A5029470367- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Solar Radiation and Photovoltaics
- IoT and Edge/Fog Computing
- Neural Networks and Applications
- Cloud Computing and Resource Management
- Smart Agriculture and AI
- Digital Imaging for Blood Diseases
- Metaheuristic Optimization Algorithms Research
- Cutaneous Melanoma Detection and Management
- Photovoltaic System Optimization Techniques
- Retinal Diseases and Treatments
- Text and Document Classification Technologies
- Caching and Content Delivery
- Machine Learning and ELM
- Medical Image Segmentation Techniques
- Atmospheric aerosols and clouds
- Machine Learning and Data Classification
- Vehicle License Plate Recognition
- Head and Neck Cancer Studies
- Handwritten Text Recognition Techniques
- Climate variability and models
- Solar Thermal and Photovoltaic Systems
Chungbuk National University
2025
Université de Haute-Alsace
2023-2024
COMSATS University Islamabad
2018-2022
Virtual University of Pakistan
2022
University of Engineering and Technology Lahore
2021
Abstract Melanoma is considered to be one of the deadliest skin cancer types, whose occurring frequency elevated in last few years; its earlier diagnosis, however, significantly increases chances patients’ survival. In quest for same, a computer based methods, capable diagnosing lesion at initial stages, have been recently proposed. Despite some success, margin exists, due which machine learning community still considers this an outstanding research challenge. work, we come up with novel...
According to statistics, there are 422 million speakers of the Arabic language. Islam is second-largest religion in world, and its followers constitute approximately 25% world’s population. Since Holy Quran Arabic, nearly all Muslims understand language per some analytical information. Many countries have as their native official well. In recent years, number internet users speaking has been increased, but very little work on it due complications. It challenging build a robust recognition...
The exponential growth of population in developing countries like India should focus on innovative technologies the Agricultural process to meet future crisis. One vital tasks is crop yield prediction at its early stage; because it forms one most challenging precision agriculture as demands a deep understanding pattern with highly nonlinear parameters. Environmental parameters rainfall, temperature, humidity, and management practices fertilizers, pesticides, irrigation are very dynamic...
Astrocytoma IV or glioblastoma is one of the fatal and dangerous types brain tumors. Early detection tumor increases survival rate helps in reducing fatality rate. Various imaging modalities have been used for diagnosing by expert radiologists, Medical Resonance Image (MRI) considered a better option detecting tumors as MRI non-invasive technique provides visualization region. One challenging issues to identify tumorous region from scans correctly. Manual segmentation performed medical...
Abstract The precise detection and segmentation of pectoral muscle areas in mediolateral oblique (MLO) views is an essential step the development a computer‐aided diagnosis system to access breast malignant lesions or parenchyma. goal this article develop robust fully automatic algorithm for from mammography images. This paper presents image enhancement approach that improves quality mammogram scans convolutional neural network‐based network architecture enhanced with residual connections...
Tumor detection has been an active research topic in recent years due to the high mortality rate. Computer vision (CV) and image processing techniques have recently become popular for detecting tumors MRI images. The automated process is simpler takes less time than manual processing. In addition, difference expanding shape of brain tumor tissues complicates clinicians. We proposed a new framework as well classification into relevant categories this paper. For segmentation, employs Particle...
Diabetes or Mellitus (DM) is the upset that happens due to high glucose level within body. With passage of time, this polygenic disease creates eye deficiency referred as Diabetic Retinopathy (DR) which can cause a major loss vision. The symptoms typically originate retinal space square in form enlarged veins, liquid dribble, exudates, haemorrhages and small scale aneurysms. In current therapeutic science, pictures are key device for an exact finding patients’ illness. Meanwhile, assessment...
Building an automatic fish recognition and detection system for large-scale classes is helpful marine researchers scientists because there are large numbers of species. However, it quite difficult to build such systems owing the lack data imbalance problems number classes. To solve these issues, we propose a transfer learning-based technique in which use Efficient-Net, pre-trained on ImageNet dataset fine-tuned QuT Fish Database, scale dataset. Furthermore, prior activation layer, Global...
Abstract Glioblastoma (GBM) is the most high‐risk and grievous tumour in brain that causes death of more than 50% patients within one to 2 years after diagnosis. Accurate detection prognosis this disease are critical provide essential guidelines for treatment planning. This study proposed using a deep learning‐based network GBM segmentation radiomic features patient's overall survival (OS) time prediction. The model used was modified U‐Net‐based 3D multi‐level dilated convolutional neural...
This paper presents hourly Global Horizontal Irradiance (GHI) measured data at three stations (Lahore, Multan, Bahawalpur) in Punjab, Pakistan. The estimated GHI from reanalysis datasets have also been presented. Clearness index (KT), Solar zenith angle (θsza) and Periodicity factor (Pf) were calculated used to develop bias correction models. corrected using best model M20 for years 2015 2016 is
Brain tumors have existed for a long time, but their rate is increasing among all age groups. Early detection essential timely prognosis as it dangerous and life-threatening disease. Since the advent of artificial intelligence machine learning, different algorithms been proposed to classify segment brain tumors. However, limitations when comes local deployment. The main drawback designing multiple architectures tasks, which increases time computational complexity affects performance. This...
Pashto is a language that belongs to the Indo-European family, mostly spoken in South Asian countries, especially Pakistan and Afghanistan. To build software enables us translate sentences into various languages building Natural Language Understand (NLU) applications make interactive requires well-defined corpus Parts of Speech (POS) tagging approach. Therefore, developed by scraping data from different websites. We have prepared dataset according guidelines written for Persian Arabic...
Recently, Deep Learning (DL) algorithms have shown state-of-the-art performance in numerous tasks. The design of DL is time-consuming process that requires expert-level knowledge. To overcome this problem, Neural Architecture Search (NAS) proposed, which automatically searches for the best neural network architecture a given task. Indeed, evolutionary NAS has emerged as widely studied research area, are used to networks. In study, we proposed novel encoding scheme represent Convolutional...