![Sample our Economics, Finance,Business & Industry journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5931/TOC-Subject-Sample-2021-Economics-Finance-Business-Industry.jpg"})
ABSTRACT
Forecasting of air quality is an emerging process to evade the entailment of several defects for human as well as environmental resources. Because of the poor quality of air substances, air pollution occurs. Living beings and other economic resources get affected by this polluted air very frequently. Therefore, air quality prediction is a trendsetting method to maintain a healthy life and infrastructure. Though multiple existing models are implemented, managing high-level data and deploying such standard models become cumbersome. Rather than indoor air quality, the ambient (outdoor) air quality should require the prediction process as it exists in the open environment. Thus, an intelligent ambient air quality prediction model is needed, which is designed in this paper by adopting a heuristic-aided deep learning model. The original air data is initially fetched from the three diverse data sources. It is followed by the data pre-processing stage with standard techniques. Subsequently, the resultant data is given to Adaptive Serial Cascaded Autoencoder and Long Short-Term Memory (LSTM) with Multivariate Regression (ASCA-LSMR), in which some of the hyper-parameters are tuned by proposing the novel algorithm as Fitness-based Improved Flow Direction Algorithm (FIFDA) to produce the better prediction results. Finally, experimental results indicate that our method enables more accurate predictions than all the listed traditional models and performs better in predictive performance. The RMSE of the designed FIFDA-ASCA-LSMR method attains 31.9%, 33.5%, 6.66%, and 23.7% elevated than SSA-ASCA-LSMR, DHOA-ASCA-LSMR, EHO-ASCA-LSMR, and FDA-ASCA-LSMR, for dataset 2. Thus, the designed ambient air quality prediction model reveals better performance than the other baseline approaches.
Nomenclature
| Abbreviations | = | Description |
| ASCA-LSMR | = | Adaptive Serial Cascaded Autoencoder and Long Short-Term Memory |
| FIFDA | = | Fitness-based Improved Flow Direction Algorithm |
| AQI | = | Air Quality Index |
| MLR | = | Multiple Linear Regression |
| ANN | = | Artificial Neural Network |
| SVM | = | Support Vector Machine |
| BPNN | = | Back Propagation Neural Network |
| CNN | = | Convolutional Neural Network |
| GRU | = | Gated Recurrent Unit |
| SHAP | = | SHapley Additive exPlanation |
| PSO | = | Particle Swarm Optimization |
| XGBoosting | = | eXtreme Gradient Boosting |
| ST-DMTL | = | Spatial – Temporal Deep Multitask Learning |
| RNN | = | Recurrent Neural Network |
| TCN | = | Temporal Convolutional Network |
| GWO | = | Grey Wolf Optimization |
| DNN | = | Deep Neural Network |
| MO-GWO | = | Multi-Objective-Grey Wolf Optimization |
| OGD | = | Open Government Data |
| ARIMA | = | Auto-Regressive Integrated Moving Average |
| SVR | = | Support Vector Regression |
| RBF | = | Radial Basis Function |
| DBN | = | Deep Belief Network |
| MEP | = | Mean Percentage Error |
| MASE | = | Mean Absolute Scaled Error |
| SMAPE | = | Symmetric Mean Absolute Percentage Error |
| MAE | = | Mean Absolute Error |
| RMSE | = | Root Mean Square Error |
| RSA | = | Reptile Search Algorithm |
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
Munirathnam Lakshmipathy
Munirathnam Lakshmipathy completed B.Tech in E.C.E from Sree Vidhyanikethan College of Engineering, A Rangampet, Chittoor(District), Andhra pradesh. He received M.Tech(Electronic Design & Technology) from National Institute of Technology, Calicut. He worked as an Assistant Professor in the Dept. of ECE, Gokula Krishna College of Engineering, Sullurpeta, Nellore (District) from 2007 to 2009. In 2009 joined Kuppam Engineering College, Kuppam as an Assistant Professor in the Dept. of ECE. Currently working as an Associate professor in Kuppam Engineering College, Kuppam. His areas of interest are Embedded Systems, Wireless networks, Analog Circuit Design and Artificial Intelligence. He is a Lifetime member of ISTE and ISRD Professional bodies.
Shanthi Prasad Mysore Jeevandharakumar
Shanthi Prasad Mysore Jeevandharakumar completed B.E in E.C.E from the National Institute of Engineering, Mysore, M.Tech (Industrial Electronics) from NIT, Surathkal, Karnataka, and Ph.D from Arizona State University, Phoenix. He has teaching experience of more than 46 years. He also presented various academic as well as research-based papers at several national and international conferences. He has guided several Ph.D/PG/UG projects and acted as coordinator for several AICTE projects. He held several managerial positions in reputed engineering colleges. His areas of interest include VLSI design, Embedded systems and Wireless networks. He is a senior IEEE member.
Goddamachinnehalli Narayanappa Kodandaramaiah
Goddamachinnehalli Narayanappa Kodandaramaiah completed B.E in E.C.E from the National Institute of Engineering, Mysore, M.Tech (Industrial Electronics) from NIT, Surathkal, Karnataka, and Ph.D from Arizona State University, Phoenix. He has teaching experience of more than 46 years. He also presented various academic as well as research-based papers at several national and international conferences. He has guided several Ph.D/PG/UG projects and acted as coordinator for several AICTE projects. He held several managerial positions in reputed engineering colleges. His areas of interest include VLSI design, Embedded systems and Wireless networks. He is a senior IEEE member.