eprintid: 18969 rev_number: 2 eprint_status: archive userid: 1 dir: disk0/00/01/89/69 datestamp: 2024-06-04 14:11:25 lastmod: 2024-06-04 14:11:25 status_changed: 2024-06-04 14:04:33 type: conference_item metadata_visibility: show creators_name: Sundari, C.D. creators_name: Putri, A.N.A.R. creators_name: Kinanti, I.W. creators_name: Chandra, I. creators_name: Romadhony, A. creators_name: Aziz, A.A. creators_name: Rachmawati, L.M. creators_name: Sandrina, T. creators_name: Chandra, F. creators_name: Sugiarto, E. creators_name: Putra, M.B.R. creators_name: Pulungan, R.A.I. title: Artificial Neural Network Based Prediction of PM25Mass Concentration ispublished: pub keywords: Air quality; Atmospheric humidity; Atmospheric pressure; Economics; Forecasting; Microsensors; Wind speed, Economic growths; Fore-casting; Forecasting system; Growth activity; Human activities; Mass concentration; Meteorological factors; Meteorological parameters; Network models; Network-based, Neural networks note: cited By 0; Conference of 29th International Conference on Telecommunications, ICT 2023 ; Conference Date: 8 November 2023 Through 9 November 2023; Conference Code:196070 abstract: Economic growth and human activities affect the increase of particulate matter (PM2.5) concentration. In addition to the sources of emissions, the mass concentration of PM2.5 may be impacted by meteorological factors such as temperature, humidity levels, atmospheric pressure, precipitation, and the speed/direction of the wind. A previous study established a monitoring system for air quality at Tokong Nanas (GKU) and the Deli Building of Telkom University, located in Bandung, using microsensor technology. Various forecasting techniques were also employed to predict the mass concentration of PM2.5, considering its meteorological factors. However, the study found that not all the meteorological parameters give significant results in PM2.5 forecasting, with an RMSE value of 27 μg/m3. Hence, this study optimized the forecasting system of PM2.5 mass concentration using the Artificial Neural Network Backpropagation method. Only a few meteorological parameters were taken into consider-ation in the forecasting system, which has a significant impact on the forecast quality, such as rainfall intensity, relative humidity, and wind speed. As a result, the Tokong Nanas (GKU) has the best network model for 4-9-12-9-1 architecture with a learning value of 0.2, whereas the Deli Building is 4-20-9-9-1 with a 0.3 value. The RMSE and MAPE performances generated by GKU and Deli best network models were 8 μg/m3 at 37 and 13 μg/m3 at 15, respectively. Additional investigation is required to scrutinize the conduct of contaminated atmosphere and to tackle the predicament of air purity in Bandung Metropolitan in forthcoming times. © 2023 IEEE. date: 2023 publisher: Institute of Electrical and Electronics Engineers Inc. official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85182993521&doi=10.1109%2fICT60153.2023.10374055&partnerID=40&md5=f8e5a99f8dc6272aed0fe4dd379282ad id_number: 10.1109/ICT60153.2023.10374055 full_text_status: none publication: Proceedings - ICT 2023 - 29th International Conference on Telecommunications: Next-Generation Telecommunications for Digital Inclusion and Universal Access refereed: TRUE isbn: 9798350361100 citation: Sundari, C.D. and Putri, A.N.A.R. and Kinanti, I.W. and Chandra, I. and Romadhony, A. and Aziz, A.A. and Rachmawati, L.M. and Sandrina, T. and Chandra, F. and Sugiarto, E. and Putra, M.B.R. and Pulungan, R.A.I. (2023) Artificial Neural Network Based Prediction of PM25Mass Concentration. In: UNSPECIFIED.