Regulations Compliance And Governance
AI Bias Mitigation Safety Models
AI Bias Mitigation Safety Models refer to frameworks designed to identify and reduce biases in artificial intelligence systems, particularly in the Construction and Infrastructure sector. These models focus on ensuring that AI technologies are applied ethically and equitably, addressing concerns related to fairness and accountability. As stakeholders increasingly rely on AI for decision-making, the relevance of these safety models grows, aligning with the sector's push towards innovative practices that enhance operational efficiency and strategic alignment. By embedding bias mitigation into AI processes, organizations can foster trust and safeguard the well-being of all involved. The Construction and Infrastructure ecosystem is experiencing significant shifts due to the integration of AI Bias Mitigation Safety Models. As firms adopt AI-driven practices, they are not only reshaping competitive dynamics but also accelerating innovation cycles and enhancing stakeholder engagement. This transformation leads to improved efficiency and informed decision-making, ultimately steering long-term strategic direction. However, the journey is not without its challenges; organizations must navigate barriers to adoption, complexities in integration, and evolving expectations from a diverse range of stakeholders. Successfully addressing these factors will unlock new growth opportunities while ensuring that AI advancements contribute positively to the sector's future.
{"page_num":4,"introduction":{"title":"AI Bias Mitigation Safety Models","content":"AI Bias Mitigation Safety Models refer to frameworks designed to identify and reduce biases in artificial intelligence systems, particularly in the Construction and Infrastructure sector. These models focus on ensuring that AI technologies are applied ethically and equitably, addressing concerns related to fairness and accountability. As stakeholders increasingly rely on AI for decision-making, the relevance of these safety models grows, aligning with the sector's push towards innovative practices that enhance operational efficiency and strategic alignment <\/a>. By embedding bias mitigation into AI processes, organizations can foster trust and safeguard the well-being of all involved.\n\nThe Construction and Infrastructure ecosystem is experiencing significant shifts due to the integration of AI Bias Mitigation Safety <\/a> Models. As firms adopt AI-driven practices, they are not only reshaping competitive dynamics but also accelerating innovation cycles and enhancing stakeholder engagement. This transformation leads to improved efficiency and informed decision-making, ultimately steering long-term strategic direction. However, the journey is not without its challenges; organizations must navigate barriers to adoption <\/a>, complexities in integration, and evolving expectations from a diverse range of stakeholders. Successfully addressing these factors will unlock new growth opportunities while ensuring that AI advancements <\/a> contribute positively to the sector's future.","search_term":"AI bias mitigation construction"},"description":{"title":"How AI Bias Mitigation is Transforming Construction Safety Models?","content":"The integration of AI bias mitigation safety <\/a> models in the construction and infrastructure industry is reshaping safety protocols and enhancing project outcomes. Key growth drivers include the increasing need for compliance with safety regulations and the demand for more equitable risk assessments, fueled by advancements in AI technologies."},"action_to_take":{"title":"Action to Take --- Mitigating AI Bias for Safety in Construction","content":"Construction and Infrastructure companies should strategically invest in AI Bias Mitigation Safety <\/a> Models and forge partnerships with technology firms to enhance their operational safety protocols. Leveraging AI in this manner can lead to improved workforce safety, reduced liability risks, and a stronger competitive edge in the marketplace.","primary_action":"Download Compliance Checklist for Automotive AI","secondary_action":"Book a Governance Consultation"},"implementation_framework":[{"title":"Assess Data Quality","subtitle":"Evaluate data for bias and accuracy","descriptive_text":"Conduct thorough assessments of existing datasets to identify and rectify biases, ensuring accurate AI model training. This enhances decision-making and operational efficiency in construction through reliable data utilization.","source":"Industry Standards","type":"dynamic","url":"https:\/\/www.iso.org\/iso-9001-quality-management.html","reason":"This step is crucial for establishing a strong foundation for AI models, reducing bias and improving overall project outcomes."},{"title":"Implement Bias Detection","subtitle":"Use algorithms to identify biases","descriptive_text":"Deploy advanced algorithms designed to detect and analyze biases within AI models. This proactive measure mitigates risks associated with biased decision-making, ensuring equitable outcomes in infrastructure projects and enhancing stakeholder trust.","source":"Technology Partners","type":"dynamic","url":"https:\/\/www.ibm.com\/cloud\/learn\/ai-bias","reason":"Implementing bias detection is essential for maintaining fairness and compliance, fostering a more inclusive construction environment, and enhancing AI performance."},{"title":"Train AI Models","subtitle":"Enhance models with diverse datasets","descriptive_text":"Train AI models using diverse and representative datasets to minimize bias. This approach ensures robust decision-making and improves the reliability of AI applications in construction <\/a> and infrastructure projects, driving innovation and efficiency.","source":"Internal R&D","type":"dynamic","url":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/bias-in-ai-models\/","reason":"Training with diverse datasets is vital to achieving fairness and resilience in AI systems, ultimately leading to better project outcomes and stakeholder satisfaction."},{"title":"Conduct Regular Audits","subtitle":"Evaluate AI model performance periodically","descriptive_text":"Implement regular audits of AI <\/a> models to assess performance and bias levels. This ongoing evaluation helps to identify potential issues early, ensuring continuous improvement and adherence to safety standards in construction operations.","source":"Industry Standards","type":"dynamic","url":"https:\/\/www.nist.gov\/publications\/auditing-ai-systems","reason":"Regular audits are crucial for maintaining AI accountability, ensuring compliance with safety regulations, and enhancing overall effectiveness in project management."},{"title":"Engage Stakeholders","subtitle":"Collaborate with diverse project participants","descriptive_text":"Foster collaboration among diverse stakeholders to gather insights and address biases in AI systems. This engagement promotes transparency and ensures that AI solutions align with community needs, enhancing project acceptance and success.","source":"Community Outreach","type":"dynamic","url":"https:\/\/www.apa.org\/news\/press\/releases\/2021\/06\/stakeholder-engagement","reason":"Engaging stakeholders is vital for developing AI solutions that are socially responsible and reflective of community values, ultimately enhancing project outcomes."}],"primary_functions":{"question":"What's my primary function in the company?","functions":[{"title":"Engineering","content":"I design and implement AI Bias Mitigation Safety Models tailored for the Construction and Infrastructure sector. My responsibility includes selecting appropriate algorithms, ensuring system integration, and addressing real-world challenges. I drive innovation and enhance safety protocols, directly impacting project outcomes and efficiency."},{"title":"Quality Assurance","content":"I ensure that AI Bias Mitigation Safety Models deliver reliable results in the Construction and Infrastructure industry. I conduct rigorous testing, analyze AI outputs, and identify potential biases. My focus on quality helps us build trust with stakeholders and enhances the overall effectiveness of our safety measures."},{"title":"Operations","content":"I manage the operational deployment of AI Bias Mitigation Safety Models across construction sites. I streamline processes using AI insights, monitor system performance, and ensure that safety protocols are adhered to. My proactive approach leads to improved efficiency and minimizes risks in our projects."},{"title":"Data Analysis","content":"I analyze data generated by AI Bias Mitigation Safety Models to identify trends and biases affecting our construction processes. My role involves interpreting complex datasets and providing actionable insights that drive decision-making. I contribute to refining our models and enhancing overall project safety."},{"title":"Training and Development","content":"I develop and lead training programs on AI Bias Mitigation Safety Models for team members. I ensure that everyone understands how to utilize these models effectively and ethically. My efforts cultivate a culture of safety and innovation, directly impacting project success and employee engagement."}]},"best_practices":null,"case_studies":[{"company":"Shawmut Design and Construction","subtitle":"Implemented AI-driven safety systems using video analytics and sensor data to analyze site patterns and flag risk factors proactively.","benefits":"53% reduction in OSHA recordable incidents reported.","url":"https:\/\/smartdev.com\/ai-use-cases-in-construction\/","reason":"Demonstrates proactive AI safety monitoring that integrates multiple data sources, showcasing effective risk prediction strategies in construction sites.","search_term":"Shawmut AI construction safety systems","case_study_image":"https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/shawmut_design_and_construction_case_study.png"},{"company":"Suffolk Construction","subtitle":"Used ALICE AI platform to analyze schedules, adjust sequencing, and optimize milestones on life sciences project.","benefits":"Recovered 42 days through targeted acceleration strategies.","url":"https:\/\/blog.alicetechnologies.com\/case-studies","reason":"Highlights AI-driven schedule optimization that mitigates delays, exemplifying data-informed decision-making for project efficiency.","search_term":"Suffolk ALICE AI construction scheduling","case_study_image":"https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/suffolk_construction_case_study.png"},{"company":"Buildots partner general contractor","subtitle":"Deployed Buildots AI with 360-degree helmet cameras for real-time progress verification against BIM plans.","benefits":"Up to 25% faster project completion times achieved.","url":"https:\/\/smartdev.com\/ai-use-cases-in-construction\/","reason":"Illustrates AI for early discrepancy detection, promoting accurate progress tracking and resource optimization in large-scale builds.","search_term":"Buildots AI construction progress cameras","case_study_image":"https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/buildots_partner_general_contractor_case_study.png"},{"company":"Global Infrastructure Hub projects","subtitle":"Applied AI and sensors for health monitoring to detect safety gear compliance and control site access.","benefits":"Reduced workplace hazards through real-time alerts.","url":"https:\/\/www.gihub.org\/infrastructure-technology-use-cases\/case-studies\/ai-and-sensors-for-safe-construction\/","reason":"Shows AI-sensor integration for automated safety enforcement, emphasizing preventive measures for equitable site protection.","search_term":"GIHUB AI sensors construction safety","case_study_image":"https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/global_infrastructure_hub_projects_case_study.png"}],"call_to_action":{"title":"Elevate Safety with AI Solutions","call_to_action_text":"Transform your construction projects by mitigating bias in safety models. Stay ahead of the competition and ensure a safer environment for all stakeholders today.","call_to_action_button":"Take Test"},"challenges":null,"ai_initiatives":{"values":[{"question":"How does your team identify bias in construction AI models?","choices":["Not started","Developing methods","Regular assessments","Comprehensive audits"]},{"question":"What frameworks guide your AI bias mitigation strategies?","choices":["No frameworks yet","Basic guidelines","Industry standards","Proprietary frameworks"]},{"question":"How often do you retrain AI models to reduce bias?","choices":["Rarely or never","Occasionally","Scheduled updates","Continuous monitoring"]},{"question":"What role does stakeholder feedback play in your AI safety models?","choices":["No feedback collected","Informal feedback","Regular consultations","Structured feedback loops"]},{"question":"How integrated are bias mitigation practices in project planning?","choices":["Not integrated","Ad-hoc measures","Standard part of planning","Fully integrated processes"]}],"action_to_take_ai_initiatives":"Next"},"left_side_quote":[{"text":"Including diverse, high-quality datasets mitigates bias in construction AI.","company":"Trimble","url":"https:\/\/www.constructionbriefing.com\/news\/interview-the-bias-dilemma-in-construction-ai\/8050058.article","reason":"Trimble's approach emphasizes data diversity and human oversight to prevent project errors from biased models in built environment assets like bridges, enhancing safety and reliability in infrastructure."},{"text":"Embed explainability, fairness, and transparency into AI tools for safety.","company":"RICS","url":"https:\/\/www.rics.org\/news-insights\/artificial-intelligence-in-construction-report","reason":"RICS advocates fairness in AI for construction decisions on safety and resources, promoting ethical guardrails and oversight to mitigate bias risks in industry-wide adoption."},{"text":"AI-powered capabilities automate site safety to reduce risk and bias.","company":"HammerTech","url":"https:\/\/www.prnewswire.com\/news-releases\/construction-safety-leader-hammertech-debuts-first-wave-of-ai-powered-capabilities-to-automate-site-safety-admin--reduce-risk-302499368.html","reason":"HammerTech leverages vast safety datasets for AI models that minimize admin errors and risks on construction sites, supporting unbiased, real-time safety decisions."}],"quote_1":null,"quote_2":{"text":"We must embed explainability, fairness, and transparency into AI tools, particularly those influencing decisions on safety, cost, or resources, to ensure responsible AI adoption in construction.","author":"Jeremy Kelly, Research Director, RICS (Royal Institution of Chartered Surveyors)","url":"https:\/\/www.rics.org\/news-insights\/artificial-intelligence-in-construction-report","base_url":"https:\/\/www.rics.org","reason":"Highlights ethical AI design for safety-critical decisions, addressing bias mitigation directly in construction AI models to promote fairness and trust in infrastructure projects."},"quote_3":null,"quote_4":{"text":"AI for construction safety requires actionable guidance on development workflows, maturity assessment, and key considerations to implement unbiased models effectively across project phases.","author":"CII Research Team 422, Construction Industry Institute (CII)","url":"https:\/\/www.construction-institute.org\/the-state-of-ai-for-construction-safety","base_url":"https:\/\/www.construction-institute.org","reason":"Provides framework for evaluating AI safety tools' bias risks, bridging gaps in construction safety implementation for more accurate, fair hazard identification."},"quote_5":{"text":"Construction organizations must develop robust frameworks addressing algorithmic bias in AI risk management systems, balancing innovation with transparency and accountability.","author":"Editorial Team, Sterling Access (AI Project Management Experts)","url":"https:\/\/sterlingaccess.co.za\/ai-in-project-management-2025-guide-construction-industry\/","base_url":"https:\/\/sterlingaccess.co.za","reason":"Stresses ethical frameworks to counter AI bias in predictive risk models, vital for equitable safety outcomes and workforce trust in infrastructure AI adoption."},"quote_insight":{"description":"Some construction companies report incident reductions of up to 40-50% through AI-powered safety models","source":"Associated Builders and Contractors (ABC) Carolinas","percentage":45,"url":"https:\/\/abccarolinas.org\/ai-in-construction-site-safety\/","reason":"This highlights AI safety models' role in proactive hazard detection, mitigating biases in risk assessments for fairer, more accurate safety outcomes and reduced accidents in construction."},"faq":[{"question":"What is AI Bias Mitigation Safety Models and how do they work in construction?","answer":["AI Bias Mitigation Safety Models help identify and reduce bias in decision-making processes.","They analyze data patterns to ensure fairness and accuracy in project assessments.","These models improve safety by predicting risks associated with biased decisions.","Implementation leads to better compliance with industry regulations and standards.","Companies can enhance their reputation by adopting ethical AI practices in construction."]},{"question":"How do I start implementing AI Bias Mitigation Safety Models in my projects?","answer":["Begin by assessing your current data management and AI capabilities within your organization.","Identify specific areas where bias may affect safety and decision-making processes.","Engage stakeholders to ensure alignment on goals and expectations for AI integration.","Develop a phased implementation plan, starting with pilot projects for testing.","Provide training for your team to optimize use and understanding of AI tools."]},{"question":"What are the main benefits of using AI Bias Mitigation Safety Models?","answer":["Companies experience improved project outcomes through data-driven decision-making processes.","AI helps in identifying previously overlooked safety risks and biases in operations.","Implementing these models can lead to significant cost savings over time.","Organizations gain a competitive edge by enhancing project efficiency and quality.","Ethical AI practices can improve stakeholder trust and company reputation in the industry."]},{"question":"What challenges might arise when implementing AI Bias Mitigation Safety Models?","answer":["Data quality and availability can pose significant challenges to effective implementation.","Resistance to change from employees may hinder AI adoption and integration efforts.","Ensuring compliance with industry regulations requires careful planning and resources.","Organizations may face high initial costs for technology and training investments.","Developing a clear strategy to address these challenges is vital for success."]},{"question":"When is the right time to implement AI Bias Mitigation Safety Models?","answer":["The best time to implement is during the planning phase of new projects.","Early adoption allows for integration of AI tools into existing workflows seamlessly.","Organizations should consider their digital maturity and readiness for AI solutions.","Evaluating current safety practices can highlight immediate needs for AI intervention.","Continuous monitoring and adaptation ensure that AI remains relevant and effective."]},{"question":"What are some sector-specific applications of AI Bias Mitigation Safety Models?","answer":["In construction, AI can optimize workforce allocation and enhance safety protocols.","Infrastructure projects benefit from predictive analytics to mitigate risks in planning.","AI helps in monitoring compliance with safety standards in real-time.","These models can be used to assess contractor performance and bias in selection.","Emerging technologies in AI are transforming traditional practices in construction and infrastructure."]}],"ai_use_cases":null,"roi_use_cases_list":null,"leadership_objective_list":null,"keywords":{"tag":"AI Bias Mitigation Safety Models Construction","values":[{"term":"Bias Detection","description":"The process of identifying and measuring biases in AI algorithms used in construction safety models, ensuring fairness and accuracy in predictions.","subkeywords":null},{"term":"Data Diversity","description":"Utilizing diverse datasets in AI training to mitigate bias and enhance the reliability of safety models in construction projects.","subkeywords":[{"term":"Dataset Variation"},{"term":"Demographic Representation"},{"term":"Data Sources"},{"term":"Geographical Coverage"}]},{"term":"Algorithm Transparency","description":"Ensuring that AI algorithms used in construction are interpretable and understandable, promoting trust and accountability among stakeholders.","subkeywords":null},{"term":"Ethical AI Practices","description":"Implementing ethical guidelines in AI development for construction, aimed at minimizing bias and enhancing safety outcomes for all workers.","subkeywords":[{"term":"Fairness Guidelines"},{"term":"Stakeholder Engagement"},{"term":"Compliance Standards"},{"term":"Ethical Audits"}]},{"term":"Performance Metrics","description":"Metrics used to evaluate the effectiveness of bias mitigation strategies in AI safety models, crucial for ongoing improvement in construction.","subkeywords":null},{"term":"Risk Assessment Tools","description":"Tools that leverage AI to analyze potential safety risks in construction projects, focusing on bias reduction in risk outcomes.","subkeywords":[{"term":"Predictive Analytics"},{"term":"Scenario Analysis"},{"term":"Quantitative Risk"},{"term":"Qualitative Assessment"}]},{"term":"Continuous Learning","description":"The capability of AI models to adapt and improve over time by learning from new data and feedback in construction safety contexts.","subkeywords":null},{"term":"Stakeholder Training","description":"Training programs for construction personnel aimed at understanding AI biases and effectively utilizing safety models for risk management.","subkeywords":[{"term":"Workshops"},{"term":"Simulation Exercises"},{"term":"Certification Programs"},{"term":"Awareness Campaigns"}]},{"term":"Feedback Loops","description":"Mechanisms for collecting user feedback on AI safety model performance, essential for continuous bias mitigation in construction.","subkeywords":null},{"term":"Digital Twins","description":"Virtual replicas of construction projects powered by AI that help in real-time monitoring and bias analysis for safety improvements.","subkeywords":[{"term":"Simulation Models"},{"term":"Data Integration"},{"term":"Real-time Analytics"},{"term":"Predictive Maintenance"}]},{"term":"Regulatory Compliance","description":"Adhering to legal standards and regulations regarding AI usage in construction, ensuring that bias mitigation practices are followed.","subkeywords":null},{"term":"Technology Integration","description":"The process of incorporating AI technologies into existing construction workflows to enhance safety and reduce bias in decision-making.","subkeywords":[{"term":"System Compatibility"},{"term":"Tool Selection"},{"term":"Process Optimization"},{"term":"User Interfaces"}]},{"term":"Outcome Evaluation","description":"The assessment of safety outcomes resulting from AI bias mitigation efforts, critical for measuring success in construction projects.","subkeywords":null},{"term":"Emerging Trends","description":"Innovative practices and technologies in construction focusing on AI advancements and bias mitigation, shaping the future of safety models.","subkeywords":[{"term":"Smart Automation"},{"term":"Machine Learning"},{"term":"Augmented Reality"},{"term":"Predictive Modeling"}]}]},"call_to_action_3":{"description":"Work with Atomic Loops to architect your AI implementation roadmap from PoC to enterprise scale.","action_button":"Contact Now"},"description_memo":null,"description_frameworks":null,"description_essay":null,"pyramid_values":{"title":"AI Governance Pyramid","values":[{"title":"Technical Compliance","subtitle":"Focus on fairness, privacy, and standards."},{"title":"Manage Operational Risks","subtitle":"Integrate risk assessments into workflows."},{"title":"Direct Strategic Oversight","subtitle":"Set accountability and corporate policies."}]},"risk_analysis":{"title":"Risk Senarios & Mitigation","values":[{"title":"Ignoring Bias in AI Models","subtitle":"Discrimination risks arise; conduct regular bias audits."},{"title":"Compromising Data Security Standards","subtitle":"Data breaches threaten trust; enforce encryption protocols."},{"title":"Non-Compliance with Regulatory Standards","subtitle":"Legal penalties may occur; maintain updated compliance checks."},{"title":"Underestimating Operational Failures","subtitle":"Project delays result; establish robust testing protocols."}]},"checklist":["Establish an AI ethics committee for oversight and governance.","Conduct regular audits on AI models for bias detection.","Define clear guidelines for AI data sourcing and usage.","Implement transparency reports on AI decision-making processes.","Train staff on ethical AI practices and bias mitigation techniques."],"readiness_framework":null,"domain_data":null,"table_values":null,"graph_data_values":null,"key_innovations":null,"ai_roi_calculator":null,"roi_graph":null,"downtime_graph":null,"qa_yield_graph":null,"ai_adoption_graph":null,"maturity_graph":null,"global_graph":"https:\/\/d1kmzxl7118mv8.cloudfront.net\/graphs\/global_map_ai_bias_mitigation_safety_models_construction_and_infrastructure\/ai_bias_mitigation_safety_models_construction_and_infrastructure.png","yt_video":null,"webpage_images":null,"ai_assessment":null,"metadata":{"market_title":"AI Bias Mitigation Safety Models","industry":"Construction and Infrastructure","tag_name":"Regulations, Compliance & Governance","meta_description":"Explore AI Bias Mitigation Safety Models to enhance safety and compliance in construction. Safeguard projects while meeting regulatory standards today!","meta_keywords":"AI Bias Mitigation, Construction safety models, Compliance in construction, AI regulations, Infrastructure governance, Safety compliance AI, Risk management AI"},"case_study_images":["https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/shawmut_design_and_construction_case_study.png","https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/suffolk_construction_case_study.png","https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/buildots_partner_general_contractor_case_study.png","https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/case_studies\/global_infrastructure_hub_projects_case_study.png"],"introduction_images":["https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/ai_bias_mitigation_safety_models_generated_image.png","https:\/\/d1kmzxl7118mv8.cloudfront.net\/images\/ai_bias_mitigation_safety_models\/ai_bias_mitigation_safety_models_generated_image_1.png"],"s3_urls":["https:\/\/atomicloops-website.s3.amazonaws.com\/graphs\/global_map_ai_bias_mitigation_safety_models_construction_and_infrastructure\/ai_bias_mitigation_safety_models_construction_and_infrastructure.png","https:\/\/atomicloops-website.s3.amazonaws.com\/images\/ai_bias_mitigation_safety_models\/ai_bias_mitigation_safety_models_generated_image.png","https:\/\/atomicloops-website.s3.amazonaws.com\/images\/ai_bias_mitigation_safety_models\/ai_bias_mitigation_safety_models_generated_image_1.png","https:\/\/atomicloops-website.s3.amazonaws.com\/images\/ai_bias_mitigation_safety_models\/case_studies\/buildots_partner_general_contractor_case_study.png","https:\/\/atomicloops-website.s3.amazonaws.com\/images\/ai_bias_mitigation_safety_models\/case_studies\/global_infrastructure_hub_projects_case_study.png","https:\/\/atomicloops-website.s3.amazonaws.com\/images\/ai_bias_mitigation_safety_models\/case_studies\/shawmut_design_and_construction_case_study.png","https:\/\/atomicloops-website.s3.amazonaws.com\/images\/ai_bias_mitigation_safety_models\/case_studies\/suffolk_construction_case_study.png"]}