Madiha Sher
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Madiha Sher has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Jaroslav Frnda
Department of Quantitative Methods and Economic Informatics, University of Zilina, Zilina, Slovakia
3 shared publications Nasru Minallah
Department of Computer Systems Engineering, University of Engineering and Technology, Peshawar, Pakistan
2 shared publications- Nasru Minallah
Department of Computer Systems Engineering, University of Engineering and Technology (UET), Peshawar, Pakistan
2 shared publications - Waleed Khan
National Center for Big Data and Cloud Computing (NCBC), University of Engineering and Technology (UET), Peshawar, Pakistan
2 shared publications Amara Haroon Durrani
Department of Radiology, Hayatabad Medical Complex, Peshawar, Pakistan
1 shared publicationMuhammad Zeeshan
National Center for Big Data and Cloud Computing (NCBC), University of Engineering and Technology, Peshawar, Khyber Pakhtunkhwa, Pakistan
1 shared publication
Latest Publications
- Open Access
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 17209-17223
Mapping Afghanistan’s Mineral Diversity With NASA EMIT Hyperspectral Data: Spatial–Spectral Transformer Versus CNN for Geo-Mineralogical Classification
Hyperspectral Imaging (HSI) is a crucial technology in mineral exploration, offering the potential to record and analyze spectral bands that reveal the actual composition of the features of the earth's surface. Although significant progress has been made in remote sensing–based mineral exploration, the availability of mineral data derived from hyperspectral sensors remains limited and not publicly available. Most existing data are available in raw unprocessed form, requiring complex, computationally intensive preprocessing to clean and refine that. Consequently, there is a pressing need for refined, geologically validated hyperspectral datasets to enable robust model training and accurate mineral identification. A novel Afghanistan-based hyperspectral dataset derived from the National Aeronautics and Space Administration (NASA) Earth Surface Mineral Dust Source Investigation (EMIT) was developed and rigorously pre processed for mineral classification. Deep Learning (DL) appli cations on hyperspectral data remain notably limited in state-of the-art literature; this study addresses this challenge by creating two DL models, a Convolutional Neural Network (CNN) and a Spatial-Spectral Transformer (SST), for hyperspectral image data applied to geological mapping in Afghanistan, a mineral rich yet underexplored diverse region. The model results validate that while CNN extracts spectral values, SST outperforms by using a multihead self-attention mechanism to capture long range dependencies and spatial details, achieving an overall accuracy of 89.24% compared to 87.71% for CNN. The SST shows superior performance and scalability, which is essential for accurate mineral classification. The advanced SST model proposed produces an adaptable framework for mineral explo ration in data-scarce terrain. Future research can investigate the potential of explainable Artificial Intelligence (AI) to improve interpretability and extend this framework to broader domains of geological surface exploration.
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 17209-17223
Open AccessMapping Afghanistan’s Mineral Diversity With NASA EMIT Hyperspectral Data: Spatial–Spectral Transformer Versus CNN for Geo-Mineralogical Classification
Hyperspectral Imaging (HSI) is a crucial technology in mineral exploration, offering the potential to record and analyze spectral bands that reveal the actual composition of the features of the earth's surface. Although significant progress has been made in remote sensing–based mineral exploration, the availability of mineral data derived from hyperspectral sensors remains limited and not publicly available. Most existing data are available in raw unprocessed form, requiring complex, computationally intensive preprocessing to clean and refine that. Consequently, there is a pressing need for refined, geologically validated hyperspectral datasets to enable robust model training and accurate mineral identification. A novel Afghanistan-based hyperspectral dataset derived from the National Aeronautics and Space Administration (NASA) Earth Surface Mineral Dust Source Investigation (EMIT) was developed and rigorously pre processed for mineral classification. Deep Learning (DL) appli cations on hyperspectral data remain notably limited in state-of the-art literature; this study addresses this challenge by creating two DL models, a Convolutional Neural Network (CNN) and a Spatial-Spectral Transformer (SST), for hyperspectral image data applied to geological mapping in Afghanistan, a mineral rich yet underexplored diverse region. The model results validate that while CNN extracts spectral values, SST outperforms by using a multihead self-attention mechanism to capture long range dependencies and spatial details, achieving an overall accuracy of 89.24% compared to 87.71% for CNN. The SST shows superior performance and scalability, which is essential for accurate mineral classification. The advanced SST model proposed produces an adaptable framework for mineral explo ration in data-scarce terrain. Future research can investigate the potential of explainable Artificial Intelligence (AI) to improve interpretability and extend this framework to broader domains of geological surface exploration.
- Open Access
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 141013-141025
Elevating Crop Classification Performance Through CNN-GRU Feature Fusion
Crop classification and its area estimation hold significant importance in agricultural production and management. It serves as a crucial tool for efficiently identifying various crops and contributes to the formulation of tailored strategies for crop-specific production and estimation purposes. Numerous deep learning techniques, with a particular emphasis on Convolutional Neural Networks (CNNs), have found application in the analysis of satellite data for crop classification. Nevertheless, this approach has its limitations, notably the challenge of sequential information loss, which hinders its ability to accurately extract features that rely on temporal changes over time. On the other hand, another deep learning technique, the Gated Recurrent Unit (GRU), excels at handling time series data but falls short in its ability to extract intricate patterns within the data, a strength of CNNs. This study explores the capabilities of these methodologies for crop classification in the Charsadda district of Pakistan, a region renowned for its diverse agricultural landscape dedicated to the cultivation of economically valuable crops. We introduce a dual-channel CNN-GRU feature fusion architecture, a method that merges individually extracted features from both CNNs and GRUs. The proposed framework is specifically designed for data obtained from Sentinel-2 and PlanetScope imagery, complemented by NDVI time series data collected from the study site. The model’s performance is assessed in comparison to the individual performance of CNN and GRU models. The models were subjected to evaluation using a variety of metrics, encompassing precision, recall, F1 Score, and overall accuracy. The outcomes reveal that the proposed model surpasses the performance of the individual models. The feature fusion-based model emerged as the top performer, achieving an overall accuracy of 96.47 percent, an F1 Score of 93.16 percent, a precision of 93.93 percent, and a recall of 92.69 percent. This research offers substantial evidence supporting the potential of the CNN-GRU feature fusion model for crop identification. By harnessing the strengths of both architectural approaches, it demonstrates its effectiveness as a valuable tool for crop classification.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 141013-141025
Open AccessElevating Crop Classification Performance Through CNN-GRU Feature Fusion
Crop classification and its area estimation hold significant importance in agricultural production and management. It serves as a crucial tool for efficiently identifying various crops and contributes to the formulation of tailored strategies for crop-specific production and estimation purposes. Numerous deep learning techniques, with a particular emphasis on Convolutional Neural Networks (CNNs), have found application in the analysis of satellite data for crop classification. Nevertheless, this approach has its limitations, notably the challenge of sequential information loss, which hinders its ability to accurately extract features that rely on temporal changes over time. On the other hand, another deep learning technique, the Gated Recurrent Unit (GRU), excels at handling time series data but falls short in its ability to extract intricate patterns within the data, a strength of CNNs. This study explores the capabilities of these methodologies for crop classification in the Charsadda district of Pakistan, a region renowned for its diverse agricultural landscape dedicated to the cultivation of economically valuable crops. We introduce a dual-channel CNN-GRU feature fusion architecture, a method that merges individually extracted features from both CNNs and GRUs. The proposed framework is specifically designed for data obtained from Sentinel-2 and PlanetScope imagery, complemented by NDVI time series data collected from the study site. The model’s performance is assessed in comparison to the individual performance of CNN and GRU models. The models were subjected to evaluation using a variety of metrics, encompassing precision, recall, F1 Score, and overall accuracy. The outcomes reveal that the proposed model surpasses the performance of the individual models. The feature fusion-based model emerged as the top performer, achieving an overall accuracy of 96.47 percent, an F1 Score of 93.16 percent, a precision of 93.93 percent, and a recall of 92.69 percent. This research offers substantial evidence supporting the potential of the CNN-GRU feature fusion model for crop identification. By harnessing the strengths of both architectural approaches, it demonstrates its effectiveness as a valuable tool for crop classification.
- Open Access
- 6 September 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (9) , e0307825
Precision meets generalization: Enhancing brain tumor classification via pretrained DenseNet with global average pooling and hyperparameter tuning
Brain tumors pose significant global health concerns due to their high mortality rates and limited treatment options. These tumors, arising from abnormal cell growth within the brain, exhibits various sizes and shapes, making their manual detection from magnetic resonance imaging (MRI) scans a subjective and challenging task for healthcare professionals, hence necessitating automated solutions. This study investigates the potential of deep learning, specifically the DenseNet architecture, to automate brain tumor classification, aiming to enhance accuracy and generalizability for clinical applications. We utilized the Figshare brain tumor dataset, comprising 3,064 T1-weighted contrast-enhanced MRI images from 233 patients with three prevalent tumor types: meningioma, glioma, and pituitary tumor. Four pre-trained deep learning models—ResNet, EfficientNet, MobileNet, and DenseNet—were evaluated using transfer learning from ImageNet. DenseNet achieved the highest test set accuracy of 96%, outperforming ResNet (91%), EfficientNet (91%), and MobileNet (93%). Therefore, we focused on improving the performance of the DenseNet, while considering it as base model. To enhance the generalizability of the base DenseNet model, we implemented a fine-tuning approach with regularization techniques, including data augmentation, dropout, batch normalization, and global average pooling, coupled with hyperparameter optimization. This enhanced DenseNet model achieved an accuracy of 97.1%. Our findings demonstrate the effectiveness of DenseNet with transfer learning and fine-tuning for brain tumor classification, highlighting its potential to improve diagnostic accuracy and reliability in clinical settings.
- 6 September 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (9) , e0307825
Open AccessPrecision meets generalization: Enhancing brain tumor classification via pretrained DenseNet with global average pooling and hyperparameter tuning
Brain tumors pose significant global health concerns due to their high mortality rates and limited treatment options. These tumors, arising from abnormal cell growth within the brain, exhibits various sizes and shapes, making their manual detection from magnetic resonance imaging (MRI) scans a subjective and challenging task for healthcare professionals, hence necessitating automated solutions. This study investigates the potential of deep learning, specifically the DenseNet architecture, to automate brain tumor classification, aiming to enhance accuracy and generalizability for clinical applications. We utilized the Figshare brain tumor dataset, comprising 3,064 T1-weighted contrast-enhanced MRI images from 233 patients with three prevalent tumor types: meningioma, glioma, and pituitary tumor. Four pre-trained deep learning models—ResNet, EfficientNet, MobileNet, and DenseNet—were evaluated using transfer learning from ImageNet. DenseNet achieved the highest test set accuracy of 96%, outperforming ResNet (91%), EfficientNet (91%), and MobileNet (93%). Therefore, we focused on improving the performance of the DenseNet, while considering it as base model. To enhance the generalizability of the base DenseNet model, we implemented a fine-tuning approach with regularization techniques, including data augmentation, dropout, batch normalization, and global average pooling, coupled with hyperparameter optimization. This enhanced DenseNet model achieved an accuracy of 97.1%. Our findings demonstrate the effectiveness of DenseNet with transfer learning and fine-tuning for brain tumor classification, highlighting its potential to improve diagnostic accuracy and reliability in clinical settings.
- Open Access
- 1 August 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (4) , 4661-4670
Hyperparameters analysis of long short-term memory architecture for crop classification
Deep learning (DL) has seen a massive rise in popularity for remote sensing (RS) based applications over the past few years. However, the performance of DL algorithms is dependent on the optimization of various hyperparameters since the hyperparameters have a huge impact on the performance of deep neural networks. The impact of hyperparameters on the accuracy and reliability of DL models is a significant area for investigation. In this study, the grid Search algorithm is used for hyperparameters optimization of long short-term memory (LSTM) network for the RS-based classification. The hyperparameters considered for this study are, optimizer, activation function, batch size, and the number of LSTM layers. In this study, over 1,000 hyperparameter sets are evaluated and the result of all the sets are analyzed to see the effects of various combinations of hyperparameters as well the individual parameter effect on the performance of the LSTM model. The performance of the LSTM model is evaluated using the performance metric of minimum loss and average loss and it was found that classification can be highly affected by the choice of optimizer; however, other parameters such as the number of LSTM layers have less influence.
- 1 August 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (4) , 4661-4670
Open AccessHyperparameters analysis of long short-term memory architecture for crop classification
Deep learning (DL) has seen a massive rise in popularity for remote sensing (RS) based applications over the past few years. However, the performance of DL algorithms is dependent on the optimization of various hyperparameters since the hyperparameters have a huge impact on the performance of deep neural networks. The impact of hyperparameters on the accuracy and reliability of DL models is a significant area for investigation. In this study, the grid Search algorithm is used for hyperparameters optimization of long short-term memory (LSTM) network for the RS-based classification. The hyperparameters considered for this study are, optimizer, activation function, batch size, and the number of LSTM layers. In this study, over 1,000 hyperparameter sets are evaluated and the result of all the sets are analyzed to see the effects of various combinations of hyperparameters as well the individual parameter effect on the performance of the LSTM model. The performance of the LSTM model is evaluated using the performance metric of minimum loss and average loss and it was found that classification can be highly affected by the choice of optimizer; however, other parameters such as the number of LSTM layers have less influence.