- Biomedical Text Mining and Ontologies
- Online Learning and Analytics
- Semantic Web and Ontologies
- Energy Efficient Wireless Sensor Networks
- Topic Modeling
- Service-Oriented Architecture and Web Services
- Data Mining Algorithms and Applications
- Academic integrity and plagiarism
- Underwater Vehicles and Communication Systems
- Business Process Modeling and Analysis
- Rough Sets and Fuzzy Logic
- Natural Language Processing Techniques
- Artificial Intelligence in Healthcare
- Model-Driven Software Engineering Techniques
- Data Management and Algorithms
- Generative Adversarial Networks and Image Synthesis
- Personal Information Management and User Behavior
- Advanced Image and Video Retrieval Techniques
- Advanced Text Analysis Techniques
- Text and Document Classification Technologies
- Video Analysis and Summarization
- Information Systems and Technology Applications
- Software System Performance and Reliability
- Energy Harvesting in Wireless Networks
- Cloud Computing and Resource Management
Saudi Electronic University
2020-2025
National University of Sciences and Technology
2012-2024
University of the Sciences
2015-2016
Shaheed Zulfiqar Ali Bhutto Institute of Science and Technology
2009
Cardiovascular diseases are considered as the most life-threatening syndromes with highest mortality rate globally. Over a period of time, they have become very common and now overstretching healthcare systems countries. The major factors cardiovascular high blood pressure, family history, stress, age, gender, cholesterol, Body Mass Index (BMI), unhealthy lifestyle. Based on these factors, researchers proposed various approaches for early diagnosis. However, accuracy techniques needs certain...
Vehicular networks improve quality of life, security, and safety, making them crucial to smart city development. With the rapid advancement intelligent vehicles, confidentiality security concerns surrounding vehicular ad hoc (VANETs) have garnered considerable attention. VANETs are intrinsically more vulnerable attacks than wired due high mobility, common network medium, lack centrally managed services. Intrusion detection (ID) servers first protection layer against cyberattacks in this...
Security in today's world is one of the important challenges that people are facing all over every aspect their lives.Similarly security electronic has a great significance.In this paper, we survey database.This an area substantial interest database because know that, use becoming very enterprise and databases contains information major asset.This was conducted to identify issues threats security, requirements how encryption used at different levels provide security.
The trend of learning from videos instead documents has increased. There could be hundreds and thousands on a single topic, with varying degrees context, content, depth the topic. literature claims that learners are nowadays less interested in viewing complete video but prefers topic their interests. This develops need for indexing lectures. Manual annotation or topic-wise is not new case videos. However, manual time-consuming due to length typical lecture intricate storylines. Automatic is,...
Image colorization is the process of estimating RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality. Deep learning techniques image have progressed notably over last decade, calling need a systematic survey benchmarking these techniques. This article presents comprehensive recent state-of-the-art deep learning-based techniques, describing fundamental block architectures, inputs, optimizers, loss functions, training protocols, data \textit{etc.}...
The information extraction from unstructured text segments is a complex task. Although manual often produces the best results, it harder to manage biomedical data manually because of exponential increase in size. Thus, there need for automatic tools and techniques mining. Relation significant area under that has gained much importance last two decades. A lot work been done on relation focusing rule-based machine learning techniques. In decade, focus changed hybrid approaches showing better...
In a serverless cloud computing environment, the provider dynamically manages allocation of resources whereas developers purely focus on their applications. The data-driven applications in mainly address web as well other distributed scenarios, and therefore, it is essential to offer consistent user experience across different connection types. order issues application real-time use GraphQL (Graph Query Language) getting more popularity state-of-the-art approaches. However, existing...
Supervised learning is the process of data mining for deducing rules from training datasets. A broad array supervised algorithms exists, every one them with its own advantages and drawbacks. There are some basic issues that affect accuracy classifier while solving a problem, like bias-variance tradeoff, dimensionality input space, noise in space. All these problems reason there no global optimal method classification. not any generalized improvement can increase addressing all stated above....
Pneumothorax, a life-threatening disease, needs to be diagnosed immediately and efficiently. The prognosis, in this case, is not only time-consuming but also prone human errors. So, an automatic way of accurate diagnosis using chest X-rays the utmost requirement. To date, most available medical image datasets have class-imbalance (CI) issue. main theme study solve problem along with proposing automated detecting pneumothorax. find optimal approach for CI problem, we first compare existing...
In this paper, a novel rotation and scale invariant approach for texture classification based on Gabor filters has been proposed. These are designed to capture the visual content of images their impulse responses which sensitive scaling in images. The filter rearranged according exhibiting response having largest amplitude, followed by calculation patterns after binarizing particular threshold. This threshold is obtained as average energy at pixel. binary converted decimal numbers,...
Availablity of information, agility business process, interoperability diverse functions and conformity the legal requirements are few critical success factors for enterprises to survive in modern competing global market space. Enterprises while striving achieve these further exposed complexity massive volumes variant data which exists a broad array formats. Complex extended processes spanning across partners around globe, need integration interoperability, fulfullment compliance regulatory...
Industrial organizations are turning to recommender systems (RSs) provide more personalized experiences customers. This technology provides an efficient solution the over-choice problem by quickly combing through large amounts of information and supplying recommendations that fit each user's individual preferences. It is becoming integral part operations, as it yields successful convenient results. research enhanced integrated fuzzy logic-based deep learning technique (EIFL-DL) for recent...
Since the emergence of mobile devices, architecture applications has been transformed significantly. In applications, User Interface (UI) is one major elements, but its development complex and time-consuming. Existing practices do not support various presentation issues UI at a higher abstraction level, in retargetable fashion, with complete tool support. Therefore, it critical to develop simple automated framework for UIs by exploiting model-driven engineering concepts. this paper, Unified...
Contemporary researches have revealed that most of the diseases are genetic. It is very important to mine relation between gene and disease. Ontology best method show concepts their relations. This research paper focuses on development ontology for domain Genetic Diseases. The data extracted from UMLS. We developed this Protégé tool also a live portal (link: http://62.151.179.113/ontology) facilitate end users clinical researchers. resultant evaluated by experts results reported in paper.
Feature selection reduces a data set into subset which also represents the entire with less computational complexity and performance does not affect much. However, to extract such is nontrivial task although there are number of methods handle this problem. In near past an approach based on rough have been used for feature selection. The dependency measure one ways find out minimal subset, called Reducts, from dataset. One mature areas reduction techniques theory, totally depends concept sets...
The Internet of Things (IoT)-based intelligent surveillance systems in smart cities are a challenging issue as various devices capture the data. These devices, deployed close to underlined phenomenon, such cameras, duplicated or redundant accuracy is main requirement these systems. For this purpose, sensor nodes provide 24/7 monitoring city, which minimizes security risks and enables quick response case any disaster. However, due large number huge data generated; thus, controlling traffic...
In this research, we applied personality psychology within Social Engineering to raise security awareness and identify the level of Dominance, Influence, Steadiness, Conscientiousness (DiSC) Personality Model William Moulton Marston, 1928. By convincing people click a scam but safe URL through an email message (URL Phishing) phrased be based on every person's pattern, were able effectively conduct pilot study. This forwards user (or victim) landing page with warning, countermeasures...
Cloud computing is a modern paradigm that significantly reduces development, deployment and maintenance cost of software systems. Model Driven Engineering (MDE) system development approach considered to be highly supportive for cloud due its proven reusability portability features. This article comprehensively investigates the application MDE in computing. To achieve this, Systematic Literature Review (SLR) has been carried out select analyze 25 research works published during 2009-2016....
An efficient and robust alarms management is an extremely desirable feature to prevent critical failures in modern Industrial Control Systems. Generally, alarm systems are categorized into two major components; i.e., Alarm Server Client. server responsible process on real time values, while clients display the generated alarms. With advent of technologies, like, Internet Thing (IoT), need for mobile has significantly been increased, as be displayed different gadgets instead traditional big...