Taylor-student psychology based optimization integrated deep learning in IoT application for plant disease classification

Vimala, S.; Rao, T. V. Madhusudhana; Balaji, A.; Maram, Balajee

doi:10.1007/s11276-022-03150-2

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The components from the e-waste product have been separated based on the classification. The automated machine learning-based category advisor can be capable of the classification of the components (Vimala et al 2022;Thakur et al 2022;Dubey et al 2021). The components are then filtered and the IoT devices will accept the filtered component and provide a name and send an alert message to the server.…”

Section: Role Of Machine Intelligence Techniques In E-waste Managementmentioning

confidence: 99%

Concepts of circular economy for sustainable management of electronic wastes: challenges and management options

Srivastav

Markandeya

Patel

et al. 2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

The electronic and electrical industrial sector is exponentially growing throughout the globe, and sometimes, these wastes are being disposed of and discarded with a faster rate in comparison to the past era due to technology advancements. As the application of electronic devices is increasing due to the digitalization of the world (IT sector, medical, domestic, etc.), a heap of discarded e-waste is also being generated. Per-capita e-waste generation is very high in developed countries as compared to developing countries. Expansion of the global population and advancement of technologies are mainly responsible to increase the e-waste volume in our surroundings. E-waste is responsible for environmental threats as it may contain dangerous and toxic substances like metals which may have harmful effects on the biodiversity and environment. Furthermore, the life span and types of e-waste determine their harmful effects on nature, and unscientific practices of their disposal may elevate the level of threats as observed in most developing countries like India, Nigeria, Pakistan, and China. In the present review paper, many possible approaches have been discussed for effective e-waste management, such as recycling, recovery of precious metals, adopting the concepts of circular economy, formulating relevant policies, and use of advance computational techniques. On the other hand, it may also provide potential secondary resources valuable/critical materials whose primary sources are at significant supply risk. Furthermore, the use of machine learning approaches can also be useful in the monitoring and treatment/processing of e-wastes. Highlights In 2019, ~ 53.6 million tons of e-wastes generated worldwide. Discarded e-wastes may be hazardous in nature due to presence of heavy metal compositions. Precious metals like gold, silver, and copper can also be procured from e-wastes. Advance tools like artificial intelligence/machine learning can be useful in the management of e-wastes. Graphical abstract

show abstract

Section: Role Of Machine Intelligence Techniques In E-waste Managementmentioning

confidence: 99%