FAHAD UL HASSAN 864-***-**** *** University Vill. Dr., Apt G, Central, SC 29630

adn98s@r.postjobfree.com LinkedIn

EDUCATION & PROFESSIONAL DEVELOPMENT

Ph.D. in Civil Engineering, GPA: 3.96 January 2019 - Present CLEMSON UNIVERSITY, CLEMSON, SC

Research Area: Implementation of NLP, Machine Learning and Deep Learning methods to automate Contractual and Administrative Documents Review

Dissertation Title: Digitalization of Construction Project Requirements Using NLP to support Automated Design and Construction Verification

Affiliations: American Society of Civil Engineers (ASCE) & Pakistan Engineering Council (PEC) Bachelor of Science in Civil Engineering, GPA: 3.753 September 2013 - May 2017 UNIVERSITY OF ENGINEERING & TECHNOLOGY, LAHORE, PUNJAB, PAKISTAN Programming with Python Workshops: Clemson University Geographical Information System (GIS) Workshops: Clemson University KEY SKILLS

Natural Language Processing – Machine Learning – Deep Learning– Automated Information Extraction Text Classification– Sentiment Analysis – Big Data Analytics – Data Visualization – Regression Analysis – Data Mining Presentation Skills – Communication Skills – Teamwork – Relationship Building – Problem Solving TECHNICAL SKILLS

Python – R Language – SQL – Microsoft Office 365 – Advance MS Excel (VBA, Macros & Pivot Tables) BIM 360 - Autodesk Revit – Navisworks – MS Project – QGIS PROFESSIONAL OVERVIEW

CLEMSON UNIVERSITY, CLEMSON, SC January 2019 to Present Clemson University is a leading public research institution located in Upstate South Carolina. Research Assistant

• Investigated the applicability of different natural language processing (NLP) techniques, machine learning and deep learning algorithms on textual data of construction domain to develop automated frameworks for construction contract comprehension, contract review, contract administration, and scheduling.

• Developed a prediction model using statistical methods to estimate the impact of lane closure restrictions on schedules of construction projects

• Developed a requirement identification system using NLP to enable automated contract review and contract administration

• Developed a requirement classification system using NLP, machine learning and deep learning to support subcontract drafting

• Developed an automated information extraction system using NLP to extract critical information for scheduling

• Developed of a requirement prioritization system using regression and deep learning methods to rank the contractual requirements for efficient construction inspection NOTEABLE PROJECTS

Design of a tool to estimate schedule impacts of traffic control restrictions: Implemented the regression methods

(univariate and multivariate regression), data analysis methods (correlation analysis, outlier analysis, residual plots generation, etc.) to develop a prediction model that can predict the production rates and duration of activities involved in a project. The final tool provided to the South Carolina Department of Transportation (SCDOT) was developed using the Visual Basics and Macros in MS Excel.

Requirements Identification Models: Implemented the rule-based methods, fundamental NLP approaches

(tokenization, lemmatization, POS tagging, etc.), feature weighting methods (TF, TF-IDF), feature generation methods

(Bag-of-ngrams, word embeddings, etc.), and machine learning methods (Naïve Bayes, SVM, Logistic Regression, Feedforward Neural Network, etc.) to develop an automated text identification tool that can identify the requirements and critical text from contracts with a recall of 95.0%. Requirements Classification Models: Implemented different NLP-based approaches, feature generation methods (Bag- of-ngrams, word embeddings), feature selection methods (Chi-square, mutual information, RFE), feature weighting methods (TF, TF-IDF), traditional machine learning methods (Naïve Bayes, SVM, Logistic Regression, Decision Tree, k- nearest neighbor, etc.), deep neural networks (CNN and RNN), and ensemble methods (Random Forest, Bagging and Boosting, etc.) to develop an optimal text classification tool to classify the contractual text into different categories for subcontract drafting, achieving a precision and recall of 93.20% and 93.08% respectively Construction Activities Information Extraction Model: Implemented different NLP methods (dependency parsing, POS tagging, etc.) to develop semantic and syntactic rules to extract activities information (such as actor, action, object, condition) from contractual requirements to support planning, scheduling and management of complex construction projects

Risk Decoding Model Design: Implemented different methods, word embedding methods (word2vec, Glove, etc.), along with domain specific ontologies to develop a risk decoding model that precisely decodes the environmental risks information from prescriptive requirements of bridge design codes Requirements Ranking System: Implementing the NLP methods, fuzzy ranking methods, regression and deep learning approaches to develop a requirement prioritization tool that can rank requirements according to different characteristics

(severity, probability and non-detectability) (In Progress) PUBLICATIONS

1. Hassan, F. U., & Le, T. (2021). “Computer-assisted separation of design-build contract requirements to support subcontract drafting.” Automation in Construction, 122, 103479. 2. Hassan, F. U., Le, T., & Lv, X. (2021). Addressing Legal and Contractual Matters in Construction Using Natural Language Processing: A Critical Review. Journal of Construction Engineering and Management, 147(9), 03121004.

3. Hassan, F. U., & Le, T. (2020). “Automated requirements identification from construction contract documents using natural language processing.” Journal of Legal Affairs and Dispute Resolution in Engineering and Construction, 12(2), 04520009.

4. Le, T., Hassan, F. U., Le, C., & Jeong, H. D. (2019). “Understanding dynamic data interaction between civil integrated management technologies: a review of use cases and enabling techniques.” International Journal of Construction Management, 1-22.

5. Hassan, F. U., Le, T., & Tran, D. H. (2020, November). “Multi-Class Categorization of Design-Build Contract Requirements Using Text Mining and Natural Language Processing Techniques.” In Construction Research Congress 2020: Project Management and Controls, Materials, and Contracts (pp. 1266-1274). Reston, VA: American Society of Civil Engineers. 6. Hassan, F. U., & Le, T. (2020). Ontology-Based Decoding of Risks Encoded in the Prescriptive Requirements in Bridge Design Codes. In ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction (Vol. 37, pp. 98-104). IAARC Publications. 7. Hassan, F. U., & Le, T. (2020). “NLP-based requirement tagging framework for activities information extraction to support scheduling.” To be submitted in ASCE Journal of Computing in Civil Engineering

(In final stage of submission).

8. Hassan, F. U., & Le, T. (2021). “Requirement extraction from the construction contracts using Natural language processing (NLP) Techniques to support scheduling.” In Construction Research Congress 2022

(Submitted to CRC 2022).

9. Hassan, F. U., & Le, T. (2021). “State-of-the-art review on the applicability of Natural Language Processing (NLP) methods to address legal issues in construction” In Construction Research Congress 2022 (Submitted to CRC 2022).

Contact this candidate