A Secure and Energy-efficient Framework for Air Quality Prediction Using Smart Sensors and ISHO-DCNN

Abstract

Background: The World Health Organization (WHO) reported that Air pollution (AP) is prone to the highest environmental risk and has caused numerous deaths. Polluted air has many constituents where Particulate Matter (PM) is majorly reported as a global concern. Currently, the most crucial challenges faced by the globe are the identification and treatment of augmenting AP. The air pollution level was indicated by the Air Quality Index (AQI). It is affected by the concentrations of several pollutants in the air. Many pollutants in the air are harmful to human health. Thus, an efficient prediction system is required. Many security problems and lower classification accuracy are faced by them even though several prediction systems have been formed. A secure air quality prediction system (AQPS) centered upon the energy efficiency of smart sensing is proposed in this paper to overcome these issues. From disparate sensor nodes, the input data is initially amassed in the proposed work. The gathered data is stored in the temporary server. Next, the air-polluted data of the temporary server is offered to the AQPS, wherein preprocessing of the input data along with classification is executed. Methods: Utilizing the Improved Spotted Hyena Optimization-based Deep Convolution Neural Network (ISHO-DCNN) algorithm, the classification is executed. Utilizing the Repetitive Data Coding Based Huffman Encoding (RDC-HE) method, the polluted data attained from the classified output is compressed and encrypted by employing the American Standard Code for Information Interchange based Elliptical Curve Cryptography (ASCII-ECC) method. Results: Afterward, the encrypted and compressed data is saved in the Cloud Server (CS). Finally, for notifying about the AP, the decrypted and decompressed data is offered to the Base Stations (BS). Conclusion: The proposed work is more effective when analogized to the prevailing methods as denoted by the experimental outcomes. Higher accuracy of 97.14% and precision of 91.44% were obtained by the proposed model. Further, lower Encryption Time (ET) and Decryption Time (DT) of 0.565584 sec and 0.005137 sec were obtained by the model.