AI & DATA

Efficient urban governance requires estimating the count of people on the move. This helps maintain real-time safety and deploy any interventions if necessary. For example, depending upon the information regarding the number of pedestrians in a busy market street, the authorities may prohibit vehicular traffic. Furthermore, people count also helps plan future resources towards civic amenities. Presently camera is the widely accepted and deployed solution to perform people counting. However, the wide deployment of cameras in public places is disapproved by people and discouraged by law. Cameras are privacy-invasive and considered susceptible to security incidents. We explore an alternative privacy-aware people counting mechanism through the use of millimeter wave radar as our sensor. Millimeter wave radar senses people as a cluster of points known as point clouds, thus minimizing the data collected by it. This reduces the risk of leakage of personal data during a security breach. Most of the current literature related to mmWave focuses on indoor applications such as gesture recognition and gait detection. These studies have typically been done in a constrained space and under controlled conditions. The indoor studies provide high accuracy but the approaches can not be directly mapped for counting people in an outdoor scenario. Two key challenges that impact the performance of radar-based counting when deployed in an outdoor environment are noise rejection and counting the number of people within a single cluster. Through this work, we attempt to address the aforementioned key challenges by implementing a neural network model to estimate the people count in a point cloud. We deploy a mmWave radar across a street together with a camera to evaluate the efficacy of our proposed solution. The camera images are used as ground truth to train and test the network model. Our initial results indicate that the radar can detect presence with an accuracy greater than 90% and can provide the exact count with an accuracy greater than 80%. Our evaluation shows that mmWave is a promising technology for counting people with inherent privacy awareness.

DEFINITION I Agent-based modeling (ABM) is a simulation method. It models individual agents and their interactions to analyze and predict complex systems, offering insights for informed decision-making. Therefore it can be employed in the disciplines of urban planning and data science to understand complicated phenomena in urban environments. PURPOSE I This special session is designed as a learning track in order to introduce the participants to ABM and the potential use cases. Some cases are useful for user oriented urban management which aims to fill the gap between urban environment specialists and behavioral researchers. Some others are used to predict future scenarios and inform and advise policymakers. SPECIFIC KNOWLEDGE I The agents in an ABM are usually programmed to follow simple rules, but when they interact with each other, they can create complex and unpredictable behavior. This is why ABMs are often used to study complex systems because they can help researchers understand how small actions by individuals can have large-scale effects on the system as a whole. Another application is conducting tests with various scenarios to evaluate how the system responds. TECHNIQUES AND PRACTICES I In an ABM, the system being studied is broken down into individual units called agents. Each agent has its own set of rules and behaviors that determine how it interacts with other agents and the environment. In a simulation of a city, agents might represent for example individual people, households, or cars. The session will question how the design of an agent happens and try to come up with new approaches. OBJECTIVES & LEARNING OUTCOMES I The main objectives of this learning track are to introduce a powerful social simulation technique, agent-based modeling, and to demonstrate its use and applicability in research and policy-making. In addition, it should raise the conversation about existing research methodologies introducing ABMs and create the space for participants to brainstorm together on different use cases in their own fields. TEACHING STRATEGIES The workshop would consist of 1. The introductory lecture on the ABM principles by Erkinai Derkenbaeva 2. Presentations of projects that use ABMs in urban contexts including the models by Petar Koljensic, Weronika Sojka, Erkinai Derkenbaeva, and Tanya Tsui. 3. An interactive Q&A session session for additional explanations and discussions. Participants will be able to try to propose ideas for their urban challenges based on the ABM approach.TARGET AUDIENCE I The session aims to address students and professionals willing to understand the basic principles of ABMs and introduce them to their work. There is no limitation regarding the field of research. This workshop can also be addressed to the local authorities and policymakers in order to showcase the possibilities of complex systems simulations.