Undarmaa Chinzorig
ABSTRACT
With modern ubiquitous computing environments, recommender systems have become a major part of modern intelligent services. Taxi recommender system allows both passengers and drivers to minimize waiting times and obtain the current location of each other. In this paper, we present a taxi recommender system based on deep learning for catching taxis. In deep learning technique, random selections of hyperparameters lead to overfitting or underfitting problems in prediction or classification. In particular, determining number of hidden units is one of the critical issues facing research. Therefore, we investigated how hidden units affect the performance of deep learning for taxi recommender system and compared the results of these existing methods for determining number of hidden units. Deep Learning algorithms, such as Deep Neural Network (DNN), which have been successfully used, were employed for classifying road segments. Finally, our proposed system can spot regions, where a passenger can catch a taxi within walkable distance.
- Pushpa C N, Arpit Singh Baghel, Thriveni J, Venugopal K R, L M Patnaik (2015). Taxi-Passenger Recommender System: An Application. International Journal of Computer Application.Google Scholar
- Weipeng Jing, Likun Hu, Lei Shu, Mithun Mukherjee, Takahiro Hara (2016). RPR: recommendation for passengers by roads based on cloud computing and taxis traces data. Personal and Ubiquitous Computing, 20, 337--347, doi: 10.1007/s00779-016-0925-9.Google ScholarDigital Library
- Nicholas Jin Yuan, Yu Zheng, Liuhang Zhang, XingXie (2013). T-Finder: A Recommender System for Finding Passengers and Vacant Taxis. IEE Transactions on Knowledge and Data Engineering, 25, 2390--2403, doi:10.1109/Tkde.2012.153.Google ScholarDigital Library
- Junghoon Lee, Inhye Shin, Gyung-Leen Park (2008). Analysis of the Passenger Pick-Up Pattern for Taxi Location Recommendation. In Proceedings of 2008 Fourth International Conference on Networked Computing and Advanced Information Management; pp. 199--204.Google ScholarDigital Library
- Paul Covington, Jay Adams, Emre Sargin (2016). Deep Neural Networks for YouTube Recommendations. In Proceedings of Proceedings of the 10th ACM Conference on Recommender Systems - RecSys '16, Boston, Massachusetts, USA; pp. 191--198Google ScholarDigital Library
- Heng-Tze Cheng, Mustafa Ispir, Rohan Anil, Zakaria Haque, Lichan Hong, Vihan Jain, et al (2016). Wide & Deep Learning for Recommender Systems. In Proceedings of Proceedings of the 1st Workshop on Deep Learning for Recommender Systems - DLRS 2016, Boston, MA, USA; pp. 7--10.Google ScholarDigital Library
- Tulasi K. Paradarami, Nathaniel Bastian, Jennifer L. Wightman (2017). A hybrid recommender system using artificial neural networks. Expert System Applied, 83, 300--313, doi: 10.1016/j.eswa.2017.04.046.Google ScholarDigital Library
- K. Gnana Sheela, S.N. Deepa (2013). Review on Methods to Fix Number of Hidden Neurons in Neural Networks. Mathematical Problems in Engineering, 10.1155/2013/425740, doi:10.1155/2013/425740.Google Scholar
- Jin-Yan Li, T.W.S Chow, Ying-Lin Yu (1995). The estimation theory and optimization algorithm for the number of hidden units in the higher-order feedforward neural network. In Proceedings of ICNN'95-International Conference on Neural Networks; pp. 1229--1233.Google Scholar
- David Hunter, Hao Yu, Michael S. Pukish, Janusz Kolbusz, Bogdan M.Wilamowski (2012). Selection of Proper Neural Network Sizes and Architectures-a Comparative Study. IEEE Transactions on Industrial Informatics, 8, 228--240, doi:10.1109/tii.2012.2187914.Google ScholarCross Ref
- Wikipedia. Available online:https://en.wikipedia.org/wiki/Haversine_formula (accessed on 25 Match 2019).Google Scholar
- TijanaVujicic, Tripo Matijevic, Jelena Ljucovic, Adis Balota, Zoran Sevarac (2016). Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network. In Proceedings of Central European Conference on Information and Intelligent Systems; p. 219.Google Scholar
Index Terms
- Investigating Methods of Determining Number of Hidden Units in Deep Learning for Taxi Recommender System
Recommendations
Deep Learning Based-Recommendation System: An Overview on Models, Datasets, Evaluation Metrics, and Future Trends
CIIS '19: Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent SystemsThe growth of data in recent years has motivated the emergence of deep learning in many Computer Sciences related fields including Recommender System (RS). Deep learning has emerged as the solution; overcoming the obstacles of traditional recommendation ...
Deep Learning Based Recommender System: A Survey and New Perspectives
With the growing volume of online information, recommender systems have been an effective strategy to overcome information overload. The utility of recommender systems cannot be overstated, given their widespread adoption in many web applications, along ...
CoDFi-DL: a hybrid recommender system combining enhanced collaborative and demographic filtering based on deep learning
AbstractThe cold start problem has always been a major challenge for recommender systems. It arises when the system lacks rating records for new users or items. Addressing the challenge of providing personalized recommendations in the cold start scenario ...
Comments