A deep learning approach for prediction of air quality index in a metropolitan city

Janarthanan, R.; Somasundaram, K.; Elamparithi, P. Navin

doi:10.1016/j.scs.2021.102720

Cited by 135 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to such a unique trait, LSTM is suitable for processing and predicting important events with very long intervals and delays in the time series. LSTM has been successfully applied to the prediction of air quality. − Forest fire data, air emissions, meteorological data, and sea ice coverage were used as input features of the LSMT model, while the historical PAH pollution data in the past 7 years (1996–2021) was learned to predict the PAH concentration in the near future (2012–2014) in the high Arctic. In comparison with the previously constructed atmospheric transport model, the obtained LSTM model has significantly improved the phenanthrene (PHE) and benzo[ a ]pyrene (B a P) predictions by 62.5% and 91.1%, respectively .…”

Section: Selelcted Applicatons Of Machine Learning In Environmental P...mentioning

confidence: 99%

Data-Driven Machine Learning in Environmental Pollution: Gains and Problems

Liu

Lü

Zhang

et al. 2022

Environ. Sci. Technol.

228

View full text Add to dashboard Cite

The complexity and dynamics of the environment make it extremely difficult to directly predict and trace the temporal and spatial changes in pollution. In the past decade, the unprecedented accumulation of data, the development of high-performance computing power, and the rise of diverse machine learning (ML) methods provide new opportunities for environmental pollution research. The ML methodology has been used in satellite data processing to obtain ground-level concentrations of atmospheric pollutants, pollution source apportionment, and spatial distribution modeling of water pollutants. However, unlike the active practices of ML in chemical toxicity prediction, advanced algorithms such as deep neural networks in environmental process studies of pollutants are still deficient. In addition, over 40% of the environmental applications of ML go to air pollution, and its application range and acceptance in other aspects of environmental science remain to be increased. The use of ML methods to revolutionize environmental science and its problem-solving scenarios has its own challenges. Several issues should be taken into consideration, such as the tradeoff between model performance and interpretability, prerequisites of the machine learning model, model selection, and data sharing.

show abstract

Section: Selelcted Applicatons Of Machine Learning In Environmental P...mentioning

confidence: 99%

Data-Driven Machine Learning in Environmental Pollution: Gains and Problems

Liu

Lü

Zhang

et al. 2022

Environ. Sci. Technol.

228

View full text Add to dashboard Cite

show abstract

“…[13] This instructed, associate degree innovative, unsupervised Deep learning motor-assisted reconstructed software engineer (UDR-RC) that optimize the info throughout pre-processing at on-nodule wearable sensors to induce reduced computation time. [14] Implementation of machine-learning-based patient processing is influenced by heterogeneous patient knowledge and inefficient in analysing feature-learning ways. [15] This works transform such every which way ordered forward/backward firing sequence of transitions within the network into a set topological order of transition-firing in forward direction solely by exchange backward firing transitions into equivalent forward firing transitions.…”

Section: Related Workmentioning

confidence: 99%

Early Strokes Detection of Patient and Health Monitoring System Based On Data Analytics Using K-Means Algorithm

Menaka¹,

Bharathiraja²,

Alekhya³

et al. 2021

Proceedings of the First International Conference on Computing, Communication and Control System, I3CAC 2021, 7-8 June 2021, Bh

View full text Add to dashboard Cite

The processing chain of scientific information in particular consists of information series, information storage, data sharing, and records evaluation. In the prevailing device, there is lots of improvisation wished for our health care device. The existing technique our affected person monitoring is a guide and time-consuming process. To conquer the task the proposed work proposed actual data series from sensors, IoT-primarily based totally sharing, and information analytics. This proposed device gives the gain for the respective medical doctor to display the affected person's health 24*7 regardless of geographical location. Example: The medical doctor can display the affected person's health even after the affected person receives discharged. This proposed work implies a health sensor named heartbeat sensor to display affected person fitness. The affected person information is monitoring through the sensorsand transmitted to the Arduino. The actual-time statistics from the COM port have acquired the usage of Net beans and stored in an SQL database. The actual-time information may be monitored with the aid of using each affected person and medical doctor. The real-time statistics are processed from Net beans as datasheet to R programming for statistical evaluation. For Clustering, we use the K-Means algorithm and for Classification, we use the Support Vector Machine. Also relying on the affected person's health situations emergency pills or injections are counseled routinely with the aid of using our device. Also, the affected person statistics have encrypted the usage of an ABE (Attribute-based Encryption) set of rules and saved in the public cloud particularly Dropbox. Thus invoking the statistics evaluation approach facilitates in identifying early stroke in the sufferers and offer medicinal diagnosis immediately.

show abstract

“…Machine learning has been used to solve the prediction and classification problems. For example, Support Vector Regression (SVR) and Long Short-Term Memory (LSTM) based deep learning model were combined to establish the deep learning method for predicting the AQI values accurately, which helped to plan the metropolitan city for sustainable development 21 . And LSTM Recurrent Neural Network was also utilized to preform the stock market prediction 22 .…”

Section: Introductionmentioning

confidence: 99%

The improved grasshopper optimization algorithm and its applications

Qin

Yang

2021

Sci Rep

View full text Add to dashboard Cite

Grasshopper optimization algorithm (GOA) proposed in 2017 mimics the behavior of grasshopper swarms in nature for solving optimization problems. In the basic GOA, the influence of the gravity force on the updated position of every grasshopper is not considered, which possibly causes GOA to have the slower convergence speed. Based on this, the improved GOA (IGOA) is obtained by the two updated ways of the position of every grasshopper in this paper. One is that the gravity force is introduced into the updated position of every grasshopper in the basic GOA. And the other is that the velocity is introduced into the updated position of every grasshopper and the new position are obtained from the sum of the current position and the velocity. Then every grasshopper adopts its suitable way of the updated position on the basis of the probability. Finally, IGOA is firstly performed on the 23 classical benchmark functions and then is combined with BP neural network to establish the predicted model IGOA-BPNN by optimizing the parameters of BP neural network for predicting the closing prices of the Shanghai Stock Exchange Index and the air quality index (AQI) of Taiyuan, Shanxi Province. The experimental results show that IGOA is superior to the compared algorithms in term of the average values and the predicted model IGOA-BPNN has the minimal predicted errors. Therefore, the proposed IGOA is an effective and efficient algorithm for optimization.

show abstract

A deep learning approach for prediction of air quality index in a metropolitan city

Cited by 135 publications

References 24 publications

Data-Driven Machine Learning in Environmental Pollution: Gains and Problems

Data-Driven Machine Learning in Environmental Pollution: Gains and Problems

Early Strokes Detection of Patient and Health Monitoring System Based On Data Analytics Using K-Means Algorithm

The improved grasshopper optimization algorithm and its applications

Contact Info

Product

Resources

About