Browsing by Author "Niazi IK"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A Brain Computer Interface Neuromodulatory Device for Stroke Rehabilitation: Iterative User-Centered Design Approach
    (JMIR Publications, 2023-12-11) Alder G; Taylor D; Rashid U; Olsen S; Brooks T; Terry G; Niazi IK; Signal N
    Background: Rehabilitation technologies for people with stroke are rapidly evolving. These technologies have the potential to support higher volumes of rehabilitation to improve outcomes for people with stroke. Despite growing evidence of their efficacy, there is a lack of uptake and sustained use in stroke rehabilitation and a call for user-centered design approaches during technology design and development. This study focuses on a novel rehabilitation technology called exciteBCI, a complex neuromodulatory wearable technology in the prototype stage that augments locomotor rehabilitation for people with stroke. The exciteBCI consists of a brain computer interface, a muscle electrical stimulator, and a mobile app. Objective: This study presents the evaluation phase of an iterative user-centered design approach supported by a qualitative descriptive methodology that sought to (1) explore users’ perspectives and experiences of exciteBCI and how well it fits with rehabilitation, and (2) facilitate modifications to exciteBCI design features. Methods: The iterative usability evaluation of exciteBCI was conducted in 2 phases. Phase 1 consisted of 3 sprint cycles consisting of single usability sessions with people with stroke (n=4) and physiotherapists (n=4). During their interactions with exciteBCI, participants used a “think-aloud” approach, followed by a semistructured interview. At the end of each sprint cycle, device requirements were gathered and the device was modified in preparation for the next cycle. Phase 2 focused on a “near-live” approach in which 2 people with stroke and 1 physiotherapist participated in a 3-week program of rehabilitation augmented by exciteBCI (n=3). Participants completed a semistructured interview at the end of the program. Data were analyzed from both phases using conventional content analysis. Results: Overall, participants perceived and experienced exciteBCI positively, while providing guidance for iterative changes. Five interrelated themes were identified from the data: (1) “This is rehab” illustrated that participants viewed exciteBCI as having a good fit with rehabilitation practice; (2) “Getting the most out of rehab” highlighted that exciteBCI was perceived as a means to enhance rehabilitation through increased engagement and challenge; (3) “It is a tool not a therapist,” revealed views that the technology could either enhance or disrupt the therapeutic relationship; and (4) “Weighing up the benefits versus the burden” and (5) “Don’t make me look different” emphasized important design considerations related to device set-up, use, and social acceptability. Conclusions: This study offers several important findings that can inform the design and implementation of rehabilitation technologies. These include (1) the design of rehabilitation technology should support the therapeutic relationship between the patient and therapist, (2) social acceptability is a design priority in rehabilitation technology but its importance varies depending on the use context, and (3) there is value in using design research methods that support understanding usability in the context of sustained use.
  • Thumbnail Image
    Item
    A comparative analysis of global optimization algorithms for surface electromyographic signal onset detection
    (Elsevier Inc, 2023-09) Alam S; Zhao X; Niazi IK; Ayub MS; Khan MA
    Surface Electromyography (sEMG) is a technique for measuring muscle activity by recording electrical signals from the surface of the body. It is widely used in fields such as medical diagnosis, human–computer interaction, and sports injury rehabilitation. The detection of the onset and offset of muscle activation is a longstanding challenge in sEMG analysis. This study pioneers the implementation, configuration, and evaluation of Particle Swarm Optimization (PSO) against other optimization algorithms for sEMG signal detection, including Genetic algorithms (GA), Simulated Annealing (SA), Ant Colony Optimization (ACO), and Tabu Search (TS). The results show that the PSO algorithm achieves the highest median accuracy and F1-Score and is the fastest among the selected algorithms but has lower stability compared to Genetic algorithms and Ant colony optimization. The design and value of the cost function had a significant impact on the results, with optimal results obtained when the cost value was between 0.1203 and 0.1384. The use of these algorithms improved detection efficiency and reduced the need for manual parameter adjustment. To the best of our knowledge, no published studies have utilized Simulated Annealing, Ant colony optimization, and Tabu search meta-heuristic algorithms to detect sEMG signal onsets.