Machine learning of swimming data via wisdom of crowd and regression analysis

Xie, Jiang; Xu, Jin; Nie, Celine; Nie, Qing

doi:10.3934/mbe.2017031

Cited by 6 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study used such techniques to analyze the age trends in junior swimming from over 4,000,000 races. 56 If height, body mass, and other anthropometric measures could be collected in world-class swimmers, then the use of machine learning techniques could be extremely useful in talent identification and the classification of world-class swimmers.…”

Section: Discussionmentioning

confidence: 99%

The age, height, and body mass of Olympic swimmers: A 50-year review and update

Mallett

Bellinger

Derave

et al. 2020

International Journal of Sports Science & Coaching

View full text Add to dashboard Cite

A difficulty in identifying the optimal age, height, and body mass of swimmers is the heterogeneity of the athletes examined (i.e., gender, caliber), the variability in race distance and stroke, and the influence of time. Nonetheless, age, height, and body mass remains the most readily available data of all athlete characteristics, supporting their contribution to the prediction of performance. This review presents the findings of previous studies over the last 50 years and offers new insights by examining data from swimmers competing at the 1968, 1992, and 2016 Olympic Games. Our data investigates gender differences in age, before exploring gender-specific variations in the age, height, and body mass across year, distance, stroke, and caliber. We show that there are differences in swimmers competing at the 2016 compared to the 1968 and 1992 Olympic Games. Today the age of world-class swimmers is independent of gender, race distance and stroke, as well as caliber. Swimmers competing in freestyle are taller and heavier than in butterfly, while height remains associated with performance in some, but not all events in female swimmers. In 2016 the average age, height and body mass of World-class swimmers is 22.7 ± 3.6 and 23.2 ± 23.3 years, 175.1 ± 6.6 cm and 188.3 ± 6.0 cm and 63.8 ± 6.8 and 81.3 ± 7.3 kg for females and males respectively. These findings provide coaches with a new perspective on the optimal age, height, and body mass of world-class female and male swimmers.

show abstract

Section: Discussionmentioning

confidence: 99%

The age, height, and body mass of Olympic swimmers: A 50-year review and update

Mallett

Bellinger

Derave

et al. 2020

International Journal of Sports Science & Coaching

View full text Add to dashboard Cite

show abstract

“…Although sensor data were not used, in [ 5 ], statistical analysis and machine learning methods were systematically applied to swimming records, investigating performance features for all strokes as a function of age and gender. It included two novel features, namely the use of machine learning methods and the use of an ensemble classifier that outperforms the single instance intelligent classifiers.…”

Section: Sensors In Sportsmentioning

confidence: 99%

“…Recently, different approaches for developing wearable sensors for sports are being sought [ 1 , 2 , 3 , 4 ]. However, initial methodologies were developed essentially for monitoring purposes, and initial approaches employing intelligent systems in sports analytics, namely in swimming, have neglected the possibility of using wearable sensors, focusing essentially on statistics or crowdsourced data [ 5 ] and recorded video [ 6 , 7 , 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

Framework for Intelligent Swimming Analytics with Wearable Sensors for Stroke Classification

Costa

Silva

Santos

et al. 2021

Sensors

View full text Add to dashboard Cite

Intelligent approaches in sports using IoT devices to gather data, attempting to optimize athlete’s training and performance, are cutting edge research. Synergies between recent wearable hardware and wireless communication strategies, together with the advances in intelligent algorithms, which are able to perform online pattern recognition and classification with seamless results, are at the front line of high-performance sports coaching. In this work, an intelligent data analytics system for swimmer performance is proposed. The system includes (i) pre-processing of raw signals; (ii) feature representation of wearable sensors and biosensors; (iii) online recognition of the swimming style and turns; and (iv) post-analysis of the performance for coaching decision support, including stroke counting and average speed. The system is supported by wearable inertial (AHRS) and biosensors (heart rate and pulse oximetry) placed on a swimmer’s body. Radio-frequency links are employed to communicate with the heart rate sensor and the station in the vicinity of the swimming pool, where analytics is carried out. Experiments were carried out in a real training setup, including 10 athletes aged 15 to 17 years. This scenario resulted in a set of circa 8000 samples. The experimental results show that the proposed system for intelligent swimming analytics with wearable sensors effectively yields immediate feedback to coaches and swimmers based on real-time data analysis. The best result was achieved with a Random Forest classifier with a macro-averaged F1 of 95.02%. The benefit of the proposed framework was demonstrated by effectively supporting coaches while monitoring the training of several swimmers.

show abstract

“…Predicting sports outcomes using ML techniques has already been applied in team sports, such as rugby, ice hockey, basketball, soccer, and American football (Bunker and Susnjak, 2019) as well as in individual sports, such as hurdle races (Przednowek et al, 2014), race walking (Przednowek and Wiktorowicz, 2013), horse racing (Lessmann et al, 2009) and swimming (Xie et al, 2017). Most of the predictions in sports outcome are achieved through a multi-label classification (e.g., win, lose, draw) and some use regression to output a performance value, such as speed (e.g., Harville, 1980;Przednowek and Wiktorowicz, 2013;Przednowek et al, 2014;Spiegeleer, 2019;Kholkine et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes

Kholkine

Servotte

Leeuw

et al. 2021

Front. Sports Act. Living

View full text Add to dashboard Cite

Professional road cycling is a very competitive sport, and many factors influence the outcome of the race. These factors can be internal (e.g., psychological preparedness, physiological profile of the rider, and the preparedness or fitness of the rider) or external (e.g., the weather or strategy of the team) to the rider, or even completely unpredictable (e.g., crashes or mechanical failure). This variety makes perfectly predicting the outcome of a certain race an impossible task and the sport even more interesting. Nonetheless, before each race, journalists, ex-pro cyclists, websites and cycling fans try to predict the possible top 3, 5, or 10 riders. In this article, we use easily accessible data on road cycling from the past 20 years and the Machine Learning technique Learn-to-Rank (LtR) to predict the top 10 contenders for 1-day road cycling races. We accomplish this by mapping a relevancy weight to the finishing place in the first 10 positions. We assess the performance of this approach on 2018, 2019, and 2021 editions of six spring classic 1-day races. In the end, we compare the output of the framework with a mass fan prediction on the Normalized Discounted Cumulative Gain (NDCG) metric and the number of correct top 10 guesses. We found that our model, on average, has slightly higher performance on both metrics than the mass fan prediction. We also analyze which variables of our model have the most influence on the prediction of each race. This approach can give interesting insights to fans before a race but can also be helpful to sports coaches to predict how a rider might perform compared to other riders outside of the team.

show abstract

Machine learning of swimming data via wisdom of crowd and regression analysis

Cited by 6 publications

References 25 publications

The age, height, and body mass of Olympic swimmers: A 50-year review and update

The age, height, and body mass of Olympic swimmers: A 50-year review and update

Framework for Intelligent Swimming Analytics with Wearable Sensors for Stroke Classification

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes

Contact Info

Product

Resources

About