IEEE Access · 2019 · 117 citations · 22 references
ComputingComputer ScienceEnvironmental EngineeringAir PollutionForecastingInternet Of ThingsAir QualityLong-term MemoryNeural NetworksTime Series ForecastingTime Series ModelingTime Series PredictionAir Pollution ForecastingGated Recurrent Unit NetworksLong Short-term Memory NetworksNeural ForecastingPm2.5PredictionPrediction ModelsRecurrent Neural Networks
With the continuous development of the Chinese economy and the gradual acceleration of urbanization, it has caused tremendous damage to the environment. The bad air environment seriously damages the physical and mental health of the people. The change in smog concentration will be affected by many realistic factors and exhibit nonlinear characteristics. The method proposed in this paper is to use the Internet of Things (IoT) technology to monitor the acquired data, process the data, and predict the next data using a neural network. The existing prediction models have limitations. They don't accurately capture the law between the concentration of haze and the factors affecting reality. It is difficult to accurately predict the nonlinear smog data. One algorithm proposed in this paper is a two-layer model prediction algorithm based on Long Short Term Memory Neural Network and Gated Recurrent Unit (LSTM&GRU). We set a double-layer Recurrent Neural Network to predict the PM2.5 value. This model is an improvement and enhancement of the existing prediction method Long Short Term Memory (LSTM). The experiment integrates data monitored by the IoT node and information released by the national environmental protection department. First, the data of 96 consecutive hours in four cities were selected as the experimental samples. The experimental results are close to the true value. Then, we selected daily smog data from 2014/1/1 to 2018/1/1 as a train and test dataset. It contains smog data for 74 city sites. The first 70% of the data was used for training and the rest for testing. The results of this experiment show that our model can play a better prediction.
22
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Learning to Forget: Continual Prediction with LSTM
Felix A. Gers, Jürgen Schmidhuber, Fred Cummins · Neural Computation · 2000 · 5.4K citations
LSTM Fully Convolutional Networks for Time Series Classification
Fazle Karim, Somshubra Majumdar, Houshang Darabi et al. · IEEE Access · 2017 · 1.4K citations · Full text