- Medical Image Segmentation Techniques
- Hate Speech and Cyberbullying Detection
- Advanced Image Processing Techniques
- Oral health in cancer treatment
- Image and Signal Denoising Methods
- AI in cancer detection
- Image Retrieval and Classification Techniques
- Image and Object Detection Techniques
- Medical Imaging Techniques and Applications
- Infectious Diseases and Tuberculosis
- Politics and Conflicts in Afghanistan, Pakistan, and Middle East
- Radiomics and Machine Learning in Medical Imaging
- Vehicle License Plate Recognition
- Multilingual Education and Policy
- Neutropenia and Cancer Infections
- Swearing, Euphemism, Multilingualism
- Intestinal and Peritoneal Adhesions
- Second Language Acquisition and Learning
- Air Traffic Management and Optimization
- Early Childhood Education and Development
- DNA and Biological Computing
- Ginger and Zingiberaceae research
- Anomaly Detection Techniques and Applications
- Academic integrity and plagiarism
- Cellular Automata and Applications
National University of Sciences and Technology
2014-2024
Qurtuba University of Science and Information Technology
2023
Military Hospital
2023
National University of Medical Sciences
2023
Raisoni Group of Institutions
2023
National University of Technology
2022
Capital University of Science and Technology
2022
Hubei University of Science and Technology
2022
Mayo Hospital
2022
Hazara University
2022
In this study, the authors propose a real‐time multiple licence plate (LP) detection algorithm for dense traffic conditions which is of vital importance in modern era due to increased congestion. The chromatic component YDbDr colour space proposed detect blue regions, whereas simple yet effective method used identify yellow LP regions. low‐intensity pixel values are eliminated as pre‐processing step enhance regions and Otsu obtain binary image. candidate acquired by using connected analysis....
Adverse drug reactions (ADRs) are the undesirable effects associated with use of a due to some pharmacological action drug. During last few years, social media has become popular platform where people discuss their health problems and, therefore, source share information related ADR in natural language. This paper presents an end-to-end system for modelling detection from given text by fine-tuning BERT highly modular Framework Adapting Representation Models (FARM). overcame predominant...
Automatic identification of offensive/abusive language is very necessary to get rid unwanted behavior. However, it more challenging generalize the solution due different grammatical structures and vocabulary each language. Most prior work targeted western languages, however, one study a low-resource (Urdu). The used basic linguistic features small dataset. This designed new dataset (collected from popular Pakistani Facebook pages) containing 7,500 posts for offensive detection in Urdu....
Background: Acute watery diarrhea remains one of the leading causes mortality and morbidity in children under five years age, particularly low- middle-income countries. Rapid fluid loss can result severe dehydration, necessitating effective management to reduce complications. Although oral rehydration therapy is cornerstone treatment, adjunct therapies such as antisecretory agents are being explored improve outcomes. Racecadotril has emerged a promising option; however, its local efficacy...
Background: The use of AI-powered nursing aides in the healthcare sector promises to improve efficiency, reduce staff workload, and increase patient outcomes. Still, how workers are utilizing benefiting from AI solutions remains an area study. This research seeks understand effectiveness, perceptions, challenges clinical context. Methods: study utilized a quantitative approach form descriptive cross-sectional survey targeting 250 workers, including doctors, nurses, hospital managers. A...
Background: Iron deficiency anemia (IDA) is the most common nutritional affecting children globally and contributes significantly to morbidity developmental delays. While iron sucrose has been extensively studied in adult populations, especially pregnancy, limited data exists comparing its efficacy with polymaltose complex pediatric patients. Given importance of effective well-tolerated treatment options for children, this study aimed provide clinical evidence guide replacement therapy IDA....
Background: Meningoencephalitis remains a significant cause of pediatric morbidity and mortality globally, particularly in low- middle-income countries. Prompt medical intervention is considered critical reducing adverse outcomes, yet limited data exists from local settings on how hospitalization timing impacts recovery survival. Given the lack comparative evidence within Pakistan, evaluating influence early versus late clinical outcomes meningoencephalitis both timely essential. Objective:...
Automated systems for road crack detection are extremely important in maintenance vehicle safety and traveler’s comfort. Emerging cracks roads need to be detected accordingly repaired as early possible avoid further damage thus reducing rehabilitation cost. In this paper, a robust method Gabor filter parameters optimization automatic is discussed. has been used previous literature similar applications. However, there selection of optimized due variation texture cracks. The problem change...
A complex domain‐based approach of active contour model has been proposed for image segmentation which deforms iteratively to partition an into various useful regions. new region‐based pressure force function designed gives shape the dynamic using forces, and efficiently control propagation moving interface. This makes level set binary, uses Gaussian smoothing kernel regulate avoid re‐initialisation procedure. The working scheme is as: real data converted by iota ( i ) times average...
This paper presents the design of a multi-axis capacitive tactile force sensor with fully decoupled output response for input normal and shear forces. A patterned elastomer is used as dielectric layer between electrodes that allows to achieve relatively higher sensitivity. The fabricated utilizing low-cost rapid prototyping technique characterized forces in range 0 ~ 10 N 3.1 respectively. achieved sensitivity axis 2.03%/N axes 1.67%/N. difference estimated from actual applied negligible,...
Today, English has emerged as an important means of communication across the world including Pakistan. In Pakistan, it enjoys status second language is offered a compulsory subject from primary level up to higher classes. addition, there great need and demand for having sound grasp over encounter professional challenges. However, Pakistani learners still face various problems while speaking writing English. This study examined abuse prepositions by learners. It focused on types prepositional...
Objective: To find out the frequency of Helicobacter Pylori infection in children with recurrent abdominal pain. Study Design: Cross Sectional study. Setting: Pediatric Medicine, Children Hospital and Institute Child Health, Multan. Period: November 2020 to May 2021. Material & Methods: A total 148 both genders aged 4-12 years presenting pain were included. Detailed history physical examination was conducted. Frequency helicobacter pylori noted it association characteristics studied...
A novel region based Active Contour Model (ACM) for image segmentation is presented using local information intensity inhomogeneity images. transcendental (trigonometric) energy functional on Local Fitted Image (LFI) suggested to extract the information. The difference between original and fitting introduced as an angular constraint of trigonometric function. This new approach has ability handle images with severe inhomogeneity, multiple classes regions non-homogeneous pixel intensities. To...
The Big Data analytics are a logical analysis of very large scale datasets. data enhances an organization and improve the decision making process. In this article, we present Airline Delay Analysis Prediction to analyze airline datasets with combination weather dataset. research work, consider various attributes flight delay, for example, day-wise, airline-wise, cloud cover, temperature, etc. Moreover, rigorous experiments on machine learning model predict correctly delay flight, namely,...
For Tracking interfaces and shapes which depends on the regions of pixel intensity is a challenging task in image segmentation.Many level set methods have been formulated for region based edge models computer aided diagnosis systems.In order to provide accurate modeling involving numerical computations, contours, lesions bias variance often rely variations Interest.The proposed method involves formulation by deriving global criterion function terms neighborhood pixels represent domain field...
Machine learning (ML)-based algorithms are playing an important role in cancer diagnosis and increasingly being used to aid clinical decision-making. However, these commonly operate as 'black boxes' it is unclear how decisions derived. Recently, techniques have been applied help us understand specific ML models work explain the rational for outputs. This study aims determine why a given type of has certain phenotypic characteristic. Cancer results cellular dysregulation thorough...
Objective: To determine the frequency of functional improvement in patients COPD receiving low-dose Theophylline.
 Study Design: Case series.
 Place and Duration Study: Junior Leaders Academy Hospital, Shinkiari, Mansehra Pakistan, from Feb to Jul 2021.
 Methodology: Patients with a previous chronic obstructive pulmonary disease diagnosis Global Initiative for Chronic Obstructive Lung Disease stage 2/3, taking long-acting muscarinic antagonists were included study. In...
Generating premium datasets is essential for developing and executing precise machine learning models. A dataset contains interlinked components of information organized in a defined model, while models identify recurrent events within the data. To generate image datasets, our offered mechanism uses several sources, including online libraries. The outcome can be modified according to user's inclinations, enabling its implementation areas like computer vision, face recognition, medical...
Driving space detection is one of the basic steps for autonomous guidance vehicles. In this paper a real time road segmentation algorithm proposed identifying driving space. The presented uses concept appearance based object (ABOD) to detect traversable area input image partitioned as and off each individual pixel classified either or non traversable. It Mean Shift Algorithm then ABOD on segmented separate areas.