Athletes can optimize training performance by measuring the oxygenation level in their muscles using Near-infrared spectroscopy (NIRS). NIRS allows athletes to measure local muscle oxygenation changes and assess performance indicators such as optimal pace or intensity during endurance activities and optimal recovery in endurance and strength activities. A novel NIRS sensor (Train.Red FYER) was developed to enable these measurements. In this this study the stability, accuracy, intra- and inter-variability of muscle oxygenation saturation (SmO2) in 10 sensors using two different phantoms and in-vivo tests, were SmO2 was defined as the percentage of the ratio of oxygenated to total hemoglobin. Stability of three sensors was tested during 3 hours on each phantom. Intra-variability of three sensors was assessed on four different days by two different operators by repositioning the sensor over the same location on both phantoms and on the forearm during resting position. Intra-variability was also assessed during vascular occlusion tests (VOT). Intervariability was assessed between 10 sensors on both phantoms on four different days. For analysis coefficient of variance (CV) was calculated. The sensor showed to be stable on both phantoms (<1% SmO2). Precision tests showed a larger inter-variability (<2% SmO2) than intra-variability (<1% SmO2). Inter-day and inter-operator variability on phantoms were also small (<4% SmO2). In vivo tests on the forearm and VOT showed higher variability (<5% SmO2) than on phantoms. It was shown a stable and precise NIRS sensor for the measurement of SmO2.

Cerebral palsy (CP) is a childhood-onset motor disability affecting movement and posture that is caused by permanent brain disturbances. 1 Low muscle force generation 2,3 and muscle fatigue are among the most commonly reported impairments in CP. 4 Low muscle force generation has been associated with a primary impairment of muscle activation, 2,5,6 including reduced muscle activity levels when performing maximum voluntary contraction (MVC), reduced neuron-firing rates, and less coordinated muscle activation compared with

The rest period in between strength exercises determines how the short-term energy supplies in the muscles are replenished and metabolites are cleared. Near-InfraRed Spectroscopy (NIRS) is a proven method to study oxidative recovery kinetics following exercise. The goal of this study is to develop a model that predicts the oxygenated recovery state, this can help athletes optimize the resumption of exercise. 17 healthy subjects performed a sustained isometric hold in a hand gripper until volitional exertion, Tissue Saturation Index (TSI) was continuously monitored throughout and following exercise by a NIRS sensor (Train.Red PLUS). The oxygenated recovery state was manually categorized by three independent experts into four different phases of recovery; I - a pronounced increase, II - a gentle increase, III - the maximum oxygenated state, and IV - the return to baseline. A Recurrent Neural Network, inspired by Natural Language Processing, was trained and tested on this data, resulting in a model that predicts shifts between phases of recovery. A 5-fold cross-validation analysis resulted in the following average performance: • Recurrent Neural Network: Accuracy: 55.17%, categorical cross-entropy: 1.02351. • Multi-Layer Perceptron: Accuracy: 57.16%, categorical cross-entropy: 0.95201. • XGBoost: accuracy: 44.85%, categorical cross-entropy: 10.1119. In predicting the user’s current state of oxygenated recovery the MLP and RNN are similar in performance, however, the MLP shows erratic behavior, while the RNN generally follows the shift in phases of the ground truth. These capabilities could enable athletes with different fitness goals to design goal-tailored and therefore more efficient training.

No abstract