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.

6 مُخرَج نتائج البحث عن «Exploit»

مراجعةوصول مفتوح202525استشهاد· Semantic Scholar

An update on the molecular mechanisms underlying the progression of miR-21 in oral cancer

World Journal of Surgical Oncology · مجلد 23 (1) · 73-73

Globally, oral cancer ranks among the top ten cancers, with a higher prevalence in lower-income countries, where risk factors such as tobacco use, excessive alcohol consumption, and poor oral hygiene are widespread. Metastasis plays a critical role in cancer progression. miR-21 is a crucial regulator of cancer metastasis, profoundly influencing cellular and molecular pathways that contribute to tumour aggressiveness. As a microRNA, miR-21 downregulates tumour suppressor genes, promoting cell proliferation, survival, invasion, and migration. Its role in epithelial-mesenchymal transition (EMT) further facilitates metastatic behaviour. miR-21 also modulates the tumour microenvironment by promoting angiogenesis and altering immune responses, thus enhancing cancer progression.Moreover, miRNA - 21 influences the various signalling pathways like PI3K/ AKT, TGF-β, NF-κB, and STAT3, as well as involved in the cell fate mechanisms known as Autophagy and apoptosis. Clinically, elevated miR-21 levels are associated with poor prognosis, advanced tumour stages, and decreased survival rates, making it a valuable prognostic marker. Additionally, miR-21 expression levels can predict resistance to chemotherapy and targeted therapies, aiding in personalized treatment planning. Therapeutically, targeting miR-21 through anti-miR-21 oligonucleotides, small molecule inhibitors, and miRNA sponges shows promise in pre-clinical studies, potentially inhibiting tumour growth and improving sensitivity to existing treatments. Overall, miR-21's multifaceted role in cancer biology, its prognostic and predictive value, and its potential as a therapeutic target highlight its significance in advancing cancer diagnosis, treatment, and patient outcomes. Further research and clinical trials are essential to exploit miR-21's capabilities in oncology fully.

miR-21oral cancermicroRNAmetastasis
مقالوصول مفتوح20252استشهاد· Semantic Scholar

Deep Learning-Enabled Interpretable Down Syndrome Detection Model

Journal of Disability Research · مجلد 4 (3)

Down syndrome (DS) is a genetic condition characterized by distinct facial features and developmental challenges, making early and accurate detection crucial for timely intervention and support. Traditional diagnostic methods often require specialized expertise, which can be resource intensive and inaccessible in many settings. In this study, we propose a novel artificial intelligence (AI)-driven approach to detecting DS using facial images, leveraging advancements in deep learning and machine learning for accurate and scalable diagnostics. A dataset of 168 facial images was curated from publicly accessible platforms, comprising 95 images of individuals without DS and 73 with the condition. The model was implemented using TensorFlow/PyTorch and employs RegNet X and Shifted Window Transformer (SWIN Transformer) for feature extraction, capturing both local and global facial features. To enhance feature representation, an attention-based fusion mechanism was applied, prioritizing the most discriminative patterns while filtering redundant information. For classification, an Extremely Randomized Tree (ExtraTrees) model was employed, known for its ability to efficiently handle high-dimensional data with strong generalization capabilities. The model was fine-tuned using Bayesian Optimization and Hyperband (BOHB), which optimized hyperparameters by balancing exploration and exploitation, thereby improving predictive performance. The final classification achieved a 99.2% accuracy with an area under the curve (AUC) of 1.00, demonstrating exceptional reliability in distinguishing DS from normal cases. By combining advanced feature extraction, fusion, and classification techniques, this study highlights the potential of AI to revolutionize DS diagnostics, offering a non-invasive, efficient, and scalable solution for early detection.

Down syndromeface classificationearly diagnosismodel interpretability
مقالوصول مفتوح20251استشهاد· Semantic Scholar

Relevance of topical application of minoxidil laden nano-lipid for hair growth enhancement

Saudi Pharmaceutical Journal · مجلد 33 (6) · 47-47

Practically, all patients treated with Minoxidil (MXD) reported experiencing hypertrichosis, even though the original intended usage of the drug was the treatment of hypertension. This limitation supports the potential of repurposing MXD as a topical agent for the treatment of hair loss. Accordingly, the outset of the current study was to exploit the cutaneous influence of MXD and limit the drawbacks of conventional available dosage forms. This could be achieved via developing a nanocarrier, mainly; nanoemulsion (NE) for transdermal delivery of MXD. Therefore, several NEs were prepared containing MXD and optimized according to their particle size and in vitro release study using Response Surface Methodology. The optimized formulation was examined for its organoleptic properties, pH, viscosity, and drug content. Moreover, Morphology, kinetic study was investigated a long with the stability testing upon keeping in two distinct settings: room temperature and refrigerator for 12 months. Eventually, the in vivo hair growth rate was monitored and documented for 28 days in pretreated mice. The developed MXD-NEs were developed and optimized using Box Behnken Design software to obtain the most desired formula. The optimized MXD-NE demonstrated a nanosize (83.1 nm) and performs a successful in vitro release (75.6%) over a period of 6 h. Additionally, it showed ideal physical properties with pH (5.9), viscosity (26.7 cP), and drug content (99.4%). The droplets in the formula seemed to be spherical. The formula was stable when preserved for 12 months at both applied conditions. Finally, the formula demonstrated significant faster rate of hair growth that mostly owed to the value of nanocarrier in delivering drug into follicular hairs.

minoxidilnanoemulsionstopical drug deliveryhair growth
ورقة مؤتمروصول مغلق20251استشهاد· Semantic Scholar

Deep Reinforcement Learning-Based Multi-Robotic Agent Motion Planning

OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · 1-6

The deep Q-network (DQN) technique, as a classic value-based deep reinforcement learning process, has been widely applied in fields such as multi-robotic agent motion planning. However, the DQN method faces a series of tasks, such as overestimating Q-values, complex Q-value computations, neural networks lacking historical memory proficiencies, and inefficient exploration when using ε-greedy strategies. This paper proposes a DQN-based multi-robot agent deep reinforcement learning motion planning approach to solve these problems. To accomplish their objectives without colliding with one another, agents can acquire stable and efficient motion planning techniques with the aid of this method. Initially, a Dueling-based optimization tool is suggested, which is based on the DQN approach. It simplifies and improves the calculation of Q-values by calculating state values and advantage function values, and by choosing the appropriate action based on the parameters of the presently updating Q-value network. Additionally, we provide a GRU-based memory mechanism that incorporates GRU modules to facilitate the network's temporal data acquisition and handling of agents' historical information. And lastly, we offer a noise-based exploration technique that works. By introducing parameterized noise, the exploration technique in DQN is modified, improving the examination efficiency of agents, and achieving a balance between exploration and exploitation in multi-robotic agent systems. Tests were conducted in six different simulation scenarios on the PyBullet simulation platform. Experimental results show that the proposed method enables efficient collaboration among multi-robotic agent teams, agreeing them to go where they're going without running into each other, and the methods' training is steady.

multi-robot motion planningdeep Q-networkdueling DQNexploration-exploitation balance
مقالوصول مفتوح2025

Elliptic curve cryptography and biometrics for iot authentication

Serbian Journal of Electrical Engineering · مجلد 22 (2) · 223-241

The Internet of Things (IoT) is now present in every aspect of our daily lives because of its ability to offer remote services. Unfortunately, the insecure transmission of user data in open channels caused by this significant use of IoT networks makes it vulnerable to malicious use. Hence, the security of the user?s data is now a serious matter in an IoT environment. Since authentication may prevent hackers from recovering and using data transmitted between IoT devices, researchers have proposed many lightweight IoT authentication protocols over the past decades. Many of these protocols are built around two authentication factors. They cannot guarantee unlinkability and perfect forward secrecy, as well as withstand well-known attacks such as node capture, DOS attack, stolen verifier, Denning-Sacco attack, and GWN bypass. This paper proposes an Elliptic Curve Cryptography (ECC) -based authentication protocol that is anonymous and exploits three authentication factors to ensure all security services and withstand well-known attacks. Our provided protocol is secure and can resist known attacks, as demonstrated by both informal security analysis and formal security proof using ProVerif. Lastly, our protocol and other protocols are compared in terms of computational costs, communication costs, and security features.

elliptic curve cryptographybiometricsanonymous authenticationthree-factor authentication