Artificial Intelligence for Smart Cities

There is a growing importance of ICT in profiling the competitiveness of cities. The next step for the smart city is the automated city – one that is predictive and responsive without human intervention. Such a city could avoid traffic congestion before it occurs and distribute resources, such as emergency services and maintenance, without time-consuming human decision-making. Urban mobility applications will also rely on collecting available information from sensor networks in and around the city and make the operation of public services (like parking, lighting, heating, garbage collection, etc.) intelligent. The smart city can make intelligent responses to different kinds of needs, including daily livelihood, environmental protection, public safety and city services, industrial and commercial activities. Among the different notable goals of smart cities, construction of intelligent transportation systems could have a significant impact to residents of future cities. Advanced Traffic Management Systems (ATMSs) and Intelligent Transportation Systems (ITSs) integrate information, communication and other technologies and apply them in the field of transportation to build an integrated system of people, roads and vehicles. These systems constitute a large, full-functioning, real-time, accurate and efficient transportation management framework.

Our research group focuses on investigation of data analytics and machine learning methods, appropriate for optimizing the transport and other public services in smart cities, using the gathered sensor network and crowdsensing information. We develop novel data gathering and filtering methods , together with data analysis and machine learning algorithms, which would help to predict future vehicle and crowd dynamics.

Research topics/competences
  • Machine learning and data analytics for intelligent and automated cities
  • Behavior prediction in smart cities based on historical data
  • Crowdsensing for mass event surveillance and urban transport optimization
  • Autonomous task allocation in flocking systems
  • Patrolling strategies for autonomous vehicles
Latest results
  • Developed machine learning solutions for warehouse optimization for the Autonomous warehouse and last mile delivery (AWARD) project, EIT Digital, 2018
  • Developed digital profiling for Nokia Bell Labs, 2017-2018
  • Developed a machine learning based solution for the intelligent parking system for T-Systems, 2017
  • Developed mobile crowdsensing methodology for smart cities, Ericsson High Speed Networks (HSN) CFT project, 2014-2015
  • Developed controlling algorithms for vehicle flocking in the FIRST project (Future Internet Research, Services and Technology)