Bike sharing demand prediction using artificial immune system and artificial neural network
- 455 Downloads
From the viewpoint of bike sharing service, the rental number is a critical performance indicator for managers and controllers to assess the demand. Bike demand prediction in bike sharing systems is hence a key indicator in economic systems. In this study, a novel prediction framework integrating AIS and the artificial neural network forecasting technique is developed for numerical predication; it is named AIS-ANN. In this proposed AIS-ANN prediction framework, there are three major mechanisms applied to build the predication system which includes cell creation by ANN, antibody generation by clonal selection, and antibody’s center adaption by similarity measuring. The experimental results show that our proposed AIS-ANN has better performance when compared with other 6 forecasting models.
KeywordsBio-inspired computation Artificial immune system Artificial neural network Numerical prediction Bike sharing demand
This research is conducted under the support of Yuan Ze University. There are no other fundings for this research.
Compliance with ethical standards
Conflict of interest
All authors of this research declare that they have no conflict of interest.
- Clark P, Niblett T (1989) The CN2 rule induction algorithm. Mach Learn 3:261–284Google Scholar
- Cui M, Liu H, Li Z, Tang Y, Guan X (2015) Identification of Hammerstein model using functional link artificial neural network. Neurocomputing 161(5):220–228Google Scholar
- Fanaee-T H, Gama J (2013) Event labeling combining ensemble detectors and background knowledge. Prog Artif Intell 2(2–3):113–127Google Scholar
- Frank E, Bouckaert RR (2009) Conditional density estimation with class probability estimators. In: Zhou E-H, Washio T (eds) Proceedings of first Asian conference on machine learning, ACML 2009, Nanjing, pp 65–81Google Scholar
- Frank R, Hall M, Pfahringer B (2003) Locally weighted naive bayes. In: Proceedings of the 19th conference in uncertainty in artificial intelligence, Acapulco, Mexico pp 249–256Google Scholar
- Frank E, Mayo M, Kramer S (2015) Alternating model tree. In: Proceedings of the 30th annual ACM symposium on applied computing, pp 871–878Google Scholar
- Kohavi R (1996) The power of decision tables. In: Proceedings of 8th european conference on machine learning, Heraclion, Crete, pp 174–189Google Scholar
- Louppe G, Geurts P (2012) Ensembles on random patches. In: Machine learning and knowledge discovery in databases, Springer, Berlin, pp 346–361Google Scholar
- Montechiesi L, Cocconcelli M, Rubini R (2016) Artificial immune system via Euclidean Distance Minimization for anomaly detection in bearings. Mech Syst Signal Process 76–77:380–393Google Scholar
- Szymczyk P, Szymczyk M (2015) Classification of geological structure using ground penetrating radar and Laplace transform artificial neural networks. Neurocomputing 148(19):354–362Google Scholar