Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach
Tabular data and images have been used from machine learning models as two diverse types of inputs, in order to perform path loss predictions in urban areas. Different types of models are applied on these distinct modes of input information. The work at hand tries to incorporate both modes of input...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9354618/ |
| id |
doaj-981a2ddabb0145a089189ab109614d73 |
|---|---|
| record_format |
Article |
| spelling |
doaj-981a2ddabb0145a089189ab109614d732021-03-30T15:06:10ZengIEEEIEEE Access2169-35362021-01-019304413045110.1109/ACCESS.2021.30595899354618Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning ApproachSotirios P. Sotiroudis0https://orcid.org/0000-0003-3557-9211Panagiotis Sarigiannidis1https://orcid.org/0000-0001-6042-0355Sotirios K. Goudos2https://orcid.org/0000-0001-5981-5683Katherine Siakavara3Department of Physics, Radiocommunications Laboratory, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, University of Western Macedonia, Kozani, GreeceDepartment of Physics, Radiocommunications Laboratory, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Physics, Radiocommunications Laboratory, Aristotle University of Thessaloniki, Thessaloniki, GreeceTabular data and images have been used from machine learning models as two diverse types of inputs, in order to perform path loss predictions in urban areas. Different types of models are applied on these distinct modes of input information. The work at hand tries to incorporate both modes of input data within a single prediction model. It therefore manipulates and transforms the vectors of tabular data into images. Each feature of the tabular data vector is spread into several pixels, corresponding to the calculated importance of the particular feature. The resulting synthetic images are then fused with images representing selected regions of the area's map. Compound pseudoimages, having channels of both map-based and tabular data-based images, are then being used as inputs for a Convolutional Neural Network (CNN), which predicts the path loss value at a specific point of the area of interest. The results are clearly better than those obtained from models based on a single mode of input data, as well as from the results produced by other bimodal-input approaches. This approach could be applied for path loss prediction in urban environments for several state-of-art wireless networks like 5G and Internet of Things (IoT).https://ieeexplore.ieee.org/document/9354618/Convolutional neural networksdata to image transformationdeep learningpath losspseudoimagesradio propagation |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Sotirios P. Sotiroudis Panagiotis Sarigiannidis Sotirios K. Goudos Katherine Siakavara |
| spellingShingle |
Sotirios P. Sotiroudis Panagiotis Sarigiannidis Sotirios K. Goudos Katherine Siakavara Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach IEEE Access Convolutional neural networks data to image transformation deep learning path loss pseudoimages radio propagation |
| author_facet |
Sotirios P. Sotiroudis Panagiotis Sarigiannidis Sotirios K. Goudos Katherine Siakavara |
| author_sort |
Sotirios P. Sotiroudis |
| title |
Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach |
| title_short |
Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach |
| title_full |
Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach |
| title_fullStr |
Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach |
| title_full_unstemmed |
Fusing Diverse Input Modalities for Path Loss Prediction: A Deep Learning Approach |
| title_sort |
fusing diverse input modalities for path loss prediction: a deep learning approach |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2021-01-01 |
| description |
Tabular data and images have been used from machine learning models as two diverse types of inputs, in order to perform path loss predictions in urban areas. Different types of models are applied on these distinct modes of input information. The work at hand tries to incorporate both modes of input data within a single prediction model. It therefore manipulates and transforms the vectors of tabular data into images. Each feature of the tabular data vector is spread into several pixels, corresponding to the calculated importance of the particular feature. The resulting synthetic images are then fused with images representing selected regions of the area's map. Compound pseudoimages, having channels of both map-based and tabular data-based images, are then being used as inputs for a Convolutional Neural Network (CNN), which predicts the path loss value at a specific point of the area of interest. The results are clearly better than those obtained from models based on a single mode of input data, as well as from the results produced by other bimodal-input approaches. This approach could be applied for path loss prediction in urban environments for several state-of-art wireless networks like 5G and Internet of Things (IoT). |
| topic |
Convolutional neural networks data to image transformation deep learning path loss pseudoimages radio propagation |
| url |
https://ieeexplore.ieee.org/document/9354618/ |
| work_keys_str_mv |
AT sotiriospsotiroudis fusingdiverseinputmodalitiesforpathlosspredictionadeeplearningapproach AT panagiotissarigiannidis fusingdiverseinputmodalitiesforpathlosspredictionadeeplearningapproach AT sotirioskgoudos fusingdiverseinputmodalitiesforpathlosspredictionadeeplearningapproach AT katherinesiakavara fusingdiverseinputmodalitiesforpathlosspredictionadeeplearningapproach |
| _version_ |
1724180009528066048 |