Understanding Origin-Destination Ride Demand with Interpretable and Scalable Nonnegative Tensor Decomposition

References

• Aalen O, Borgan O, Gjessing H (2008) Survival and Event History Analysis: A Process Point of View (Springer Science & Business Media, Boston).Crossref, Google Scholar
• Ahn D, Jang GJ, Kang U (2021) Time-aware tensor decomposition for sparse tensors. Proc. IEEE 8th Internat. Conf. on Data Sci. and Adv. Analytics (IEEE, Piscataway, NJ), 1–2.Google Scholar
• Asif MT, Mitrovic N, Dauwels J, Jaillet P (2016) Matrix and tensor based methods for missing data estimation in large traffic networks. IEEE Trans. Intelligent Transportation Systems 17(7):1816–1825.Crossref, Google Scholar
• Barratt S, Dong Y, Boyd S (2021) Low rank forecasting. Preprint, submitted January 29, https://arxiv.org/abs/2101.12414.Google Scholar
• Bell MGH (1991) The estimation of origin-destination matrices by constrained generalised least squares. Transportation Res. Part B: Methodological 25(1):13–22.Crossref, Google Scholar
• Ben-Akiva ME, Bowman JL (1998) Activity based travel demand model systems. Equilibrium and Advanced Transportation Modelling (Springer, Berlin), 27–46.Crossref, Google Scholar
• Berry MW, Browne M, Langville AN, Pauca VP, Plemmons RJ (2007) Algorithms and applications for approximate nonnegative matrix factorization. Comput. Statist. Data Anal. 52(1):155–173.Crossref, Google Scholar
• Bhat CR (2001) Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model. Transportation Res. Part B: Methodological 35(7):677–693.Crossref, Google Scholar
• Brunet J-P, Tamayo P, Golub TR, Mesirov JP (2004) Metagenes and molecular pattern discovery using matrix factorization. Proc. National Acad. Sci. USA 101(12):4164–4169.Crossref, Google Scholar
• Cai D, He X, Wu X, Han J (2008) Non-negative matrix factorization on manifold. Proc. 8th IEEE Internat. Conf. on Data Mining (IEEE, Piscataway, NJ), 63–72.Google Scholar
• Carroll JD, Chang JJ (1970) Analysis of individual differences in multidimensional scaling via an N-way generalization of “Eckart-Young” decomposition. Psychometrika 35(3):283–319.Crossref, Google Scholar
• Cascetta E (1984) Estimation of trip matrices from traffic counts and survey data: A generalized least squares estimator. Transportation Res. Part B: Methodological 18(4):289–299.Crossref, Google Scholar
• Castillo E, Conejo AJ, Menendez JM, Jimenez P (2008) The observability problem in traffic network models. Comput. Aided Civil Infrastructure Engrg. 23(3):208–222.Crossref, Google Scholar
• Chen X, Chen Y, Saunier N, Sun L (2021) Scalable low-rank tensor learning for spatiotemporal traffic data imputation. Transportation Res. Part C Emerging Tech. 129:103226.Crossref, Google Scholar
• Chi EC, Kolda TG (2012) On tensors, sparsity, and nonnegative factorizations. SIAM J. Matrix Anal. Appl. 33(4):1272–1299.Crossref, Google Scholar
• Cuzzocrea A (2019) Management and analytics of big data sources in intelligent smart environments: Where we are and where we are going. Proc. Internat. Conf. on Data Mining Workshops, 567–572.Google Scholar
• Ding C, He X, Simon HD (2005) On the equivalence of nonnegative matrix factorization and spectral clustering. Proc. SIAM Internat. Conf. on Data Mining (SIAM, Philadelphia), 606–610.Google Scholar
• Ding C, Li T, Peng W, Park H (2006) Orthogonal nonnegative matrix t-factorizations for clustering. Proc. 12th ACM SIGKDD Internat. Conf. on Knowledge Discovery and Data Mining (ACM, New York), 126–135.Google Scholar
• Fishman P, Snyder D (1976) The statistical analysis of space-time point processes. IEEE Trans. Inform. Theory 22(3):257–274.Crossref, Google Scholar
• Fox EW, Schoenberg FP, Seth J (2015) A note on nonparametric estimates of space-time Hawkes point process models for earthquake occurrences. Annals Appl. Statist. http://www.stat.ucla.edu/∼frederic/papers/EarthquakePaper.pdf .Google Scholar
• Gopalan PK, Charlin L, Blei D (2014) Content-based recommendations with Poisson factorization. Adv. Neural Inform. Processing Systems 27. https://papers.nips.cc/paper_files/paper/2014/hash/97d0145823aeb8ed80617be62e08bdcc-Abstract.html.Google Scholar
• Goulart JHM, Kibangou AY, Favier G (2017) Traffic data imputation via tensor completion based on soft thresholding of Tucker core. Transportation Res. Part C Emerging Tech. 85:348–362.Crossref, Google Scholar
• Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks. Proc. 22nd ACM SIGKDD Internat. Conf. on Knowledge Discovery and Data Mining (ACM, New York), 855–864.Google Scholar
• Harshman RA (1970) Foundations of the PARAFAC procedure: Models and conditions for an “explanatory” multimodal factor analysis. UCLA Working Papers in Phonetics, vol. 16 (University Microfilms, Ann Arbor), 1–84.Google Scholar
• Hazelton ML (2000) Estimation of origin–destination matrices from link flows on uncongested networks. Transportation Res. Part B: Methodological 34(7):549–566.Crossref, Google Scholar
• Hazelton ML (2001) Inference for origin–destination matrices: Estimation, prediction and reconstruction. Transportation Res. Part B: Methodological 35(7):667–676.Crossref, Google Scholar
• Hazelton ML (2008) Statistical inference for time varying origin–destination matrices. Transportation Res. Part B: Methodological 42(6):542–552.Crossref, Google Scholar
• Hitchcock FL (1927) The expression of a tensor or a polyadic as a sum of products. J. Math. Physics 6(1–4):164–189.Crossref, Google Scholar
• Hoyer PA (2002) Non-negative sparse coding. Proc. 12th IEEE Workshop on Neural Networks for Signal Processing (IEEE, Piscataway, NJ), 557–565.Google Scholar
• Hoyer PO (2004) Non-negative matrix factorization with sparseness constraints. J. Machine Learn. Res. 5:9.Google Scholar
• Ke J, Zhang S, Yang H, Chen X (2019) PCA-based missing information imputation for real-time crash likelihood prediction under imbalanced data. Transportmetrica A: Transportation Sci. 15(2):872–895.Crossref, Google Scholar
• Kim YD, Choi S (2007) Nonnegative tucker decomposition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (IEEE, Piscataway, NJ), 1–8.Google Scholar
• Kolda TG (2001) Orthogonal tensor decompositions. SIAM J. Matrix Anal. Appl. 23(1):243–255.Crossref, Google Scholar
• Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Rev. 51(3):455–500.Crossref, Google Scholar
• Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30–37.Crossref, Google Scholar
• Kossaifi J, Panagakis Y, Anandkumar A, Pantic M (2019) TensorLy: Tensor learning in Python. J. Machine Learn. Res. 20(26):1–6.Google Scholar
• Lai TL (1995) Sequential changepoint detection in quality control and dynamical systems. J. Royal Statist. Soc. B 57(4):613–644.Google Scholar
• Lee D, Sebastian Seung H (2000) Algorithms for non-negative matrix factorization. Adv. Neural Inform. Processing Systems 13. https://papers.nips.cc/paper_files/paper/2000/hash/f9d1152547c0bde01830b7e8bd60024c-Abstract.html.Google Scholar
• Lee DD, Sebastian Seung H (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791.Crossref, Google Scholar
• Li X, Sharpnack J (2017) Compression of spatio-temporal networks via point-to-point process models. Proc. 13th Internat. Workshop on Mining and Learn. with Graphs (National Science Foundation, Alexandria, Virginia).Google Scholar
• Li Z, Wu X, Peng H (2010) Nonnegative matrix factorization on orthogonal subspace. Pattern Recognition Lett. 31(9):905–911.Crossref, Google Scholar
• Liu Z, Hauskrecht M (2016) Learning linear dynamical systems from multivariate time series: A matrix factorization based framework. Proc. SIAM Internat. Conf. on Data Mining (SIAM, Philadelphia), 810–818.Google Scholar
• Ma H, Yang H, Lyu MR, King I (2008) Sorec: Social recommendation using probabilistic matrix factorization. Proc. 17th ACM Conf. Inform. and Knowledge Management (ACM, New York), 931–940.Google Scholar
• Ma W, Qian Z (2018a) Estimating multi-year 24/7 origin-destination demand using high-granular multi-source traffic data. Transportation Res. Part C: Emerging Tech. 96:96–121.Crossref, Google Scholar
• Ma W, Qian ZS (2018b) Statistical inference of probabilistic origin-destination demand using day-to-day traffic data. Transportation Res. Part C Emerging Tech. 88:227–256.Crossref, Google Scholar
• Maher MJ (1983) Inferences on trip matrices from observations on link volumes: A Bayesian statistical approach. Transportation Res. Part B: Methodological 17(6):435–447.Crossref, Google Scholar
• Mairal J, Bach F, Ponce J, Sapiro G (2010) Online learning for matrix factorization and sparse coding. J. Machine Learn. Res. 11(Jan):19–60.Google Scholar
• Mohammadiha N, Leijon A (2009) Nonnegative matrix factorization using projected gradient algorithms with sparseness constraints. Proc. IEEE Internat. Sympos. on Signal Processing and Inform. Tech. (IEEE, Piscataway, NJ), 418–423.Google Scholar
• Mørup M, Hansen LK, Arnfred SM (2008) Algorithms for sparse nonnegative Tucker decompositions. Neural Comput. 20(8):2112–2131.Crossref, Google Scholar
• Nguyen S (1984) Estimating Origin Destination Matrices from Observed Flows (Elsevier, New York).Google Scholar
• Paatero P, Tapper U (1994) Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2):111–126.Crossref, Google Scholar
• Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. Proc. 20th ACM SIGKDD Internat. Conf. on Knowledge Discovery and Data Mining (ACM, New York), 701–710.Google Scholar
• Ran B, Tan H, Wu Y, Jin PJ (2016a) Tensor based missing traffic data completion with spatial–temporal correlation. Phys. A 446:54–63.Crossref, Google Scholar
• Ran B, Tan H, Feng J, Wang W, Cheng Y, Jin P (2016b) Estimating missing traffic volume using low multilinear rank tensor completion. J. Intelligent Transportation Systems 20(2):152–161.Crossref, Google Scholar
• Recker WW (1995) The household activity pattern problem: General formulation and solution. Transportation Res. Part B: Methodological 29(1):61–77.Crossref, Google Scholar
• Sanandaji BM, Varaiya P (2016) Compressive origin-destination estimation. Transportation Lett. 8(3):148–157.Google Scholar
• Schein A, Zhou M, Blei D, Wallach H (2016) Bayesian Poisson Tucker decomposition for learning the structure of international relations. Proc. Internat. Conf. on Machine Learn. (PMLR), 2810–2819.Google Scholar
• Shao H, Lam WHK, Sumalee A, Hazelton ML (2015) Estimation of mean and covariance of stochastic multi-class OD demands from classified traffic counts. Transportation Res. Part C Emerging Tech. 59:92–110.Crossref, Google Scholar
• Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Machine Intelligence 22(8):888–905.Crossref, Google Scholar
• Sun L, Axhausen KW (2016) Understanding urban mobility patterns with a probabilistic tensor factorization framework. Transportation Res. Part B: Methodological 91:511–524.Crossref, Google Scholar
• Sun WW, Lu J, Liu H, Cheng G (2017) Provable sparse tensor decomposition. J. Royal Statist. Soc. Ser. B Statist. Methodology 79(3):899–916.Crossref, Google Scholar
• Tan H, Wu Y, Shen B, Jin PJ, Ran B (2016) Short-term traffic prediction based on dynamic tensor completion. IEEE Trans. Intelligent Transportation Systems 17(8):2123–2133.Crossref, Google Scholar
• Tan H, Feng G, Feng J, Wang W, Zhang Y-J, Li F (2013) A tensor-based method for missing traffic data completion. Transportation Res. Part C Emerging Tech. 28:15–27.Crossref, Google Scholar
• Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. Proc. 24th Internat. Conf. on World Wide Web (International World Wide Web Conferences Steering Committee, Geneva), 1067–1077.Google Scholar
• Tucker LR (1966) Some mathematical notes on three-mode factor analysis. Psychometrika 31(3):279–311.Crossref, Google Scholar
• Vardi Y (1996) Network tomography: Estimating source-destination traffic intensities from link data. J. Amer. Statist. Assoc. 91(433):365–377.Crossref, Google Scholar
• Vere-Jones D (2009) Some models and procedures for space-time point processes. Environment. Ecological Statist. 16(2):173–195.Crossref, Google Scholar
• Vlahogianni EI (2015) Computational intelligence and optimization for transportation big data: Challenges and opportunities. Engineering and Applied Sciences Optimization (Springer, Berlin), 107–128.Crossref, Google Scholar
• Wang Y, Zhang Y, Wang L, Hu Y, Yin B (2021) Urban traffic pattern analysis and applications based on spatio-temporal non-negative matrix factorization. IEEE Trans. Intelligent Transportation Systems. 23(8):12752–12765.Crossref, Google Scholar
• Yang H, Meng Q, Bell MGH (2001) Simultaneous estimation of the origin-destination matrices and travel-cost coefficient for congested networks in a stochastic user equilibrium. Transportation Sci. 35(2):107–123.Link, Google Scholar
• Yang H, Sasaki T, Iida Y, Asakura Y (1992) Estimation of origin-destination matrices from link traffic counts on congested networks. Transportation Res. Part B: Methodological 26(6):417–434.Crossref, Google Scholar
• Yang J-M, Peng Z-R, Lin L (2021) Real-time spatiotemporal prediction and imputation of traffic status based on LSTM and Graph Laplacian regularized matrix factorization. Transportation Res. Part C Emerging Tech. 129:103228.Crossref, Google Scholar
• Yang Y, Fan Y (2015) Data dependent input control for origin–destination demand estimation using observability analysis. Transportation Res. Part B: Methodological 78:385–403.Crossref, Google Scholar
• Yang Y, Fan Y, Royset JO (2019) Estimating probability distributions of travel demand on a congested network. Transportation Res. Part B: Methodological 122(C):265–286.Crossref, Google Scholar
• Yang Y, Fan Y, Wets RJB (2018) Stochastic travel demand estimation: Improving network identifiability using multi-day observation sets. Transportation Res. Part B: Methodological 107:192–211.Crossref, Google Scholar
• Yao H, Tang X, Wei H, Zheng G, Li Z (2019) Revisiting spatial-temporal similarity: A deep learning framework for traffic prediction. Proc. Conf. AAAI Artificial Intelligence 33:5668–5675.Crossref, Google Scholar
• Yu B, Yin H, Zhu Z (2017) Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. Preprint, submitted September 14, https://arxiv.org/abs/1709.04875.Google Scholar
• Yu H-F, Rao N, Dhillon IS (2016) Temporal regularized matrix factorization for high-dimensional time series prediction. Adv. Neural Inform. Processing Systems 29. https://papers.nips.cc/paper_files/paper/2016/hash/85422afb467e9456013a2a51d4dff702-Abstract.html.Google Scholar
• Zhang P, Ren P, Liu Y, Sun H (2022) Autoregressive matrix factorization for imputation and forecasting of spatiotemporal structural monitoring time series. Mechanical Systems Signal Process 169:108718.Crossref, Google Scholar
• Zhang W, Wang J (2015) A collective Bayesian Poisson factorization model for cold-start local event recommendation. Proc. 21th ACM SIGKDD Internat. Conf. on Knowledge Discovery and Data Mining (ACM, New York), 1455–1464.Google Scholar