Identifying and Recovering Anomalies in Intelligent Vehicle Monitoring Systems

• Leonardo Alves de Melo UNICAMP
• Luis Fernando Gomez Gonzalez UNICAMP
• Juliana Freitag Borin Konker Labs

DOI: https://doi.org/10.5753/sbcup.2021.16006

Abstract

One of the expected applications for the Internet of Things is the intelligent management and maintenance of public bus lines. In this context, the monitoring systems of these vehicles need algorithms that identify in real time possible inconsistencies in routes, being able to circumvent this type of error as soon as possible, maintaining the quality of service. This paper proposes algorithms that infer in real time paths of vehicles that have a predefined route. The proposed algorithms were analyzed and compared with a baseline solution using data from a real system.

Keywords: Geolocalization, Route Prediction, Urban Computing, Trajectories Analysis, Machine Learning

References

Atzori, L., Iera, A., and Morabito, G. (2010). The internet of things: A survey. ComputerNetworks, 54(15):2787–2805.

Barbosa, R. A., Sousa, R. P., Oliveira, F. A., Oliveira, H. C., Luz, P. D. G., and Manera, L. T. (2019). Circulino: An iot solution applied in the university transport service. In Iano, Y., Arthur, R., Saotome, O., Vieira Estrela, V., and Loschi, H. J., editors, Proceedings of the 4th Brazilian Technology Symposium (BTSym’18), pages 503–514,Cham. Springer International Publishing.

Bessa, A., de Mesentier Silva, F., Nogueira, R. F., Bertini, E., and Freire, J. (2016). Riobusdata: Outlier detection in bus routes of rio de janeiro. CoRR, abs/1601.06128.

Chen, C., Zhang, D., Li, N., and Zhou, Z. (2014). B-planner: Planning bidirectionalnight bus routes using large-scale taxi gps traces. IEEE Transactions on IntelligentTransportation Systems, 15(4):1451–1465.

Gong, J., Liu, M., and Zhang, S. (2013). Hybrid dynamic prediction model of bus arrivaltime based on weighted of historical and real-time gps data. In2013 25th ChineseControl and Decision Conference (CCDC), pages 972–976.

IBGE. População rural e urbana. IBGEeduca.

Martins, K. S. and Cunha, F. D. (2018). Explorando dados urbanos: um estudo usando viagens de táxi da cidade de são francisco. In Anais do II Workshop de Computação Urbana, Porto Alegre, RS, Brasil. SBC.

Miranda, W., Mendonça, R., Silva, A., Curvello, A., Souza, F., and Silva, H. (2017). Busme: Automatic bus localization system and route registration.Procedia ComputerScience, 109:1098–1103.

Neves, D. V. (2019). Uso de aprendizado supervisionado para análise de confiabilidade de dados de crowdsourcing sobre posicionamento de ônibus. In Dissertação de Mestrado em Sistemas de Informação.

Nunes, D. E., Fagundes, A., and Mota, V. F. S. (2018). Classificação da qualidade de vias urbanas baseado em sensoriamento participativo. In Anais do II Workshop de Computação Urbana, Porto Alegre, RS, Brasil. SBC.

Saad, S. A., Hisham, A. . B., Ishak, M. H. I., Fauzi, M. H. M., Baharudin, M. A., and Idris,N. H. (2018). Real-time on-campus public transportation monitoring system. In 2018 IEEE 14th International Colloquium on Signal Processing Its Applications (CSPA), pages 215–220.

Simmons, R., Browning, B., Yilu Zhang, and Sadekar, V. (2006). Learning to predictdriver route and destination intent. In 2006 IEEE Intelligent Transportation Systems Conference, pages 127–132.

Sousa, P., Costa, J., Castro, A., Neto, W., Bezerra, C. I. M., and Coutinho, E. (2019). Uma infraestrutura para o monitoramento e predição de rotas e paradas de Ônibus no transporte universitário.

Viana, J. D. F., Braga, O., Silva, L., and Neto, F. M. (2019). Analyzing patterns of a bicycle sharing system for generating rental flow predictive models. In Anais do III Workshop de Computação Urbana, pages 57–70, Porto Alegre, RS, Brasil. SBC.