Disability and Rehabilitation-Assistive Technology最新文献_第7页

CHATWELL: an AI-enabled adaptive tutoring system for improving mandarin composition skills in L2 students with learning difficulties. CHATWELL：一个基于人工智能的自适应辅导系统，用于提高有学习困难的第二语言学生的普通话写作技能。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-10-01 Epub Date: 2025-09-09 DOI: 10.1080/17483107.2025.2554955

Wenwen Cheng, Jiahui Guo, Duwen Lu

{"title":"CHATWELL: an AI-enabled adaptive tutoring system for improving mandarin composition skills in L2 students with learning difficulties.","authors":"Wenwen Cheng, Jiahui Guo, Duwen Lu","doi":"10.1080/17483107.2025.2554955","DOIUrl":"10.1080/17483107.2025.2554955","url":null,"abstract":"Background: Conventional automated writing evaluation systems typically provide insufficient support for students with special needs, especially in tonal language acquisition such as Chinese, primarily because of rigid feedback mechanisms and limited customisation.Objective: This research develops context-aware Hierarchical AI Tutor for Writing Enhancement(CHATWELL), an intelligent tutoring platform that incorporates optimised large language models to deliver instantaneous, customised, and multi-dimensional writing assistance for Chinese language learners, with special consideration for those with cognitive learning barriers.Methods: CHATWELL employs a hierarchical AI framework with a four-tier feedback mechanism designed to accommodate diverse learning needs. In a 12-week quasi-experiment involving 100 HSK4 learners (including participants with dyslexia and other learning challenges), the system was compared against a conventional Bi-LSTM-based AES, assessing improvements in writing scores, error reduction, and accessibility metrics.Results: The AI-powered CHATWELL group showed significantly greater score gains (14.2 vs. 6.8 points, t(98) = 7.85, p < 0.001), with marked reductions in grammatical (72.1%) and logical (75.3%) errors. Learners with disabilities particularly benefitted from its scaffolded feedback, with 89% rating the system as \"highly accessible and effective.\" Engagement data revealed increased use of deeper feedback tiers, suggesting improved self-regulated learning.Conclusions: The CHATWELL system substantiates the effectiveness of AI-augmented language instruction in advancing writing capabilities and promoting inclusive pedagogy for second language learners, including those with special educational requirements. These results emphasise the transformative potential of intelligent tutoring systems in addressing linguistic learning challenges.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"2358-2374"},"PeriodicalIF":2.2,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145024456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Good intentions may be wrong: evidence from anonymous donation behaviour on Chinese charitable crowdfunding platform. 善意可能是错误的：来自中国慈善众筹平台上匿名捐赠行为的证据。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-30 DOI: 10.1080/17483107.2025.2565405

Danqing Zhu, Qifa Xu, Cuixia Jiang

{"title":"Good intentions may be wrong: evidence from anonymous donation behaviour on Chinese charitable crowdfunding platform.","authors":"Danqing Zhu, Qifa Xu, Cuixia Jiang","doi":"10.1080/17483107.2025.2565405","DOIUrl":"https://doi.org/10.1080/17483107.2025.2565405","url":null,"abstract":"Using web crawling and statistical regression models based on large-scale platform data, this study examines how previous anonymous and non-anonymous donations influence subsequent contributions on charitable crowdfunding platforms, with a particular focus on health-related campaigns. Through web crawling, this study collected 1,136 projects from Qingsongchou and empirically analysed the herding effect in donation behaviour. Results indicate a significant herding effect in both anonymous and non-anonymous donations, as well as in donation amounts. This effect is stronger among non-anonymous donors compared to anonymous ones. Furthermore, this study explore moderating channels and find that social media sharing weakens the herding effect for anonymous donations but does not significantly alter the differential herding behaviour between the two groups. By distinguishing between early and late fundraising stages, this study also observe that the herding effect difference is more pronounced in the early stage. These findings enhance understanding of the economic implications of anonymous donations under information asymmetry and offer practical insights for improving anonymity mechanisms in health-oriented charitable crowdfunding.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-14"},"PeriodicalIF":2.2,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145193425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Personalised sports rehabilitation analysis using a fitness enhanced model based on big data and deep learning. 使用基于大数据和深度学习的健身增强模型进行个性化运动康复分析。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-29 DOI: 10.1080/17483107.2025.2561926

Rui Zhang

{"title":"Personalised sports rehabilitation analysis using a fitness enhanced model based on big data and deep learning.","authors":"Rui Zhang","doi":"10.1080/17483107.2025.2561926","DOIUrl":"https://doi.org/10.1080/17483107.2025.2561926","url":null,"abstract":"Introduction: Health rehabilitation plays a vital role in contemporary healthcare in ensuring post-illness, post-injury, and post chronic condition recovery, and serving on maintaining or improving physical functions and overall quality of life and preventing long-term complications and conditions. Conventional approaches to rehabilitation have tended to involve off-the-shelf procedures and frequent clinical assessments.Purpose: Purpose of this study is to establish a modern health rehabilitation management model. This is through implementing the embedded technology and big data analytic in Fitness Qigong. The system incorporates wearable devices and sensors in the environment.Results: Physiologically, results indicated critical advances in physiological functioning following international training periods of Qigong training: increasing Heart Rate Variability (HRV) by 29.7%, decreasing breathing rate by 17.8%, improving movements efficiency by 20.3% and dropping the level of stress by 46.2% (all p < 0.001). Correlation analysis showed that improving HRV and moving with efficiency were strongly related to the intensity of practice (r = +0.84 and r = +0.90, respectively), whereas breathing rate showed a considerable negative relationship with practice intensity (r = -0.72). Comparison with Traditional Model In addition to that, the technology-enabled model exhibited further significant improvement, exceeding the traditional model increase by more than 200% HRV (+34.2% vs. +14.%) and breathing efficiency as well as adherence rates (91.5% vs. 65.8%).Implications: The implications of these findings emphasise the potential of technology-integrated Qigong practice to reliably, scalable and data-informed health management.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-14"},"PeriodicalIF":2.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145187291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Developing National Priority Assistive Products Lists: experiences and lessons from six Sub-Saharan African countries. 制定国家重点辅助产品清单：撒哈拉以南非洲六个国家的经验和教训。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-27 DOI: 10.1080/17483107.2025.2561246

Sarah Anderson, Frederic Seghers, Lillian Saunders, Charles Reza, Frank Chikhata, Eshetu Bekele, Satish Mishra

{"title":"Developing National Priority Assistive Products Lists: experiences and lessons from six Sub-Saharan African countries.","authors":"Sarah Anderson, Frederic Seghers, Lillian Saunders, Charles Reza, Frank Chikhata, Eshetu Bekele, Satish Mishra","doi":"10.1080/17483107.2025.2561246","DOIUrl":"https://doi.org/10.1080/17483107.2025.2561246","url":null,"abstract":"Purpose: This study examines the experiences and lessons learned from six Sub-Saharan African countries in developing National Priority Assistive Products Lists (APLs) between 2020 and 2024, aiming to provide insights for improving assistive technology (AT) access in low- and middle-income countries (LMICs).Materials and methods: The study employed qualitative descriptive methodology with a multi-faceted approach, including a comprehensive desktop review of documentation and publications, followed by semi-structured interviews and information review with key stakeholders (n = 9) from all six countries. Data analysis involved synthesising information to identify common themes, challenges, and best practices in APL development.Results: Key findings include the importance of multi-stakeholder engagement, challenges in data availability, varied prioritisation frameworks, and the need for local context adaptation. Countries faced common barriers, such as limited funding and regulatory challenges, however also identified facilitators like government leadership and integration with existing health systems.Conclusions: The study highlights the complex nature of developing National APLs and emphasises the importance of inclusive stakeholder engagement, data-driven prioritisation, and integration within broader health system strengthening efforts. These insights can guide other countries in developing and implementing effective APLs, ultimately improving AT access and advancing disability rights.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-17"},"PeriodicalIF":2.2,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145179230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Between intimacy and surveillance: elderly users' adaptation and privacy negotiation in human-robot interaction. 在亲密与监视之间：老年用户在人机交互中的适应与隐私协商。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-27 DOI: 10.1080/17483107.2025.2566379

Rui Huang

{"title":"Between intimacy and surveillance: elderly users' adaptation and privacy negotiation in human-robot interaction.","authors":"Rui Huang","doi":"10.1080/17483107.2025.2566379","DOIUrl":"https://doi.org/10.1080/17483107.2025.2566379","url":null,"abstract":"Elderly users adapt through compromise and negotiation on how to assert control over the interaction with social robots. Privacy negotiation involves preserving dignity by installing clear consents on what are the boundaries of data access. This paper aims to understand how elderly individuals, informal caregivers, and formal caregivers in Chengdu, China, adapt to and interact with social care robots in the context of home-based aging. With 498 participants, this qualitative investigation looks at the subtle ethical, emotional, and practical nuances in human-robot interaction, focusing on values such as devolution, safety, privacy, enablement, independence, and social connectedness. It studies how compromise, persuasion, and negotiation come to form the main avenues through which old people keep a sense of empowerment while integrating robotic assistance into their daily lives. It further explores how participants assign variable social roles to the robots from obedient servants to healthcare aides and how prior agreements and user control can influence acceptance and reduce resistance. The focus goes on how the balance between technological assistance and personal liberty is negotiated, and also on how emotional reassurance and trust tie into long-term adaptation. The study thereby contributes to the worldwide conversation about ethical eldercare technology by situating findings within a non-Western, community-based setting. Gains from this research should feed back into the design, policy, and implementation of social robots in aging societies and make sure that they abide by human dignity, cultural expectations, and lived realities.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-20"},"PeriodicalIF":2.2,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145179102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From cognitive alignment to technological adaptation: understanding rural digital governance through AI-augmented human-data collaboration. 从认知一致性到技术适应：通过人工智能增强的人-数据协作理解农村数字治理。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-26 DOI: 10.1080/17483107.2025.2564370

Xiaofang Yan, Hong Chen

{"title":"From cognitive alignment to technological adaptation: understanding rural digital governance through AI-augmented human-data collaboration.","authors":"Xiaofang Yan, Hong Chen","doi":"10.1080/17483107.2025.2564370","DOIUrl":"https://doi.org/10.1080/17483107.2025.2564370","url":null,"abstract":"Under the dual impetus of China's digitalization strategy and rural revitalization initiatives, rural social governance has entered a key phase of digital transformation. As artificial intelligence (AI) and big data technologies are increasingly integrated into governance platforms, the capacity for AI-augmented human-data collaboration is becoming essential to effective multi-stakeholder interaction. Sustainable multi-stakeholder collaboration (SMC) represents both a core requirement and central value of rural digital governance. This study investigates the determinants of SMC and proposes strategies to enhance stakeholder synergy. Through grounded theory analysis of semi-structured interviews with 26 rural digital governance practitioners, six key factors were identified: (1) awareness intensity, (2) technical adaptability, (3) institutional completeness, (4) scenario compatibility, (5) interest relevance, and (6) situational appeal. These factors were validated via structural equation modeling (SEM) using 1,370 questionnaire responses. The results show that all six factors significantly promote SMC (β = 0.109-0.184, p < 0.001), with awareness intensity and interest relevance having stronger effects. Based on the findings, this study proposes strategies including strengthening publicity and guidance, implementing tiered training, promoting data interoperability, safeguarding public rights, optimizing evaluation mechanisms, and refining institutional frameworks to support sustainable collaboration. This research advances understanding of sustainable governance and provides insights for policy development and implementation of digital technologies in rural China. By highlighting the cognitive and technological dimensions of stakeholder collaboration, it offers an empirical basis for integrating AI-supported human-data interaction into rural governance, paving the way for more adaptive and inclusive digital governance systems.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-24"},"PeriodicalIF":2.2,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145179191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI-driven neural implants for vision and hearing: a qualitative study of user perspectives. 人工智能驱动的视觉和听觉神经植入物：用户视角的定性研究。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-26 DOI: 10.1080/17483107.2025.2559188

Odile C van Stuijvenberg, Katherine Bassil, Marike L D Broekman, Annelien L Bredenoord, Johan H M Frijns, Karin R Jongsma

{"title":"AI-driven neural implants for vision and hearing: a qualitative study of user perspectives.","authors":"Odile C van Stuijvenberg, Katherine Bassil, Marike L D Broekman, Annelien L Bredenoord, Johan H M Frijns, Karin R Jongsma","doi":"10.1080/17483107.2025.2559188","DOIUrl":"https://doi.org/10.1080/17483107.2025.2559188","url":null,"abstract":"Neural implants are being developed to treat various conditions, including sensory impairments such as blindness and deafness. In these technologies there is a growing role for artificial intelligence (AI) to enable interpretation of complex data input. Current users of cochlear implants (CIs) face challenges in noisy environments, prompting the development of AI-driven software for personalized and context-aware noise suppression and speech enhancement. For blindness, an AI-driven cortical visual neural implant (cVNI) for artificial visual perception is under development. Here, AI-driven software may be used to process camera imaging for interfacing with the brain. If successful, these devices can offer important advantages for their users yet may also have ethical implications. Perspectives of (potential) users of these technologies is an important source for ethical analysis, yet so far these have not been explored in-depth. We performed a focus-group and interview study including potential users of a) the AI-driven cVNI (n = 5) and of b) the AI-driven CI (n = 3), and c) current or (former) users or a retinal implant (n = 3). Focus groups and interviews were transcribed and analyzed thematically. Perspectives were clustered under 1) expectations and experiences, including improvements from the status quo, enhancement of autonomy and design requirements, and 2) perceived risks and anticipated disadvantages, including uncertainty on effectiveness, operational risks, surgical risks, and media attention. AI-driven neural implants for vision and hearing were positively received by potential users due to their potential to improve autonomy. Yet, possible conditions for uptake were identified, including device aesthetics and sufficient levels of user-control.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-17"},"PeriodicalIF":2.2,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145179117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reducing upper-limb strain in rehabilitation: usability evaluation of a detachable bidirectional propulsion device for spinal cord injury users. 减轻康复中上肢劳损：脊髓损伤患者可拆卸双向推进装置的可用性评估。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-25 DOI: 10.1080/17483107.2025.2565407

Jihye Choi, Jiyoung Park, Seon-Deok Eun, Dongheon Kang

{"title":"Reducing upper-limb strain in rehabilitation: usability evaluation of a detachable bidirectional propulsion device for spinal cord injury users.","authors":"Jihye Choi, Jiyoung Park, Seon-Deok Eun, Dongheon Kang","doi":"10.1080/17483107.2025.2565407","DOIUrl":"https://doi.org/10.1080/17483107.2025.2565407","url":null,"abstract":"To determine whether a detachable bidirectional (push-pull) propulsion module for manual wheelchairs can be rapidly learned, perceived as safe, and accepted by long-term users with spinal cord injury (SCI). Twenty adult SCI wheelchair users (mean age 59.4 ± 11.2 yr; wheelchair experience 20.1 ± 12.3 yr) propelled their chairs, equipped with the module, along a 20 m indoor corridor, completing five push and five pull trials after ∼10 min of familiarization and seat-belt fitting. Usability was assessed using a 45-item, 7-domain Likert scale (1 = strongly disagree, 5 = strongly agree) with excellent internal consistency (Cronbach's α = 0.927). Across domains, learnability, safety, user satisfaction, effectiveness, and efficiency were rated highly, with mean scores above 4.3 on a 5-point scale. Universality received comparatively lower ratings, reflecting cost considerations and adaptability to different contexts. The highest-rated single item was ease of understanding propulsion-mode switching, while willingness to use the device considering cost was lowest. No falls or entrapment events occurred during the trials. Overall, the push-pull module was intuitive, safe, and efficient after minimal training, with potential to diversify upper limb loading patterns and reduce shoulder strain in manual wheelchair users. Some participants noted challenges related to device width, weight (∼8 kg), and cost, indicating the need for further design optimization and structured training resources prior to widespread implementation.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-12"},"PeriodicalIF":2.2,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145151406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Perspectives and barriers of healthcare professionals in providing assistive products for cognitive function to older adults with cognitive impairment living at home in Japan: a qualitative interview study. 医疗保健专业人员在为居住在日本的老年认知障碍患者提供认知功能辅助产品方面的观点和障碍：一项定性访谈研究。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-24 DOI: 10.1080/17483107.2025.2563674

Megumi Kawasaki, Yuko Nishiura, Takenobu Inoue

{"title":"Perspectives and barriers of healthcare professionals in providing assistive products for cognitive function to older adults with cognitive impairment living at home in Japan: a qualitative interview study.","authors":"Megumi Kawasaki, Yuko Nishiura, Takenobu Inoue","doi":"10.1080/17483107.2025.2563674","DOIUrl":"https://doi.org/10.1080/17483107.2025.2563674","url":null,"abstract":"Purpose: To clarify the issues in providing assistive products for cognitive function (APCs) to older adults with dementia or cognitive impairment based on healthcare professionals' perceptions in Japan.Methods: Fifteen healthcare professionals providing assistive products to older adults with dementia participated in semi-structured online interviews (mean age 44.6 ± 6.5 years, 11 women, 4 men). Data were analyzed using qualitative thematic analysis.Results: The following four categories were identified as issues in the introduction, assessment, and use of assistive products for cognitive impairment: (1) lack of acceptance of assistive products by older adults with dementia and their ability to operate these products; (2) lack of cognitive assistive products available to older adults; (3) gaps in awareness of APC between professionals and caregivers; and (4) insufficient follow-up systems. Opinions were also extracted to create an environment in which it was easier for older adults with dementia to use electronic devices and information and communication technology (ICT).Conclusions: To effectively utilize the assistive products needed by older adults with dementia or cognitive impairment, caregivers' understanding of assistive products and the continued involvement of professionals are essential so that the functions of assistive products match the characteristics of the users. To facilitate these efforts, it is necessary to establish a framework for providing assistive products for dementia-related cognitive function.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-13"},"PeriodicalIF":2.2,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing communication for people with hearing disabilities through robust sign language recognition using deep learning and the internet of things. 通过使用深度学习和物联网的强大手语识别，加强听障人士的沟通。

IF 2.2 4区医学

Disability and Rehabilitation-Assistive Technology Pub Date : 2025-09-24 DOI: 10.1080/17483107.2025.2562454

Mashael Maashi, Abdulaziz Alhefdhi, Fuhid Alanazi, Mohammed Rizwanullah

{"title":"Enhancing communication for people with hearing disabilities through robust sign language recognition using deep learning and the internet of things.","authors":"Mashael Maashi, Abdulaziz Alhefdhi, Fuhid Alanazi, Mohammed Rizwanullah","doi":"10.1080/17483107.2025.2562454","DOIUrl":"https://doi.org/10.1080/17483107.2025.2562454","url":null,"abstract":"Sign language recognition (SLR) was employed in human-machine interactions, enhancing the survival of people with speech losses or who rely on non-verbal cues. The Internet of Things (IoT), the world of sensors, might reduce the absence of the hearing sense class of the physically challenged. IoT's explosive expansion can help those with hearing impairments by enhancing their everyday activities, communication, access to education, and general quality of life, both for them and their caretakers. The usage of DL techniques can aid in decreasing barriers to communication. This manuscript proposes an Enhancing Communications with Others through Robust Sign Language Recognition using the Sparse Autoencoder with Hearing Disabilities (ECRSLR-SAEHD) approach. The presented ECRSLR-SAEHD approach utilises a hyperparameter-tuned deep learning model to detect SL and leverages the IoT to assist people with hearing disabilities. Initially, the Gaussian filtering (GF) method is utilised for the image preprocessing process to enhance image clarity by reducing noise. For the feature extraction process, the EfficientNetB7 method is used to capture complex image patterns for a robust representation of complex SL movements. For the recognition of SL, the sparse auto-encoder (SAE) model is employed. To improve the SL performance of the SAE model, the fennec fox algorithm (FFA) model is used for the hyperparameter tuning process. To demonstrate the good classification outcome of the ECRSLR-SAEHD technique, a wide range of simulations is accomplished under a benchmark dataset. A widespread experimental validation of the ECRSLR-SAEHD technique portrayed a superior accuracy value of 93.07% over existing methods.","PeriodicalId":47806,"journal":{"name":"Disability and Rehabilitation-Assistive Technology","volume":" ","pages":"1-19"},"PeriodicalIF":2.2,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0