Assessment of Purposeful Movements for Post-Stroke Patients in Activites of Daily Living with Wearable Sensor Device

Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review

“…The system objective is to classify well and poorly executed tasks [52][53][54][55][56][57][58][59][60][61]63,64], to do so many approaches were followed. Some researchers implemented systems to distinguish between normal and abnormal gaits for lower-limb rehabilitation [56,59,60], in which participants executed 10 m walks.…”

“…Some researchers implemented systems to distinguish between normal and abnormal gaits for lower-limb rehabilitation [56,59,60], in which participants executed 10 m walks. Other researchers assessed the execution of ADLs [54,57] like different kitchen related activities or routine bedroom tasks. Moreover, Lee et.al [52] utilised exercises that belong to popular batteries of tests like Fugi Mayer assessment (FMA) [76,77], and extension or flexion of elbow and flexibility movements of shoulders [55,61].…”

“…Over the past few years, effort has been put into developing unobtrusive, effective and objective motion-modeling systems, taking advantage of the progress made in the sensor technology which became more compact and more power-efficient [83]. All the included works utilised IMUs for the data acquisition [42][43][44][45][46][47][48][49][50][52][53][54][55][56][57][58][59][60][61][65][66][67][68][69][70]63,[71][72][73][74]64]. IMUs are devices that combine linear acceleration from accelerometer and the angular turning rates from gyroscopes [84].…”

“…Placement of the sensing technology on the body has shown a heterogeneous distribution linked to the different nature of the employed technology and to the purpose for which the monitoring system was designed. Systems that focused on upper-limb rehabilitation used more frequently the wrists [46,49,52,53,58,65,68,69,[71][72][73][74] in twelve studies, arms [43,49,54,58,61,67,69,70,63,64] in ten studies, four studies used forearm [41,66,63,64], three studies used fingers [53,57,68], and hands [42,45,64], and a single study used elbow and shoulder [68]. These placements were targeted to monitor activities that involved using hands.…”

Pattern Recognition. ICPR International Workshops and Challenges

“…In [30] authors provided a proof-of-principle regarding the identification of a set of daily life activities within stroke patients. In [31], inertial sensors from high-end clinical devices were used for evaluating the functional improvement of stroke patients (in lieu of relying on diaries and self-questionnaire which does not bespeak the patient's real condition). Anyway, the above methods present several limitations: in [6] and [29], the data was collected from perfectly healthy subjects, while in [31] the work's aim was to classify the movements into purposeful and non-purposeful solely movements rather than recognizing them.…”