TY - GEN
T1 - Energy content modelling for municipal solid waste using adaptive neuro-fuzzy inference system (anfis)
AU - Adeleke, Oluwatobi
AU - Akinlabi, Stephen A.
AU - Adedeji, Paul A.
AU - Jen, Tien Chien
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd 2020.
PY - 2020
Y1 - 2020
N2 - Recovery of energy from municipal solid waste (MSW) will not only add to the national electrical energy generation capacity, but it will also minimize the quantity of waste that ends up in landfill, consequently mitigating its environmental impact. This study has developed ANFIS model to forecast the energy content of waste generated in Johannesburg, South Africa, based on the physical component of the waste: plastic, paper, organics, metals, and textile as input against the energy content. The fuzzy c-means (FCM) clustering technique was explored for data clustering in the ANFIS model. The model was trained with 70% of the data and 30% for validation. The performance of the network was evaluated using root mean square error (RMSE), mean absolute deviation (MAD), and mean absolute percentage error (MAPE). The RMSE, MAD, and MAPE of the model were 0.3418, 0.2692, and 7.7991, respectively. The forecast accuracy of ANFIS was compared with ANN, giving a MAPE of 7.7991 and 13.7870, respectively. ANFIS gave a better forecast accuracy and recommended for energy content prediction of municipal solid waste.
AB - Recovery of energy from municipal solid waste (MSW) will not only add to the national electrical energy generation capacity, but it will also minimize the quantity of waste that ends up in landfill, consequently mitigating its environmental impact. This study has developed ANFIS model to forecast the energy content of waste generated in Johannesburg, South Africa, based on the physical component of the waste: plastic, paper, organics, metals, and textile as input against the energy content. The fuzzy c-means (FCM) clustering technique was explored for data clustering in the ANFIS model. The model was trained with 70% of the data and 30% for validation. The performance of the network was evaluated using root mean square error (RMSE), mean absolute deviation (MAD), and mean absolute percentage error (MAPE). The RMSE, MAD, and MAPE of the model were 0.3418, 0.2692, and 7.7991, respectively. The forecast accuracy of ANFIS was compared with ANN, giving a MAPE of 7.7991 and 13.7870, respectively. ANFIS gave a better forecast accuracy and recommended for energy content prediction of municipal solid waste.
KW - Adaptive neuro-fuzzy inference system
KW - Municipal solid waste
KW - Season
UR - http://www.scopus.com/inward/record.url?scp=85091291672&partnerID=8YFLogxK
U2 - 10.1007/978-981-15-5753-8_17
DO - 10.1007/978-981-15-5753-8_17
M3 - Conference contribution
AN - SCOPUS:85091291672
SN - 9789811557521
T3 - Lecture Notes in Mechanical Engineering
SP - 177
EP - 185
BT - Advances in Manufacturing Engineering - Selected Articles from ICMMPE 2019
A2 - Emamian, Seyed Sattar
A2 - Yusof, Farazila
A2 - Awang, Mokhtar
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th International Conference on Mechanical, Manufacturing and Plant Engineering, ICMMPE 2019
Y2 - 19 November 2019 through 21 November 2019
ER -
