A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images
Abstract Weather recognition is crucial due to its significant impact on various aspects of daily life, such as weather prediction, environmental monitoring, tourism, and energy production. Several studies have already conducted research on image-based weather recognition. However, previous studies...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-80657-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559451016888320 |
|---|---|
| author | Maqsood Ahmed Xiang Zhang Yonglin Shen Nafees Ali Aymen Flah Mohammad Kanan Mohammad Alsharef Sherif S. M. Ghoneim |
| author_facet | Maqsood Ahmed Xiang Zhang Yonglin Shen Nafees Ali Aymen Flah Mohammad Kanan Mohammad Alsharef Sherif S. M. Ghoneim |
| author_sort | Maqsood Ahmed |
| collection | DOAJ |
| description | Abstract Weather recognition is crucial due to its significant impact on various aspects of daily life, such as weather prediction, environmental monitoring, tourism, and energy production. Several studies have already conducted research on image-based weather recognition. However, previous studies have addressed few types of weather phenomena recognition from images with insufficient accuracy. In this paper, we propose a transfer learning CNN framework for classifying air temperature levels from human clothing images. The framework incorporates various deep transfer learning approaches, including DeepLabV3 Plus for semantic segmentation and others for classification such as BigTransfer (BiT), Vision Transformer (ViT), ResNet101, VGG16, VGG19, and DenseNet121. Meanwhile, we have collected a dataset called the Human Clothing Image Dataset (HCID), consisting of 10,000 images with two categories (High and Low air temperature). All the models were evaluated using various classification metrics, such as the confusion matrix, loss, precision, F1-score, recall, accuracy, and AUC-ROC. Additionally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) to emphasize significant features and regions identified by models during the classification process. The results show that DenseNet121 outperformed other models with an accuracy of 98.13%. Promising experimental results highlight the potential benefits of the proposed framework for detecting air temperature levels, aiding in weather prediction and environmental monitoring. |
| format | Article |
| id | doaj-art-92e3eb49220847b9820530362ad610b5 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-92e3eb49220847b9820530362ad610b52025-01-05T12:30:01ZengNature PortfolioScientific Reports2045-23222024-12-0114111710.1038/s41598-024-80657-yA deep transfer learning based convolution neural network framework for air temperature classification using human clothing imagesMaqsood Ahmed0Xiang Zhang1Yonglin Shen2Nafees Ali3Aymen Flah4Mohammad Kanan5Mohammad Alsharef6Sherif S. M. Ghoneim7School of Geography and Information Engineering, China University of GeosciencesSchool of Geography and Information Engineering, China University of GeosciencesNational Engineering Research Center of Geographic Information System, China University of GeosciencesState Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of SciencesNational Engineering School of Gabès, University of GabèsIndustrial Engineering Department, College of Engineering, University of Business and Technology (UBT)Department of Electrical Engineering, College of Engineering, Taif UniversityDepartment of Electrical Engineering, College of Engineering, Taif UniversityAbstract Weather recognition is crucial due to its significant impact on various aspects of daily life, such as weather prediction, environmental monitoring, tourism, and energy production. Several studies have already conducted research on image-based weather recognition. However, previous studies have addressed few types of weather phenomena recognition from images with insufficient accuracy. In this paper, we propose a transfer learning CNN framework for classifying air temperature levels from human clothing images. The framework incorporates various deep transfer learning approaches, including DeepLabV3 Plus for semantic segmentation and others for classification such as BigTransfer (BiT), Vision Transformer (ViT), ResNet101, VGG16, VGG19, and DenseNet121. Meanwhile, we have collected a dataset called the Human Clothing Image Dataset (HCID), consisting of 10,000 images with two categories (High and Low air temperature). All the models were evaluated using various classification metrics, such as the confusion matrix, loss, precision, F1-score, recall, accuracy, and AUC-ROC. Additionally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) to emphasize significant features and regions identified by models during the classification process. The results show that DenseNet121 outperformed other models with an accuracy of 98.13%. Promising experimental results highlight the potential benefits of the proposed framework for detecting air temperature levels, aiding in weather prediction and environmental monitoring.https://doi.org/10.1038/s41598-024-80657-yAir temperatureHuman clothingDeep transfer learningClassification |
| spellingShingle | Maqsood Ahmed Xiang Zhang Yonglin Shen Nafees Ali Aymen Flah Mohammad Kanan Mohammad Alsharef Sherif S. M. Ghoneim A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images Scientific Reports Air temperature Human clothing Deep transfer learning Classification |
| title | A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images |
| title_full | A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images |
| title_fullStr | A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images |
| title_full_unstemmed | A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images |
| title_short | A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images |
| title_sort | deep transfer learning based convolution neural network framework for air temperature classification using human clothing images |
| topic | Air temperature Human clothing Deep transfer learning Classification |
| url | https://doi.org/10.1038/s41598-024-80657-y |
| work_keys_str_mv | AT maqsoodahmed adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT xiangzhang adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT yonglinshen adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT nafeesali adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT aymenflah adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT mohammadkanan adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT mohammadalsharef adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT sherifsmghoneim adeeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT maqsoodahmed deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT xiangzhang deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT yonglinshen deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT nafeesali deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT aymenflah deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT mohammadkanan deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT mohammadalsharef deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages AT sherifsmghoneim deeptransferlearningbasedconvolutionneuralnetworkframeworkforairtemperatureclassificationusinghumanclothingimages |