Deep multimodal fusion for ground-based cloud classification in weather station networks
Abstract Most existing methods only utilize the visual sensors for ground-based cloud classification, which neglects other important characteristics of cloud. In this paper, we utilize the multimodal information collected from weather station networks for ground-based cloud classification and propos...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2018-02-01
|
Series: | EURASIP Journal on Wireless Communications and Networking |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13638-018-1062-0 |
id |
doaj-2973e4fe02eb4b00b0bf2fc74d3230a4 |
---|---|
record_format |
Article |
spelling |
doaj-2973e4fe02eb4b00b0bf2fc74d3230a42020-11-24T21:16:00ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992018-02-01201811810.1186/s13638-018-1062-0Deep multimodal fusion for ground-based cloud classification in weather station networksShuang Liu0Mei Li1Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal UniversityTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal UniversityAbstract Most existing methods only utilize the visual sensors for ground-based cloud classification, which neglects other important characteristics of cloud. In this paper, we utilize the multimodal information collected from weather station networks for ground-based cloud classification and propose a novel method named deep multimodal fusion (DMF). In order to learn the visual features, we train a convolutional neural network (CNN) model to obtain the sum convolutional map (SCM) by using a pooling operation across all the feature maps in deep layers. Afterwards, we employ a weighted strategy to integrate the visual features with multimodal features. We validate the effectiveness of the proposed DMF on the multimodal ground-based cloud (MGC) dataset, and the experimental results demonstrate the proposed DMF achieves better results than the state-of-the-art methods.http://link.springer.com/article/10.1186/s13638-018-1062-0Ground-based cloudMutlimodal informationConvolutional neural networksWeather station networks |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shuang Liu Mei Li |
spellingShingle |
Shuang Liu Mei Li Deep multimodal fusion for ground-based cloud classification in weather station networks EURASIP Journal on Wireless Communications and Networking Ground-based cloud Mutlimodal information Convolutional neural networks Weather station networks |
author_facet |
Shuang Liu Mei Li |
author_sort |
Shuang Liu |
title |
Deep multimodal fusion for ground-based cloud classification in weather station networks |
title_short |
Deep multimodal fusion for ground-based cloud classification in weather station networks |
title_full |
Deep multimodal fusion for ground-based cloud classification in weather station networks |
title_fullStr |
Deep multimodal fusion for ground-based cloud classification in weather station networks |
title_full_unstemmed |
Deep multimodal fusion for ground-based cloud classification in weather station networks |
title_sort |
deep multimodal fusion for ground-based cloud classification in weather station networks |
publisher |
SpringerOpen |
series |
EURASIP Journal on Wireless Communications and Networking |
issn |
1687-1499 |
publishDate |
2018-02-01 |
description |
Abstract Most existing methods only utilize the visual sensors for ground-based cloud classification, which neglects other important characteristics of cloud. In this paper, we utilize the multimodal information collected from weather station networks for ground-based cloud classification and propose a novel method named deep multimodal fusion (DMF). In order to learn the visual features, we train a convolutional neural network (CNN) model to obtain the sum convolutional map (SCM) by using a pooling operation across all the feature maps in deep layers. Afterwards, we employ a weighted strategy to integrate the visual features with multimodal features. We validate the effectiveness of the proposed DMF on the multimodal ground-based cloud (MGC) dataset, and the experimental results demonstrate the proposed DMF achieves better results than the state-of-the-art methods. |
topic |
Ground-based cloud Mutlimodal information Convolutional neural networks Weather station networks |
url |
http://link.springer.com/article/10.1186/s13638-018-1062-0 |
work_keys_str_mv |
AT shuangliu deepmultimodalfusionforgroundbasedcloudclassificationinweatherstationnetworks AT meili deepmultimodalfusionforgroundbasedcloudclassificationinweatherstationnetworks |
_version_ |
1716743744556892160 |