جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

220 مُخرَج نتائج البحث عن «mentation»

مقالوصول مفتوح202422استشهاد· Semantic Scholar

Brain tumor segmentation using neuro-technology enabled intelligence-cascaded U-Net model

Frontiers in Computational Neuroscience · مجلد 18 · 1391025-1391025

According to experts in neurology, brain tumours pose a serious risk to human health. The clinical identification and treatment of brain tumours rely heavily on accurate segmentation. The varied sizes, forms, and locations of brain tumours make accurate automated segmentation a formidable obstacle in the field of neuroscience. U-Net, with its computational intelligence and concise design, has lately been the go-to model for fixing medical picture segmentation issues. Problems with restricted local receptive fields, lost spatial information, and inadequate contextual information are still plaguing artificial intelligence. A convolutional neural network (CNN) and a Mel-spectrogram are the basis of this cough recognition technique. First, we combine the voice in a variety of intricate settings and improve the audio data. After that, we preprocess the data to make sure its length is consistent and create a Mel-spectrogram out of it. A novel model for brain tumor segmentation (BTS), Intelligence Cascade U-Net (ICU-Net), is proposed to address these issues. It is built on dynamic convolution and uses a non-local attention mechanism. In order to reconstruct more detailed spatial information on brain tumours, the principal design is a two-stage cascade of 3DU-Net. The paper's objective is to identify the best learnable parameters that will maximize the likelihood of the data. After the network's ability to gather long-distance dependencies for AI, Expectation-Maximization is applied to the cascade network's lateral connections, enabling it to leverage contextual data more effectively. Lastly, to enhance the network's ability to capture local characteristics, dynamic convolutions with local adaptive capabilities are used in place of the cascade network's standard convolutions. We compared our results to those of other typical methods and ran extensive testing utilising the publicly available BraTS 2019/2020 datasets. The suggested method performs well on tasks involving BTS, according to the experimental data. The Dice scores for tumor core (TC), complete tumor, and enhanced tumor segmentation BraTS 2019/2020 validation sets are 0.897/0.903, 0.826/0.828, and 0.781/0.786, respectively, indicating high performance in BTS.

brain tumor segmentationU-Netdynamic convolutionnon-local attention
مقالوصول مفتوح202420استشهاد· Semantic Scholar

Data-centric automated approach to predict autism spectrum disorder based on selective features and explainable artificial intelligence

Frontiers in Computational Neuroscience · مجلد 18 · 1489463-1489463

Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by notable challenges in cognitive function, understanding language, recognizing objects, interacting with others, and communicating effectively. Its origins are mainly genetic, and identifying it early and intervening promptly can reduce the necessity for extensive medical treatments and lengthy diagnostic procedures for those impacted by ASD. This research is designed with two types of experimentation for ASD analysis. In the first set of experiments, authors utilized three feature engineering techniques (Chi-square, backward feature elimination, and PCA) with multiple machine learning models for autism presence prediction in toddlers. The proposed XGBoost 2.0 obtained 99% accuracy, F1 score, and recall with 98% precision with chi-square significant features. In the second scenario, main focus shifts to identifying tailored educational methods for children with ASD through the assessment of their behavioral, verbal, and physical responses. Again, the proposed approach performs well with 99% accuracy, F1 score, recall, and precision. In this research, cross-validation technique is also implemented to check the stability of the proposed model along with the comparison of previously published research works to show the significance of the proposed model. This study aims to develop personalized educational strategies for individuals with ASD using machine learning techniques to meet their specific needs better.

autism spectrum disorderautism predictiontoddlersfeature selection
مقالوصول مفتوح202419استشهاد· Semantic Scholar

FacialNet: facial emotion recognition for mental health analysis using UNet segmentation with transfer learning model

Frontiers in Computational Neuroscience · مجلد 18 · 1485121-1485121

Facial emotion recognition (FER) can serve as a valuable tool for assessing emotional states, which are often linked to mental health. However, mental health encompasses a broad range of factors that go beyond facial expressions. While FER provides insights into certain aspects of emotional well-being, it can be used in conjunction with other assessments to form a more comprehensive understanding of an individual's mental health. This research work proposes a framework for human FER using UNet image segmentation and transfer learning with the EfficientNetB4 model (called FacialNet). The proposed model demonstrates promising results, achieving an accuracy of 90% for six emotion classes (happy, sad, fear, pain, anger, and disgust) and 96.39% for binary classification (happy and sad). The significance of FacialNet is judged by extensive experiments conducted against various machine learning and deep learning models, as well as state-of-the-art previous research works in FER. The significance of FacialNet is further validated using a cross-validation technique, ensuring reliable performance across different data splits. The findings highlight the effectiveness of leveraging UNet image segmentation and EfficientNetB4 transfer learning for accurate and efficient human facial emotion recognition, offering promising avenues for real-world applications in emotion-aware systems and effective computing platforms. Experimental findings reveal that the proposed approach performs substantially better than existing works with an improved accuracy of 96.39% compared to existing 94.26%.

facial emotion recognitionmental health assessmentEfficientNet-B4transfer learning
مقالوصول مفتوح202417استشهاد· Semantic Scholar

Design and implementation of single DC-link based three-phase multilevel inverter with CB-PWM techniques

Scientific Reports · مجلد 14 (1) · 18078-18078

Simulation and implementation of a single DC-link-based three-phase inverter are investigated in this article. The primary focus is on designing a single DC-link three-phase inverter for high power applications. Unlike conventional inverters that require 600 V to generate 400 V (RMS) at the output, the proposed system achieves this with only 330 V, facilitated by a 12-terminal 1:1 transformer. The system employs Proportional Integral (PI) and Neural Network (NN) controllers to optimize performance. Various Carrier-Based Pulse Width Modulation (CB-PWM) techniques, including Phase Disposition (PD), Phase Opposition Disposition (POD), and Alternative Phase Opposition Disposition (APOD), are implemented and evaluated based on Total Harmonics Distortion (THD) concerning the Modulation Index (MI) of the inverter. The proposed inverter achieves a THD reduction to 4.8%, demonstrating superior performance compared to recent studies. The system's performance is validated through extensive MATLAB/Simulink simulations and practical implementation using XILINX FPGA software, confirming the efficacy of the proposed design.

multilevel inverterthree-phase invertercarrier-based pulse width modulationphase disposition PWM
مقالوصول مفتوح202417استشهاد· Semantic Scholar

Precision Diagnosis: An Automated Method for Detecting Congenital Heart Diseases in Children From Phonocardiogram Signals Employing Deep Neural Network

IEEE Access · مجلد 12 · 76053-76064

According to the World Health Organization (WHO), congenital heart disorders (CHDs) impact a significant proportion of babies worldwide, with prevalence rates ranging from 0.8% to 1.2%. Phonocardiography (PCG) is the leading non-invasive method for detecting congenital heart defects (CHDs), offering important information about cardiac signals i.e. S1, S2, S3, and S4 and heartbeat patterns. This research study focuses on developing a strong binary classification system for congenital heart diseases (CHDs) utilizing deep neural networks. The system will be trained on a combined dataset that includes both local and publicly available repositories. The local dataset (LD) consists of 583 signals containing both normal and aberrant PCG recordings, while the public dataset (PD) obtained from Michigan University consists of 23 PCG recordings. In order to achieve consistency and compatibility, both datasets are subjected to down-sampling, resulting in a frequency of 8 kHz. A well-engineered band-pass filter efficiently removes signals outside the 20-650 Hz range, allowing for exclusive processing of the desired frequencies. The signals are divided into segments, each lasting exactly 4 seconds. The study utilizes data augmentation techniques, specifically pitch-shifting, to boost the model’s robustness. This is accomplished by implementing a 1D convolutional neural network (CNN). The most notable outcomes are achieved in case C, exhibiting a sensitivity of 99.0%, specificity of 98.0%, F1 score of 98.56%, precision of 98.57%, and an accuracy of 98.56%. This study enhances the progress of automated techniques for detecting congenital heart disease (CHD), demonstrating the potential of deep neural networks in precision medicine for pediatric cardiology.

congenital heart diseasephonocardiogram1D convolutional neural networkbinary classification
مقالوصول مفتوح202417استشهاد· Semantic Scholar

A CRC-Based Authentication Model and ECC-Based Authentication Protocol for Resource-Constrained IoT Applications

IEEE Access · مجلد 12 · 156765-156784

The Internet of Things (IoT) is resource-constrained and faces the challenge of ensuring information authentication due to the continuous exchange of information between multiple physical devices. Integrating wireless sensor nodes (WSN) into IoT devices makes this information fusion possible. However, transmitting this information via wireless channels exposes it to numerous threats, making information authentication in the IoT a complex issue that requires rigorous attention. In response, the article proposes a model incorporating the use of CRC (Cyclic Redundancy Check) for the information authentication model and an Elliptic Curve Cryptographic (ECC)-based message authentication protocol. The CRC-based model is designed to be evaluated against other cryptographic-based protocols, providing an effective solution for resource-constrained IoT devices used in various domains, including healthcare, smart home, transportation, logistics, and everyday electronics. The ECC-based message authentication protocol can be scrutinized through BAN (Burrows-Abadi–Needham) logic. The proposed CRC-based protocol’s performance can be measured regarding power consumption and storage overheads of the information fusion among IoT, while the performance metrics of the proposed ECC-based protocol can be measured by considering storage, communication, and computation costs. The result shows that the efficiency of the CRC-based information authentication model is smaller by 22 characters and that the significant message bytes are 88 characters. In contrast, upon comparing the ECC-based message authentication protocol in terms of performance metrics and security functionalities, the result obtained demonstrated that both the CRC model and ECC protocol reduced power, bandwidth, memory, communication, and computation costs and CPU (Central Processing Unit) usage, making them a cost-effective solution for practical implementation in IoT-deployed areas.

Internet of Thingsdata authenticationcyclic redundancy checkelliptic curve cryptography
مقالوصول مفتوح202415استشهاد· Semantic Scholar

Classification of cervical cancer using Dense CapsNet with Seg-UNet and denoising autoencoders

Scientific Reports · مجلد 14 (1) · 31764-31764

Cervical cancer is one of the deadly diseases that affects women, which requires periodic examinations to identify and treat any cancerous tumors at a preliminary stage. The most prevalent examination tool for cervical cancer prompt identification is the cervical smear (Pap smear) testing; however, due to human negligence, this examination method has an elevated probability of negative findings. Cervical cancer classification using machine learning (ML) and deep learning (DL) has been extensively studied to enhance the conventional diagnostic process. Robust classification results were achieved through the pre-segmented imagery in most current investigations. Conversely, cellular grouping makes reliable cervical cellular segmentation difficult. Additionally, the deep learning methods used in the existing works perform poorly on a multiclass classification when the data distribution is skewed, which is common in the cervical cancer dataset. To mitigate these restrictions in cervical cancer research, this proposed work uses a combination of four different deep-learning methods in various phases of this research. The proposed work is segregated into five phases: pre-processing, data augmentation, segmentation, feature extraction, and classification. Contrast maximization is performed in the pre-processing phase, and the images are augmented using Multi-modal Generative Adversarial Networks (m-GAN) in the second phase. In the third phase, cervical cancer images are segmented using the Seg-UNet model, which is forwarded to the feature extraction phase that employs denoising autoencoders. Finally, the classification is implemented using the Dense CapsNet model and applied to the SIPaKMeD dataset to categorize between normal, abnormal, and benign classes. The proposed system achieves an accuracy of 99.65%, which is higher than the other works in the literature.

cervical cancer classificationPap smeardenoising autoencoderdata augmentation
مقالوصول مغلق202415استشهاد· Semantic Scholar

The varying viscosity impact in an inclined peristaltic channel with diffusion‐thermo and thermo‐diffusion

ZAMM ‐ Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik · مجلد 104 (8)

Abstract A mathematical model is constructed to investigate the behavior of peristaltic flow of Jeffrey fluid in an inclined tapered asymmetric porous channel. The fluid viscosity is taken as space dependent variable quantity. Heat absorption, Soret and Dufour effects are also retained in the current scrutiny. These preferences have broad applications in engineering, biology and industry. We began our investigation by taking into account the two‐dimensional inclined asymmetric porous channel. In the context of mathematical modeling, the appropriate dimensional nonlinear equations for momentum, heat and mass transport are simplified into dimensionless equations by applying the essential estimation of long wavelength and low Reynolds number. The solution of the governing equations is executed numerically. A graphical depiction of many crucial physical characteristics on velocity, temperature, concentration, heat transfer rate, Nusselt number and Streamlines have been reported in ending section. Temperature profile exhibits an escalation with the augmentation of Brinkman number and Dufour number . For the growing values of Prandtl number , an increment in temperature profile is observed whilst a reverse tendency is captured for concentration profile. It is noted that concentration profile falls down owing to the enhancement in Soret number and Schmidt number . An oscillatory outlook is noticed for heat transfer rate and Nusselt number. The novelty of this proposed model in the research domain specifically depends on considerations of the combined study of the Variable viscosity, Darcy resistance, Viscous dissipation, Mixed convention, Heat absorption, Soret and Dufour effects in peristaltic flow of non‐ Newtonian Jeffrey fluid in an inclined Asymmetric tapered channel under the influence of convective boundary conditions.

peristaltic flowJeffrey fluidvariable viscositytapered channel
مقالوصول مفتوح202414استشهاد· Semantic Scholar

Epidemiology and Outcomes of Neurofibromatosis Type 1 (NF-1): Multicenter Tertiary Experience

Journal of Multidisciplinary Healthcare · مجلد Volume 17 · 1303-1314

Purpose: The aim of this manuscript was to assess the epidemiology and clinical features of Neurofibromatosis type 1 (NF-1) based on the newly published revised NF-1 diagnostic criteria and to evaluate complications of NF-1 including neurodevelopmental disorders. Patients and methods: A retrospective cross-sectional observational study was conducted in the Ministry of National Guard Health Affairs (MNGHA) healthcare organization branches including four tertiary hospitals and 51 primary health care centers in different regions in Saudi Arabia. This study included all patients diagnosed with NF1 using the revised NIH diagnostic criteria published in 2021 that were registered at the electronic medical records (EMR) from 2015 to 2021. Results: A total of 184 patients fulfilled the diagnostic criteria and were included in this study. The median age at diagnosis was 11 years (IQR: 4.00-20.25). The most encountered diagnostic criteria in this study were Café-au-lait macules (85.3%), and (42.9%) were found to have two or more neurofibromas with plexiform neurofibroma being the most common subtype (23.36%), approximately (36.4%) of the patient with optic pathway glioma. Nearby (26.6%) of the patients displayed different type of tumors. Iris Lisch nodules were presented in 36.4% of patients at a median age of 12 years (IQR: 9.0-21.8). Cardiovascular abnormality was encountered in 9.8% of the patients. Around 27.7% of the patients reported headache and 11.4% of the patient suffered from different type of epilepsy. Besides, 10.5% of the patients had intellectual disability, 33.8% suffered from communication disorders, and 4.9% patients had ADHD. Conclusion: The results of this study will enable practitioners to adopt a more holistic approach and prioritize numerous attributes, which they can subsequently incorporate into their therapeutic methodologies. Furthermore, the identification of these attributes will facilitate an expeditious and accurate diagnosis. Hence, the implementation of intervention during its nascent phase may result in a more advantageous consequence.

neurofibromatosis type 1epidemiologyclinical featurescafé-au-lait spots
مراجعةوصول مفتوح202413استشهاد· Semantic Scholar

Challenges of therapeutic applications and regenerative capacities of urine based stem cells in oral, and maxillofacial reconstruction

Biomedicine & Pharmacotherapy · مجلد 177 · 117005-117005

Urine-derived stem cells (USCs) have gained the attention of researchers in the biomedical field in the past few years . Regarding the several varieties of cells that have been used for this purpose, USCs have demonstrated mesenchymal stem cell-like properties, such as differentiation and immunomodulation. Furthermore, they could be differentiated into several lineages. This is very interesting for regenerative techniques based on cell therapy. This review will embark on describing their separation, and profiling. We will specifically describe the USCs characteristics, in addition to their differentiation potential. Then, we will introduce and explore the primary uses of USCs. These involve thier utilization as a platform to produce stem cells, however, we shall concentrate on the utilization of USCs for therapeutic, and regenerative orofacial applications, providing an in-depth evaluation of this purpose. The final portion will address the limitations and challenges of their implementation in regenerative dentistry.

urine-derived stem cellsmesenchymal stem cellsoral reconstructionmaxillofacial reconstruction
مقالوصول مفتوح20249استشهاد· Semantic Scholar

Design of Artificial Intelligence Driven Crowd Density Analysis for Sustainable Smart Cities

IEEE Access · مجلد 12 · 121983-121993

Smart Cities refer to urban areas which exploits recent technologies for improving the performance, sustainability, and livability of their infrastructure and services. Crowd Density Analysis (CDA), a vital component of Smart Cities, involves the use of sensors, cameras, and data analytics to monitor and analyze the density and movement of people in public spaces. CDA utilizing DL harnesses the control of neural networks to mechanically and exactly evaluate the density of crowds in numerous settings, mainly in smart cities. DL techniques like Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN), are trained on vast datasets of crowd videos or images to learn complex designs and features. These models can forecast crowd density levels, recognize crowd anomalies, and offer real-time visions into crowd behavior. This study designs an Artificial Intelligence Driven Crowd Density Analysis for Sustainable Smart Cities (AICDA-SSC) technique. The aim of the AICDA-SSC method is to analyze the crowd density and classify it into multiple classes by the use of hyperparameter-tuned DL models. To accomplish this, the AICDA-SSC technique applies contrast enhancement using the CLAHE approach. Besides, the complex and intrinsic features can be derived by the use of the Inception v3 model and its hyperparameters can be chosen by the use of the marine predator’s algorithm (MPA). For crowd density detection and classification, the AICDA-SSC technique applies a gated recurrent unit (GRU) model. Finally, a chaotic sooty tern optimizer algorithm (CSTOA) based hyperparameter selection procedure takes place to increase the effectiveness of the GRU system. The experimental evaluation of the AICDA-SSC technique takes place on a crowd-density image dataset. The experimentation values showcase the superior performance of the AICDA-SSC method to the recently developed DL models.

smart citiesgated recurrent unitmarine predators algorithmhyperparameter optimization
مقالوصول مفتوح20249استشهاد· Semantic Scholar

Prioritizing Strategic Objectives and Projects in Higher Education Institutions: A New Hybrid Fuzzy MEREC-G-TOPSIS Approach

IEEE Access · مجلد 12 · 89735-89753

Higher education institutions (HEIs) aim to achieve a significant impact on research, learning, teaching, and community services, which are core elements of their strategic plans. Determining the priorities of strategic objectives and related projects is crucial for the successful implementation of HEIs’ strategic plans. However, such prioritization necessitates the use of effective methods capable of dealing with several conflicting criteria in their objectives and ambiguous inputs from the decision-makers. Therefore, this study proposes a new integrated approach for prioritizing the objectives and projects of strategic plans in HEIs. The proposed approach utilizes a hybrid of the fuzzy method based on the removal effects of criteria using the geometric mean (fuzzy MEREC-G) and the fuzzy technique for order preference by similarity to the ideal solution (fuzzy TOPSIS). The proposed approach was tested on a strategic transformation plan at one of the Saudi Arabian universities and showed that it effectively prioritizes the objectives and projects of the university’s strategic transformation plan. Sensitivity analysis demonstrated the proposed approach’s stability in providing consistent rankings under different criteria weights. The proposed approach offers decision-makers in HEIs an effective tool that assists in prioritizing the objectives and projects of their strategic plans.

strategic planninghigher education institutionsproject prioritizationfuzzy TOPSIS