Participants will receive additional technology-based upper extremity training for 120 min/day, 5d/w, 4 weeks.

The program will be tailored to their impairment level, and will be added to the usual treatment given during hospitalization.

This group is comprised of patients with similar characteristics and the intervention group will be compared to this group.

Participants will receive additional technology-based upper extremity training for 120 min/day, 5d/w, 4 weeks.

The Upper Extremity Fugl-Meyer Assessment (UE-FMA) is a standardized clinical tool designed to evaluate motor impairment in the upper limb following a stroke. It is part of the broader Fugl-Meyer Assessment, one of the most widely used and validated scales in stroke rehabilitation research. The UE-FMA specifically assesses movement, coordination, and reflexes in the shoulder, elbow, forearm, wrist, and hand, with a maximum score of 66 points. The scale is divided into subcomponents, including upper limb movement (36 points), wrist (10 points), hand (14 points), and coordination/speed (6 points). Each item is scored on a 3-point ordinal scale (0 = cannot perform, 1 = performs partially, 2 = performs fully), offering a total score that reflects the level of motor impairment-higher scores indicate better motor function. The UE-FMA is valued for its reliability, sensitivity to impairment (rather than function), and its ability to track motor recovery over time.

The Action Research Arm Test (ARAT) is a standardized clinical tool used to assess upper limb function following stroke or neurological injury, with a focus on evaluating the ability to perform purposeful, goal-directed tasks. It consists of 19 items grouped into four subscales: grasp, grip, pinch, and gross movement, each designed to measure different aspects of upper limb activity. Tasks include actions such as picking up small blocks, pouring water, or moving objects across a table. Each item is scored on a 4-point ordinal scale ranging from 0 (no movement) to 3 (normal performance), yielding a maximum total score of 57. The ARAT captures the functional use of the hand and arm in a way that reflects real-world tasks, making it especially relevant for tracking meaningful improvements during rehabilitation. It is known for its high inter-rater and intra-rater reliability and is sensitive to changes in functional performance across a wide spectrum of impairment levels.

The Stroke Impact Scale (SIS) hand domain, version 2.0, is a patient-reported outcome measure that assesses the perceived difficulty of using the affected hand in everyday tasks following a stroke. This domain includes five items that ask individuals to rate the difficulty of performing common activities such as carrying heavy objects, turning a doorknob, or picking up a coin. Each item is scored on a 5-point Likert scale ranging from 1 (could not do it at all) to 5 (not difficult at all), reflecting the patient's experience over the past week. Scores are converted to a 0-100 scale, with higher scores indicating better perceived hand function. The SIS hand domain captures the individual's perspective on the functional impact of stroke on daily activities, providing valuable insight into real-world hand use. It is frequently used in stroke rehabilitation studies to complement performance-based assessments and to evaluate patient-centered outcomes.

Daily natural activity will be monitored for using IMUs (Movella DOT) worn on upper extremity and trunk for periods of up-to 6 hours.

Consists of 14 items for assessing static and dynamic balance and risk of falls for different populations. The test includes different tasks in various challenging positions and scored up to 56 points. A higher score indicated better balance and lower risk of falls.