Course Overview
The course focuses on the application of artificial intelligence (AI) and information and communication technologies (ICT) to smart roads and smart cities.
Students will be involved in discussions, class projects, and lessons dealing with:
1) the main characteristics of smart roads and smart cities;
2) the current state-of-the-art;
3) the primary needs of transportation infrastructures and systems;
3) how AI-oriented smart roads and smart cities could be supported by advancements in computing power, big data, development of more sophisticated algorithms, open source frameworks, increased research and investments, cloud computing, interdisciplinary collaboration, improved sensors and IoT devices, global connectivity, and industry adoption of AI.
Learning Outcomes
The course goals and outcomes are to: A. Stimulate an interest in AI-oriented smart roads and smart cities as the basis for citizen health in current or/and critical conditions (e.g., virus pandemic, particulate matter pollution, and digital/technological contexts). B. Stimulate a corresponding interest in smart cities and smart roads per se, in terms of construction issues, environmental impact of transportation infrastructures, and new vehicles, within the context of transportation/pavement performance more broadly. C. Develop an understanding of how sensor-based monitoring, energy harvesting, AI applications, material properties and design (e.g., aggregate source and consensus properties, gradation analysis, bitumen percentage and quality), construction (e.g., HMA production, hauling, and placement operations) impact functional properties and people health. D. Expose students to some of the diverse innovative thoughts in pavement functional properties, energy harvesting, sensor-based monitoring, electric cars, and driverless vehicles. E. Encourage the interrogation of experimental data and models through the assignment of often conflicting narratives (e.g., balancing monitoring costs and monitoring positive effects). F. Advance student oral, written, and critical thinking skills and expertise by engaging in informed and up-to-date discussions of course reading materials.
Course Content
This is a multi-level and interdisciplinary course aiming at providing students with diverse backgrounds with both simple and complex concepts and abilities:
• Different areas of Engineering, Architecture, Physics, and Urbanism are involved.
• Concepts and applications start from very simple and “horizontal” examples but provide more expert students with advanced tools and concepts.
With respect to the courses previously presented, this year's course will build on the discussion of new frontiers and new projects emerging, namely in the field of Artificial Intelligence and PM-pollution-people health relationships. Smart cities, pavement-tire interaction, electric vehicles, smart roads, and other emerging pollution-related issues will be part of the course too.
Preliminary concepts will be as follows.
UNIT I (Basics). Transportation infrastructures (from design to management, using diverse tools, e.g., including BIM). Roads. Cities. ICT. AI basics. Intelligent mobility, intelligent transportation systems, smart roads, smart cities. Relationships among smart city, smart road, and sustainable mobility.
UNIT II (Transportation and primary needs). Sustainability. Acoustic impact. Air quality impact. Particulate matter, biological entities, RNA, DNA, viruses, and bacteria, recent literature about covid-19 pandemic, pollution, and other relevant factors. Meteorological effects. Tests to assess transportation-related effects (pavement and mobility).
UNIT III (Methodologies) Analysis and decision-making techniques and tools (Cost–benefit analysis, multi-criteria analysis/ ELimination Et Choix Traduisant la REalité, analytic hierarchy process technique, fuzzy techniques, etc.). Environmental impacts (noise, pollution). Environmental impact assessment (European approach, EIA versus strategic environmental assessment; scoping, Life cycle cost analysis, etc.).
UNIT IV (AI-ICT Applications). Sensors, ICT, vehicles, infrastructures, and functions. AI applications to design, construction, monitoring, maintenance, and safety. AI-oriented smart roads/cities. Intelligent traffic management systems. Predictive maintenance based on AI analytics. Responsive infrastructure that adapts to changing conditions.
Continuous monitoring of transportation infrastructures (sensors, type, data gathered, pros and cons). Energy harvesting from transportation infrastructures (types, pros and cons, potential). Electric vehicles and autonomous vehicles impact. Information and Communications Technologies applied to infrastructure assets.
Instructional Method
The following chain of instructional methods is scheduled:
• Brainstorming;
• Direct Teaching;
• Lectures with discussion;
• Case Studies;
• Group projects;
• Multimedia;
• Worksheets and Surveys;
• (Guest Speakers)
• Summative and formative feedback.
Required Course Materials
The majority of concepts and methods are discussed and clarified during the lessons with very limited homework tasks.
Very limited required readings are suggested during the course. No specific software is required.
The following readings only provide an idea of the “big picture” “behind” the course lessons.
UNIT I.
• Xu Yang, Jinchao Guan, Ling Ding, Zhanping You, Vincent C.S. Lee, Mohd Rosli Mohd Hasan, Xiaoyun Cheng, Research and applications of artificial neural network in pavement engineering: A state-of-the-art review, Journal of Traffic and Transportation Engineering (English Edition), Volume 8, Issue 6, 2021.
• New frontiers and new projects emerged.
• Directive 2010/40/EU of the European Parliament and of the Council of 7 July 2010 on the framework for the deployment of Intelligent Transport Systems in the field of road transport and for interfaces with other modes of transport.
• Yang H. Huang, "Pavement Analysis and Design (2nd Edition)". Prentice Hall | 2003 | ISBN: 0131424734 | 792 pages.
UNIT II.
• Pratico, F.G., Briante, P.G., Speranza, G., Acoustic Impact of Electric Vehicles (2020) 20th IEEE Mediterranean Electrotechnical Conference, MELECON 2020 - Proceedings, art. no. 9140669, pp. 7-12 DOI: 10.1109/MELECON48756.2020.9140669
• Praticò F.G. Briante P.G., Particulate Matter from Non-exhaust Sources, August 2020, DOI: 10.3846/enviro.2020.622, Conference: 11th International Conference “Environmental Engineering” (ENVIRO), At: Vilnius, Lithuania, 21-22 August 2020
• Cacciapaglia, G., Cot, C. & Sannino, F. Second wave COVID-19 pandemics in Europe: a temporal playbook. Sci Rep 10, 15514 (2020). https://doi.org/10.1038/s41598-020-72611-5
• Leonardo Setti, Fabrizio Passarini, Gianluigi De Gennaro, Pierluigi Baribieri, Maria Grazia Perrone, Massimo Borelli, Jolanda Palmisani, Alessia Di Gilio, Valentina Torboli, Alberto Pallavicini, Maurizio Ruscio, PRISCO PISCITELLI, Alessandro Miani, SARS-Cov-2 RNA Found on Particulate Matter of Bergamo in Northern Italy: First Preliminary Evidence, medRxiv 2020.04.15.20065995; doi: https://doi.org/10.1101/2020.04.15.20065995, Now published in Environmental Research doi: 10.1016/j.envres.2020.109754
• Mishra R, Krishnamoorthy P, Gangamma S, Raut AA, Kumar H. Particulate matter (PM10) enhances RNA virus infection through modulation of innate immune responses. Environ Pollut. 2020;266(Pt 1):115148. doi:10.1016/j.envpol.2020.115148.
• Richa Mishra, K Pandikannan, S Gangamma, Ashwin Ashok Raut, Himanshu Kumar, Imperative role of particulate matter in innate immunity during RNA virus infection, bioRxiv 2020.03.28.013169; doi: https://doi.org/10.1101/2020.03.28.013169 Now published in Environmental Pollution doi: 10.1016/j.envpol.2020.115148
• Wu, X., Nethery, R. C., Sabath, M. B., Braun, D. and Dominici, F., 2020. Air pollution and COVID-19 mortality in the United States: Strengths and limitations of an ecological regression analysis. Science advances, 6(45), p.eabd4049.
• Maria A. Zoran, Roxana S. Savastru, Dan M. Savastru, Marina N. Tautan, Assessing the relationship between surface levels of PM2.5 and PM10 particulate matter impact on COVID-19 in Milan, Italy, Science of The Total Environment, Volume 738, 2020, 139825, ISSN 0048-9697.
• Ye Yao, Jinhua Pan, Weidong Wang, Zhixi Liu, Haidong Kan, Yang Qiu, Xia Meng, Weibing Wang, Association of particulate matter pollution and case fatality rate of COVID-19 in 49 Chinese cities, Science of The Total Environment, Volume 741, 2020, 140396, ISSN 0048-9697.
UNIT III.
• Praticò, F. et al, 2017, Sustainability Issues in Civil Engineering, Springer Transactions in Civil and Environmental Engineering, © 2017, Editors: Sivakumar Babu, G.L., Saride, Sireesh, B, Munwar Basha.
• Directive 2011/92/EU (known as 'Environmental Impact Assessment' – EIA Directive).
• Treloar, G., Love, P., and Crawford, R. (2004). ”Hybrid Life-Cycle Inventory for Road Construction and Use.” J. Constr. Eng. Manage., 130(1), 43–49.
UNIT IV.
• Sang-Kwon Lee, Jinhwan Yoo, Chang-Hun Lee, Kanghyun An, Young-Sam Yoon, Jaehun Lee, Gi-Ho Yeom, Seoung-Uk Hwang, Road type classification using deep learning for Tire-Pavement interaction noise data in autonomous driving vehicle, Applied Acoustics, Volume 212, 2023.
• Praticò, F.G., Swanlund, M., George, L-A., Anfosso, F., Tremblay, G., Tellez, R., KAMIYA, K., Del Cerro, J., Van der Zwan, J., Dimitri, G.(2013). Quiet pavement technologies, Pages : 105, PIARC Ref. : 2013R10EN, ISBN : 978-2-84060-327-6.
• Lajnef et al. (2013), Report No. FHWA-HRT-12-072, Smart Pavement Monitoring System, May 2013.
Yun et al., (2014) Smart wireless sensing and assessment for civil infrastructure, Structure and Infrastructure Engineering: Maintenance, Management, Life-Cycle Design and Performance, 10:4, 534-550.
• Ceylan et al., (2013), Highway Infrastructure Health Monitoring Using Microelectromechanical Sensors And Systems (Mems), Journal Of Civil Engineering And Management, Volume 19 (Supplement 1): S188–S201.
• Praticò F.G., SUSPAV Project (National project): Interim Report, Internal Document, University Mediterranea.
• Fedele, R., Praticò, F.G., Carotenuto, R., Della Corte, Damage detection into road pavement through acoustic signature analysis: first results, the 24th International Congress on Sound and Vibration (ICSV24), London, 23 – 27 July 2017.
• Bevacqua, M.T., Isernia, T., Praticò, F.G., Zumbo, S., A method for bottom-up cracks healing via selective and deep microwave heating, (2021) Automation in Construction, 121, art. no. 103426.
Assessment
During the course: daily summative and formative feedback, following group projects and lectures.
Towards the end of the course: 1) Explicit information about grading procedures, based on UDC directives, is provided. 2) Explicit information about overall expectations and specific assignments is provided. 3) A report is usually required (3.1: General part, summary of the course. 3.2: Short essay on a specific topic, selected by professor and student). 4) A number of topics is previously selected (areas of main interest). 5) The examination is going to address: topics among the ones selected and discussion of the report.
Explicit information about assignments and grading procedures will clarify expectations and allay student anxiety while supporting students in pacing their studies, gauging their progress, and achieving learning outcomes.