Crowd mobility prediction, in particular, forecasting flows at and transitions across different locations, is essential for crowd analytics and management in spacious environments featured with large gathering. We propose GAEFT, a novel crowd mobility analytics system based on the multi-task graph attention neural network to forecast crowd flows (inflows/outflows) and transitions. Specifically, we leverage the collective and sanitized campus Wi-Fi association data provided by our university information technology service and conduct a relatable case study. Our comprehensive data analysis reveals the important challenges of sparsity and skewness, as well as the complex spatio-temporal variations within the crowd mobility data. Therefore, we design a novel spatio-temporal clustering method to group Wi-Fi access points (APs) with similar transition features, and obtain more regular mobility features for model inputs. We then propose an attention-based graph embedding design to capture the correlations among the crowd flows and transitions, and jointly predict the AP-level flows as well as transitions across buildings and clusters through a multi-task formulation. Extensive experimental studies using more than 28 million association records collected during 2020-2021 academic year validate the excellent accuracy of GAEFT in forecasting dynamic and complex crowd mobility.
Driver maneuver identification (DMI), i.e., the task of predicting the driver maneuver classes given sensor measurements (such as IMU sensors from mobile devices), can serve as a key enabler for many ubiquitous driver behavior analysis applications. Despite the prior studies, two major technical challenges remain before an effective DMI system can be deployed: (i) latent complex maneuver behavior feature relations for accuracy enhancement, and (ii) inconsistency and uncertainty in model adaptation given dynamic data collection settings (e.g., given different urban environments, drivers, and mobile devices). To address the aforementioned challenges, we propose MetaDMI, a novel and adaptive driver maneuver identification framework based on multi-representation learning and meta model update, with the case study on the inertial measurement unit (IMU) sensor measurements (i.e., accelerometer and gyroscope). Specifically, we first extract multiple feature representations for each driver maneuver record in the forms of graph, spectral, and time sequence. Next, MetaDMI processes them with a novel multi-representation learning network, extracting complex patterns and feature relations from the driver maneuvers. Finally, to further enhance the adaptivity of our DMI model to external impacts with dynamic data collection, we have designed a regularized meta learning-based training method to regularize the knowledge transfers across the source and target datasets (e.g., across cities/devices, and few-shot initialization) for consistent and robust identification performance. We have conducted extensive experimental studies upon our MetaDMI prototype based on two datasets (one is collected on our own) and shown that our approach outperforms other baseline approaches for DMI in terms of accuracy and adaptivity.
Smart micromobility, particularly the electric (e)-scooters, has emerged as an important ubiquitous mobility option that has proliferated within and across many cities in North America and Europe. Due to the fast speed (say, ~15km/h) and ease of maneuvering, understanding how the micromobility rider interacts with the scooter becomes essential for the e-scooter manufacturers, e-scooter sharing operators, and rider communities in promoting riding safety and relevant policy or regulations. In this paper, we propose FCRIL, a novel Federated maneuver identification and Contrastive e-scooter Rider Interaction Learning system. FCRIL aims at: (i) understanding, learning, and identifying the e-scooter rider interaction behaviors during naturalistic riding (NR) experience (without constraints on the data collection settings); and (ii) providing a novel federated maneuver learning model training and contrastive identification design for our proposed rider interaction learning (RIL). Towards the prototype and case studies of FCRIL, we have harvested an NR behavior dataset based on the inertial measurement units (IMUs), e.g., accelerometer and gyroscope, from the ubiquitous smartphones/embedded IoT devices attached to the e-scooters. Based on the harvested IMU sensor data, we have conducted extensive data analytics to derive the relevant rider maneuver patterns, including time series, spectrogram, and other statistical features, for the RIL model designs. We have designed a contrastive RIL network which takes in these maneuver features with class-to-class differentiation for comprehensive RIL and enhanced identification accuracy. Furthermore, to enhance the dynamic model training efficiency and coping with the emerging micromobility rider data privacy concerns, we have designed a novel asynchronous federated maneuver learning module, which asynchronously takes in multiple sets of model gradients (e.g., based on the IMU data from the riders' smartphones) for dynamic RIL model training and communication overhead reduction. We have conducted extensive experimental studies with different smartphone models and stand-alone IMU sensors on the e-scooters. Our experimental results have demonstrated the accuracy and effectiveness of FCRIL in learning and recognizing the e-scooter rider maneuvers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.