ABSTRACT
The current pollution measurement methodology is coarse-grained where the pollution measurements are spatiotemporally few and far in-between. Our vision is to provide broadly accessible, fine-grained pollution information to a variety of end-users, and in turn, allow them to make better informed decisions using a new, more accurate information stream. To this end, this study proposes a new neural network model to estimate Carbon Monoxide (CO) concentrations outside vehicle from crowd-sourced CO measurements inside vehicles measured using mobile devices (dosimeters). End-users can benefit from the fine-grained pollution information generated by this prediction model along with data from direct measurements. A neural network is used to model the dynamic relationship between the CO measurements inside and outside a moving vehicle. The resulting neural network model is then used to predict outside CO concentrations from CO measurements inside vehicles. Mobile CO dosimeters were used inside and outside vehicles to collect measurements used in training a neural network based regression model. For this regression task, a new neural network architecture was designed using Convolutional layers and Gated Recurrent Unit (GRU) layers. The results show that outside CO concentrations can be estimated from inside vehicle CO measurements with high accuracy. The proposed neural network model provides a promising new and novel source of fine-grained pollution information along with direct measurement streams.
- 2020. Air Quality Egg. Retrieved June 11, 2020 from https://airqualityegg.com/eggGoogle Scholar
- 2020. Awair. Retrieved June 11, 2020 from https://getawair.com/Google Scholar
- 2020. Categorical Variables. Retrieved November 15, 2020 from https://en.wikipedia.org/wiki/Categorical_variableGoogle Scholar
- 2020. Keras. Retrieved November 15, 2020 from https://keras.io/Google Scholar
- 2020. NODE Sensor Platform. Retrieved June 11, 2020 from https://www.smarthome.com/variable-technologies-nk-0001-node-kore-wireless-bluetooth-smartphone-sensor.htmlGoogle Scholar
- 2020. One-hot Encoding. Retrieved November 15, 2020 from https://en.wikipedia.org/wiki/One-hotGoogle Scholar
- 2020. Reverse geocoding API. Retrieved November 15, 2020 from https://developers.google.com/maps/documentation/geocoding/startGoogle Scholar
- 2020. Sensirion. Retrieved June 11, 2020 from https://www.sensirion.com/en/environmental-sensors/Google Scholar
- 2020. TensorFlow. Retrieved November 15, 2020 from https://www.tensorflow.org/Google Scholar
- 2020. Waspmote. Retrieved June 11, 2020 from http://www.libelium.com/calibrated-air-quality-gas-dust-particle-matter-pm10-smart-cities/Google Scholar
- 2020. Weather information. Retrieved November 15, 2020 from https://www.worldweatheronline.com/Google Scholar
- Karl Aberer, Saket Sathe, Dipanjan Chakraborty, Alcherio Martinoli, Guillermo Barrenetxea, Boi Faltings, and Lothar Thiele. 2010. OpenSense: Open Community Driven Sensing of Environment. In Proceedings of the ACM SIGSPATIAL International Workshop on GeoStreaming. ACM, New York, NY, USA, 39–42. https://doi.org/10.1145/1878500.1878509Google ScholarDigital Library
- M. Budde, M. Berning, M. Busse, T. Miyaki, and M. Beigl. 2012. The TECO Envboard: A mobile sensor platform for accurate urban sensing — And more. In 2012 Ninth International Conference on Networked Sensing (INSS). 1–2. https://doi.org/10.1109/INSS.2012.6240573Google ScholarCross Ref
- Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. (06 2014). https://doi.org/10.3115/v1/D14-1179Google Scholar
- Ralph J. Delfino and Jun Wu. 2012. In-vehicle air pollution exposure measurement and modeling. Technical Report. Irvine, CA, USA.Google Scholar
- Srinivas Devarakonda, Parveen Sevusu, Hongzhang Liu, Ruilin Liu, Liviu Iftode, and Badri Nath. 2013. Real-time air quality monitoring through mobile sensing in metropolitan areas. In ACM SIGKDD International Workshop on Urban Computing (UrbComp ’13). ACM, New York, NY, 8. https://doi.org/10.1145/2505821.2505834Google ScholarDigital Library
- Stuart K. Grange, Naomi J. Farren, Adam R. Vaughan, Rebecca A. Rose, and David C. Carslaw. 2019. Strong Temperature Dependence for Light-Duty Diesel Vehicle NOx Emissions. Environmental Science & Technology 53 (2019), 6587–6596. https://doi.org/10.1021/acs.est.9b01024Google ScholarCross Ref
- Yu H, Samuels DC, Zhao YY, and Guo Y. 2019. Architectures and accuracy of artificial neural network for disease classification from omics data. BMC Genomics 20(1):167(2019). https://doi.org/10.1186/s12864-019-5546-zGoogle Scholar
- Fei Hao, Mingjie Jiao, Geyong Min, and Laurence T. Yang. 2015. Launching an Efficient Participatory Sensing Campaign: A Smart Mobile Device-Based Approach. ACM Trans. Multimedia Comput. Commun. Appl. 12, 1s, Article 18 (Oct. 2015), 22 pages. https://doi.org/10.1145/2808198Google ScholarDigital Library
- Sepp Hochreiter and Jurgen Schmidhuber. 1997. Long Short-Term Memory. In Neural Computation, Vol. 9:8. MIT Press, Cambridge, MA, 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735Google ScholarDigital Library
- Richard Honicky, Eric A. Brewer, Eric Paulos, and Richard White. 2008. N-smarts: Networked Suite of Mobile Atmospheric Real-time Sensors. In Proceedings of the Second ACM SIGCOMM Workshop on Networked Systems for Developing Regions. ACM, New York, NY, USA, 25–30. https://doi.org/10.1145/1397705.1397713Google ScholarDigital Library
- Andrew Kimbrell. 2000. An assessment of air quality inside automobile passenger compartments. Technical Report. Washington DC, USA.Google Scholar
- Luke D. Knibbs, Richard deDear, and Steven E. Atkinson. 2009. Field study of air change and flow rate in six automobiles, Vol. 19(4). 303–313.Google Scholar
- Parviz A. Koushki, Khaled H. Al-Dhowalia, and Said A. Niaizi. 1992. Vehicle Occupant Exposure to Carbon Monoxide. Journal of the Air & Waste Management Association 42:12 (1992), 1603–1608. https://doi.org/10.1080/10473289.1992.10467104Google ScholarCross Ref
- Wayne R. Ott and Neil H. Willits. 1981. CO exposures of occupants of motor vehicles: modeling the dynamic response of the vehicle. Technical Report. Stanford, CA, USA.Google Scholar
- Olalekan A.M. Popoola, Gregor B. Stewart, Mohammed I. Mead, and Roderic L. Jones. 2016. Development of a baseline-temperature correction methodology for electrochemical sensors and its implications for long-term stability. Atmospheric Environment 147 (2016), 330 – 343. https://doi.org/10.1016/j.atmosenv.2016.10.024Google ScholarCross Ref
- Richard Rohwer. 1994. The Time Dimension of Neural Network Models. Technical Report.Google Scholar
- Jurgen Schmidhuber. 1989. A Local Learning Algorithm for Dynamic Feedforward and Recurrent Networks. Connection Science 1:4(1989), 403–412. https://doi.org/10.1080/09540098908915650Google ScholarCross Ref
- Claudia Ulbricht. 1994. Multi-Recurrent Networks for Traffic Forecasting. In Twelfth National Conference on Artificial Intelligence, Vol. 19(4). AAAI Press/MIT Press, Cambridge, MA, 883–888.Google Scholar
- Claudia Ulbricht, Georg Dorffner, Stéphane Canu, Didier Guillemyn, Gurutze Marijuán, Javier Olarte, Clemente Rodríguez, and Ignacio Martín. 1992. Mechanisms For Handling Sequences With Neural Networks. Intelligent Engineering Systems through Artificial Neural Networks 2 (1992).Google Scholar
- R. Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, and H. Lee. 2017. Decomposing Motion and Content for Natural Video Sequence Prediction. ArXiv abs/1706.08033(2017).Google Scholar
Recommendations
Application of Neural Network Model in Insulating Oil Fault Diagnosis
ICMTMA '10: Proceedings of the 2010 International Conference on Measuring Technology and Mechatronics Automation - Volume 01:This paper introduced the practical value of artificial neural network in fault diagnosis field, respectively, applied the BP network, ELMAN network, RBF neural networks insulating oil fault diagnosis. Simulation results show that, in the transformer ...
Towards a practical remote-sensing model of suspended sediment concentrations in turbid waters using MERIS measurements
A new empirical index, termed the normalized suspended sediment index NSSI, is proposed to predict total suspended sediment TSS concentrations in inland turbid waters using Medium Resolution Imaging Spectrometer MERIS full-resolution FR 300 m data. The ...
Comments