DeCoach: Deep Learning-based Coaching for Badminton Player Assessment

Ghosh, Indrajeet; Ramamurthy, Sreenivasan Ramasamy; Chakma, Avijoy; Roy, Nirmalya

doi:10.1016/j.pmcj.2022.101608

Cited by 19 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Ghosh et al [11] have proposed the use of 4 accelerometers and a CNN to classify the strokes into 12 types. This information is used as a basis for other modules of the proposal, such as score estimation.…”

Section: Related Workmentioning

confidence: 99%

“…It has already been established by this previous research that the differences between individual players can be significantly large, which hinders the performance of trained classification models when applied on new players [10], especially in the case of amateur players [11]. However, recent algorithmic developments such as data augmentation and transfer learning open new possibilities to enable the training of general models for badminton stroke classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Badminton stroke classification based on accelerometer data: from individual to generalized models

Peralta

Herbruggen

Fontaine

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Activity recognition models based on wearable devices are becoming increasingly popular. However, models that are trained and tested on the same players show a large bias and are not generalizable to previously unseen players. In this paper, we tackle the badminton stroke recognition problem from this perspective, comparing the performance of individual and generalized models based on an accelerometer and a gyroscope, and identifying which components of the solution can maximize the performance of generalized models. First, we describe a simple convolutional neural network trained to classify 7 types of stroke. Second, the model is extended in a hybrid way to identify two additional classes (movement and rest). Third, data augmentation is applied on the training set. Fourth, transfer learning is applied to use data from the test player to fine-tune the generalized model and attempt to reach the performance of an individual model. These models are evaluated on a dataset collected from amateur players, both in a controlled environment and in a match simulation. The results showed a large difference between the performance of individual and generalized models; however, the latter could be improved by increasing the number of players in the training set, by data augmentation, and by transfer learning, highlighting the necessity of larger datasets in this field.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Badminton stroke classification based on accelerometer data: from individual to generalized models

Peralta

Herbruggen

Fontaine

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

show abstract

“…Sports analytics is the training, collecting and investigation of analytical data, and employing state‐of‐the‐art data mining techniques to predict and determine the players' performance to determine their weaknesses and strengths in their game. Sports analytics has opened a vast spectrum of research problems and challenges, mainly covering real‐time players'/team performance assessment (I. Ghosh et al, 2022), 3D pose estimation (Cai et al, 2019), game dynamics (A. Ghosh et al, 2018), tactics, behavioral and psychological study of the players in the competitive environments (Sheehan et al, 2023), and so on. Gerrard and Alamar (2014) introduce and present an overall sports analytics framework which is comprised of four main components: analytic models, data management, information systems, and the decision maker.…”

Section: Introductionmentioning

confidence: 99%

“…Sports analytics has opened a vast spectrum of research problems and challenges, mainly covering real-time players'/team performance assessment (I. Ghosh et al, 2022), 3D pose estimation (Cai et al, 2019), game dynamics (A. Ghosh et al, 2018), tactics, behavioral and psychological study of the players in the competitive environments (Sheehan et al, 2023), and so on.…”

mentioning

confidence: 99%

“…The high area under the Precision-Recall Curve represents both high recall and high precision. High precision correlates to a low false-positive (FP) rate, and high recall correlates to a low false-negative (FN) rate Classification I Ghosh et al (2022)Chakma et al (2020) F1 Score is compute by combining the precision and recall scores by computing the harmonic mean between the scoresClassification Cai et al (2019) Percentage of Correct Keypoints Pose Estimation measures the predicted keypoints, and the true joint is within a certain distance threshold.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Sports analytics review: Artificial intelligence applications, emerging technologies, and algorithmic perspective

Ghosh

Ramamurthy

Chakma

et al. 2023

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

The rapid and impromptu interest in the coupling of machine learning (ML) algorithms with wearable and contactless sensors aimed at tackling real‐world problems warrants a pedagogical study to understand all the aspects of this research direction. Considering this aspect, this survey aims to review the state‐of‐the‐art literature on ML algorithms, methodologies, and hypotheses adopted to solve the research problems and challenges in the domain of sports. First, we categorize this study into three main research fields: sensors, computer vision, and wireless and mobile‐based applications. Then, for each of these fields, we thoroughly analyze the systems that are deployable for real‐time sports analytics. Next, we meticulously discuss the learning algorithms (e.g., statistical learning, deep learning, reinforcement learning) that power those deployable systems while also comparing and contrasting the benefits of those learning methodologies. Finally, we highlight the possible future open‐research opportunities and emerging technologies that could contribute to the domain of sports analytics.This article is categorized under: Technologies > Machine Learning Technologies > Artificial Intelligence Technologies > Internet of Things

show abstract