Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Air Quality Prediction Using the Fractional Gradient-Based Recurrent Neural Network

View through CrossRef
In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN). AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air. Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution. Also, the current air quality is dependent on the climate conditions and industrialization in that area. Thus, the AQI is history-dependent. To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo’s derivative has been used in the backpropagation algorithm for training of the RNN. Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction. But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives. The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy. It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).
Title: Air Quality Prediction Using the Fractional Gradient-Based Recurrent Neural Network
Description:
In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN).
AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air.
Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution.
Also, the current air quality is dependent on the climate conditions and industrialization in that area.
Thus, the AQI is history-dependent.
To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo’s derivative has been used in the backpropagation algorithm for training of the RNN.
Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction.
But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives.
The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy.
It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).

Related Results

Solving Undamped and Damped Fractional Oscillators via Integral Rohit Transform
Solving Undamped and Damped Fractional Oscillators via Integral Rohit Transform
Background: The dynamics of fractional oscillators are generally described by fractional differential equations, which include the fractional derivative of the Caputo or Riemann-Li...
On α-Fractional Bregman Divergence to study α-Fractional Minty’s Lemma
On α-Fractional Bregman Divergence to study α-Fractional Minty’s Lemma
In this paper fractional variational inequality problems (FVIP) and dual fractional variational inequality problems (DFVIP), Fractional minimization problems are defined with the h...
Removal of toxic vapors by oxidation: Development of laboratory test procedures for in-duct air cleaning systems
Removal of toxic vapors by oxidation: Development of laboratory test procedures for in-duct air cleaning systems
Exposure to volatile organic compounds (VOC) in workplaces can cause acute effects such as irritation of the skin, the eyes, the mouth, and the nose. Some products may also cause c...
Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning
Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning
Abstract In arid areas, estimation of crop water demand through potential evapotranspiration (PET) forecast has a guiding effect on water-saving irrigation, to cope with th...
Air convection in coarse blocky permafrost : a numerical modelling approach to improve the understanding of the ground thermal regime
Air convection in coarse blocky permafrost : a numerical modelling approach to improve the understanding of the ground thermal regime
Permafrost is a thermal phenomenon, defined as subsurface material with a temperature remaining below 0°C for at least two consecutive years. Permafrost occurs at high latitudes an...
On Λ-Fractional fluid mechanics
On Λ-Fractional fluid mechanics
Λ-fractional analysis has already been presented as the only fractional analysis conforming with the Differential Topology prerequisites. That is, the Leibniz rule and chain rule d...
Study of Honeycomb Air Curtain for a Freezer Room to Enhance Protection against Warm Air Infiltration
Study of Honeycomb Air Curtain for a Freezer Room to Enhance Protection against Warm Air Infiltration
The objective of this research is to present the energy-saving effect of applying an air curtain to prevent the penetration of warm air through a freezer door. Retail business is h...

Back to Top