season (TMNBL: p<0.001, d = −2.89; TSNBL: p<0.001, d = −2.99; TMMPA: p<0.001, d = −3.28; and TSMPA: p<0.001, d = −3.25) and end-season (TMNBL: p<0.001, d = −2.89; TSNBL: p<0.001, d = −3.07; TMMPA: p<0.001, d = −3.16; and TSMPA: p<0.001, d = −3.58). In summary, the results of this study revealed that starters present regularly higher values of NBL, MPA-based weekly training monotony, and training strain than non-starters. This result must be taken into account when planning weekly workloads for these groups. Specifically, starters might experience high values of external workloads because of match-related demands. Therefore, weekly adjustments in their training workload are required to reduce injury risk.

scholarly journals Towards Automatic Modeling of Volleyball Players’ Behavior for Analysis, Feedback, and Hybrid Training

2020 ◽  
Vol 3 (4) ◽  
pp. 323-330
Author(s):  
Fahim A. Salim ◽  
Fasih Haider ◽  
Dees Postma ◽  
Robby van Delden ◽  
Dennis Reidsma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inertial Measurement Unit ◽  
Measurement Unit ◽  
Dominant Hand ◽  
Average Precision ◽  
Inertial Measurement ◽  
Average Recall ◽  
Automatic Tagging ◽  
Volleyball Players ◽  
And Training

Automatic tagging of video recordings of sports matches and training sessions can be helpful to coaches and players and provide access to structured data at a scale that would be unfeasible if one were to rely on manual tagging. Recognition of different actions forms an essential part of sports video tagging. In this paper, the authors employ machine learning techniques to automatically recognize specific types of volleyball actions (i.e., underhand serve, overhead pass, serve, forearm pass, one hand pass, smash, and block which are manually annotated) during matches and training sessions (uncontrolled, in the wild data) based on motion data captured by inertial measurement unit sensors strapped on the wrists of eight female volleyball players. Analysis of the results suggests that all sensors in the inertial measurement unit (i.e., magnetometer, accelerometer, barometer, and gyroscope) contribute unique information in the classification of volleyball actions types. The authors demonstrate that while the accelerometer feature set provides better results than other sensors, overall (i.e., gyroscope, magnetometer, and barometer) feature fusion of the accelerometer, magnetometer, and gyroscope provides the bests results (unweighted average recall = 67.87%, unweighted average precision = 68.68%, and κ = .727), well above the chance level of 14.28%. Interestingly, it is also demonstrated that the dominant hand (unweighted average recall = 61.45%, unweighted average precision = 65.41%, and κ = .652) provides better results than the nondominant (unweighted average recall = 45.56%, unweighted average precision = 55.45, and κ = .553) hand. Apart from machine learning models, this paper also discusses a modular architecture for a system to automatically supplement video recording by detecting events of interests in volleyball matches and training sessions and to provide tailored and interactive multimodal feedback by utilizing an HTML5/JavaScript application. A proof of concept prototype developed based on this architecture is also described.

scholarly journals Sprint Variables Are Associated with the Odds Ratios of Non-Contact Injuries in Professional Soccer Players

2021 ◽  
Vol 18 (19) ◽  
pp. 10417
Author(s):  
Hadi Nobari ◽  
Elena Mainer-Pardos ◽  
Angel Denche Zamorano ◽  
Thomas G. Bowman ◽  
Filipe Manuel Clemente ◽  
...  
Keyword(s):  
Inertial Measurement Unit ◽  
High Speed ◽  
High Volume ◽  
High Load ◽  
Soccer Players ◽  
Measurement Unit ◽  
Interval Time ◽  
Professional Soccer ◽  
Increased Risk ◽  
Low Load

Significant evidence has emerged that a high volume of sprinting during training is associated with an increased risk of non-contact injuries in professional soccer players. Training load has been reported as a modifiable risk factor for successive injury in soccer. Sprint workload measures and non-contact injuries were recorded weekly in twenty-one professional soccer players over a one season period. Odds ratio (OR) and relative risk (RR) were calculated based on the weeks of high and low load of total distance (TD), high-speed distance (HSD), sprint distance (SPD). and repeated sprints (RS). The Poisson distribution estimated the interval time between the last injury and the new injury. The weeks with high-load levels increased the risk of non-contact injury associated with TD (OR: 4.1; RR: 2.4), HSD (OR: 4.6; RR: 2.6), SPD (OR: 6.9; RR: 3.7), and RS (OR: 4.3; RR: 2.7). The time between injuries was significantly longer in weeks of low-load in TD (rate ratio time (RRT) 1.5 vs. 4.2), HSD (RRT: 1.6 vs. 4.6), and SPD (RRT: 1.7 vs. 7.7) compared to weeks of high-load. The findings highlight an increased risk of non-contact injuries during high weekly sprint workloads. Possibly, TD, HSD, and SPD measured via a wearable inertial measurement unit could be modeled to track training and to reduce non-contact injuries. Finally, the interval time between the last injury and the new injury at the high-load is shorter than the low-load.

scholarly journals Automatically evaluating balance using machine learning and data from a single inertial measurement unit

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Fahad Kamran ◽  
Kathryn Harrold ◽  
Jonathan Zwier ◽  
Wendy Carender ◽  
Tian Bao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inertial Measurement Unit ◽  
Physical Therapists ◽  
Physical Therapist ◽  
Model Performance ◽  
Machine Learning Techniques ◽  
Measurement Unit ◽  
Balance Performance ◽  
Inertial Measurement ◽  
Self Assessments

Abstract Background Recently, machine learning techniques have been applied to data collected from inertial measurement units to automatically assess balance, but rely on hand-engineered features. We explore the utility of machine learning to automatically extract important features from inertial measurement unit data for balance assessment. Findings Ten participants with balance concerns performed multiple balance exercises in a laboratory setting while wearing an inertial measurement unit on their lower back. Physical therapists watched video recordings of participants performing the exercises and rated balance on a 5-point scale. We trained machine learning models using different representations of the unprocessed inertial measurement unit data to estimate physical therapist ratings. On a held-out test set, we compared these learned models to one another, to participants’ self-assessments of balance, and to models trained using hand-engineered features. Utilizing the unprocessed kinematic data from the inertial measurement unit provided significant improvements over both self-assessments and models using hand-engineered features (AUROC of 0.806 vs. 0.768, 0.665). Conclusions Unprocessed data from an inertial measurement unit used as input to a machine learning model produced accurate estimates of balance performance. The ability to learn from unprocessed data presents a potentially generalizable approach for assessing balance without the need for labor-intensive feature engineering, while maintaining comparable model performance.

scholarly journals Inertial Measurement Unit Sensors in Assistive Technologies for Visually Impaired People, a Review

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4767
Author(s):  
Karla Miriam Reyes Leiva ◽  
Milagros Jaén-Vargas ◽  
Benito Codina ◽  
José Javier Serrano Olmedo
Keyword(s):  
Inertial Measurement Unit ◽  
Visually Impaired ◽  
Inertial Sensors ◽  
Assistive Technologies ◽  
Biomechanical Analysis ◽  
Measurement Unit ◽  
Inertial Measurement ◽  
Visually Impaired People ◽  
Impaired People ◽  
Application Fields

A diverse array of assistive technologies have been developed to help Visually Impaired People (VIP) face many basic daily autonomy challenges. Inertial measurement unit sensors, on the other hand, have been used for navigation, guidance, and localization but especially for full body motion tracking due to their low cost and miniaturization, which have allowed the estimation of kinematic parameters and biomechanical analysis for different field of applications. The aim of this work was to present a comprehensive approach of assistive technologies for VIP that include inertial sensors as input, producing results on the comprehension of technical characteristics of the inertial sensors, the methodologies applied, and their specific role in each developed system. The results show that there are just a few inertial sensor-based systems. However, these sensors provide essential information when combined with optical sensors and radio signals for navigation and special application fields. The discussion includes new avenues of research, missing elements, and usability analysis, since a limitation evidenced in the selected articles is the lack of user-centered designs. Finally, regarding application fields, it has been highlighted that a gap exists in the literature regarding aids for rehabilitation and biomechanical analysis of VIP. Most of the findings are focused on navigation and obstacle detection, and this should be considered for future applications.

scholarly journals Early Detection of Freezing of Gait during Walking Using Inertial Measurement Unit and Plantar Pressure Distribution Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2246
Author(s):  
Scott Pardoel ◽  
Gaurav Shalin ◽  
Julie Nantel ◽  
Edward D. Lemaire ◽  
Jonathan Kofman
Keyword(s):  
Early Detection ◽  
Plantar Pressure ◽  
Inertial Measurement Unit ◽  
Binary Classification ◽  
Freezing Of Gait ◽  
Pressure Sensors ◽  
Measurement Unit ◽  
Distribution Data ◽  
Inertial Measurement ◽  
Plantar Pressure Distribution

Freezing of gait (FOG) is a sudden and highly disruptive gait dysfunction that appears in mid to late-stage Parkinson’s disease (PD) and can lead to falling and injury. A system that predicts freezing before it occurs or detects freezing immediately after onset would generate an opportunity for FOG prevention or mitigation and thus enhance safe mobility and quality of life. This research used accelerometer, gyroscope, and plantar pressure sensors to extract 861 features from walking data collected from 11 people with FOG. Minimum-redundancy maximum-relevance and Relief-F feature selection were performed prior to training boosted ensembles of decision trees. The binary classification models identified Total-FOG or No FOG states, wherein the Total-FOG class included data windows from 2 s before the FOG onset until the end of the FOG episode. Three feature sets were compared: plantar pressure, inertial measurement unit (IMU), and both plantar pressure and IMU features. The plantar-pressure-only model had the greatest sensitivity and the IMU-only model had the greatest specificity. The best overall model used the combination of plantar pressure and IMU features, achieving 76.4% sensitivity and 86.2% specificity. Next, the Total-FOG class components were evaluated individually (i.e., Pre-FOG windows, Freeze windows, transition windows between Pre-FOG and Freeze). The best model detected windows that contained both Pre-FOG and FOG data with 85.2% sensitivity, which is equivalent to detecting FOG less than 1 s after the freeze began. Windows of FOG data were detected with 93.4% sensitivity. The IMU and plantar pressure feature-based model slightly outperformed models that used data from a single sensor type. The model achieved early detection by identifying the transition from Pre-FOG to FOG while maintaining excellent FOG detection performance (93.4% sensitivity). Therefore, if used as part of an intelligent, real-time FOG identification and cueing system, even if the Pre-FOG state were missed, the model would perform well as a freeze detection and cueing system that could improve the mobility and independence of people with PD during their daily activities.

Sign in / Sign up

Export Citation Format

Share Document