A5091151166- IoT and Edge/Fog Computing
- Blockchain Technology Applications and Security
- COVID-19 diagnosis using AI
- Brain Tumor Detection and Classification
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare
- Fuzzy and Soft Set Theory
- Multi-Criteria Decision Making
- Context-Aware Activity Recognition Systems
- EEG and Brain-Computer Interfaces
- Network Security and Intrusion Detection
- Medical Image Segmentation Techniques
- Internet Traffic Analysis and Secure E-voting
- Advanced Neural Network Applications
- ECG Monitoring and Analysis
- Anomaly Detection Techniques and Applications
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Voice and Speech Disorders
- Advanced Malware Detection Techniques
- Cloud Computing and Resource Management
- Digital Imaging for Blood Diseases
- Vehicular Ad Hoc Networks (VANETs)
- Privacy-Preserving Technologies in Data
Baghdad Medical City
2024-2025
University of Anbar
2016-2024
VSB - Technical University of Ostrava
2022-2024
Technical University of Malaysia Malacca
2017-2024
University of Monastir
2024
Naval Academy
2023
Universidad de Deusto
2023
Ministry of Higher Education and Scientific Research
2023
Ştefan cel Mare University of Suceava
2022
Dehradun Institute of Technology University
2022
Using gestures can help people with certain disabilities in communicating other people. This paper proposes a lightweight model based on YOLO (You Only Look Once) v3 and DarkNet-53 convolutional neural networks for gesture recognition without additional preprocessing, image filtering, enhancement of images. The proposed achieved high accuracy even complex environment, it successfully detected low-resolution picture mode. was evaluated labeled dataset hand both Pascal VOC format. We better...
Nowadays, coronavirus (COVID-19) is getting international attention due it considered as a life-threatened epidemic disease that hard to control the spread of infection around world. Machine learning (ML) one intelligent technique able automatically predict event with reasonable accuracy based on experience and process. In meantime, rapid number ML models have been proposed for predicate cases COVID-19. Thus, there need an evaluation benchmarking COVID-19 which main challenge this study....
The aim of this study is to propose a model based on machine learning (ML) and Internet Things (IoT) diagnose patients with COVID-19 in smart hospitals. In sense, it was emphasized that by the representation for role ML models IoT relevant technologies hospital environment. accuracy rate diagnosis (classification) laboratory findings can be improved via light models. Three models, namely, naive Bayes (NB), Random Forest (RF), support vector (SVM), were trained tested basis datasets. main...
The outbreaks of Coronavirus (COVID-19) epidemic have increased the pressure on healthcare and medical systems worldwide. timely diagnosis infected patients is a critical step to limit spread COVID-19 epidemic. chest radiography imaging has shown be an effective screening technique in diagnosing To reduce radiologists control epidemic, fast accurate hybrid deep learning framework for virus X-ray images developed termed as COVID-CheXNet system. First, contrast image was enhanced noise level...
Voice pathology disorders can be effectively detected using computer-aided voice classification tools. These tools diagnose pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction detection tool based on Deep Learning. In this paper, pre-trained Convolutional Neural Network (CNN) was applied dataset of maximize the accuracy. also proposes distinguished training method combined with various strategies in order generalize...
Globally, breast cancer is one of the most significant causes death among women. Early detection accompanied by prompt treatment can reduce risk due to cancer. Currently, machine learning in cloud computing plays a pivotal role disease diagnosis, but predominantly people living remote areas where medical facilities are scarce. Diagnosis systems based on act as secondary readers and assist radiologists proper diagnosis diseases, whereas cloud-based support telehealth services diagnostics....
Until now, an effective defense method against Distributed Denial of Service (DDoS) attacks is yet to be offered by security systems. Incidents serious damage due DDoS have been increasing, thereby leading urgent need for new attack identification, mitigation, and prevention mechanisms. To prevent attacks, the basic features dynamically analyzed because their patterns, ports, protocols or operation mechanisms are rapidly changed manipulated. Most proposed methods different types drawbacks...
COVID-19 is the disease evoked by a new breed of coronavirus called severe acute respiratory syndrome 2 (SARS-CoV-2). Recently, has become pandemic infecting more than 152 million people in over 216 countries and territories. The exponential increase number infections rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) machine (ML), which can assist healthcare sector providing quick...
These days, the usage of machine-learning-enabled dynamic Internet Medical Things (IoMT) systems with multiple technologies for digital healthcare applications has been growing progressively in practice. Machine learning plays a vital role IoMT system to balance load between delay and energy. However, traditional models fraud on data distributed are still critical research problem The study devises federated learning-based blockchain-enabled task scheduling (FL-BETS) framework different...
The most commonly injured ligament in the human body is an anterior cruciate (ACL). ACL injury standard among football, basketball and soccer players. study aims to detect early stage via efficient thorough automatic magnetic resonance imaging without involving radiologists, through a deep learning method. proposed approach this paper used customized 14 layers ResNet-14 architecture of convolutional neural network (CNN) with six different directions by using class balancing data...
Recently, development in intelligent transportation systems (ITS) requires the input of various kinds data real-time and from multiple sources, which imposes additional research application challenges. Ongoing studies on Data Fusion (DF) have produced significant improvement ITS manifested an enormous impact its growth. This paper reviews implementation DF methods to facilitate traffic flow analysis (TFA) solutions that entail prediction variables such as driving behavior, travel time,...
Coronavirus (COVID-19) epidemic outbreak has devastating effects on daily lives and healthcare systems worldwide. This newly recognized virus is highly transmissible, no clinically approved vaccine or antiviral medicine currently available. Early diagnosis of infected patients through effective screening needed to control the rapid spread this virus. Chest radiography imaging an tool for COVID-19 follow-up. Here, a novel hybrid multimodal deep learning system identifying in chest X-ray...
In recent years the amount of malware spreading through internet and infecting computers other communication devices has tremendously increased. To date, countless techniques methodologies have been proposed to detect neutralize these malicious agents. However, as new automated generation emerge, a lot continues be produced, which can bypass some state-of-the-art detection methods. Therefore, there is need for classification adversarial agents that compromise security people, organizations,...
Concrete is the most commonly used construction material. The physical properties of concrete vary with type concrete, such as high and ultra-high-strength fibre-reinforced polymer-modified lightweight concrete. precise prediction a problem due to design code, which typically requires specific characteristics. emergence new category technology has motivated researchers develop mechanical strength models using Artificial Intelligence (AI). Empirical statistical have been extensively used....
Detecting multiple ocular diseases in fundus images is crucial ophthalmic diagnosis. This study introduces the Fundus-DeepNet system, an automated multi-label deep learning classification system designed to identify by integrating feature representations from pairs of (e.g., left and right eyes). The initiates with a comprehensive image pre-processing procedure, including circular border cropping, resizing, contrast enhancement, noise removal, data augmentation. Subsequently, discriminative...
Summary The accuracy of brain tumor diagnosis based on medical images is greatly affected by the segmentation process. determines shape, location, size, and texture. In this study, we proposed a new approach for tissues using MR images. method includes three computer vision fiction strategies which are enhancing images, segmenting filtering out non ROI texture HOG features. A fully automatic model‐based trainable classification MRI tumour artificial neural networks to precisely identifying...