Advanced E-Waste Management Solutions using A-BiCNN-RNN Model to Tackle Modern Challenges

As a term, “e-waste” refers to the trash produced by the disposal of electronic devices such as old phones, computers, and televisions. As far as waste management problems go, online trash is quickly becoming one of the biggest ones. The concerning increase of electronic garbage is due to numerous causes. Included in this category are developments in technology, the frequency with which products break, shifts in customer taste, and the use of intentional obsolescence in product design to increase profits through increased product turnover. The rapid increase in worldwide e-waste output is a major threat to both the environment and human health, making efficient e-waste treatment a critical need. However, low recycling rates and large yearly e-waste production make effective management of discarded electronics a major challenge in developing nations. Preprocessing, feature selection, and training the model are the three stages that make up the process. Reverse filling is a preprocessing technique that is used to find and remove empty cells. One popular method for extracting features is Linear Discriminant Analysis, or LDA. The A-BiCNN-RNN was utilized for the model’s training. Compared to Attention models and RNNs, the proposed technique achieves a higher average accuracy of $\mathbf{9 3. 4 7 \%}$.