A5014580983- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Remote-Sensing Image Classification
- Plant Water Relations and Carbon Dynamics
- Educational and Technological Research
- Smart Agriculture and AI
- Advanced Technologies in Various Fields
- Spectroscopy and Chemometric Analyses
- Astronomy and Astrophysical Research
- Brain Tumor Detection and Classification
- Proteoglycans and glycosaminoglycans research
- Digital Imaging for Blood Diseases
- Advanced Neural Network Applications
- Cancer, Lipids, and Metabolism
Universiti Teknologi MARA
2025
University of Engineering and Technology Peshawar
2016-2024
Deep learning based data driven methods with multi-sensors spectro-temporal are widely used for pattern identification and land-cover classification in remote sensing domain. However, adjusting the right tuning deep models is extremely important as different parameter setting can alter performance of model. In our research work, we have evaluated Convolutional Long Short-Term Memory (ConvLSTM) techniques, over various hyper-parameters an imbalanced dataset one highest utilized...
This research work aims to develop a deep learning-based crop classification framework for remotely sensed time series data. Tobacco is major revenue generating of Khyber Pakhtunkhwa (KP) province Pakistan, with over 90% the country’s production. In order analyze performance developed framework, pilot sub-region named Yar Hussain selected experimentation work. tehsil district Swabi, within KP having highest contribution gross production crop. generally consists diverse land different...
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 shapes, making manual detection magnetic resonance imaging (MRI) scans a subjective challenging task for healthcare professionals, hence necessitating automated solutions. This study investigates potential of deep learning, specifically DenseNet architecture, automate brain tumor...
<span lang="EN-US">Deep learning (DL) techniques are effective in various applications, such as parameter estimation, image classification, recognition, and anomaly detection. They excel with abundant training data but struggle limited data. To overcome this, transfer is commonly used, leveraging complex abilities, saving time, handling labeled This study assesses a (TL)-based pre-trained “deep convolutional neural network (DCNN)” for classifying land use cover using imbalanced dataset...
This study intends to classify the land cover of an area especially small farmlands using object-based image analysis (OBIA) method and evaluates performance a supervised classifier. Multi-spectral Sentinel-2 imagery which is freely available used four classifiers are applied it. The was divided into major classes namely Urban, Wheat, Tobacco Other Vegetation with varying accuracy values. first resampled 10 m spatial resolution then NDI45 layer stacked A widely MRS technique for delineating...
This article was withdrawn and retracted by the Journal of Fundamental Applied Sciences and has been removed from AJOL at the request journal Editor in Chief organisers conference which articles were presented ( www.iccmit.net ). Please address any queries to editor@jfas.info.
Due to the rapid growth of population food need also increases which is center focus for various researchers and governments.For this purpose crop information system has been made, aim monitor health estimate needs next four five years.Geo graphic plays an important role in estimation identification.GIS uses remote sensing technique identify crops their yield.In paper novel approaches are used identification tobacco.SPOT 5 imagery having resolution 2.5m tobacco.For post processing,...
As Human population is increasing, a number of small towns are turning into big cities. But human race has developed itself in technological terms smartly, which helping kind to act efficiently and consume the resources appropriately. Collection urban sprawl statistics an area become efficient by using remote sensing. In comparison traditional methods, new method sensing for detection classification substantially enhanced. Using this data management capable taking suitable measures its...