Skip to content

References

This research draws on academic literature, industry reports, technical standards, and open-source frameworks. References are organized by topic area for easy navigation.

AI Research Methodology

  1. Bommasani, R., et al. "On the Opportunities and Risks of Foundation Models." Stanford HAI (2021). arXiv:2108.07258 — Foundational survey of large language models and their capabilities across domains.

  2. Brown, T., et al. "Language Models are Few-Shot Learners." OpenAI (2020). arXiv:2005.14165 — GPT-3 paper demonstrating in-context learning and task adaptation without fine-tuning.

  3. Wei, J., et al. "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models." Google Research (2022). arXiv:2201.11903 — Foundational work on improving LLM reasoning through structured prompting.

  4. Lewis, P., et al. "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks." Meta AI (2020). arXiv:2005.11401 — RAG architecture for grounding LLM outputs in external knowledge bases.

  5. Anthropic Research Team "Claude 3 Model Card." Anthropic (2024). anthropic.com/claude — Technical specifications and safety characteristics of Claude models.

Agent Architecture & Orchestration

  1. Park, J.S., et al. "Generative Agents: Interactive Simulacra of Human Behavior." Stanford University (2023). arXiv:2304.03442 — Framework for autonomous agents with memory, planning, and social interaction.

  2. Wang, L., et al. "A Survey on Large Language Model-Based Autonomous Agents." Renmin University (2023). arXiv:2308.11432 — Comprehensive review of LLM-based agent architectures and coordination strategies.

  3. Wu, Q., et al. "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation." Microsoft Research (2023). arXiv:2308.08155 — Framework for building conversational multi-agent systems.

  4. LangChain Documentation "LangChain Agent Framework." LangChain (2024). langchain.com/docs — Production framework for LLM orchestration and tool integration.

  5. CrewAI Documentation "CrewAI Multi-Agent Framework." CrewAI (2024). crewai.com — Role-based multi-agent orchestration for complex workflows.

Construction Safety & Computer Vision

  1. OSHA "Commonly Used Statistics." U.S. Department of Labor (2024). osha.gov/data — Construction industry safety statistics and regulatory requirements.

  2. Fang, Q., et al. "Computer Vision Applications in Construction Safety Assurance." Automation in Construction (2020). DOI: 10.1016/j.autcon.2020.103351 — Review of CV techniques for PPE detection and hazard recognition.

  3. Shen, X., et al. "Deep Learning-Based Detection for Safety Helmet Wearing on Construction Sites." Sensors (2021). DOI: 10.3390/s21113061 — YOLO-based model for real-time helmet detection.

  4. Kim, H., et al. "Vision-Based Monitoring of Construction Worker Actions Using Pose Estimation." Journal of Computing in Civil Engineering (2020). DOI: 10.1061/(ASCE)CP.1943-5487.0000911 — Ergonomic risk assessment using pose detection.

  5. NVIDIA Jetson Documentation "Edge AI Computing Platform." NVIDIA (2024). nvidia.com/jetson — Edge deployment specifications for real-time CV inference.

Data Center Construction

  1. Uptime Institute "Global Data Center Survey 2024." Uptime Institute (2024). uptimeinstitute.com — Industry trends, outage causes, and construction challenges in hyperscale facilities.

  2. Turner & Townsend "Data Center Cost Index 2024." Turner & Townsend (2024). turnerandtownsend.com — Construction cost benchmarks and regional variations for data centers.

  3. ASHRAE TC 9.9 "Thermal Guidelines for Data Processing Environments (5th Edition)." ASHRAE (2021). ISBN: 978-1-947192-47-5 — Temperature and humidity specifications for data center design.

  4. 7x24 Exchange "Data Center Design and Operations Best Practices." 7x24 Exchange (2024). 7x24exchange.org — Industry standards for mission-critical facility construction and operations.

  5. Mortenson Construction "Data Center Expertise." Mortenson (2024). mortenson.com/markets/data-centers — Case studies and technical capabilities in hyperscale data center construction.

Knowledge Graphs & BIM Integration

  1. buildingSMART International "Industry Foundation Classes (IFC) Schema." buildingSMART (2024). buildingsmart.org/standards/bsi-standards/industry-foundation-classes — Open data standard for BIM interoperability.

  2. NIBS "COBie (Construction Operations Building Information Exchange) Standard." National Institute of Building Sciences (2024). nibs.org/cobie — Structured format for facility handover data.

  3. Neo4j "Graph Data Science for Construction and Engineering." Neo4j (2024). neo4j.com — Graph database applications in BIM and asset management.

  4. Zheng, Y., et al. "Knowledge Graph for Construction Project Management." Advanced Engineering Informatics (2021). DOI: 10.1016/j.aei.2021.101311 — Ontology design for construction domain knowledge representation.

  5. El-Diraby, T., et al. "Domain Ontology for Construction Concepts in Urban Infrastructure Products." Journal of Construction Engineering and Management (2005). DOI: 10.1061/(ASCE)0733-9364(2005)131:5(556) — Foundational work on construction ontologies and semantic interoperability.

Generative AI & RAG Architectures

  1. Gao, Y., et al. "Retrieval-Augmented Generation for Large Language Models: A Survey." arXiv (2023). arXiv:2312.10997 — Comprehensive review of RAG techniques and architectures.

  2. OpenAI "GPT-4 Technical Report." OpenAI (2023). arXiv:2303.08774 — Multimodal capabilities and performance benchmarks for GPT-4.

  3. Anthropic "Constitutional AI: Harmlessness from AI Feedback." Anthropic (2022). arXiv:2212.08073 — Training methodology for aligning AI systems with human values and safety constraints.

  4. Pinecone "Vector Database for Production AI." Pinecone (2024). pinecone.io — Vector database architecture for semantic search in RAG systems.

  5. LlamaIndex Documentation "Building RAG Applications." LlamaIndex (2024). llamaindex.ai — Framework for connecting LLMs to external data sources and knowledge bases.

Construction Technology & Productivity

  1. McKinsey Global Institute "Reinventing Construction: A Route to Higher Productivity." McKinsey & Company (2017). mckinsey.com — Analysis of productivity challenges and digital transformation opportunities in construction.

  2. Procore Technologies "Construction Technology Report 2024." Procore (2024). procore.com/research — Adoption trends and ROI data for construction software platforms.

  3. Autodesk "The Future of Making Things: State of Design & Make 2024." Autodesk (2024). autodesk.com/state-of-design-and-make — Digital workflows, BIM adoption, and AI integration in AEC industries.

  4. KPMG "Global Construction Survey 2024." KPMG (2024). kpmg.com/construction — Construction industry trends, risk factors, and technology investment priorities.

  5. AGC (Associated General Contractors) "Construction Technology Trends Survey." AGC of America (2024). agc.org — Contractor perspectives on technology adoption, workforce challenges, and productivity tools.

Additional Technical Resources

  1. Hugging Face "Transformers Library Documentation." Hugging Face (2024). huggingface.co/docs/transformers — Open-source framework for deploying pre-trained language and vision models.

  2. Ultralytics "YOLOv8 Documentation." Ultralytics (2024). ultralytics.com/yolov8 — State-of-the-art object detection models for real-time computer vision.

  3. ONNX Runtime "Cross-Platform AI Inference." Microsoft (2024). onnxruntime.ai — Optimized runtime for deploying AI models on edge devices and production systems.

  4. Wikipedia "Knowledge Graph." Wikipedia (2024). wikipedia.org/wiki/Knowledge_graph — Overview of knowledge graph concepts, history, and applications.

  5. Wikipedia "Construction Management." Wikipedia (2024). wikipedia.org/wiki/Construction_management — Foundational concepts in construction project delivery and management.

These references provide the technical foundation and domain context for the research presented in this portfolio. For specific citations within individual chapters, see the reference sections at the end of each chapter.