| Title |
Enhancing Smart City And Iot Solutions With Deep Residual Bi-Lstm Model |
| ID_Doc |
23950 |
| Authors |
Madumidha S.; Chander Rao S.P.; Yadav S.; Hashmi S.G.; Ahmad J.; Syed Z. |
| Year |
2023 |
| Published |
International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023 - Proceedings |
| DOI |
http://dx.doi.org/10.1109/ICSSAS57918.2023.10331792 |
| Abstract |
There is a limitless supply of useful information and services made available by IoT devices connected to the internet. The Internet of Things (IoT) refers to the vast network of interconnected devices seen in a smart city. The scattered and dynamic natures of entities such as sensing, actuating devices, humans, and computing resources make it challenging to design applications in such large-scale IoT systems, despite the promise nature of the new breed of data and resources. In this research study, the proposed approach takes a coordinated look at the process of creating Internet of Things apps for use in Smart Cities. The proposed approach demonstrates the need for a distributed coordination model capable of monitoring such a vast number of independently operating parts while constructing Smart City IoT applications. Preprocessing, feature selection, and model performance evaluation are all used in the suggested method. Normalization and standardization are used during preprocessing. It uses entropy HOA for feature selection. The model's effectiveness is measured with Deep Residual Bi-LSTM. When compared to BiLSTM and Residual LSTM, two existing approaches, the suggested methodology performs admirably. © 2023 IEEE. |
| Author Keywords |
Bidirectional Long Short-Term Memory (Bi-LSTM); Internet of Things (IOT); Normalization; Smart City (SC); Standardization |
