Handbook of Mobility Data Mining, Volume 1: Data Preprocessing and Visualization

✍ Scribed by Haoran Zhang

• Publisher: Elsevier
• Year: 2023
• Tongue: English
• Leaves: 224
• Category: Library

✦ Synopsis

Handbook of Mobility Data Mining, Volume One: Data Preprocessing and Visualization introduces the fundamental technologies of mobile big data mining (MDM), advanced AI methods, and upper-level applications, helping readers comprehensively understand MDM with a bottom-up approach. The book explains how to preprocess mobile big data, visualize urban mobility, simulate and predict human travel behavior, and assess urban mobility characteristics and their matching performance as conditions and constraints in transport, emergency management, and sustainability development systems. The book contains crucial information for researchers, engineers, operators, administrators, and policymakers seeking greater understanding of current technologies' infra-knowledge structure and limitations.

Further, the book introduces how to design MDM platforms that adapt to the evolving mobility environment, new types of transportation, and users based on an integrated solution that utilizes sensing and communication capabilities to tackle significant challenges faced by the MDM field. This volume focuses on how to efficiently pre-process mobile big data to extract and utilize critical feature information of high-dimensional city people flow. The book first provides a conceptual theory and framework, then discusses data sources, trajectory map-matching, noise filtering, trajectory data segmentation, data quality assessment, and more, concluding with a chapter on privacy protection in mobile big data mining.

✦ Table of Contents

Front Cover
Handbook of Mobility Data Mining
Handbook of Mobility Data Mining: Data Preprocessing and Visualization
Copyright
Contents
List of contributors
Preface
Acknowledgments
One - An overview of urban data variety and respective value to urban computing
1. Introduction
1.1 Definition of big data
1.2 Definition of urban data
1.3 Urban computing and challenges
2. Urban data variety and value
2.1 Trajectory
2.2 Human trip record
2.3 CDR
2.4 Event record
2.5 Urban sensor record
2.6 Environmental monitoring data
2.7 Social media data
2.8 Surveillance camera data
3. Conclusion
References
Two - Quality assessment for big mobility data
1. Introduction
2. Trajectory similarity
2.1 Point-to-point distance metric
2.1.1 Euclidean distance
2.1.2 Manhattan distance
2.1.3 Chebyshev distance
2.1.4 Minkowski distance
2.2 Similarity function of trajectory
2.2.1 Euclidean distance
2.2.2 Dynamic time warping
2.2.3 Longest common subsequence
2.2.4 Edit distance on real sequence
2.2.5 Edit distance with real penalty
2.2.6 Hausdorff distance
2.2.7 Frechet distance
2.2.8 One way distance
2.2.9 Locality in-between polylines
3. Travel pattern similarity
4. Origin-destination matrix similarity
4.1 Volume difference focused measure
4.2 Image-based measure
4.2.1 Mean structural SIMilarity index (MSSIM)
4.2.2 MSSIM's variants
4.3 Transforming distance-based measure
4.3.1 Wasserstein metric
4.3.2 Levenshtein metric
5. Conclusion and future directions
References
Three - Noise filter method for mobile trajectory data
1. Introduction
2. Simple data cleaning
3. Mean filter and median filter
4. Kalman filter
5. Particle filter
6. Road network matching
7. An example of mobile trajectory data noise filter
References
Four - Modifiable areal unit problem in grided population density map
1. Introduction
2. Error analysis
2.1 Distributing error rate
2.2 Crowd density error rate
3. Real case experiment
4. Conclusion
References
Five - Few-shot count estimation of mobility dynamics by scaling GPS
1. Introduction
2. Related works
2.1 Population estimation
2.2 Vehicle flow estimation
3. Methodology
3.1 Preliminary
3.2 Problem define
3.3 Feature extraction
3.4 Cross attention
3.5 Cross scaling factors
4. Experiments
4.1 Experimental setting
4.2 Results
4.3 Transfer learning
4.4 Predicting results on time horizon
4.5 Ablation study
5. Conclusion
References
Further reading
Six - Trip segmentation and mode detection for human mobility data
1. Introduction
2. Hidden Markov Model
2.1 Transferring speed state
2.2 Position state
3. Model training
3.1 Supervised learning
3.2 Unsupervised learning
4. Decoding
5. Application
5.1 Spatial distributions of the short trips
5.2 Spatial patterns of walkability and its components
5.3 Correlation between walkability and short-trip density
5.3.1 Linear regression results between the subindices of walkability and short-trip density index
5.3.2 Spatial lag regression results between walkability index and short-trip density index
References
Seven - Benchmark of travel mode detection with smartphone GPS trajectories
1. Introduction
2. Ground truth data collection
3. Method for travel mode detection
4. Case study
4.1 Velocity analysis
4.2 Training of the detection model
5. Conclusion
References
Eight - Trajectory super-resolution methods
1. Introduction
2. Related work
2.1 Trajectory completion
2.2 Trajectory generation
2.3 Super-resolution
3. Preliminary
4. Data description
4.1 Data preprocessing
4.2 Evaluation metrics
4.2.1 Metrics of microview
4.2.2 Metrics of macroview
5. Baseline methods
5.1 Method 1—DeepMove: predicting human mobility with attentional recurrent networks [37]
5.2 Method 2—convolutional neural network for trajectory prediction [38]
5.3 Method 3—TrajVAE: a variational AutoEncoder model for trajectory generation [39]
6. Experiments and results
7. Conclusion and discussion
References
Nine - Map-matching for low accuracy trajectory data
1. Introduction
2. Traditional map-matching method
3. Multi-steps least cost algorithm
3.1 Indicator factors
3.2 Dijkstra algorithm
3.3 Original Hidden Markov Model
3.4 Model simplifying
4. Real world application
References
Ten - Social information labeling for individual mobile phone user
1. Background
2. Data description
2.1 Human mobility dataset
2.2 Administrative border dataset
2.3 Social information dataset
2.4 Prior dataset
3. Framework and case study
4. Methodology
4.1 Social information matching
4.2 Bayesian network
4.3 Sampling
5. Evaluation metrics
5.1 Evaluation by the marginal probability
5.2 Evaluation by the joint probability
6. Result
References
Eleven - Web-based spatio-temporal data visualization technology for urban digital twin
1. Introduction
2. Web-based data visualization technology
2.1 Advantages of web-based data visualization
2.2 The key technology of web-based data visualization
2.2.1 HTML5 webpage standard
2.2.2 WebGL 3D graphics rendering
2.2.3 JavaScript framework
2.2.4 Interaction between frontend and backend
2.3 Web-based visualization tools
3. Visualization of data
3.1 Point：GPS points, point of interests
3.2 Line: trajectory data, traffic line data, OD data
3.3 Region：AOI, buildings, grids, 3D bars
4. Case of web-based urban digital twin application: 3D UrbanMOB
4.1 Trajectory visualization
4.2 The active population inside a certain area
4.3 Advertisement calculation
4.4 Accessibility evaluation
5. Conclusion
References
Index
A
B
C
D
E
F
G
H
I
J
K
L
M
O
P
R
S
T
U
V
W
Back Cover