Municipal solid waste data quality on artificial neural network performance

S. O. Masebinu, E. T. Akinlabi, Edison Muzenda, A. O. Aboyade, Charles Mbohwa, Musaida Mercy Manyuchi, P. Naidoo

Research output: Contribution to conferencePaper

Abstract

Short and long-term municipal solid waste (MSW) management requires adequate planning. Understanding the relationship among variables that affect MSW generation and predicting MSW based on them is needed for an effective planning. Methodologies to forecast MSW are numerous and have been implemented at different level of data granularity. Lack of data in many African cities and countries has hampered effective waste management plan. The lack
of data has mainly been attributed to insufficient budget and lack of capacity to implement such management structure. In this study, we investigated the impact of data quality on forecasting efficiency using advanced prediction techniques. It was observed that the quality of waste related data variables determines the extent of model reliability and prediction accuracy.
Original languageEnglish
Number of pages8
Publication statusPublished - 2017
Event2nd International Engineering Conference 2017 - Minna, Nigeria
Duration: Oct 17 2017Oct 19 2017

Conference

Conference2nd International Engineering Conference 2017
Abbreviated titleIEC 2017
CountryNigeria
CityMinna
Period10/17/1710/19/17

Fingerprint

data quality
municipal solid waste
artificial neural network
waste management
prediction
methodology
planning

Cite this

Masebinu, S. O., Akinlabi, E. T., Muzenda, E., Aboyade, A. O., Mbohwa, C., Manyuchi, M. M., & Naidoo, P. (2017). Municipal solid waste data quality on artificial neural network performance. Paper presented at 2nd International Engineering Conference 2017, Minna, Nigeria.
Masebinu, S. O. ; Akinlabi, E. T. ; Muzenda, Edison ; Aboyade, A. O. ; Mbohwa, Charles ; Manyuchi, Musaida Mercy ; Naidoo, P. / Municipal solid waste data quality on artificial neural network performance. Paper presented at 2nd International Engineering Conference 2017, Minna, Nigeria.8 p.
@conference{6b2197c8f62f469a8d8a1109dadde89c,
title = "Municipal solid waste data quality on artificial neural network performance",
abstract = "Short and long-term municipal solid waste (MSW) management requires adequate planning. Understanding the relationship among variables that affect MSW generation and predicting MSW based on them is needed for an effective planning. Methodologies to forecast MSW are numerous and have been implemented at different level of data granularity. Lack of data in many African cities and countries has hampered effective waste management plan. The lackof data has mainly been attributed to insufficient budget and lack of capacity to implement such management structure. In this study, we investigated the impact of data quality on forecasting efficiency using advanced prediction techniques. It was observed that the quality of waste related data variables determines the extent of model reliability and prediction accuracy.",
author = "Masebinu, {S. O.} and Akinlabi, {E. T.} and Edison Muzenda and Aboyade, {A. O.} and Charles Mbohwa and Manyuchi, {Musaida Mercy} and P. Naidoo",
year = "2017",
language = "English",
note = "2nd International Engineering Conference 2017, IEC 2017 ; Conference date: 17-10-2017 Through 19-10-2017",

}

Masebinu, SO, Akinlabi, ET, Muzenda, E, Aboyade, AO, Mbohwa, C, Manyuchi, MM & Naidoo, P 2017, 'Municipal solid waste data quality on artificial neural network performance' Paper presented at 2nd International Engineering Conference 2017, Minna, Nigeria, 10/17/17 - 10/19/17, .

Municipal solid waste data quality on artificial neural network performance. / Masebinu, S. O.; Akinlabi, E. T.; Muzenda, Edison; Aboyade, A. O.; Mbohwa, Charles; Manyuchi, Musaida Mercy; Naidoo, P.

2017. Paper presented at 2nd International Engineering Conference 2017, Minna, Nigeria.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Municipal solid waste data quality on artificial neural network performance

AU - Masebinu, S. O.

AU - Akinlabi, E. T.

AU - Muzenda, Edison

AU - Aboyade, A. O.

AU - Mbohwa, Charles

AU - Manyuchi, Musaida Mercy

AU - Naidoo, P.

PY - 2017

Y1 - 2017

N2 - Short and long-term municipal solid waste (MSW) management requires adequate planning. Understanding the relationship among variables that affect MSW generation and predicting MSW based on them is needed for an effective planning. Methodologies to forecast MSW are numerous and have been implemented at different level of data granularity. Lack of data in many African cities and countries has hampered effective waste management plan. The lackof data has mainly been attributed to insufficient budget and lack of capacity to implement such management structure. In this study, we investigated the impact of data quality on forecasting efficiency using advanced prediction techniques. It was observed that the quality of waste related data variables determines the extent of model reliability and prediction accuracy.

AB - Short and long-term municipal solid waste (MSW) management requires adequate planning. Understanding the relationship among variables that affect MSW generation and predicting MSW based on them is needed for an effective planning. Methodologies to forecast MSW are numerous and have been implemented at different level of data granularity. Lack of data in many African cities and countries has hampered effective waste management plan. The lackof data has mainly been attributed to insufficient budget and lack of capacity to implement such management structure. In this study, we investigated the impact of data quality on forecasting efficiency using advanced prediction techniques. It was observed that the quality of waste related data variables determines the extent of model reliability and prediction accuracy.

M3 - Paper

ER -

Masebinu SO, Akinlabi ET, Muzenda E, Aboyade AO, Mbohwa C, Manyuchi MM et al. Municipal solid waste data quality on artificial neural network performance. 2017. Paper presented at 2nd International Engineering Conference 2017, Minna, Nigeria.