Open Access Open Access  Restricted Access Subscription Access

A Smart Garbage Classification based on Deep Learning

Ankitha Bekal, Afthab ., Mishal Ibrahim, Jisin Farhan, Mohammad Shammas KN

Abstract


The Garbage categorization has long been a significant problem for resource recycling, environmental protection, and social well-being. To increase the efficiency of front-end garbage collection, a deep learning-based autonomous trash categorization system is proposed. The hardware framework and mobile app for the entire garbage can system are first developed. Three additional factors help to further optimize the network structure of the proposed garbage classification algorithm: the multi-feature fusion of input images, the feature reuse of the residual unit, and the development of a new activation function. The Training algorithm serves as the foundation for the proposed garbage classification algorithm. Last but not least, artificial trash data is used to demonstrate the proposed categorization system's superiority. The classification accuracy of the suggested algorithm has increased by 99%.


Full Text:

PDF

References


P.Kellow,R.J.P.C.Joel,D.Ousmane,D.A.Kumar,D.-A.C.V.Hugo, and K. A. Sergei, ‗‗A smart waste management solution geared towards citizens,‘‘ Sensors, vol. 20, no. 8, pp.1–15, Apr. 2020, doi: 10. 3390/s20082380

T. Kano, E. Naito, and T. Aoshima, ‗‗Decentralized control for swarm robots that can effectively execute spatially distributed tasks,‘‘ Artif. Life, vol. 26, pp. 243– 260, Apr. 2020, doi: 10.1162/artl_a_00317.

A. Azarmi Gilan, M. Emad, and B. Alizadeh, ‗‗FPGA-based implemen- tation of a real-time object recognition system using convolutional neu-ral network,‘‘ IEEE Trans. Circuits Syst. II, Exp. Briefs, vol. 67, no. 4, pp. 755–759, Apr. 2020, doi: 10.1109/TCSII.2019.2922372.

G. Zhong, W. Jiao, W. Gao, and K. Huang, ‗‗Automatic design of deep networks with neural blocks,‘‘ Cognit. Comput., vol. 12, no. 1, pp. 1–12, Jan. 2020, doi: 10.1007/s12559-019-09677-5

K.-H.Liu,P.-S.Zhong,D.-F.Xu,Q.Xia,andM.Liu,‗‗Tangent- basedrec- tified linear unit,‘‘ Comput. Integr. Manuf. Syst., vol. 26, no. 1, pp. 145–151, Jan. 2020, doi: 10.13196/j.cims.2020.01.015

W.-F.Gong,H.Chen,Z.-H.Zhang,ML.Zhang,C.Guan,andX.Wang

Intelligent fault diagnosis for rolling bearing based on improved convolu- tional neural network,‘‘ J. Vib. Eng., vol. 33, no. 2, pp. 400–413, Apr. 2020, doi: 10.16385/j.cnki.issn.1004-

4523.2020.02.021.

K.L.Sun,J.M.Yu,andG.Sun,‗Aconvolutionalneuralnetworkmodel based on improved Softplus activation function,‘‘ J. Fuy-ang Normal Univ. (Natural Sci.), vol. 37, no. 1, pp. 75–79, Mar. 2020, doi: 10.14096/ j.cnki.cn34-1069/n/1004-4329(2020)01-075-05.

Y.G.Cheng,N.Chen,andH.Zhang,‗‗Coalflyashasaninducertostudy its application in the production of methane gas from domestic waste,‘‘ Fresenius Environ. Bull., vol. 29, no. 2, pp. 1082–1089, 2020.

D. Porshnov, V. Ozols, and M. Klavins, ‗‗Thermogravimetric analysis as express tool for quality assessment of refuse derived fuels used for pyro- gasification,‘‘ Environ. Technol., vol. 41, no. 1, pp. 35–39, Mar. 2020.


Refbacks

  • There are currently no refbacks.