- Metaheuristic Optimization Algorithms Research
- Neural Networks and Applications
- Evolutionary Algorithms and Applications
- Advanced Multi-Objective Optimization Algorithms
- Stock Market Forecasting Methods
- Energy Load and Power Forecasting
- Blockchain Technology Applications and Security
- IoT and Edge/Fog Computing
- AI in cancer detection
- Forecasting Techniques and Applications
- Complex Systems and Time Series Analysis
- Spectroscopy and Chemometric Analyses
- Optimization and Mathematical Programming
- Time Series Analysis and Forecasting
- Topic Modeling
- Natural Language Processing Techniques
- COVID-19 diagnosis using AI
- Cryptography and Data Security
- Machine Learning in Healthcare
- Software System Performance and Reliability
- Software Engineering Research
- Advanced Text Analysis Techniques
- Fluid Dynamics and Thin Films
- Software Testing and Debugging Techniques
- Brain Tumor Detection and Classification
King Khalid University
2016-2024
Kohat University of Science and Technology
2021
Smart Homes
2019
Ion Exchange (India)
2019
King Khaled Hospital
2018
Islamic University of Madinah
2015-2017
Tun Hussein Onn University of Malaysia
2012-2014
Information Technology University
2011
Nowadays, cloud-based storage systems play a vital role in IoT data storage, processing, and sharing. Despite its contribution, the current architecture may cause severe leakage or jeopardize user privacy. Meanwhile, heavily relies on trusted third-party auditor (TPA) runs centralized control manner. However, TPA not be completely trustworthy entity, single point of failure might system to collapse. Fortunately, with advent blockchain technology, decentralized model has gained popularity. A...
The purpose of this research is to demonstrate the ability machine-learning (ML) methods for liver cancer classification using a fused dataset two-dimensional (2D) computed tomography (CT) scans and magnetic resonance imaging (MRI). Datasets benign (hepatocellular adenoma, hemangioma, cyst) malignant carcinoma, hepatoblastoma, metastasis) were acquired at Bahawal Victoria Hospital (BVH), Bahawalpur, Pakistan. final was generated by fusion 1200 (100 × 6 2) MR CT-scan images, 200 MRI 100...
Extractive text summarization involves selecting and combining key sentences directly from the original text, rather than generating new content. While various methods, both statistical graph-based, have been explored for this purpose, accurately capturing intended meaning remains a challenge. To address this, researchers are investigating innovative techniques that harness deep learning models like BERT (Bidirectional Encoder Representations Transformers). However, has limitations in...
Histopathology images are very distinctive, and one image may contain thousands of objects. Transferring features from natural to histopathology not provide impressive outcomes. In this study, we have proposed a novel modality-specific CBAM-VGGNet model for classifying H E stained breast images. Instead using pre-trained models on ImageNet, trained VGG16 VGG19 the same domain cancerous datasets which then used as fixed feature extractors. We added GAP layer Convolutional block attention...
In this emerging computing and digital globe, information Knowledge are created then collected with a rapid approach by wide range of applications through scientific commercial workloads. Over 3.8 billion people out 7.6 population the world connected to internet. Out 13.4 devices, 8.06 devices have mobile connection. 2020, 38.5 will be globally internet traffic 92 times greater than it was in 2005. The use such not only increase data volume but velocity market brings fast-track accelerates...
Energy is considered the most costly and scarce resource, demand for it increasing daily. Globally, a significant amount of energy consumed in residential buildings, i.e., 30–40% total consumption. An active prediction system highly desirable efficient production utilization. In this paper, we have proposed methodology to predict short-term consumption building. The consisted four different layers, namely data acquisition, preprocessing, prediction, performance evaluation. For experimental...
Smart manufacturing is pivotal in the context of Industry 4.0, as it integrates advanced technologies like Internet Things (IoT) and automation to streamline production processes improve product quality, paving way for a competitive industrial landscape. Machines have become network-based through IoT, where integrated collaborated system responds real time meet demand fluctuations personalized customization. Within (NBMS), mobile robots (MiRs) are vital increasing operational efficiency,...
A recently developed language representation model named Bidirectional Encoder Representation from Transformers (BERT) is based on an advanced trained deep learning approach that has achieved excellent results in many complex tasks, the same as classification, Natural Language Processing (NLP), prediction, etc. This survey paper mainly adopts summary of BERT, its multiple types, and latest developments applications various computer science engineering fields. Furthermore, it puts forward...
Internet of Drones (IoD) is a decentralized networking architecture that makes use the internet for uniting drones to enter controlled airspace in coordinated manner. On one hand, this new clan interconnected has ushered era real-world applications; Small drones, on other are generally not designed with security mind, making them exposed fundamental and privacy concerns. Limited computing capabilities, along communication over an open wireless channel, exacerbate these challenges, IoD...
Internet of Things-enabled smart grid (SG) technology provides ample advantages to traditional power grids. In an SG system, the meter (SM) is critical component that collects usage information related users and delivers accumulated vital central service provider (CSP) via Internet, imperiled numerous pernicious security threats. Consequently, it crucial preserve integrity communication between SMs CSP for smooth running system. Authentication protocol effectively enables SM communicate...
The objective of this work is to present a Quick Gbest Guided artificial bee colony (ABC) learning algorithm train the feedforward neural network (QGGABC-FFNN) model for prediction trends in stock markets. As it quite important know that nowadays, market significant financial global issue. scientists, finance administration, companies, and leadership given country struggle towards developing strong position. Several technical, industrial, fundamental, scientific, statistical tools have been...
Abstract The present paper related to thin film flows of two immiscible third grade fluids past a vertical moving belt with slip conditions in the presence uniform magnetic field. Immiscible we mean superposed different densities and viscosities. basic governing equations continuity, momentum energy are incorporated. modeled coupled solved analytically by using Adomian Decomposition Method (ADM) along Homotopy Analysis (HAM). residual errors show authentication work. For comparison,...
Brain Hemorrhage is the eruption of brain arteries due to high blood pressure or clotting that could be a cause traumatic injury death. It medical emergency in which doctor also need years experience immediately diagnose region internal bleeding before starting treatment. In this study, deep learning models Convolutional Neural Network (CNN), hybrid CNN + LSTM and GRU are proposed for classification. The 200 head CT scan images dataset used boost accuracy rate computational power models....
Document Image Analysis (DIA) is one of the research areas Artificial Intelligence (AI) that converts document images into machine-readable codes. In DIA systems, Optical Character Recognition (OCR) plays a key role in digitizing images. The output an OCR system further used many applications including, Natural Language Processing (NLP), Sentiment Analysis, Speech Recognition, and Translation Services. However, standard datasets are essential requirement for development, evaluation...
Customer satisfaction and loyalty are essential for every business. Feedback prediction social media classification crucial play a key role in accurately identifying customer satisfaction. This paper presents sentiment analysis-based feedback based on Twitter Arabic datasets of telecommunications companies Saudi Arabia. The human brain, which contains billions neurons, provides the current past experience provided by services other related stakeholders. Artificial Intelligent (AI) methods,...
Nowadays, computer scientists have shown the interest in study of social insect's behaviour neural networks area for solving different combinatorial and statistical problems. Chief among these is Artificial Bee Colony (ABC) algorithm. This paper investigates use ABC algorithm that simulates intelligent foraging a honey bee swarm. Multilayer Perceptron (MLP) trained with standard back propagation normally utilises computationally intensive training algorithms. One crucial problems...
Unmanned aerial vehicles/drones are considered an essential ingredient of traffic motoring systems in smart cities. Interconnected drones, also called the Internet Drones (IoD), gather critical data from environmental area interest and transmit to a server located at control room for further processing. This transmission occurs via wireless communication channels, which exposed various security risks. Besides this, External User (EU) occasionally demands access real-time information stored...
One of the most common causes mortality for women globally is breast cancer. Early cancer identification could make it possible people to receive appropriate treatment save their lives and return routine lives. Breast diagnosis by histopathology referred as gold standard. In recent years, convolutional neural network-based techniques are used classification. However, they faced domain adaptation, small objects retention, feature extraction issues complex microscopic images. this study, we...
Different algorithms have been used for training neural networks (NNs) such as back propagation (BP), gradient descent (GA), partial swarm optimization (PSO), and ant colony algorithm (ACO). Most of these focused on NNs weight values, activation functions, network structures providing optimal outputs. Ordinary BP is one well known technique which updates the values minimizing error but still it has some drawbacks trapping in local minima slow convergence. Therefore, this work a population...
Numerous computational algorithms are used to obtain a high performance in solving mathematics, engineering and statistical complexities. Recently, an attractive bio-inspired method—namely the Artificial Bee Colony (ABC)—has shown outstanding with some typical different complex problems. The modification, hybridization improvement strategies made ABC more science researchers. two well-known honeybees-based upgraded algorithms, Gbest Guided (GGABC) Global Search (GABCS), use foraging behavior...
In recent years, the significant growth in Internet of Things (IoT) technology has brought a lot attention to information and communication industry. Various IoT paradigms like Vehicle (IoVT) Health (IoHT) create massive volumes data every day which consume bandwidth storage. However, process such large data, existing cloud computing platforms offer limited resources due their distance from devices. Consequently, cloud-computing systems produce intolerable latency problems for...