CoChat
Sign Up
Cited by 5Digital Accessibility for DisabilitiesAssistive Technology in Communication and MobilityUsability and User Interface Design

Accessible IoT Dashboard Design with AI-Enhanced Descriptions for Visually Impaired Users

Open access
Stelea, George Alex, Sangeorzan, Livia, Enache-David, Nicoleta·2025·Future Internet
DOI 10.3390/fi17070274
Open this paper in CoChat — free accountOpen PDF

Abstract

The proliferation of the Internet of Things (IoT) has led to an abundance of data streams and real-time dashboards in domains such as smart cities, healthcare, manufacturing, and agriculture. However, many current IoT dashboards emphasize complex visualizations with minimal textual cues, posing significant barriers to users with visual impairments who rely on screen readers or other assistive technologies. This paper presents AccessiDashboard, a web-based IoT dashboard platform that prioritizes accessible design from the ground up. The system uses semantic HTML5 and WAI-ARIA compliance to ensure that screen readers can accurately interpret and navigate the interface. In addition to standard chart presentations, AccessiDashboard automatically generates long descriptions of graphs and visual elements, offering a text-first alternative interface for non-visual data exploration. The platform supports multi-modal data consumption (visual charts, bullet lists, tables, and narrative descriptions) and leverages Large Language Models (LLMs) to produce context-aware textual representations of sensor data. A privacy-by-design approach is adopted for the AI integration to address ethical and regulatory concerns. Early evaluation suggests that AccessiDashboard reduces cognitive and navigational load for users with vision disabilities, demonstrating its potential as a blueprint for future inclusive IoT monitoring solutions.

Verified 2026-10-06 · 2 references not checked yet

AI snapshot

Written from the paper’s full text.

TL;DR

AccessiDashboard is a web-based IoT dashboard designed accessibility-first with semantic HTML5, WAI-ARIA, multi-modal data views, and LLM-generated long descriptions for visually impaired users. A preliminary audit indicates the prototype satisfies WCAG 2.1 AA, but the paper reports no completed user study with blind or low-vision participants.

Key findings

  • The prototype uses semantic HTML5, ARIA roles, keyboard navigation, and synchronized visual/textual modes; a preliminary audit combining expert screen-reader walkthroughs with Lighthouse and WAVE confirmed it satisfies WCAG 2.1 AA criteria.
  • AccessiDashboard generates AI long descriptions via the OpenAI API, with prompts including recent readings, min/max/average, and context; descriptions are stored in a `LongDescription` model and can be human-reviewed.
  • The paper’s comparison table claims AccessiDashboard provides real-time accessible IoT updates, AI-enhanced descriptions, rich multimodal output, and human-in-the-loop validation, whereas Azimuth uses rule-based non-LLM text and Grafana lacks AI-generated descriptions and has only partial WCAG 2.1 AA conformance as of 2023.
  • Background statistics cited include WHO’s estimate that more than 2.2 billion people globally experience near- or distance-vision impairment, WebAIM 2024 finding that 68% of blind respondents interact with dashboards at least weekly, and an audit of 87 public COVID-19 dashboards where fewer than 20% provided basic text alternatives.

Methods

  • Design and implementation study: a functional Laravel/PHP MVC prototype with RESTful IoT data ingestion, semantic HTML5/WAI-ARIA front end, OpenAI API integration for long descriptions, Redis caching, and privacy-by-design controls.
  • Multi-modal interface modes: visual chart mode, bullet trend list, data grid table, and detailed AI-generated analysis, all synchronized from the same sensor data.
  • Evaluation: preliminary accessibility audit using expert screen-reader walkthroughs plus automated Lighthouse and WAVE tools; qualitative comparison against Azimuth and Grafana. Planned future user study metrics include task success rate, completion time, error rate, and comprehension score, with preliminary thresholds of at least 90% task completion and no more than 15% critical errors.

Limitations

  • The paper states the initial testing relied on a small sample of accessibility experts and focused predominantly on English-language screen reader environments; broader linguistic and cultural accessibility remains unexplored.
  • The paper states automated tools cannot assess contextual comprehension, navigational intuitiveness, or cognitive load, so the demonstrator is a strong technical foundation rather than a complete solution; formal load testing and performance benchmarks are planned but not reported.
  • Evident from the text: no completed empirical user study with blind or low-vision participants is reported, and the AI layer may introduce bias, overgeneralizations, or contextual inaccuracies, which the paper acknowledges and mitigates with disclaimers, bounded prompts, human review, and fallback mechanisms.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/fi17070274

Cites

30 of 32 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 25 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    AccessiDashboard meets or exceeds WCAG 2.1 AA accessibility criteria, as verified by manual testing and automated tools.

    “To validate our approach, we conducted an initial evaluation through manual testing and the use of automated tools to verify that the dashboard meets or exceeds WCAG 2.1 AA accessibility criteria [19].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [19]

      Not checked in the free run.

  • Findingown data

    Early evaluation suggests that AccessiDashboard reduces cognitive and navigational load for users with vision disabilities.

    “Early evaluation suggests that AccessiDashboard reduces cognitive and navigational load for users with vision disabilities, demonstrating its potential as a blueprint for future inclusive IoT monitoring solutions.”
    Quote in the paperSubstantial claim
  • Findingreasoning

    AccessiDashboard includes built-in safeguards: all AI-generated interpretations are accompanied by explicit disclaimers.

    “First, all AI-generated interpretations are accompanied by explicit disclaimers that inform users of the automated nature of the content.”
    Quote in the paperNot a substantial claim
  • Findingown data

    Early evaluations suggest that the approach is effective in making complex data more understandable to blind users.

    “Early evaluations suggest that the approach is effective in making complex data more understandable to blind users, although further user testing is required to quantify the benefits.”
    Quote in the paperSubstantial claim
  • Findingreasoning

    AccessiDashboard includes a human-in-the-loop validation mechanism enabling administrators to review and refine AI-generated outputs.

    “Crucially, a human-in-the-loop validation mechanism enables administrators to review and refine AI-generated outputs, ensuring both reliability and editorial oversight.”
    • Also stated in: § 6. Conclusions and Future Work · plain
      “AccessiDashboard includes a human oversight mechanism for its AI-generated content. Administrators can review the long descriptions produced by the AI and adjust or approve them before they reach end-users.”
    Quote in the paperSubstantial claim
  • Classified as probably not a substantial claim. 58
  • May combine two claims. 34
  • The quote only partly states this claim. 2

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Findingnone given

    Stateless Laravel services, Redis queues, and effective caching ensure that real-time scale-out is feasible.

    “Stateless Laravel services, Redis queues, and effective caching ensure that real-time scale-out is feasible, while privacy-by-design safeguards and audit logs maintain transparency and compliance in AI usage.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Findingnone given

    Privacy-by-design safeguards and audit logs maintain transparency and compliance in AI usage.

    “Stateless Laravel services, Redis queues, and effective caching ensure that real-time scale-out is feasible, while privacy-by-design safeguards and audit logs maintain transparency and compliance in AI usage.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingreasoning

    The system offers concise stories of what the data are doing, turning numeric trends into immediately understandable insights.

    “Instead of forcing users to infer patterns from raw tables, the system now offers concise stories of what the data are doing, thereby turning numeric trends into immediately understandable insights.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingreasoning

    AccessiDashboard presents data through multiple synchronized modalities: visual charts/graphs, structured data tables, bullet-list summaries, and AI-generated narrative descriptions.

    “AccessiDashboard presents data through multiple synchronized modalities.Alongside the usual visual charts/graphs, it provides text-first alternatives: structured data tables, bullet-list summaries of sensor readings, and narrative descriptions generated by AI.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductcitation

    All communication in AccessiDashboard is over HTTPS to secure data in transit.

    “All communication is over HTTPS [39] to secure data in transit.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [39]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The Detailed Analysis Mode provides a narrative, paragraph-based summary where the AI generates long-form textual descriptions of data trends and contextual insights.

    “This mode provides a narrative, paragraph-based summary where the AI generates long-form textual descriptions of data trends and contextual insights.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Providing both graphical and textual forms of data has been shown to cater to different user preferences and needs, enhancing accessibility and usability.

    “In the web and data visualization contexts, providing both graphical and textual forms of data, as well as enabling natural language querying of visualizations, has been shown to cater to different user preferences and needs, enhancing accessibility and usability [27].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [27] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The Data Grid Table Mode structured layout enables users to navigate cell by cell and compare values across time or across sensors.

    “This structured layout enables users to navigate cell by cell and compare values across time or across sensors.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    Few existing solutions offer both a typical visual interface for sighted users and a thorough alternative textual interface that can keep pace with frequent data changes.

    “Few existing solutions offer both a typical visual interface for sighted users and a thorough alternative textual interface that can keep pace with frequent data changes.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Study design and conductreasoning

    If a new sensor value arrives, the visual chart updates, the bullet list updates, the table updates, and the narrative could be refreshed if needed.

    “If a new sensor value arrives, the visual chart updates, the bullet list updates, the table updates, and even the narrative could be refreshed if needed.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    Keeping the human-in-the-loop option (admins can review outputs) ensures accuracy for mission-critical deployments.

    “Additionally, by keeping the human-in-the-loop option (admins can review outputs), the system can ensure accuracy for mission-critical deployments.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    In cases where IoT data might be sensitive, AccessiDashboard ensures that personal identifiers are not included with sensor data, or provides anonymization if needed.

    “In cases where IoT data might be sensitive (e.g., health data), we ensure that personal identifiers are not included with sensor data, or we provide anonymization if needed.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductreasoning

    AccessiDashboard automatically generates long descriptions of graphs and visual elements using an LLM, providing a text-first alternative interface for non-visual data exploration.

    “AccessiDashboard automatically generates long descriptions of graphs and visual elements, offering a text-first alternative interface for non-visual data exploration.”
    • Also stated in: § • · plain
      “Moving beyond simple alt text, the system leverages an LLM to produce extended textual descriptions of charts and complex graphics.”
    • Also stated in: § 3.2.3. AI Integration for Generating Long Descriptions · plain
      “A core innovation of AccessiDashboard is the automated generation of long descriptions for charts and complex data using an LLM.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    In Detailed Analysis Mode, instead of displaying raw values, the user receives a coherent and context-rich interpretation of the data similar to an automated report or commentary powered by a large language model.

    “Instead of displaying raw values, the user receives a coherent and context-rich interpretation of the data-similar to an automated report or commentary powered by a large language model.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Providing multiple modes addresses different cognitive styles and situations.

    “Providing multiple modes addresses different cognitive styles [40] and situations.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [40]

      Not checked in the free run.

  • May combine two claims. The quote only partly states this claim.

    Study design and conductnone given

    AccessiDashboard supports multi-modal data consumption (visual charts, bullet lists, tables, and narrative descriptions) and allows users to switch between modes.

    “The platform supports multi-modal data consumption (visual charts, bullet lists, tables, and narrative descriptions) and leverages Large Language Models (LLMs) to produce context-aware textual representations of sensor data.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    This is a key aspect of inclusive design: one platform that adapts to the user, rather than parallel platforms.

    “This is a key aspect of inclusive design: one platform that adapts to the user, rather than parallel platforms.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    Fully accessible IoT dashboards that integrate long-form AI-generated descriptions, real-time sensor updates, and strict compliance with accessibility standards (like WAI-ARIA) are still rare.

    “While there have been notable steps toward accessible data visualization and AIassisted interfaces, we find that fully accessible IoT dashboards that integrate long-form AI-generated descriptions, real-time sensor updates, and strict compliance with accessibility standards (like WAI-ARIA) are still rare.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Most existing IoT dashboards are designed with primarily visual paradigms and minimal textual description.
    • Rests on an assumption: Current IoT dashboard solutions often treat accessibility as an afterthought.
    • Rests on an assumption: Many dashboards comply only with minimal requirements, offering generic alt text or basic high-contrast mode, while ignoring deeper issues of navigability and interpretability for screen reader users.
    • Rests on an assumption: In practice, many IoT solutions ignore WCAG guideline or implement it in a minimal way.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning

    By generating multi-sentence narratives, these long descriptions give visually impaired users a much richer understanding of the data.

    “By generating multi-sentence narratives, these long descriptions give visually impaired users a much richer understanding of the data.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Murtaza et al. demonstrated that AI systems can produce simplified, domain-appropriate explanations of complex learning materials.

    “In the context of educational technology, Murtaza et al. [24] demonstrated that AI systems can produce simplified, domain-appropriate explanations of complex learning materials, helping to make content more accessible to learners.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [24] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    WCAG 2.1 specifies that images and charts should have meaningful alternative text so that users of assistive technologies can perceive the content.

    “The Web Content Accessibility Guidelines (WCAG) 2.1 [21] specify that images and charts should have meaningful alternative text so that users of assistive technologies can perceive the content.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [21] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Study design and conductnone given

    All these modes are kept in sync with the underlying data.

    “All these modes are kept in sync with the underlying data.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationnone given

    AccessiDashboard's user interface supports multiple modes of data representation to accommodate different user needs and preferences, all within the same platform.

    “AccessiDashboard's user interface supports multiple modes of data representation to accommodate different user needs and preferences, all within the same platform.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    Each new data source is initially reviewed by a designated administrator who compares the system-generated narrative with the corresponding live data visualization.

    “Each new data source is initially reviewed by a designated administrator, who compares the system-generated narrative with the corresponding live data visualization.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Interpretationreasoning

    The Bullet Trend List Mode format is accessible for screen reader users and presents clearly separated data points in a linear sequence, enabling efficient comprehension.

    “This format is accessible for screen reader users and presents clearly separated data points in a linear sequence, enabling efficient comprehension.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductcitation

    Scalability considerations, such as deploying the application in a load-balanced setup and using caching layers and optimizing database indices, have been incorporated to handle potentially high-frequency data streams.

    “Scalability considerations, such as deploying the application in a load-balanced setup and using caching layers (Redis [36] for session or description caching) and optimizing database indices, have been incorporated to handle potentially high-frequency data streams.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [36]

      Not checked in the free run.

  • May combine two claims.

    Study design and conductreasoning

    This integration enables near real-time, human-readable summaries of IoT data without manual authoring, supporting accessibility by transforming visual sensor trends into descriptive language.

    “This integration enables near real-time, human-readable summaries of IoT data without manual authoring, supporting accessibility by transforming visual sensor trends into descriptive language.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Study design and conductnone given

    The Data Grid Table Mode leverages semantic HTML table markup, ensuring relationships between headers and data remain accessible and clear to assistive technologies.

    “It leverages semantic HTML table markup, ensuring relationships between headers and data remain accessible and clear to assistive technologies.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    Discrepancies such as factual inaccuracies, omitted anomalies, or unit mismatches are documented and categorized.

    “Discrepancies, such as factual inaccuracies, omitted anomalies, or unit mismatches, are documented and categorized.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductreasoning

    Data tables in AccessiDashboard are marked up with <table>, <thead>, <tbody>, and <th> elements, which ensures that screen reader software can read out row and column headers when a cell is focused.

    “Data tables (when used to display numeric readings) are marked up with <table> along with <thead> and <tbody> to separate headers and data rows, and <th scope=”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Study design and conductnone given

    A privacy-by-design approach is adopted for the AI integration, with user data handled in compliance with GDPR guidelines and controls to prevent sensitive information from being sent to external AI services.

    “A privacy-by-design approach is adopted for the AI integration to address ethical and regulatory concerns.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [18]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The AI is used as an assistant in AccessiDashboard.

    “It is important to note that the AI is used as an assistant.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationnone given

    Most prior solutions either require authors to manually write long descriptions or focus on static datasets rather than live IoT data streams.

    “However, most prior solutions either require authors to manually write long descriptions or focus on static datasets rather than live IoT data streams.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Multi-modal design has been found beneficial not only for users with disabilities but also for users operating in constrained environments.

    “Multi-modal design has been found beneficial not only for users with disabilities but also for users operating in constrained environments, such as technicians listening to a dashboard readout while repairing a machine or users who cannot look at a screen [25].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [25] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationown data

    The Data Grid Table Mode is AI-generated and presents data in a tabular format similar to a spreadsheet.

    “Also AI-generated, this mode presents data in a tabular format similar to a spreadsheet.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    AccessiDashboard is designed as a web-based platform that can be deployed on a typical server or cloud environment to monitor IoT sensor data in real-time.

    “AccessiDashboard is designed as a web-based platform that can be deployed on a typical server or cloud environment to monitor IoT sensor data in real-time.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductcitation

    The AccessiDashboard interface is responsive and tested to work with screen readers like NVDA and VoiceOver.

    “The interface is responsive and tested to work with screen readers like NVDA [34] and VoiceOver [35].”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [34]

      Not checked in the free run.

    • cites [35]

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    The system mitigates risks of erroneous information by carefully crafting prompts and limiting the scope so the model focuses on the given data and does not introduce external facts unless relevant.

    “We mitigate risks of erroneous information by carefully crafting prompts and limiting the scope: the model is asked to focus on the given data and not introduce external facts unless relevant.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The modular nature of the description generation means the AI component could be improved or replaced without affecting the rest of the system.

    “The modular nature of the description generation (encapsulated in one service) means the AI component could be improved or replaced without affecting the rest of the system.”
    Quote in the paperNot a substantial claim

  • May combine two claims. The quote only partly states this claim.

    Study design and conductreasoning

    Each sensor widget in AccessiDashboard is identified with a heading and contained in a region with an ARIA label, enabling screen reader users to quickly navigate by regions.

    “Each sensor”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The lightweight validation process provides an early assessment of practical reliability.

    “This lightweight validation process provides an early assessment of practical reliability and will be replicated with independent reviewers during the full user study.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationnone given

    The Bullet Trend List Mode is AI-generated and presents the latest sensor readings or summarized trends as bullet points.

    “In this AI-generated textual mode, the latest sensor readings or summarized trends are presented as bullet points.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductcitation

    User authentication and role-based access control are implemented via Laravel's built-in mechanisms.

    “On the security side, user authentication and role-based access control [43] are implemented via Laravel's built-in mechanisms.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [43] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductreasoning

    If factual accuracy remains within an acceptable threshold, the source is considered verified and subsequently monitored through periodic spot-checks.

    “If factual accuracy remains within an acceptable threshold, the source is considered verified and subsequently monitored through periodic spot-checks.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    We developed a functional prototype that realizes the design principles described above.

    “To demonstrate the practical viability of AccessiDashboard, we developed a functional prototype that realizes the design principles described above.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductown data

    Key accessibility features were validated: logically ordered headings, semantically meaningful landmarks, and full keyboard navigability.

    “Key accessibility features were validated, including logically ordered headings, semantically meaningful landmarks, and full keyboard navigability.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    In compliance with regulations like GDPR, users have control over their data.

    “In compliance with regulations like GDPR, users have control over their data.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    By addressing both technical and UX aspects, we move toward closing the accessibility gap in IoT applications.

    “By addressing both the technical aspects (real-time data handling, AI integration) and the user experience aspects (clear structure, meaningful text alternatives), we move toward closing the accessibility gap in IoT applications.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductnone given

    The initial testing relied on a small sample of accessibility experts and focused predominantly on English-language screen reader environments.

    “The initial testing relied on a small sample of accessibility experts and focused predominantly on English-language screen reader environments.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    AccessiDashboard demonstrates that accessible IoT dashboards augmented with AI are not only possible but highly practical.

    “In conclusion, AccessiDashboard demonstrates that accessible IoT dashboards augmented with AI are not only possible but highly practical.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    AccessiDashboard provides an audit log for AI usage.

    “Moreover, AccessiDashboard provides an audit log for AI usage.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductown data

    A preliminary audit of AccessiDashboard combined expert screen-reader walkthroughs with automated tools such as Lighthouse and WAVE, confirming that the current prototype satisfies WCAG 2.1 AA criteria.

    “A preliminary audit of AccessiDashboard combined expert screen-reader walkthroughs with automated tools such as Lighthouse [55] and WAVE, confirming that the current prototype satisfies WCAG 2.1 AA criteria.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [55]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Study design and conductnone given

    Any labels that could reveal identity or location are removed or generalized before being sent.

    “Any labels that could reveal identity or location are removed or generalized before being sent.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The AI-generated content, being derived from sensor data, is treated as part of the user's data stream and thus accorded the same protections.

    “The AI-generated content, being derived from sensor data, is treated as part of the user's data stream and thus accorded the same protections.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    Sensor data is stored for up to 30 days, and AI outputs for up to 90 days before anonymization.

    “Storage Limitation and Security: Sensor data is stored for up to 30 days, and AI outputs for up to 90 days before anonymization.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    The user agreement or system documentation includes what kind of data might be sent to third-party AI services, to be transparent.

    “We also include in the user agreement or system documentation what kind of data might be sent to third-party AI services, to be transparent.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    If an AI-generated description ever provided an incorrect or inappropriate statement, the maintainers can review the log and adjust the system (by refining the prompt or correcting the output manually, and in some cases reporting issues to the AI service if needed).

    “If an AI-generated description ever provided an incorrect or inappropriate statement, the maintainers can review the log and adjust the system (either by refining the prompt or correcting the output manually, and in some cases reporting issues to the AI service if needed).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    All user interactions with the dashboard (beyond public data viewing, if any) require a login.

    “All user interactions with the dashboard (beyond public data viewing, if any) require a login.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationown data

    Our comparative analysis indicates that AccessiDashboard could serve as a blueprint for inclusive dashboard design.

    “Our comparative analysis indicates that AccessiDashboard could serve as a blueprint for inclusive dashboard design.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    Since most sensor data are numeric and generic, stripping out or abstracting labels that might contain names or specific locations is the main privacy measure.

    “Since most sensor data are numeric and generic, this mainly involves stripping out or abstracting any labels that might contain names or specific locations.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Most sensor data are numeric and generic.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Study design and conductnone given

    Before using sensor data, organizations agree to a data-processing policy based on legitimate interest.

    “Lawfulness, Fairness, and Consent: Before using sensor data, organizations agree to a data-processing policy based on legitimate interest.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    The result is a scalable and sustainable dashboarding solution that delivers timely, rich insights to blind or visually impaired users, fully aligned with the experience provided to sighted users.

    “The result is a scalable and sustainable dashboarding solution that delivers timely, rich insights to blind or visually impaired users, fully aligned with the experience provided to sighted users.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    Users are clearly informed about what data is shared and why, supporting transparency.

    “Users are clearly informed about what data is shared and why, supporting transparency.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Study design and conductnone given

    Only essential fields, like timestamp, sensor ID, and readings, are used for AI processing.

    “Purpose Limitation and Data Minimization: Only essential fields, like timestamp, sensor ID, and readings, are used for AI processing.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductown data

    Automated accessibility tools were valuable in detecting structural issues such as contrast errors or ARIA misconfigurations, and helped guide iterative improvements.

    “Automated accessibility tools were valuable in detecting structural issues such as contrast errors or ARIA misconfigurations, and they helped guide iterative improvements.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Study design and conductnone given

    If personal metadata is included (e.g., names in alerts), explicit opt-in is required.

    “If personal metadata is included (e.g., names in alerts), explicit opt-in is required.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductcitation

    Sessions are managed securely, and Laravel's CSRF protection is used for forms and state-changing requests to prevent cross-site request forgery.

    “Sessions are managed securely, and we use Laravel's CSRF [44] protection for forms and state-changing requests to prevent cross-site request forgery.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [44] source

      Not checked in the free run.

  • May combine two claims.

    Interpretationreasoning

    Because descriptions are generated automatically, expanding the dashboard to dozens or hundreds of sensors no longer multiplies authoring effort, making accessibility a built-in property.

    “Because descriptions are generated automatically, expanding the dashboard to dozens or hundreds of sensors no longer multiplies authoring effort, making accessibility a built-in property rather than an afterthought.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Study design and conductnone given

    All communications are encrypted, and access is logged to ensure accountability.

    “All communications are encrypted, and access is logged to ensure accountability.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductreasoning

    Every time a prompt is sent and a response received, it can be recorded (and shown to an admin if needed) to track what the AI was asked and what it replied.

    “Every time a prompt is sent and a response received, it can be recorded (and shown to an admin if needed) to track what the AI was asked and what it replied.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    The system can switch between cloud-based and self-hosted AI models, allowing organizations to keep data processing within their jurisdiction.

    “Model Flexibility and Data Sovereignty: The system can switch between cloud-based and self-hosted AI models, allowing organizations to keep data processing within their jurisdiction.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Study design and conductnone given

    Identifiers are securely hashed, data is encrypted at rest, and AI-generated outputs are linked to anonymized keys for added protection.

    “Anonymization and Pseudonymization: Identifiers are securely hashed, data is encrypted at rest, and AI-generated outputs are linked to anonymized keys for added protection.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    In a scenario where users might input personal data, the system would allow them to delete or export their data.

    “In a scenario where users might input personal data (not the case for simple sensor dashboards, but if it extended to user-generated content), the system would allow them to delete or export their data.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    Access to data is logged such that any unauthorized access attempts can be detected.

    “We also log access to data such that any unauthorized access attempts can be detected.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

    Interpretationreasoning

    These considerations ensure that an inclusive solution like Accessi-Dashboard can be adopted in practice within organizations that have strict IT and data governance policies.

    “These considerations ensure that an inclusive solution like Accessi-Dashboard can be adopted in practice within organizations that have strict IT and data governance policies.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    The architecture combining automation with ethical safeguards streamlines inclusive design workflows and reduces the maintenance burden typically associated with accessibility.

    “This architecture-combining automation with ethical safeguards-streamlines inclusive design workflows and reduces the maintenance burden typically associated with accessibility.”
    Quote in the paperNot a substantial claim
76 of 76

  • The paper relies on this without support.

    Most existing IoT dashboards are designed with primarily visual paradigms and minimal textual description.

    “However, most of these IoT dashboards are designed with primarily visual paradigms (color-coded charts, graphs, and interactive graphical controls) often with minimal textual description.”

  • The paper relies on this without support.

    Current IoT dashboard solutions often treat accessibility as an afterthought.

    “Current IoT dashboard solutions often treat accessibility as an afterthought, if they address it at all.”

  • The paper relies on this without support.

    Many dashboards comply only with minimal requirements, offering generic alt text or basic high-contrast mode, while ignoring deeper issues of navigability and interpretability for screen reader users.

    “Many dashboards comply only with minimal requirements, offering, for example, a generic alt text for a chart or a basic high-contrast mode, while ignoring deeper issues of navigability and interpretability for screen reader users.”

  • The paper relies on this without support.

    In practice, many IoT solutions ignore WCAG guideline or implement it in a minimal way.

    “In practice, however, many IoT solutions ignore this guideline or implement it in a minimal way.”

  • The paper relies on this without support.

    Most sensor data are numeric and generic.

    “Since most sensor data are numeric and generic, this mainly involves stripping out or abstracting any labels that might contain names or specific locations.”

  • The paper relies on this without support.

    Grafana has keyboard accessibility gaps: some controls or panels cannot be fully used via keyboard alone.

    “Keyboard accessibility is another known gap-some controls or panels cannot be fully used via keyboard alone, though work is underway to fix these (adding skip-to-content links, fixing focus traps, etc.).”

  • The paper relies on this without support.

    Grafana supports multiple data presentation formats (graphs, tables, single-value stats, text markdown).

    “Grafana supports multiple data presentation formats (it has panel types for graphs, tables, single-value stats, text markdown, etc.)”

  • The paper relies on this without support.

    Grafana does not automatically produce synchronized narrative descriptions.

    “but it does not automatically produce synchronized narrative descriptions.”

  • The paper relies on this without support.

    Grafana requires manual effort to meet even basic accessibility standards.

    “Grafana, which requires manual effort to meet even basic accessibility standards”

  • The paper relies on this without support.

    Grafana does not have any concept of human-in-the-loop accessibility verification built into the platform.

    “Grafana does not have any concept of human-in-the-loop accessibility verification built into the platform.”

  • The paper relies on this without support.

    Azimuth supports charts, structured text, and underlying tables, covering multiple modalities.

    “Azimuth supports charts, structured text, and underlying tables, covering multiple modalities.”

  • The paper relies on this without support.

    Azimuth does not provide AI narrative; the text is formulaic.

    “One thing it does not provide is AI narrative-the text is formulaic-but it still ensures that the information conveyed by visuals is also available in textual form.”

  • The paper relies on this without support.

    Azimuth generates rule-based textual summaries from static dashboard specifications.

    “Azimuth, which generates rule-based textual summaries from static dashboard specifications”

  • The paper relies on this without support.

    Azimuth's model is to generate accessible dashboards automatically from a specification.

    “Azimuth's model is to generate accessible dashboards automatically from a specification.”

  • The paper relies on this without support.

    Azimuth does not have a dedicated step for human validation of generated textual descriptions.

    “There is not a dedicated step for human validation of the generated textual descriptions.”

  • The paper relies on this without support.

    AI-generated textual summaries may introduce bias, overgeneralizations, or contextual inaccuracies that could have consequences in high-stakes environments.

    “AI-generated textual summaries-though designed to be informative and screen-reader friendly-may introduce bias, overgeneralizations, or contextual inaccuracies that could have consequences in high-stakes environments.”

  • The paper relies on this without support.

    Automated accessibility tools cannot assess contextual comprehension, navigational intuitiveness, or cognitive load.

    “They cannot assess contextual comprehension, navigational intuitiveness, or cognitive load.”

  • The paper relies on this without support.

    The metrics align with those commonly used in prior accessibility studies.

    “These metrics align with those commonly used in prior accessibility studies, supporting meaningful comparison with existing research.”

  • The paper relies on this without support.

    In various professional settings, inclusive access means that professionals who rely on assistive technologies can act on time-critical information as independently and confidently as their sighted peers.

    “In each setting, inclusive access means that professionals who rely on assistive technologies can act on time-critical information as independently and confidently as their sighted peers.”
19 of 19

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Latest temperature exceeds the stated recent range

    Minor

    The accessible summary gives a current temperature of 23.66 °C, but its recent-trends summary says temperature varied only up to 23.48 °C over the past 50 minutes. A current reading should fall within that recent period.

  • Interface is described as both single-page and separate server-rendered views

    Minor

    The architecture calls the front end a single-page interface, whereas the implementation says each view is a separate route returning its own Blade template.

  • Prototype descriptions are claimed to update automatically but were triggered manually

    Minor

    The comparison claims that AI descriptions are updated as data changes. The implementation section says generation in the prototype was manually triggered and automatic updating was only a possibility.

3 of 3

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Stelea, G. A., Sangeorzan, L., & Enache-David, N.
Affiliations
  • Transilvania University of Brașov (RO)
  • Department of Mathematics and Informatics, Transilvania University of Brașov, 500036 Brașov, Romania
Corresponding author
Stelea, George Alex
ORCID
Venue
Future Internet
Publisher
MDPI AG
Published
2025-06-21
Volume
17
Issue
7
Pages
274
ISSN
1999-5903 (ISSN-L)
DOI
10.3390/fi17070274
OpenAlex
W4411568410
Cited by
5
References
31
Citations by year
2026: 2 · 2025: 3
FWCI
30.44
Type
journal article
Language
en
Open access
Licence
Locations
  • Future Internet (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Transilvania University of Brașov
Topics
  • Social Sciences › Human Factors and Ergonomics › Digital Accessibility for Disabilities
  • Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
  • Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
Keywords
visual impairment, screen readers, WAI-ARIA, large language models, privacy by design, inclusive design, sensor data visualization, cognitive load

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-06.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-06.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review