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.
more »
« less
Towards Dynamic Crowd Mobility Learning and Meta Model Updates for A Smart Connected Campus
In this paper, we propose MetaMobi, a novel spatio-temporal multi-dots connectivity-aware modeling and Meta model update approach for crowd Mobility learning. MetaMobi analyzes real-world Wi-Fi association data collected from our campus wireless infrastructure, with the goal towards enabling a smart connected campus. Specifically, MetaMobi aims at addressing the following two major challenges with existing crowd mobility sensing system designs: (a) how to handle the spatially, temporally, and contextually varying features in large-scale human crowd mobility distributions; and (b) how to adapt to the impacts of such crowd mobility patterns as well as the dynamic changes in crowd sensing infrastructures. To handle the first challenge, we design a novel multi-dots connectivity-aware learning approach, which jointly learns the crowd flow time series of multiple buildings with fusion of spatial graph connectivities and temporal attention mechanisms. Furthermore, to overcome the adaptivity issues due to changes in the crowd sensing infrastructures (e.g., installation of new ac- cess points), we further design a novel meta model update approach with Bernoulli dropout, which mitigates the over- fitting behaviors of the model given few-shot distributions of new crowd mobility datasets. Extensive experimental evaluations based on the real-world campus wireless dataset (including over 76 million Wi-Fi association and disassociation records) demonstrate the accuracy, effectiveness, and adaptivity of MetaMobi in forecasting the campus crowd flows, with 30% higher accuracy compared to the state-of-the-art approaches.
more »
« less
- Award ID(s):
- 2118102
- NSF-PAR ID:
- 10356957
- Date Published:
- Journal Name:
- International Conference on Embedded Wireless Systems and Networks EWSN
- ISSN:
- 2562-2331
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
One of the biggest challenges that Universities face today is the safety of its people on campus from crimes like mugging, battery and even shooting in or around the campus area. Using SJSU campus as an example, over 50 alert cases of burglaries, thefts, batteries, sexual assaults and other incidents have been reported in and around the SJSU campus over the last year. We have Bluelight emergency telephones placed all over the campus, in all buildings, elevators and on the campus grounds. These phones can be used to report emergency situations, suspicious activities, request escorts etc. However, there is a huge delay between the occurrence of incidents and the arrival of the policeman at the site. There is a critical need for a system that would allow the authorities to locate victims and respond faster to these incidents. To reduce the delay in reporting incidents and their occurrence time, we have developed a mobile application that will let users send alerts along with their real-time location to the UPD directly from their mobile phones. However, finding the position of a victim in a building is the most important challenge we are facing. Many existing systems do not work in indoor environment, and the state-of-the-art localization systems are either inconvenience to use or inaccurate enough to pin-point user's locations inside the building. In this paper, we propose a fine-grained location-aware smart campus security systems that leverages hybrid localization approaches with minimum deployment cost. Specifically, we effectively combines the Wi-Fi fingerprinting localization approach with the Bluetooth beacon based trilateration approach, and improves the location accuracy to the meter-level with low cost.more » « less
-
In this paper, we present ViTag to associate user identities across multimodal data, particularly those obtained from cameras and smartphones. ViTag associates a sequence of vision tracker generated bounding boxes with Inertial Measurement Unit (IMU) data and Wi-Fi Fine Time Measurements (FTM) from smartphones. We formulate the problem as association by sequence to sequence (seq2seq) translation. In this two-step process, our system first performs cross-modal translation using a multimodal LSTM encoder-decoder network (X-Translator) that translates one modality to another, e.g. reconstructing IMU and FTM readings purely from camera bounding boxes. Second, an association module finds identity matches between camera and phone domains, where the translated modality is then matched with the observed data from the same modality. In contrast to existing works, our proposed approach can associate identities in multi-person scenarios where all users may be performing the same activity. Extensive experiments in real-world indoor and outdoor environments demonstrate that online association on camera and phone data (IMU and FTM) achieves an average Identity Precision Accuracy (IDP) of 88.39% on a 1 to 3 seconds window, outperforming the state-of-the-art Vi-Fi (82.93%). Further study on modalities within the phone domain shows the FTM can improve association performance by 12.56% on average. Finally, results from our sensitivity experiments demonstrate the robustness of ViTag under different noise and environment variations.more » « less
-
Cognitive radio (CR) technology is envisioned to use wireless spectrum opportunistically when the primary user (PU) is not using it. In cognitive radio ad-hoc networks (CRAHNs), the mobile users form a distributed multi-hop network using the unused spectrum. The qualities of the channels are different in different locations. When a user moves from one place to another, it needs to switch the channel to maintain the quality-of-service (QoS) required by different applications. The QoS of a channel depends on the amount of usage. A user can select the channels that meet the QoS requirement during its movement. In this paper, we study the mobility patterns of users, predict their next locations and probabilities to move there based on its history. We extract the mobility patterns from each user’s location history and match the recent trajectory with the patterns to find future locations. We construct a spectrum database using Wi-Fi access point location data and the free space path loss formula. We propose a machine learning-based mechanism to predict spectrum status of some missing locations in the spectrum database. We formulate a problem to select the current channel in order to minimize the total number of channel switches during a certain number of next moves of a user. We conduct an extensive simulation combining real and synthetic datasets to support our model.more » « less
-
As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal predictive modeling for crowd movements is a challenging task particularly considering scenarios where societal events drive mobility behavior deviated from the normality. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes nor adaptive to unprecedented volatility brought by potential societal events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced event-aware spatio-temporal network, namely EAST-Net, is evaluated on several real-world datasets with a wide variety and coverage of societal events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/underdoc-wang/EAST-Net.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
