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.

53 مُخرَج نتائج البحث عن «artificial intelligence»

مقالوصول مفتوح20266استشهاد· Semantic Scholar

Personalized multi-agent reinforcement learning framework for adaptive chronic disease therapy management

Scientific Reports · مجلد 16 (1)

Long-term, flexible therapy strategies are needed for chronic diseases like cardiovascular ailments, diabetes, and chronic kidney disease and they have to deal with patient heterogeneity, changing physiological states and privacy constraints. This research suggests a framework for privacy-preserving and personalized artificial intelligence that combines Federated Learning (FL), a Res-HyperTransformerNet deep prediction model, Personalized Multi-Agent Reinforcement Learning (PMARL) and Explainable Artificial Intelligence (XAI) for adaptive chronic disease management. The framework is structured with two main aims: (i) to create an accurate and privacy-aware predictive model for chronic disease risk using diverse data sources, and (ii) to permit adaptive, individual therapy optimization through multi-agent reinforcement learning. Federated learning is utilized to conduct the training of Res-HyperTransformerNet over distributed Internet of Medical Things (IoMT) nodes without the requirement of transferring raw patient data. The embeddings that are created from patient data are then passed on to a PMARL module, where several agents optimize therapy dimensions like medications, diet, physical activity, and mental health interventions independently. To make the clinical support more understandable, the SHAP-based explainability method is used for both predictive and decision-making parts. The framework is tested using two public datasets—the CDC Chronic Disease dataset and the UCI Chronic Kidney Disease Risk Factor dataset. The performance is measured by employing classification metrics (accuracy, precision, recall, F1-score, MCC) as well as reinforcement learning metrics (reward score, convergence steps, episode return) and federated system metrics (communication overhead, convergence rounds, and training time). The experiments indicate that the proposed framework demonstrated improved performance in terms of predictive accuracy and policy convergence speed compared to the baseline deep learning and reinforcement learning models, and at the same time it is more cost-effective when it comes to communication in a federated setting. This means that the proposed method suggests the potential of being a reproducible and open AI framework for adaptive chronic disease therapy management. The combination of ResNet and Transformer blocks, i.e., Federated Res-HyperTransformerNet, achieved strong performance in both datasets, namely CDC Chronic Disease (Dataset 1) and UCI CKD Risk Factor (Dataset 2). The obtained accuracy for Dataset 1 was 98.61% and for Dataset 2, it was 97.75%, under the conducted experimental settings.

chronic disease managementfederated learningprivacy-preserving healthcarechronic disease risk prediction
مقالوصول مفتوح20264استشهاد· Semantic Scholar

Exploring the synergistic collaboration of Human Agentic-AI in enhancing the security of the software development lifecycle

Egyptian Informatics Journal · مجلد 33 · 100915-100915

The increasing complexity and sophistication of cyber threats have heightened the need for robust security mechanisms throughout the Software Development Lifecycle (SDLC). Traditional security methods have proven insufficient in addressing evolving risks, prompting the exploration of advanced technologies such as Artificial Intelligence (AI). However, integrating AI into SDLC raises challenges related to human-AI collaboration, trust, and alignment. This paper aims to explore the synergistic collaboration between Human Agentic and AI agents to enhance the security of SDLC. By integrating human expertise with AI capabilities, the study investigates how this collaboration can address existing security gaps and improve threat detection, vulnerability management, and secure code development. A qualitative approach is employed, reviewing existing literature on Human-Agentic AI frameworks, AI-driven security models, and their application in SDLC security. We also propose a conceptual framework for Human Agentic-AI collaboration in SDLC security, encompassing AI’s role in automated threat detection, vulnerability scanning, and model optimization, alongside human agents’ roles in decision-making, risk evaluation, and response validation. The proposed framework demonstrates that combining human intuition with AI’s computational power significantly enhances the security posture of SDLC processes. AI’s ability to quickly process and analyze large datasets complements human agents’ contextual understanding, leading to more effective identification of vulnerabilities and proactive security measures. The collaboration results in improved threat mitigation strategies, faster response times, and more reliable secure code deployment. The integration of Human Agentic-AI collaboration offers promising potential in enhancing SDLC security. The synergistic approach bridges the limitations of traditional methods and AI systems, offering a more dynamic and adaptable security solution. Future research should focus on optimizing human-AI interfaces and addressing trust and transparency challenges to further strengthen SDLC security.

human-AI collaborationagentic AIAI agentsthreat detection
مقالوصول مفتوح20261استشهاد· Semantic Scholar

A hybrid deep learning framework for early detection of developmental disabilities using speech and behavioral biomarkers

Array · مجلد 29 · 100691-100691

Early and precise recognition of developmental disabilities (DDs) is essential for the timely intervention of preschool-age children. Although various predictive models have been developed in the past, they cannot provide accurate detections and face challenges like high false prediction, limited generalization, etc. To address these issues, a novel artificial intelligence (AI)-based algorithm was proposed for accurate DD detection. The proposed system integrates digital biomarkers from speech and behavioral domains for predicting DDs. Consequently, an Enhanced Gaussian-Based Noise Filtering (EGNF) is applied to speech data, and Z-score normalization is applied to behavioral data for preprocessing, which makes the raw data reliable for subsequent analysis. Further, feature extraction is performed using Convolutional-Bidirectional Long Short-Term Memory (Conv-BiLSTM) for speech data and Graph Attention Network (GAT) for behavioral data. Subsequently, a Hybrid Feature Selection (HFS) method was developed by combining the Harmony Search Algorithm (HSA) and ReliefF ranking for selecting informative and relevant attributes for model training. Finally, a hybrid classification model named DeepSTNet has been developed by integrating MnasNet and Independently Recurrent Neural Networks (IndRNN), which allows the capture of spatial and temporal long-term dependencies within the data, resulting in high detection performances. The proposed framework was implemented in Python and validated using comprehensive data formed by combining the Dysarthria Detection dataset and the Autism Dataset for Toddlers. The execution outcomes highlighted that the developed framework achieved an accuracy of 99.46%, a precision of 97.74%, and a recall of 98.05%, illustrating that this AI-centric system can be equipped by end users, including healthcare professionals and caregivers, with tools for early screening and detection of DDs.

developmental disabilitiesearly detectionspeech biomarkersbehavioral biomarkers
مقالوصول مفتوح2026

Artificial Intelligence-Driven Sensor Network Approach for Optimizing Halted Product Delivery in E-Commerce Platforms

International Journal of Computational Intelligence Systems · مجلد 19 (1)

Sensor network architectures incorporated with artificial intelligence are exploited for process automation in e-commerce platforms. Specifically, product management is automated through sale-based tracking, enabled by the rapid exchange of information within the sensor network. A Paused Product-based Data Management Scheme is proposed in this article to track and improve the delivery of halted products through e-commerce platforms. The sensor network architecture performs individual identification and tracking of halted/delayed products at any hub through synchronized data updates. The synchronization of product information, delay time, and its associated paused information is performed by identifying the product delivery time. For this purpose, a deep neural network is employed to compute the difference between actual and paused delivery intervals. The higher the difference, the synchronization and delivery re-initialization processes are through the sensor network’s interconnected data exchange. Besides, the network is trained until the delay time is reduced with the re-scheduled time as the base. This infers precise product tracking under fewer missing order complaints in an e-commerce platform.

e-commercesensor networksdeep neural networkdelivery delay prediction
مقالوصول مفتوح2026

Digital epidemiology investments Saudi Arabia

Bulletin of the World Health Organization · مجلد 104 (08) · 573-578

Problem: Traditional epidemiological surveillance methods are often limited by delays in reporting and fragmented data systems. Saudi Arabia faces additional public health challenges from mass gatherings during Hajj and Umrah, an increasing burden of noncommunicable diseases and rapid urbanization, highlighting the need for investing in digital epidemiology. Approach: Saudi Arabia has accelerated digital transformation in health care through Vision 2030 initiatives. The strategies include health information exchange platforms, analytics driven by artificial intelligence, telemedicine services and digital monitoring systems used during Hajj. We review current initiatives to invest in digital epidemiology in Saudi Arabia, implementation challenges and policy priorities. Local setting: Saudi Arabia's health system operates under a predominantly public model. The health ministry is the main provider, regulator and finance provider of most health-care services. Health-care coverage is nearly universal, with citizens receiving services free of charge through the public system. Ongoing reforms aim to gradually decentralize certain functions. Relevant changes: The initiatives under Vision 2030 have supported disease surveillance, data integration and public health response capacities. Existing digital health reforms have created a foundation for integrating digital epidemiology into routine public health practice. However, challenges remain, including fragmented interoperability between institutions, workforce shortages, unequal digital access, and concerns about data governance, privacy and algorithmic bias. Lessons learnt: Saudi Arabia's experience suggests that digital epidemiology is more effective when integrated within broader digital health reforms. Successful implementation requires not only digital infrastructure, but also workforce development, ethical governance, transparency and mechanisms for integrating digital data into public health decision-making.

digital epidemiologySaudi Vision 2030digitalization of healthcaredisease surveillance
مقالوصول مفتوح2026

Development and validation of a predictive AI model for differential diagnosis of endodontic and non-endodontic orofacial pain: a comparative study

Scientific Reports · مجلد 16 (1)

Differentiating between endodontic and non-endodontic sources of orofacial pain is a diagnostic challenge owing to overlapping clinical presentations. Artificial intelligence (AI) offers a potential solution to improve the diagnostic accuracy of endodontics by analysing complex clinical and radiographic data. To evaluate the performance of an artificial intelligence (AI) model in distinguishing endodontic pain from non-endodontic pain and compare its diagnostic accuracy, sensitivity, and specificity with those of an expert panel. This cross-sectional diagnostic study included 224 participants (134 with endodontic pain and 90 without endodontic pain). Clinical and radiographic data were analysed using a random forest AI model trained on features including radiographic lesions, pain characteristics, and pulp vitality tests. Model performance metrics, including accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC-ROC), were assessed across the training, validation, and test datasets. The model’s performance was compared to that of an expert panel using statistical tests. The AI model demonstrated an overall diagnostic accuracy of 91.8% on the test set, with sensitivity and specificity of 92.1% and 91.4%, respectively. The AI model showed significantly higher sensitivity (p = 0.03) than the expert panel (accuracy: 89.2%). Feature importance analysis identified radiographic lesions (34%), pain characteristics (28%), and pulp vitality test results (25%) as the most influential predictors. The AI model exhibited superior diagnostic accuracy compared with the expert panel, indicating its potential as a reliable tool for differentiating endodontic pain from non-endodontic sources. Incorporating AI into clinical workflows can enhance diagnostic precision and improve patient outcomes in endodontics.

endodontic painorofacial paindifferential diagnosisartificial intelligence
مقالوصول مفتوح2026

PET Imaging in Alzheimer Disease: Diagnostic and Prognostic Applications

International Journal of Clinical and Medical Research · مجلد 3 (1) · 47-50

Alzheimer Disease (AD) is a progressive neurodegenerative disorder characterized by amyloid-β deposition, tau pathology, synaptic dysfunction, neuronal injury and cerebral atrophy. Positron Emission Tomography (PET) has transformed AD evaluation by enabling in-vivo visualization of molecular and metabolic abnormalities. 18F-Fluorodeoxyglucose (FDG) PET evaluates cerebral glucose metabolism, amyloid PET identifies fibrillar amyloid-β and tau PET provides information about neurofibrillary pathology. This review examines diagnostic and prognostic applications of PET in AD, particularly in mild cognitive impairment, atypical dementia, differential diagnosis, disease staging, progression prediction and treatment selection. Evidence indicates that amyloid PET is highly useful for establishing amyloid pathology, whereas tau PET is more closely associated with disease stage and clinical severity. FDG PET remains valuable for identifying patterns of neurodegeneration and distinguishing AD from other dementias. With the emergence of disease-modifying anti-amyloid therapies, molecular confirmation has become increasingly relevant to treatment decisions. Important limitations include cost, availability, radiation exposure, tracer-specific limitations, mixed pathology and interpretation variability. Future integration of PET with MRI, blood biomarkers and artificial intelligence may improve individualized diagnosis, prognosis and therapeutic monitoring.

Alzheimer's diseasepositron emission tomographyamyloid PETtau PET
مقالوصول مفتوح2026

NeuroTLEDNet: a novel artificial intelligence with squirrel reptilian optimization (SRO) and TLE-SegNet+ for early detection of temporal lobe epilepsy from medical imaging

Journal Of Big Data · مجلد 13 (1)

Temporal Lobe Epilepsy (TLE), a very common type of focal epilepsy, requires early and precise identification to enable prompt treatment and enhance patient outcomes. Traditional methods of detection, most notably manual MRI interpretation, tend to be time-consuming, subjective, and dependent on expert specialists, hindering their scalability and reliability. Due to the limitations of conventional and current automated systems—e.g., poor feature extraction, poor segmentation, and low accuracy in classification—this work presents NeuroTLEDNet, a new end-to-end artificial intelligence model for early TLE detection from medical images. The new methodology integrates multiple series of innovations across every processing phase. In preprocessing, skull stripping, Gaussian blurring, and color normalization are used to improve image uniformity and suppress irrelevant structures. In segmentation, the improved TLE-SegNet + is suggested—based on Mask R-CNN and supplemented with DarkNet-53, DenseNet, HetConv layers, and Attention Feature Pyramid Networks (FPN)—to facilitate highly accurate delineation of epileptogenic areas. For further describing the segmented areas, a rich feature space encompassing color histograms, Local Binary Patterns (LBP), and geometric features (eccentricity, area, perimeter) is developed. To resolve inefficiencies in feature selection, this paper presents the Squirrel Reptilian Optimization (SRO) algorithm, a new hybrid metaheuristic that incorporates both the Squirrel Search Algorithm (SSA) and the Reptile Search Algorithm (RSA). The hybrid enhances discriminative feature selection by handling exploration and exploitation dynamics better compared to individual methods. For categorization, NeuroTLEDNet utilizes an in-depth hybrid ensemble of 3D Convolutional Neural Networks (3D-CNN), Recurrent Neural Networks (RNN), Radial Basis Function Networks (RBFN), and SqueezeNet, facilitating powerful modeling of spatial-temporal relationships in brain MRI scans. Tested on an 80/30 split MRI dataset, the designed model attains a remarkable accuracy of 98.6%, outperforming current methods like CNN-LSTM (94.2%), Mask R-CNN (92.7%), and ResNet-based architectures (93.1%). Indeed, NeuroTLEDNet provides an end-to-end solution for the shortcomings of existing TLE detection methods by utilizing advanced preprocessing, segmentation, feature optimization, and hybrid classification, with state-of-the-art performance in terms of both accuracy and explainability. The suggested model is a promising candidate for clinical application, and it has the potential to assist neurologists in faster and more accurate TLE diagnosis.

temporal lobe epilepsybrain MRIMask R-CNNDarknet-53
مقالمفتوح (مستودع)2026

Awareness and Detection of Artificial Intelligence-generated Misinformation in Medical Contexts among Health Professions Students in Riyadh, Saudi Arabia: A Cross-sectional Study

Advanced Health Science and Technology Journal · مجلد 2 (1) · 53-62

Abstract Background: Artificial intelligence (AI) is increasingly used in health care and medical education; however, concerns persist regarding health professions students’ ability to evaluate the accuracy of AI-generated medical content, particularly when such content contains misinformation. Objectives: This study assessed the awareness, attitudes, and ability of health professions students in Riyadh, Saudi Arabia, to detect AI-generated misinformation in medical contexts. Methodology: A cross-sectional study was conducted among 354 health professions students using a structured online questionnaire. The survey captured demographics, AI usage patterns, awareness of AI concepts, verification behaviors, and the ability to identify inaccurate AI-generated statements. Descriptive and inferential analyses were performed. Results: Most students reported prior use of AI tools (86.7%), yet only half (50.0%) were aware of the term AI hallucination. A large proportion (77.7%) had previously encountered wrong or confusing AI-generated information. Despite this, only 37.9% consistently verified AI outputs using other sources. Performance on the hallucination-detection items revealed substantial gaps: only 25.1% correctly identified the false statement that magnetic resonance imaging uses ionizing radiation, 40.1% correctly recognized that vitamin C does not prevent the common cold, and 54.1% correctly affirmed the aspirin–Reye’s syndrome association. While attitudes toward AI were generally positive – with 89.3% agreeing it is a useful educational tool – significant limitations in critical appraisal skills were evident. Conclusion: Health professions students in Riyadh are active users of AI technologies but demonstrate limited ability to detect AI-generated medical misinformation. Given the high reliance on AI for academic and clinical learning, these findings highlight an urgent need to integrate structured AI literacy, critical appraisal training, and misinformation-detection exercises into health professions curricula to promote safe and responsible use of AI in healthcare.

AI-generated misinformationhealth professions studentsAI hallucinationmisinformation detection
مقالمفتوح (مستودع)2026

Cracking the Code: Performance Convergence and Reasoning Blind Spots of Large Language Models on Alzheimer’s Questions in Medical Licensing Examinations

Advanced Health Science and Technology Journal · مجلد 2 (1) · 97-103

Abstract Background: Artificial intelligence (AI), particularly large language models (LLMs), is increasingly used in medical education and examination preparation. Recent studies suggest that frontier LLMs may have reached near-ceiling performance on standardized medical benchmarks; however, less is known about whether such performance converges across models and whether shared reasoning vulnerabilities persist, particularly in clinically complex domains such as Alzheimer’s disease. Aims and Objectives: This study aimed to evaluate the performance of three frontier LLMs—ChatGPT-4 (OpenAI), Gemini 2.5 Flash (Google), and Claude Sonnet 4 (Anthropic)—on Alzheimer’s disease-related multiple-choice questions drawn from international medical licensing examinations. A secondary objective was to assess the guideline alignment of model explanations to identify differences in reasoning quality beyond accuracy. Materials and Methods: A total of 49 Alzheimer’s disease-focused multiple-choice questions were curated from peer-reviewed preparatory resources and represented five international examinations: USMLE, SMLE, MCCQE, IFOM, and PNA. Each model answered all questions under standardized, independent conditions. Accuracy was recorded, and explanations were evaluated using a guideline alignment score (0–1) based on consistency with authoritative clinical guidelines (NICE, WHO, and AAN). Interrater reliability was assessed using Cohen’s kappa. Results: All three models achieved identical overall accuracy of 98% (48/49 correct). Each model made the same diagnostic error on a single USMLE vignette, misclassifying Alzheimer’s disease as normal pressure hydrocephalus, revealing a shared reasoning blind spot. Accuracy was uniform across clinical domains, except for diagnosis (94.1%). Guideline alignment scores differed modestly, with Claude Sonnet 4 demonstrating the highest alignment (0.95), followed by ChatGPT-4 (0.92) and Gemini 2.5 Flash (0.88). Conclusion: Frontier LLMs demonstrate performance convergence on structured Alzheimer’s disease examination questions, achieving near-identical accuracy. However, convergence also extends to shared diagnostic errors, highlighting systematic reasoning vulnerabilities. Incorporating guideline alignment reveals meaningful differences in explanatory quality despite similar accuracy. These findings underscore the importance of evaluating not only correctness but also reasoning quality and guideline fidelity when integrating LLMs into medical education and clinical decision support.

large language modelsAlzheimer's diseasemedical licensing examinationsmultiple-choice questions
مقالوصول مفتوح202549استشهاد· Semantic Scholar

Neonatal nurses’ experiences with generative AI in clinical decision-making: a qualitative exploration in high-risk nicus

BMC Nursing · مجلد 24 (1) · 386-386

BACKGROUND: Neonatal nurses in high-risk Neonatal Intensive Care Units (NICUs) navigate complex, time-sensitive clinical decisions where accuracy and judgment are critical. Generative artificial intelligence (AI) has emerged as a supportive tool, yet its integration raises concerns about its impact on nurses' decision-making, professional autonomy, and organizational workflows. AIM: This study explored how neonatal nurses experience and integrate generative AI in clinical decision-making, examining its influence on nursing practice, organizational dynamics, and cultural adaptation in Saudi Arabian NICUs. METHODS: An interpretive phenomenological approach, guided by Complexity Science, Normalization Process Theory, and Tanner's Clinical Judgment Model, was employed. A purposive sample of 33 neonatal nurses participated in semi-structured interviews and focus groups. Thematic analysis was used to code and interpret data, supported by an inter-rater reliability of 0.88. Simple frequency counts were included to illustrate the prevalence of themes but were not used as quantitative measures. Trustworthiness was ensured through reflexive journaling, peer debriefing, and member checking. RESULTS: Five themes emerged: (1) Clinical Decision-Making, where 93.9% of nurses reported that AI-enhanced judgment but required human validation; (2) Professional Practice Transformation, with 84.8% noting evolving role boundaries and workflow changes; (3) Organizational Factors, as 97.0% emphasized the necessity of infrastructure, training, and policy integration; (4) Cultural Influences, with 87.9% highlighting AI's alignment with family-centered care; and (5) Implementation Challenges, where 90.9% identified technical barriers and adaptation strategies. CONCLUSIONS: Generative AI can support neonatal nurses in clinical decision-making, but its effectiveness depends on structured training, reliable infrastructure, and culturally sensitive implementation. These findings provide evidence-based insights for policymakers and healthcare leaders to ensure AI integration enhances nursing expertise while maintaining safe, patient-centered care.

generative AIneonatal nursingclinical decision-makinghigh-risk infants
مقالوصول مفتوح202533استشهاد· Semantic Scholar

GraphFedAI framework for DDoS attack detection in IoT systems using federated learning and graph based artificial intelligence

Scientific Reports · مجلد 15 (1) · 28050-28050

The Internet of Things (IoT) consists of physical objects and devices embedded with network connectivity, software, and sensors to collect and transmit data. The development of the Internet of Things (IoT) has led to various security and privacy issues, including distributed denial-of-service (DDoS) attacks. Conventional attack detection methods face significant challenges related to privacy, scalability, and adaptability due to the dynamic nature of IoT environments. To address these limitations, this research proposes GraphFedAI, a novel framework that integrates adaptive session-based graph modeling, Pearson correlation-guided feature selection, interpolation-aware graph neural network (GNN) training, and federated learning to enable robust, scalable, and privacy-preserving DDoS detection in heterogeneous Internet of Things (IoT) networks.The framework represents the IoT network as dynamic graphs where communication patterns among devices are modeled as edges that evolve over time. Graph neural networks are utilized to extract both temporal and structural features from these graphs, thereby enhancing the accuracy of DDoS detection. Federated learning is incorporated to maintain data privacy by training models locally on each device without sharing raw data. This integration also ensures system scalability, as FL adapts training based on localized network topology.The system is evaluated using the CIC-IoT-2023 dataset, demonstrating its effectiveness in achieving high detection accuracy, low false positive rates, and strong resilience under dynamic IoT conditions.

DDoS attack detectionInternet of Things securityfederated learninggraph neural networks
مقالمفتوح (مستودع)202523استشهاد· Semantic Scholar

Assessing the Anatomical Accuracy of AI‐Generated Medical Illustrations: A Comparative Study of Text‐to‐Image Generator Tools in Anatomy Education

Clinical Anatomy · مجلد 38 (6) · 712-717

Historically, human anatomy education has been an essential part of medical training, depending on cadaveric dissection and anatomical representations. However, financial and ethical limitations have resulted in a decline in conventional teaching techniques, necessitating the investigation of alternative resources such as digital drawings and artificial intelligence (AI). The aim of this research was to assess and compare the anatomical precision of graphics produced by four AI text-to-image generators: Microsoft Bing, DeepAI, Freepik, and Gemini, emphasizing their value in medical education. On February 6, 2025, four AI text-to-image generators were used. Prompts for creating intricate anatomical images included the human heart, brain, skeletal thorax, and hand bones. Two anatomists and a radiologist evaluated the pictures produced according to anatomical standards. Bing and Gemini generated anatomically correct representations of the human heart, but DeepAI and Freepik were less accurate. All generators offered accurate reconstructions of the human brain; however, there were disparities in sulci and gyri, with Gemini performing best. Only Gemini delivered a correct sternum; the other generators misrepresented the rib count. The Gemini platform provided a satisfactory depiction of the human hand skeleton, but the outputs from other text-to-image generators were not anatomically accurate. This work examines the potential of generative AI in medical illustration, noting significant limitations in accuracy and detail, especially with bony structures. Although AI accelerates the drawing process, it cannot replace the proficiency of skilled medical illustrators. Continuous assessment and improvement of AI-generated material are essential to ensure that the criteria mandated for medical education are met.

anatomical accuracyanatomy educationGeminiBing
مقالوصول مفتوح202518استشهاد· Semantic Scholar

Novel deep reinforcement learning based collision avoidance approach for path planning of robots in unknown environment

PLoS ONE · مجلد 20 (1) · e0312559-e0312559

Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system's capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach's agent converged in 210th episodes in a cluttered environment and 400th episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.

collision avoidancerobot path planningdeep reinforcement learningQ-learning
مقالوصول مفتوح202518استشهاد· Semantic Scholar

Logical reasoning for human activity recognition based on multisource data from wearable device

Scientific Reports · مجلد 15 (1) · 380-380

Smart wearable devices detection and recording of people's everyday activities is critical for health monitoring, helping persons with disabilities, and providing care for the elderly. Most of the research that is being conducted uses a machine learning-based methodology; however, these approaches frequently have issues with high computing resource consumption, burdensome training data gathering, and restricted scalability across many contexts. This research suggests a behaviour detection technology based on multi-source sensing and logical reasoning to address these problems. In order to realize the natural fusion of signal processing and logical reasoning in behavior recognition research, this work designs a lightweight behavior recognition solution using the pertinent theories of ontology reasoning in classical artificial intelligence. Machine learning technology is also employed for behavior recognition using the same data set. Once the best model has been chosen, the cross-person recognition results after testing and modification of parameters are 90.8% and 92.1%, respectively. This technology was used to create a behaviour recognition system, and several tests were run to assess how well it worked. The findings demonstrate that the suggested strategy achieves over 90% recognition accuracy for 11 different daily activities, including jogging, walking, and stair climbing. Additionally, the suggested strategy dramatically minimises the quantity of user-provided training data needed in comparison to machine learning-based behaviour identification techniques.

human activity recognitionwearable deviceslogical reasoningontology reasoning