Cite Article

Assessment of Multimodal Rainfall Classification Systems Based on an Audio/Video Dataset

Choose citation format

BibTeX

@article{IJASEIT12130,
   author = {Roberta Avanzato and Francesco Beritelli and Antonio Raspanti and Michele Russo},
   title = {Assessment of Multimodal Rainfall Classification Systems Based on  an Audio/Video Dataset},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {10},
   number = {3},
   year = {2020},
   pages = {1163--1168},
   keywords = {audio/video database; rainfall classification; open dataset; performance evaluation; convolutional neural network.},
   abstract = {In the past few years, there has been an increase in natural disasters due to hydrogeological instability caused by heavy rain. Therefore, to reduce the risk of an imminent occurrence of a disastrous event and reduce the risk to humans, an accurate estimate of the precipitation levels based on advanced machine learning techniques is necessary. In this paper, a new dataset is proposed containing audio/video data recorded via a multimodal rain gauge created ad hoc. The dataset, denominated AVDB-4RC (Audio/Video Database for Rainfall Classification), contains digital audio/video sequences recorded for seven different levels of precipitation intensity. In particular, the database presents a set of audio sequences containing the acoustic timbre produced by the rain and video sequences containing rain videos, both in seven different intensities, i.e., “No rain,” “Weak rain,” “Moderate rain,” “Heavy rain” and “Very heavy rain,” "Shower rain" and "Cloudburst rain." For the validation of the dataset, the paper proposes a novel rainfall classification approach based on a video pattern recognition system that uses CNN neural networks. The average classification accuracy is approximately 49% and can reach 75% if the adjacent misclassifications are not considered. Presumably, it is the first open dataset from the new generation acoustic/video rain gauges available for evaluating the estimated rainfall performance. We hope that this new open dataset will encourage a comparison of rainfall estimation/classification algorithms on this common database so that the adopted techniques are objectively assessed and improved.},
   issn = {2088-5334},
   publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},
   url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=12130},
   doi = {10.18517/ijaseit.10.3.12130}
}

EndNote

%A Avanzato, Roberta
%A Beritelli, Francesco
%A Raspanti, Antonio
%A Russo, Michele
%D 2020
%T Assessment of Multimodal Rainfall Classification Systems Based on  an Audio/Video Dataset
%B 2020
%9 audio/video database; rainfall classification; open dataset; performance evaluation; convolutional neural network.
%! Assessment of Multimodal Rainfall Classification Systems Based on  an Audio/Video Dataset
%K audio/video database; rainfall classification; open dataset; performance evaluation; convolutional neural network.
%X In the past few years, there has been an increase in natural disasters due to hydrogeological instability caused by heavy rain. Therefore, to reduce the risk of an imminent occurrence of a disastrous event and reduce the risk to humans, an accurate estimate of the precipitation levels based on advanced machine learning techniques is necessary. In this paper, a new dataset is proposed containing audio/video data recorded via a multimodal rain gauge created ad hoc. The dataset, denominated AVDB-4RC (Audio/Video Database for Rainfall Classification), contains digital audio/video sequences recorded for seven different levels of precipitation intensity. In particular, the database presents a set of audio sequences containing the acoustic timbre produced by the rain and video sequences containing rain videos, both in seven different intensities, i.e., “No rain,” “Weak rain,” “Moderate rain,” “Heavy rain” and “Very heavy rain,” "Shower rain" and "Cloudburst rain." For the validation of the dataset, the paper proposes a novel rainfall classification approach based on a video pattern recognition system that uses CNN neural networks. The average classification accuracy is approximately 49% and can reach 75% if the adjacent misclassifications are not considered. Presumably, it is the first open dataset from the new generation acoustic/video rain gauges available for evaluating the estimated rainfall performance. We hope that this new open dataset will encourage a comparison of rainfall estimation/classification algorithms on this common database so that the adopted techniques are objectively assessed and improved.
%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=12130
%R doi:10.18517/ijaseit.10.3.12130
%J International Journal on Advanced Science, Engineering and Information Technology
%V 10
%N 3
%@ 2088-5334

IEEE

Roberta Avanzato,Francesco Beritelli,Antonio Raspanti and Michele Russo,"Assessment of Multimodal Rainfall Classification Systems Based on  an Audio/Video Dataset," International Journal on Advanced Science, Engineering and Information Technology, vol. 10, no. 3, pp. 1163-1168, 2020. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.10.3.12130.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Avanzato, Roberta
AU  - Beritelli, Francesco
AU  - Raspanti, Antonio
AU  - Russo, Michele
PY  - 2020
TI  - Assessment of Multimodal Rainfall Classification Systems Based on  an Audio/Video Dataset
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 10 (2020) No. 3
Y2  - 2020
SP  - 1163
EP  - 1168
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - audio/video database; rainfall classification; open dataset; performance evaluation; convolutional neural network.
N2  - In the past few years, there has been an increase in natural disasters due to hydrogeological instability caused by heavy rain. Therefore, to reduce the risk of an imminent occurrence of a disastrous event and reduce the risk to humans, an accurate estimate of the precipitation levels based on advanced machine learning techniques is necessary. In this paper, a new dataset is proposed containing audio/video data recorded via a multimodal rain gauge created ad hoc. The dataset, denominated AVDB-4RC (Audio/Video Database for Rainfall Classification), contains digital audio/video sequences recorded for seven different levels of precipitation intensity. In particular, the database presents a set of audio sequences containing the acoustic timbre produced by the rain and video sequences containing rain videos, both in seven different intensities, i.e., “No rain,” “Weak rain,” “Moderate rain,” “Heavy rain” and “Very heavy rain,” "Shower rain" and "Cloudburst rain." For the validation of the dataset, the paper proposes a novel rainfall classification approach based on a video pattern recognition system that uses CNN neural networks. The average classification accuracy is approximately 49% and can reach 75% if the adjacent misclassifications are not considered. Presumably, it is the first open dataset from the new generation acoustic/video rain gauges available for evaluating the estimated rainfall performance. We hope that this new open dataset will encourage a comparison of rainfall estimation/classification algorithms on this common database so that the adopted techniques are objectively assessed and improved.
UR  - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=12130
DO  - 10.18517/ijaseit.10.3.12130

RefWorks

RT Journal Article
ID 12130
A1 Avanzato, Roberta
A1 Beritelli, Francesco
A1 Raspanti, Antonio
A1 Russo, Michele
T1 Assessment of Multimodal Rainfall Classification Systems Based on  an Audio/Video Dataset
JF International Journal on Advanced Science, Engineering and Information Technology
VO 10
IS 3
YR 2020
SP 1163
OP 1168
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 audio/video database; rainfall classification; open dataset; performance evaluation; convolutional neural network.
AB In the past few years, there has been an increase in natural disasters due to hydrogeological instability caused by heavy rain. Therefore, to reduce the risk of an imminent occurrence of a disastrous event and reduce the risk to humans, an accurate estimate of the precipitation levels based on advanced machine learning techniques is necessary. In this paper, a new dataset is proposed containing audio/video data recorded via a multimodal rain gauge created ad hoc. The dataset, denominated AVDB-4RC (Audio/Video Database for Rainfall Classification), contains digital audio/video sequences recorded for seven different levels of precipitation intensity. In particular, the database presents a set of audio sequences containing the acoustic timbre produced by the rain and video sequences containing rain videos, both in seven different intensities, i.e., “No rain,” “Weak rain,” “Moderate rain,” “Heavy rain” and “Very heavy rain,” "Shower rain" and "Cloudburst rain." For the validation of the dataset, the paper proposes a novel rainfall classification approach based on a video pattern recognition system that uses CNN neural networks. The average classification accuracy is approximately 49% and can reach 75% if the adjacent misclassifications are not considered. Presumably, it is the first open dataset from the new generation acoustic/video rain gauges available for evaluating the estimated rainfall performance. We hope that this new open dataset will encourage a comparison of rainfall estimation/classification algorithms on this common database so that the adopted techniques are objectively assessed and improved.
LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=12130
DO  - 10.18517/ijaseit.10.3.12130