scholarly journals Air Quality Forecasting with Hybrid LSTM and Extended Stationary Wavelet Transform

2021 ◽  
Author(s):  
Yongkang Zeng ◽  
Xiang Ma ◽  
Ning Jin ◽  
Xiaokang Zhou ◽  
Ke Yan
Keyword(s):  
Wavelet Transform ◽  
Air Quality ◽  
Prediction Models ◽  
Short Term Memory ◽  
Weather Conditions ◽  
Training Data ◽  
Sensor Data ◽  
Stationary Wavelet Transform ◽  
Real World Data ◽  
Air Quality Forecasting

Abstract Artificial intelligence (AI) technology-enhanced air quality forecasting is one of the most promising directions in the field of smart environment development. Despite recent advances in this area, two difficulties remain unsolved. First, multiple factors influence forecasting results, such as weather conditions, fuel usage and traffic conditions. These factors are usually unavailable in air quality sensor data. Second, traditional predicting models typically use the most recent training data, which neglects the historical data. In this study, we propose a hybrid deep learning model that embraces the merits of the stationary wavelet transform (SWT) and the nested long short term memory networks (NLSTM) to improve the prediction quality in the problem of hour-ahead air quality forecasting. The proposed method decomposes the original PM2.5 data into several more stationary sub-signals with different resolutions using an extended SWT algorithm. A framework that leverages several NLSTM recurrent neural networks is constructed to output forecasting results for different sub-signals, respectively. The final forecasting result is obtained by combining all sub-signal forecasting results using the inverse wavelet transform. Experiments on real-world data show that, accuracy-wise, our proposed method outperforms most of the existing prediction models in the literature. And the resulting forecasting curves of the proposed method are much closer to the real values without any lags, comparing with existing prediction models.

scholarly journals Development of a deep neural network for predicting 6-hour average PM<sub>2.5</sub> concentrations up to two subsequent days using various training data

2021 ◽  
Author(s):  
Jeong-Beom Lee ◽  
Jae-Bum Lee ◽  
Youn-Seo Koo ◽  
Hee-Yong Kwon ◽  
Min-Hyeok Choi ◽  
...  
Keyword(s):  
Neural Network ◽  
Air Quality ◽  
Deep Neural Network ◽  
Model Performance ◽  
Prediction Performance ◽  
Training Data ◽  
Forecasting Model ◽  
Observation Data ◽  
Forecast Data ◽  
Air Quality Forecasting

Abstract. This study aims to develop a deep neural network (DNN) model as an artificial neural network (ANN) for the prediction of 6-hour average fine particulate matter (PM2.5) concentrations for a three-day period—the day of prediction (D+0), one day after prediction (D+1) and two days after prediction (D+2)—using observation data and forecast data obtained via numerical models. The performance of the DNN model was comparatively evaluated against that of the currently operational Community Multiscale Air Quality (CMAQ) modelling system for air quality forecasting in South Korea. In addition, the effect on predictive performance of the DNN model on using different training data was analyzed. For the D+0 forecast, the DNN model performance was superior to that of the CMAQ model, and there was no significant dependence on the training data. For the D+1 and D+2 forecasts, the DNN model that used the observation and forecast data (DNN-ALL) outperformed the CMAQ model. The root-mean-squared error (RMSE) of DNN-ALL was lower than that of the CMAQ model by 2.2 μgm−3, and 3.0 μgm−3 for the D+1 and D+2 forecasts, respectively, because the overprediction of higher concentrations was curtailed. An IOA increase of 0.46 for D+1 prediction and 0.59 for the D+2 prediction was observed in case of the DNN-ALL model compared to the IOA of the DNN model that used only observation data (DNN-OBS). In additionally, An RMSE decrease of 7.2 μgm−3 for the D+1 prediction and 6.3 μgm−3 for the D+2 prediction was observed in case of the DNN-ALL model, compared to the RMSE of DNN-OBS, indicating that the inclusion of forecast data in the training data greatly affected the DNN model performance. Considering the prediction of the 6-hour average PM2.5 concentration, the 8.8 μgm−3 RMSE of the DNN-ALL model was 2.7 μgm−3 lower than that of the CMAQ model, indicating the superior prediction performance of the former. These results suggest that the DNN model could be utilized as a better-performing air quality forecasting model than the CMAQ, and that observation data plays an important role in determining the prediction performance of the DNN model for D+0 forecasting, while prediction data does the same for D+1 and D+2 forecasting. The use of the proposed DNN model as a forecasting model may result in a reduction in the economic losses caused by pollution-mitigation policies and aid better protection of public health.

scholarly journals COLLAPSE WARNING SYSTEM USING LSTM NEURAL NETWORKS FOR CONSTRUCTION DISASTER PREVENTION IN EXTREME WIND WEATHER

2021 ◽  
Vol 27 (4) ◽  
pp. 230-245
Author(s):  
Chih-Chiang Wei
Keyword(s):  
Neural Networks ◽  
Prediction Models ◽  
Short Term Memory ◽  
Meteorological Data ◽  
Warning System ◽  
Weather Conditions ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Strong Wind ◽  
Wind Force

Strong wind during extreme weather conditions (e.g., strong winds during typhoons) is one of the natural factors that cause the collapse of frame-type scaffolds used in façade work. This study developed an alert system for use in determining whether the scaffold structure could withstand the stress of the wind force. Conceptually, the scaffolds collapsed by the warning system developed in the study contains three modules. The first module involves the establishment of wind velocity prediction models. This study employed various deep learning and machine learning techniques, namely deep neural networks, long short-term memory neural networks, support vector regressions, random forest, and k-nearest neighbors. Then, the second module contains the analysis of wind force on the scaffolds. The third module involves the development of the scaffold collapse evaluation approach. The study area was Taichung City, Taiwan. This study collected meteorological data from the ground stations from 2012 to 2019. Results revealed that the system successfully predicted the possible collapse time for scaffolds within 1 to 6 h, and effectively issued a warning time. Overall, the warning system can provide practical warning information related to the destruction of scaffolds to construction teams in need of the information to reduce the damage risk.

scholarly journals Fall detection system based on BiLSTM neural network

2019 ◽  
Vol 7 (5) ◽  
pp. 01-12
Author(s):  
Biao YE ◽  
Lasheng Yu
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Detection System ◽  
Input Sequence ◽  
Fall Detection ◽  
Detection Algorithm ◽  
Training Data ◽  
Sensor Data ◽  
Data Set ◽  
Sequence Modeling

The purpose of this article is to analyze the characteristics of human fall behavior to design a fall detection system. The existing fall detection algorithms have problems such as poor adaptability, single function and difficulty in processing large data and strong randomness. Therefore, a long-term and short-term memory recurrent neural network is used to improve the effect of falling behavior detection by exploring the internal correlation between sensor data. Firstly, the serialization representation method of sensor data, training data and detection input data is designed. The BiLSTM network has the characteristics of strong ability to sequence modeling and it is used to reduce the dimension of the data required by the fall detection model. then, the BiLSTM training algorithm for fall detection and the BiLSTM-based fall detection algorithm convert the fall detection into the classification problem of the input sequence; finally, the BiLSTM-based fall detection system was implemented on the TensorFlow platform. The detection and analysis of system were carried out using a bionic experiment data set which mimics a fall. The experimental results verify that the system can effectively improve the accuracy of fall detection to 90.47%. At the same time, it can effectively detect the behavior of Near-falling, and help to take corresponding protective measures.

scholarly journals Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1064
Author(s):  
I Nyoman Kusuma Wardana ◽  
Julian W. Gardner ◽  
Suhaib A. Fahmy
Keyword(s):  
Deep Learning ◽  
Air Quality ◽  
Short Term Memory ◽  
Model Performance ◽  
Learning Model ◽  
Sensor Data ◽  
Raspberry Pi ◽  
Learning Models ◽  
Proposed Model ◽  
Deep Learning Model

Accurate air quality monitoring requires processing of multi-dimensional, multi-location sensor data, which has previously been considered in centralised machine learning models. These are often unsuitable for resource-constrained edge devices. In this article, we address this challenge by: (1) designing a novel hybrid deep learning model for hourly PM2.5 pollutant prediction; (2) optimising the obtained model for edge devices; and (3) examining model performance running on the edge devices in terms of both accuracy and latency. The hybrid deep learning model in this work comprises a 1D Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to predict hourly PM2.5 concentration. The results show that our proposed model outperforms other deep learning models, evaluated by calculating RMSE and MAE errors. The proposed model was optimised for edge devices, the Raspberry Pi 3 Model B+ (RPi3B+) and Raspberry Pi 4 Model B (RPi4B). This optimised model reduced file size to a quarter of the original, with further size reduction achieved by implementing different post-training quantisation. In total, 8272 hourly samples were continuously fed to the edge device, with the RPi4B executing the model twice as fast as the RPi3B+ in all quantisation modes. Full-integer quantisation produced the lowest execution time, with latencies of 2.19 s and 4.73 s for RPi4B and RPi3B+, respectively.

scholarly journals Improving the Accuracy of Dam Inflow Predictions Using a Long Short-Term Memory Network Coupled with Wavelet Transform and Predictor Selection

Mathematics ◽  
2021 ◽  
Vol 9 (5) ◽  
pp. 551
Author(s):  
Trung Duc Tran ◽  
Vinh Ngoc Tran ◽  
Jongho Kim
Keyword(s):  
Wavelet Transform ◽  
Prediction Models ◽  
Short Term Memory ◽  
Random Search ◽  
Data Driven ◽  
Time Lags ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Dam Inflow

Accurate and reliable dam inflow prediction models are essential for effective reservoir operation and management. This study presents a data-driven model that couples a long short-term memory (LSTM) network with robust input predictor selection, input reconstruction by wavelet transformation, and efficient hyper-parameter optimization by K-fold cross-validation and the random search. First, a robust analysis using a “correlation threshold” for partial autocorrelation and cross-correlation functions is proposed, and only variables greater than this threshold are selected as input predictors and their time lags. This analysis indicates that a model trained on a threshold of 0.4 returns the highest Nash–Sutcliffe efficiency value; as a result, six principal inputs are selected. Second, using additional subseries reconstructed by the wavelet transform improves predictability, particularly for flow peak. The peak error values of LSTM with the transform are approximately one-half to one-quarter the size of those without the transform. Third, for a K of 5 as determined by the Silhouette coefficients and the distortion score, the wavelet-transformed LSTMs require a larger number of hidden units, epochs, dropout, and batch size. This complex configuration is needed because the amount of inputs used by these LSTMs is five times greater than that of other models. Last, an evaluation of accuracy performance reveals that the model proposed in this study, called SWLSTM, provides superior predictions of the daily inflow of the Hwacheon dam in South Korea compared with three other LSTM models by 84%, 78%, and 65%. These results strengthen the potential of data-driven models for efficient and effective reservoir inflow predictions, and should help policy-makers and operators better manage their reservoir operations.

scholarly journals Air Quality Prediction Model Based on Spatiotemporal Data Analysis and Metalearning

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Kejia Zhang ◽  
Xu Zhang ◽  
Hongtao Song ◽  
Haiwei Pan ◽  
Bangju Wang
Keyword(s):  
Air Quality ◽  
Prediction Model ◽  
Local Governments ◽  
Short Term Memory ◽  
Temporal Correlation ◽  
Environmental Data ◽  
Training Data ◽  
Public Data ◽  
Monitoring Stations

With the continuous improvement of people’s quality of life, air quality issues have become one of the topics of daily concern. How to achieve accurate predictions of air quality in a variety of complex situations is the key to the rapid response of local governments. This paper studies two problems: (1) how to predict the air quality of any monitoring station based on the existing weather and environmental data while considering the spatiotemporal correlation among monitoring stations and (2) how to maintain the accuracy and stability of the forecast even when the available data is severely insufficient. A prediction model combining Long Short-Term Memory networks (LSTM) and Graph Attention (GAT) mechanism is proposed to solve the first problems. A metalearning algorithm for the prediction model is proposed to solve the second problem. LSTM is used to characterize the temporal correlation of historical data and GAT is used to characterize the spatial correlation among all the monitoring stations in the target city. In the case of insufficient training data, the proposed metalearning algorithm can be used to transfer knowledge from other cities with abundant training data. Through testing on public data sets, the proposed model has obvious advantages in accuracy compared with baseline models. Combining with the metalearning algorithm, it gives a much better performance in the case of insufficient training data.

scholarly journals Incorporation of Shipping Activity Data in Recurrent Neural Networks and Long Short-Term Memory Models to Improve Air Quality Predictions around Busan Port

Atmosphere ◽  
2021 ◽  
Vol 12 (9) ◽  
pp. 1172
Author(s):  
Hyunsu Hong ◽  
Hyungjin Jeon ◽  
Cheong Youn ◽  
Hyeon-Soo Kim
Keyword(s):  
Air Pollution ◽  
Air Quality ◽  
Prediction Models ◽  
Short Term Memory ◽  
Air Pollutant ◽  
Short Term ◽  
Activity Data ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Mean Square Errors

Air pollution sources and the hazards of high particulate matter 2.5 (PM2.5) concentrations among air pollutants have been well documented. Shipping emissions have been identified as a source of air pollution; therefore, it is necessary to predict air pollutant concentrations to manage seaport air quality. However, air pollution prediction models rarely consider shipping emissions. Here, the PM2.5 concentrations of the Busan North and Busan New Ports were predicted using a recurrent neural network and long short-term memory model by employing the shipping activity data of Busan Port. In contrast to previous studies that employed only air quality and meteorological data as input data, our model considered shipping activity data as an emission source. The model was trained from 1 January 2019 to 31 January 2020 and predictions and verifications were performed from 1–28 February 2020. Verifications revealed an index of agreements (IOA) of 0.975 and 0.970 and root mean square errors of 4.88 and 5.87 µg/m3 for Busan North Port and Busan New Port, respectively. Regarding the results based on the activity data, a previous study reported an IOA of 0.62–0.84, with a higher predictive power of 0.970–0.975. Thus, the extended approach offers a useful strategy to prevent PM2.5 air pollutant-induced damage in seaports.

scholarly journals Stationary Wavelet Transform based Radiometric Error Correction Technique for NOAA-AVHRR sensor data

2018 ◽  
Vol 7 (2.15) ◽  
pp. 177 ◽  
Author(s):  
V Raja Rajeswari ◽  
S Narayana Reddy ◽  
P Jagadamba
Keyword(s):  
Remote Sensing ◽  
Wavelet Transform ◽  
Median Filter ◽  
Similarity Index ◽  
Structural Similarity ◽  
Sensor Data ◽  
Discrete Wavelet ◽  
Stationary Wavelet Transform ◽  
Noaa Avhrr ◽  
Correction Technique

Due to the inaccuracy of the sensing devices remote sensing images contain radiometric errors, which can be severe in many cases. Therefore, the preprocessing is an inevitable step in the remote sensing image analysis. This paper presents radiometric errors and evaluates methodologies to retrieve information contained in images by means of filtering in the spatial domain and wavelet domain. Among those, the wavelet techniques are more effective to reduce noise because of their ability to capture the energy of a signal in fewer wavelet coefficients. In this study, Stationary Wavelet Transform (SWT) method and its application to NOAA -18, 19AVHRR/3 channel 3 and channel 4 images to correct radiometric error is presented. Qualitative and quantitative analysis was carried to evaluate the performance of SWT method, both by measuring the Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM), mean value, standard deviation and by visual inspection. The SWT based method can remove radiometric error effectively and preserves radiometric information to a desirable amount. From the results, SWT based method is better in smoothness and accuracy than the conventional mean filter, median filter and Discrete Wavelet Transform (DWT) based method  

scholarly journals Machine Learning-Based Vehicle Trajectory Prediction Using V2V Communications and On-Board Sensors

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 420
Author(s):  
Dongho Choi ◽  
Janghyuk Yim ◽  
Minjin Baek ◽  
Sangsun Lee
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Short Term Memory ◽  
Prediction Method ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Trajectory Prediction ◽  
Target Vehicle ◽  
Decoder Architecture ◽  
V2v Communications

Predicting the trajectories of surrounding vehicles is important to avoid or mitigate collision with traffic participants. However, due to limited past information and the uncertainty in future driving maneuvers, trajectory prediction is a challenging task. Recently, trajectory prediction models using machine learning algorithms have been addressed solve to this problem. In this paper, we present a trajectory prediction method based on the random forest (RF) algorithm and the long short term memory (LSTM) encoder-decoder architecture. An occupancy grid map is first defined for the region surrounding the target vehicle, and then the row and the column that will be occupied by the target vehicle at future time steps are determined using the RF algorithm and the LSTM encoder-decoder architecture, respectively. For the collection of training data, the test vehicle was equipped with a camera and LIDAR sensors along with vehicular wireless communication devices, and the experiments were conducted under various driving scenarios. The vehicle test results demonstrate that the proposed method provides more robust trajectory prediction compared with existing trajectory prediction methods.

Sign in / Sign up

Export Citation Format

Share Document