21 skills found
mie-lab / Trackinteltrackintel is a framework for spatio-temporal analysis of movement trajectory and mobility data.
vonfeng / DeepMove[WWW 2018] DeepMove: Predicting Human Mobility with Attentional Recurrent Network
gcooq / TULIdentifying Human Mobility via Trajectory Embeddings(TUL)
FIBLAB / MoveSim[KDD 2020 (AI for COVID-19)] Learning to Simulate Human Mobility
SalilVishnuKapur / Predicting Transportation Modes Of GPS TrajectoriesUnderstanding transportation mode from GPS (Global Positioning System) traces is an essential topic in the data mobility domain. In this paper, a framework is proposed to predict transportation modes. This framework follows a sequence of five steps: (i) data preparation, where GPS points are grouped in trajectory samples; (ii) point features generation; (iii) trajectory features extraction; (iv) noise removal; (v) normalization. We show that the extraction of the new point features: bearing rate, the rate of rate of change of the bearing rate and the global and local trajectory features, like medians and percentiles enables many classifiers to achieve high accuracy (96.5%) and f1 (96.3%) scores. We also show that the noise removal task affects the performance of all the models tested. Finally, the empirical tests where we compare this work against state-of-art transportation mode prediction strategies show that our framework is competitive and outperforms most of them.
vonfeng / DPLink[WWW 2019] DPLink: User Identity Linkage via Deep Neural Network From Heterogeneous Mobility Data
jonpappalord / DITRASDITRAS (DIary-based TRAjectory Simulator), a mathematical model to simulate human mobility
ZPGuiGroupWhu / Human Mobility AnalysisA toolkit and models for individual and crowd level human mobility analysis based on trajectory data, including travel destination prediction, travel spatiotemporal and semantic features calculations (e.g., entropy, radius of gyration, motif ratio, travel rhythm, etc), driving characters and dispositions.
whd14 / De Anonymization Of Mobility TrajectoriesDe-anonymization algorithm of mobility trajectories
chuchen2017 / TrajGDMSimulating human mobility with a trajectory generation framework based on diffusion model
caochuntu / KDD2021 GuizuSource codes of KDD2021 paper "Generating Mobility Trajectories with Retained Data Utility"
matteoboh / Mobility EmissionsCollection of methods that compute emissions starting from mobility trajectories.
Yasoz / SynMobCreating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis
Star607 / Cross City Mobility TransformerThe official implementation of "COLA: Cross-city Mobility Transformer for Human Trajectory Simulation".
zihenglin / LSTM Mobility ModelLSTM Mobility Model implementation using Tensorflow
GeoDS / IntraCounty Mobility SEIRA human mobility flow-augmented stochastic SEIR-style epidemic modeling framework is developed, which combines with data assimilation and machine learning to reconstruct the historical growth trajectories of COVID-19 infection within a county.
chenrui2408 / Mobility Modes Awareness From TrajectoryCode for trajectory mining, including three parts: 1) trajectory preprocessing, 2) OD points clustering for route patterns discovery, and 3) CNN based method for mobility modes identification.
marsk7 / Gowalla Trajectory AnalysisA full-stack geospatial web application for analyzing user mobility patterns based on the Gowalla check-in dataset. Built with React, Leaflet, FastAPI, and PostGIS, it supports time-space filtering, nearest location queries, trajectory comparison, and friend similarity analysis.
1057499672 / Globalized Stochastic Meta Population SEIR ModelThe COVID-19 (COVID-19) epidemic has entered the era of globalization. As of September in 2020, 25.84 million people have been diagnosed globally. In order to help public health decision-makers improve their decision-making effectiveness, timeliness, and accuracy. Epidemic trajectory prediction and policy intervention simulation are useful tools, especially when vaccines are not yet available globally. SEIR model is a mainstream and developing dynamics model of infectious diseases, embodying the idea of differential, able to predict the future outbreak scenario based on initial data. This study further develops the traditional SEIR model by integrating human mobility and non-pharmaceutical interventions into the model. This model has four objectives: 1. Evaluate the effect of Wuhan shutdown policy (such as how much R0 has been reduced and how many cases have been avoided) 2. Assess the effectiveness of epidemic intervention policies in Wuhan, China, and western countries after the Wuhan shutdown 3. Evaluate the effects of non-drug interventions (such as inter-city travel restrictions, international travel ban, suspected-cases isolation and social-distance control) 4. Forecast the future trajectory of the epidemic in each region This model is significantly different from the traditional SEIR model in the following three aspects: 1. Allow people infected in the incubation period and those with symptoms to spread across regions (the scale of population migration is based on baidu migration platform and national transport database). In terms of regional scope, this paper covers 31 provinces in China and 13 western countries with severe epidemics. 2. Allow different levels of government policy intervention, including isolation, social distance control, and border closure. 3. Parameters such as basic infection number R0 are allowed to change with time. Therefore, the "global SEIR model", to some extent, avoids the staticity of the traditional SEIR model, simulating the real social environment better. This model can help public health event decision makers to make decisions, including the following three points: 1. In the early stage of the outbreak, it can assist decision makers to quickly make the most economic and effective policy intervention decisions, so as to control the development of the epidemic as soon as possible. 2. In the middle stage of epidemic development, decision-makers can be assisted to evaluate the effectiveness of initial intervention policies, so as to dynamically optimize and adjust policies based on feedback. 3. In the later stage of the epidemic, it can assist decision makers to assess the possibility of imported cases from abroad. Given the high variability of COVID-19 virus, the fact that vaccines are not yet globally available, and global medical resources are far away from adequate, it is necessary for policy makers in all countries to build a globalized SEIR model that integrated as many nations and regions as possible.
CATHI2018 / CATHIContext-aware Trajectory Embedding and Human Mobility Inference
