Abstract
Paralympic cross-country skiing is a competitiveand physically demanding sport developed for individualswith physical disabilities. In addition to good training and en-durance, sports equipment is a key factor in achieving success.The design of sports equipment must be customized to ac-commodate specific impairments. Furthermore, biomechani-cal and neurophysiological factors need to be considered whendesigning equipment such as ski sledges. Among other neuro-physiological factors, muscle activity, typically measured us-ing electromyography (EMG), plays a crucial role. However,due to the high level of dynamic movement in the sport, EMGmeasurements are not always feasible. This study explores thepossibility of estimating EMG data using neural networks andacceleration data. A feedforward neural network model wascreated and trained to predict upper body muscle activationfrom acceleration data. Validation of the model using statisti-cal metrics yielded promising results, suggesting its effectiveuse in predicting muscle activity. This research sets the stagefor enhancing understanding and optimizing equipment in Par-alympic cross-country skiing, ultimately enhancing the perfor-mance of para-athletes.