A5018840188- Neural Networks and Applications
- COVID-19 diagnosis using AI
- Blind Source Separation Techniques
- EEG and Brain-Computer Interfaces
- Artificial Intelligence in Healthcare and Education
- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Mobile Health and mHealth Applications
- IoT and Edge/Fog Computing
- Context-Aware Activity Recognition Systems
- Sports Performance and Training
- ECG Monitoring and Analysis
- Emergency and Acute Care Studies
- Non-Invasive Vital Sign Monitoring
- Privacy-Preserving Technologies in Data
- Gear and Bearing Dynamics Analysis
- Energy Harvesting in Wireless Networks
- Image and Signal Denoising Methods
- Integrated Circuits and Semiconductor Failure Analysis
- Kidney Stones and Urolithiasis Treatments
- Artificial Intelligence in Healthcare
- Advancements in Photolithography Techniques
- Advanced Image Fusion Techniques
- Politics and Conflicts in Afghanistan, Pakistan, and Middle East
- Biodiesel Production and Applications
Universiti Tenaga Nasional
2023-2024
Iraqi University
2018-2024
Iraq University College
2022
University of Baghdad
2014
University of Malaya
2003
Cardiff Metropolitan University
1996
Recently, wireless sensor networks (WSNs) were perceived as the foundation infrastructure that paved way to emergence of Internet Things (IoT). However, a challenging issue exists when WSNs are integrated into IoT because high energy consumption in their nodes and poor network lifespan. Therefore, elementary discussions WSN scarcity nodes, sensors' data exchange, routing protocols. To address aforesaid shortcomings, this paper develops an optimized energy-efficient path planning strategy...
Recent advances in deep learning (DL) have shown that data-driven insights can be used smart healthcare applications to improve the quality of life for patients. DL needs more data and diversity build a accurate system. To satisfy these requirements, need pooled at centralized server train model deeply, but process pooling faces privacy regulatory challenges. settle them, concept sharing rather than through federated (FL) is proposed. FL creates reliable system without transferring server,...
This study investigated structure strategies and exploratory scenarios for a half mode substrate integrated waveguide (HMSIW) antenna. The proposed antenna consists of three Hilbert cells, which are simulated by using CST programming. was manufactured with the realities minor imperfections high incorporation. offers suitable (SIW) about decrease in size half. In addition, cells were added to realize triple-band characteristics good impedance matching, radiation patterns, performance....
The current study explores the most significant psychological skills needed for the accomplishment of high archery scores and determines discriminating psychological coping skills needed for archery performance. 32 archers completed inventory before their shooting tests. Multivariate techniques of principal component analysis, hierarchical agglomerative cluster analysis and discriminant were applied. rotated PCA indicates 3 parameters containing 6 components (Pcs). first Pcs...
This paper provides simulated datasets for triaging and prioritizing patients that are essentially required to support multi emergency levels. To this end, four types of input signals presented, namely, electrocardiogram (ECG), blood pressure, oxygen saturation (SpO2), where the latter is text. obtain aforementioned signals, PhysioNet online library [1], used, which considered as one most reliable relevant libraries in healthcare services bioinformatics sciences. In particular, contains...
This paper shows a novel hybrid approach using an Auto-Regressive (AR) model and Quantum Recurrent Neural Network (QRNN) for classification of two classes Electroencephalography (EEG) signals. The QRNN-AR has been shown to be capable capture quantify the uncertainty inherently in EEG signals because it uses fuzzy decision boundaries partition feature space. Two diverse element extraction techniques were used extract features from signals; AR coefficients are processed with Levinson-Durbin...
Federated learning is increasingly being considered for sensor-driven human activity recognition, offering advantages in terms of privacy and scalability compared to centralized methods. However, challenges such as feature selection client imbalanced data persist. In this study, FLP-DS2MOTE-USA suggested, a system that integrates federated local preprocessing, adaptive thresholding based on uncertainty symmetry, density- sensitive synthetic minority over-sampling approach. Each preprocesses...
This paper shows a novel hybrid approach using an Auto-Regressive (AR) model and Quantum Recurrent Neural Network (QRNN) for classification of two classes Electroencephalography (EEG) signals. The QRNN-AR has been shown to be capable capture quantify the uncertainty inherently in EEG signals because it uses fuzzy decision boundaries partition feature space. Two diverse element extraction techniques were used extract features from signals; AR coefficients are processed with Levinson-Durbin...
The security of the transmitted data over internet has become one challenges sharing with communication computer network. In this paper, a new stegnography system is developed using Improved Least Significant Bit (ILSB) preprocessing operation for concealing data. mixes several technological rules to enhance performance scheme. original secret image divided into segments then rearranged even and odd. Rivest Cipher 4 (RC4) algorithm applied on preprocessed before it cover ILSB. proposed...
In this paper, electroencephalographic (EEG) signals are analyzed and classified based on a new multilevel transfer function quantum wavelet neural network (QWNN) model.The independent component analysis (ICA) is used as processing after normalization of these signals.Some features extracted from the data using clustering technique (CT).The classification result model compared with that (WNN), (QNN), feed forward (FFNN).The QWNN found to achieve average accuracy 94.187%, but accuracies WNN,...
According to the survey, 17.5 million people die each year as a result of cardiovascular disease, which causes heart attacks, chest pain, and stroke. Based on results study, it is clear that majority with problems need be diagnosed earlier. The paper presents monitoring framework enabled by Cloud-based Intelligent System-Supervised Patient Monitoring Platform (CBIS-SPMP), where sensors collect ECG SPO2 are transmitted cloud for seamless access health care professionals. patient can used WiFi...
In this paper, new steganographic systems employing least significant bit technique and wavelet transform for embedding are proposed. These incorporate threshold level to enhance the performance of scheme. Further, Forward error correcting code is used improve system performance. proposed system, cover image a gray applied directly. The secret coded using Reed Solomon preparing process. locations randomly selected according pseudorandom number sequence. combination between ciphering process...
Abstract This paper introduces a new approach to ensure the certainty of medical diagnosis by eliminating salt-and-pepper noise (SPN) in applications for both gray and coloured computed tomography (CT) images. The proposed is based on median filter which utilized value-preserving edge-preserving digital image processing applications, Thus, called improved adaptive (IAMF). In contrast available research literature, introduced method characterized high filtering quality, robust different...
Automatic focusing of a visual inspection system is described. A vidicon camera was mounted on top high powered microscope to capture an image, process it and send appropriate signal stepper motor which controls the movements microscope. The method used based acutance video waveform. Acutance measure steepness It implies that sharp image will have gradient gray level across image. This measured vertically horizontally control achieve optimal state. On achieving from circuitry automatic be...