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.

مقالوصول مفتوح20245استشهاد· Semantic Scholar

Developing a Pain Identification Model Using a Deep Learning Technique

Journal of Disability Research · مجلد 3 (3)

In this study, the authors proposed a pain identification model using facial expressions. An image extraction technique was developed using the liquid neural network to extract diverse images from the video files. The authors used the DenseNet 201 and MobileNet V3 models to build a hybrid feature engineering technique. They applied quantization aware training to improve the efficiency of the models. The Prkachin and Solomon Pain Intensity score was used for the image classification. They fine-tuned the LightGBM model using the random search algorithm for identifying pain from the facial images. The authors used the Denver Intensity of Spontaneous Facial Action dataset to generalize the proposed model. The performance evaluation outlined the significant performance of the proposed model in identifying pain using the images. In addition, it demands limited computational resources to identify pain. Healthcare and rehabilitation centers can implement the proposed model to provide adequate services to disabled individuals.

pain intensity estimationfacial expression analysisfacial action unitsliquid neural networks
فصل كتابوصول مغلق20245استشهاد

Spatial federated learning and blockchain-based 5G communication model for hiding confidential information

CRC Press eBooks · 40-63

At present, the preferred method of transmitting a rapid blockchain message is to send several transactions, constituting a covert 5G communication technique. However, this approach is inadequate for processing larger quantities of sensitive data, and the potential for losing confidential information is significant. Additionally, the sender’s identity is not concealed. Despite the high embedding rate of steganography techniques, they are increasingly vulnerable to detection and statistical feature-based analysis. This investigation suggests a covert blockchain communication methodology that incorporates spatial federated learning and spatial blockchain as a means of fixing these issues. By utilizing Ciphertext-Policy Attribute-Based Encryption (CP-ABE) to encrypt the sensitive document and uploading it to the Inter Planetary File System (IPFS), the technique conceals sensitive files and the sender’s identity. Then, using image steganography based on Generative Adversarial Networks (GAN), the sender implants the hash value of the encrypted document into a carrier image. After uploading the encrypted image to IPFS, the sender creates a transaction with the hash value of the encrypted image. This transaction is then signed by a ring signature and broadcasted to the blockchain network for verification and confirmation. The recipient retrieves the encrypted document and decrypts it according to the access control policy established by CP-ABE. According to experimental findings, this model can increase the volume of sensitive data transmitted from KB to MB while providing higher confidentiality and security.

covert communicationblockchain5Gciphertext-policy attribute-based encryption
مقالوصول مفتوح20245استشهاد· Semantic Scholar

Design and In Silico and In Vitro Evaluations of a Novel Nicotinamide Derivative as a VEGFR-2 Inhibitor

Journal of Chemistry · مجلد 2024 · 1-25

A new nicotinamide derivative, (E)-N-(4-(1-(2-(4-benzamidobenzoyl)hydrazone)ethyl)phenyl)nicotinamide, was designed as a VEGFR-2 inhibitor. Utilizing the density functional theory (DFT) calculations, the three-dimensional structure of the designed compound was determined, shedding light on its stability and reactivity. Molecular docking revealed its capability to inhibit VEGFR-2, which was further supported by molecular dynamics (MD) simulations confirming its binding to the target protein. In addition, molecular mechanics-generalized born surface area (MM-GBSA), protein-ligand interactions profiler (PLIP), and essential dynamics studies provided further validation of the compound’s precise binding with optimal energy. Then, the “compound 10” was synthesized and subjected to in vitro assays. Compound 10 inhibited VEGFR-2 with an IC50 value of 105.4 ± 0.896 nM, comparing sorafenib’s IC50 value of 61.65 ± 0.934 nM. Besides, it exhibited cytotoxicity against HepG2 and MCF-7 cancer cell lines, with IC50 values of 35.78 ± 0.863 μM and 57.62 μM ± 0.871, comparing sorafenib’s IC50 values of 5.95 ± 0.917 μM and 8.45 ± 0.912 μM. Furthermore, compound 10 demonstrated a lower level of toxicity towards Vero cell lines, with an IC50 value of 127.3 μM. Likewise, compound 10 induced apoptosis in HepG2 cell lines through a flow cytometric analysis in addition to an increase in the levels of caspase-3 and caspase-9. Moreover, compound 10 hindered the migration and healing abilities of HepG2 cells. In conclusion, our study positions compound 10 as a promising candidate for further chemical modifications and biological evaluations.

nicotinamide derivativesVEGFR-2 inhibitorshydrazonesanticancer drug design
مراجعةوصول مغلق20245استشهاد· Semantic Scholar

Surgical intervention ≤ 24 hours versus > 24 hours after injury for the management of acute traumatic central cord syndrome: a systematic review and meta-analysis

Journal of Neurosurgery Spine · مجلد 40 (5) · 653-661

OBJECTIVE: The objective was to evaluate the efficacy, outcomes, and complications of surgical intervention performed within 24 hours (≤ 24 hours) versus after 24 hours (> 24 hours) in managing acute traumatic central cord syndrome (ATCCS). METHODS: Articles pertinent to the study were retrieved from PubMed, Scopus, Web of Science, and Cochrane. The authors performed a systematic review and meta-analysis of treatment procedures and outcomes according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRIMSA) guidelines. RESULTS: Seven articles comprising 488 patients were included, with 188 (38.5%) patients in the ≤ 24-hour group and 300 (61.5%) in the > 24-hour group. Significant differences were not found between groups in terms of demographic characteristics, injury mechanism, spinal cord compression level, neuroimaging features, and the American Spinal Injury Association (ASIA) motor score at admission. Both groups had a similar approach to surgery and steroid administration. The surgical complication rate was significantly higher in the > 24-hour group (4.5%) compared to the ≤ 24-hour group (1.2%) (p = 0.05). Clinical follow-up duration was similar at 12 months (interquartile range 3-36) for both groups (p > 0.99). The ≤ 24-hour group demonstrated a not statistically significant greater improvement in ASIA motor score, with a mean difference of 12 (95% CI -20.7 to 44.6) compared to the > 24-hour group. CONCLUSIONS: The present study indicates potential advantages of early (≤ 24 hours) surgery in ATCCS patients, specifically in terms of lower complication rates. However, further research is needed to confirm these findings and their clinical implications.

spinal cord injurytiming of surgeryearly surgical interventiondelayed surgery
مقالمفتوح (مستودع)20245استشهاد· Semantic Scholar

Enhanced slime mould optimization with convolutional BLSTM autoencoder based malware classification in intelligent systems

Expert Systems · مجلد 42 (1)

Abstract Autonomous intelligent systems are artificial intelligence (AI) tools that act autonomously without direct human supervision. Cloud computing (CC) and Internet of Things (IoT) technologies find it challenging to deploy sufficient security defences because of the different structures, storage, and limited computing capabilities that make them more vulnerable to attacks. Security threats against IoT structures, devices, and applications are increasing with the demand for IoT technology. The training data available to AI models may be limited, which could impact their performance and generalizability. Adopting AI solutions in real‐world situations may be impeded by compatibility concerns and the requirement for flawless integration. Malware classification errors can occur due to a lack of contextual knowledge, particularly in cases where benign files behave identically to malicious. Various studies were carried out on detecting IoT malware to evade the menaces posed by malicious code. However, prevailing techniques of IoT malware classification supported particular platforms or demanded complicated methods for attaining higher accuracy. This study introduces an enhanced slime mould optimization with a convolutional BLSTM autoencoder‐based malware classification (ESMO‐CBLSTMAE) system in the IoT cloud platform. The projected ESMO‐CBLSTMAE system focuses on detecting and classifying malware in the IoT cloud platform. To achieve that, the ESMO‐CBLSTMAE algorithm employs a min–max normalization technique for scaling the input dataset. The ESMO‐CBLSTMAE method uses a convolutional bidirectional long short‐term memory autoencoder (CBLSTM‐AE) model for the malware detection process. Lastly, the ESMO method is executed for the optimum hyperparameter tuning of the CBLSTM‐AE technique, which boosts the malware classification results. The experimental analysis of the ESMO‐CBLSTMAE method is tested against a benchmark database, and the outcomes portray the greater efficacy of the ESMO‐CBLSTMAE approach over other existing techniques. The proposed malware classification model achieved an accuracy of 98.57 and F Score of 80.77 and outperformed the existing models.

malware classificationIoT malware detectionhyperparameter optimizationmin-max normalization
مقالوصول مفتوح20245استشهاد· Semantic Scholar

RETRACTED ARTICLE: Non-sample fuzzy based convolutional neural network model for noise artifact in biomedical images

Discover Applied Sciences · مجلد 6 (1)

Abstract The use of a light-weight deep learning Convolutional Neural Network (CNN) augmented with the power of Fuzzy Non-Sample Shearlet Transformation (FNSST) has successfully solved the problem of reducing noise and artifacts in Low-Dose Computed Tomography (LDCT) pictures. Both the Normal-Dose Computed Tomography (NDCT) and the Low-Dose Computed Tomography (LDCT) images from the dataset are subjected to the FNSST decomposition procedure during the training phase, producing high-frequency sub-images that act as input for the CNN. The CNN creates a meaningful connection between the high-frequency sub-images from LDCT and their corresponding residual sub-images during the training operation. The CNN is given the capacity to distinguish between LDCT high-frequency sub-images and expected high-frequency sub-images, which frequently have varying levels of noise or artifacts, especially in a fuzzy setting. The FNSST-CNN then successfully distinguishes LDCT high-frequency sub-images from the expected high-frequency sub-images during the testing phase, thereby reducing noise and artifacts. When compared to other approaches like KSVD, BM3D, and conventional image domain CNNs, the performance of FNSST-CNN is impressive as shown by better peak signal-to-noise ratios, stronger structural similarity, and a closer likeness to NDCT pictures.

low-dose CTnoise reductionartifact reductionconvolutional neural networks
مقالوصول مفتوح20245استشهاد· Semantic Scholar

Assessment of Knowledge, Attitude, and Practice of First Aid Management of Choking Among Primary School Teachers in Riyadh, Saudi Arabia: A Cross-Sectional Study

Cureus · مجلد 16 (1) · e51519-e51519

BACKGROUND: Understanding first aid is crucial for immediate intervention during health emergencies, with choking representing a significant danger, particularly for young children. Obstructed airways commonly lead to choking incidents, carrying substantial risks if not swiftly dealt with. This research endeavors to evaluate the comprehension, perspectives, and implementation of first aid measures for choking incidents among primary school teachers in Riyadh, Saudi Arabia, an area of paramount importance with minimal existing research within this particular demographic. METHODOLOGY: This was a cross-sectional study conducted from the beginning of July till the end of October 2023, among 447 primary school teachers in Riyadh, Saudi Arabia. Data collection was carried out by administering a questionnaire through an online platform. The questionnaire included demographic information, knowledge about signs and symptoms of choking, the attitude of participants, participant's practice, and the relationship between the knowledge level about choking and practice. The data collected were reviewed, coded, and then fed into IBM SPSS Statistics for Windows, Version 29 (Released 2023; IBM Corp., Armonk, New York, United States). Results: Our study on first aid management of choking among primary school teachers highlighted significant findings. Participants demonstrated high awareness of choking signs with 386 (86.3%) recognizing universal signs and 330 (73.8%) claiming proficiency in first aid. Attitudes favored the importance of immediate treatment in 394 participants (88.1%) and the necessity of first aid knowledge for teachers (92.2%). One-hundred and fifty-one participants (33.8%) reported performing choking first aid with 328 (73.4%) opting for the Heimlich maneuver for a six-year-old. Significantly, higher knowledge correlated with increased first aid performance (p < 0.001) and support for mandatory training (p < 0.001). CONCLUSION: Our study indicates a higher knowledge level in primary school teachers with positive attitudes and practices regarding choking first aid management. It underscores the importance of enhancing first aid training among primary school teachers, emphasizing its positive impact on choking management and the necessity of immediate intervention in such cases.

chokingfirst aidprimary school teachersknowledge, attitudes and practices
مقالوصول مفتوح20245استشهاد· Semantic Scholar

Convergence results for cyclic-orbital contraction in a more generalized setting with application

AIMS Mathematics · مجلد 9 (6) · 15543-15558

In the realm of double-controlled metric-type spaces, we investigated obtaining fixed points using the application of cyclic orbital contractive conditions. Diverging from conventional approaches utilized in standard metric spaces, our technique took a unique route due to the unique features of our structure. We demonstrated the significance of our outcomes through exemplary cases, clarifying the breadth of our results through comprehensive investigations. Significantly, our work not only improved and broadened earlier findings in the literature, but also offered unique notions that were discussed in our explanatory notes. Towards the end of our inquiry, we used insights obtained from previous discoveries to develop a second-order differential equation. This equation was an effective tool for dealing with the second class of Fredholm integral problems. In conclusion, this investigation extended our examination of double-controlled metric type spaces by providing new insights on fixed point theory, expanding on prior debates and building a substantial road towards solving a class of integral equations.

fixed point theoremsconvergence of iterationssecond-order differential equationsFredholm integral equations
مقالوصول مغلق20245استشهاد· Semantic Scholar

Trusted Personalized and Contextualized E-Commerce Services for Consumer Electronics over Wireless Sensor Network

IEEE Transactions on Consumer Electronics · 1-1

Wireless sensor network-based edge computing (WEC) technology enables e-commerce to provide reliable and real-time services over the wireless sensor network (WSN). To enable efficient pseudonym updates and pseudonym tracking, an access point pseudonym management method for wireless edge computing is described in personalization and contextualization e-commerce services. Instead of the central cloud, the edge cloud with high real-time performance authenticates the access point identity, which increases identity authentication and pseudonym update. This study presents an access point pseudonym management strategy for edge computing based on wireless sensor network, addressing the security concern of leakage of SNU pseudonym information in the edge data center. To maintain the confidentiality of pseudonym information, it is homomorphically encrypted. Each WSN pseudonym table is associated with a search word, and the system’s highest authority can calculate the search word from pseudonym table ciphertext to reveal enemy SNUs’ true identities and achieve pseudonym traceability. According to established security theory, the approach is indistinguishable during a chosen-plaintext attack. Access point anonymity, message integrity, and nonrepudiation security studies in the system satisfy Internet of Consumer Electronics Access Point standards for identity privacy protection. The performance of identity authentication, pseudonym request, and homomorphic encryption is studied and simulated.

wireless sensor networksedge computinge-commerce securityhomomorphic encryption
مراجعةوصول مفتوح20245استشهاد· Semantic Scholar

Cross interaction between bacterial and fungal microbiota and their relevance to human health and disease: mechanistic pathways and prospective therapy

Bioscience of Microbiota Food and Health · مجلد 43 (4) · 309-320

Diverse bacterial and fungal microbiota communities inhabit the human body, and their presence is essential for maintaining host homeostasis. The oral cavity, lung, gut, and vagina are just a few of the bodily cavities where these microorganisms communicate with one another, either directly or indirectly. The effects of this interaction can be either useful or detrimental to the host. When the healthy microbial diversity is disturbed, for instance, as a result of prolonged treatment with broad spectrum antibiotics, this allows the growth of specific microbes at the expense of others and alters their pathogenicity, causing a switch of commensal germs into pathogenic germs, which could promote tissue invasion and damage, as occurs in immunocompromised patients. Consequently, antimicrobials that specifically target pathogens may help in minimizing secondary issues that result from the disruption of useful bacterial/fungal interactions (BFIs). The interface between Candida albicans and Aspergillus fumigatus with bacteria at various body sites is emphasized in the majority of the medically important BFIs that have been reported thus far. This interface either supports or inhibits growth, or it enhances or blocks the generation of virulence factors. The aim of this review is to draw attention to the link between the bacterial and fungal microbiota and how they contribute to both normal homeostasis and disease development. Additionally, recent research that has studied microbiota as novel antimicrobials is summarized.

fungal-bacterial interactionsmicrobiotaCandida albicansAspergillus fumigatus