Enter your keyword

2-s2.0-85084806255

[vc_empty_space][vc_empty_space]

Artificial neural networks (ANN)-based seismic signal source identification from MEMS accelerometer measurements

Irawan H.a, Prihatmanto A.S.a, Machbub C.a, Widiyantoro S.a

a School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, Indonesia

[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2019 IEEE.This paper reports initial findings on Artificial Neural Networks (ANN)-based methods to identify seismic signal source using only low-quality MEMS accelerometer signals. We collected annotated signals sampled at 50 Hz from several mobile devices and built an open source linear acceleration dataset. From this dataset, we performed and compared several feature extraction techniques based on signal length and spectrogram parameters. We trained the resulting features using three-layer neural networks with a hidden layer of 32 neurons and a dropout layer. Training was performed using Tensorflow 2.0 and Google Colaboratory with GPU backend. The results show 95.83% validation accuracy from spectrogram signals with length of 2 seconds and 3 seconds, and 79.17% validation accuracy from raw amplitude inputs.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Feature extraction techniques,Hidden layers,Linear accelerations,Low qualities,MEMS accelerometer,Seismic signals,Signal length,Three-layer neural networks[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]machine learning,MEMS accelerometer,neural networks,seismic signal[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text]We would like to thank Ministry of Research, Technology and Higher Education of the Republic of Indonesia for supporting this paper. We thank Indonesia Endowment Fund for Education (LPDP) for taking part in supporting the PhD study. We also thank U-Inspire Indonesia and Integrated Research on Disaster Risk (IRDR) for valuable discussions within disaster risk research community.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICSPC47137.2019.9068004[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]