Payment Type Classification on Urban Taxi Big Data using Deep Learning Neural Network

Taxi service as a reliable means of public transportation is a public need. Classification of payment types is performed on New York City Yellow Taxi Trip Open Data that considered as big data and there is a number of unlabelled data greater than the number of labeled training data was situated. We used the framework namely learning from unlabelled data (lfun) and deep learning neural network as the classifier to address the classification problem. Experimentation to find out the better performance of using lfun was conducted. We achieved the f-measure average value reaching 0.725 for classification using the lfun framework.

[1]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[2]  Yu Wang,et al.  Statistical Features-Based Real-Time Detection of Drifted Twitter Spam , 2017, IEEE Transactions on Information Forensics and Security.

[3]  Kai Zhang,et al.  A Framework for Passengers Demand Prediction and Recommendation , 2016, 2016 IEEE International Conference on Services Computing (SCC).

[4]  Jorge Bernardino,et al.  Big Data Issues , 2015, IDEAS.

[5]  Siti Mariyam Shamsuddin,et al.  Data science vs big data @ UTM big data centre , 2015, 2015 International Conference on Science in Information Technology (ICSITech).

[6]  Robert D. Nowak,et al.  Unlabeled data: Now it helps, now it doesn't , 2008, NIPS.

[7]  Partha Pratim Talukdar,et al.  Graph-Based Semi-Supervised Learning , 2014, Graph-Based Semi-Supervised Learning.

[8]  Etienne E. Kerre,et al.  Uncertainty Modeling in Knowledge Engineering and Decision Making: Proceedings of the 10th International FLINS Conference , 2012 .

[9]  Jun Xu,et al.  A Sequence Learning Model with Recurrent Neural Networks for Taxi Demand Prediction , 2017, 2017 IEEE 42nd Conference on Local Computer Networks (LCN).

[10]  Abhishek Singhal,et al.  A big data driven model for taxi drivers' airport pick-up decisions in New York City , 2013, 2013 IEEE International Conference on Big Data.

[11]  Chao Yang,et al.  Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers , 2011, IEEE Transactions on Information Forensics and Security.

[12]  Narasimhan Sundararajan,et al.  Supervised Learning with Complex-valued Neural Networks , 2012, Studies in Computational Intelligence.

[13]  Jun Zhang,et al.  Asymmetric self-learning for tackling Twitter Spam Drift , 2015, 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[14]  Jun Xu,et al.  Real-Time Prediction of Taxi Demand Using Recurrent Neural Networks , 2018, IEEE Transactions on Intelligent Transportation Systems.

[15]  David A. King,et al.  Access to Taxicabs for Unbanked Households: An Exploratory Analysis in New York City , 2016, ArXiv.

[16]  Md. Zakirul Alam Bhuiyan,et al.  A Survey on Deep Learning in Big Data , 2017, 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC).

[17]  Xiao Chen,et al.  6 million spam tweets: A large ground truth for timely Twitter spam detection , 2015, 2015 IEEE International Conference on Communications (ICC).