CNNs-Transformer based day-ahead probabilistic load forecasting for weekends with limited data availability

Energy, Journal Year: 2024, Volume and Issue: 293, P. 130666 - 130666

Published: Feb. 10, 2024

Language: Английский

---

Empowering Modern Dentistry: The Impact of Artificial Intelligence on Patient Care and Clinical Decision Making

Diagnostics, Journal Year: 2024, Volume and Issue: 14(12), P. 1260 - 1260

Published: June 14, 2024

Advancements in artificial intelligence (AI) are poised to catalyze a transformative shift across diverse dental disciplines including endodontics, oral radiology, orthodontics, pediatric dentistry, periodontology, prosthodontics, and restorative dentistry. This narrative review delineates the burgeoning role of AI enhancing diagnostic precision, streamlining treatment planning, potentially unveiling innovative therapeutic modalities, thereby elevating patient care standards. Recent analyses corroborate superiority AI-assisted methodologies over conventional techniques, affirming their capacity for personalization, accuracy, efficiency care. Central these applications convolutional neural networks deep learning models, which have demonstrated efficacy diagnosis, prognosis, decision making, some instances surpassing traditional methods complex cases. Despite advancements, integration into clinical practice is accompanied by challenges, such as data security concerns, demand transparency AI-generated outcomes, imperative ongoing validation establish reliability applicability tools. underscores prospective benefits practice, envisioning not replacement professionals but an adjunctive tool that fortifies profession. While heralds improvements diagnostics, personalized care, ethical practical considerations must be meticulously navigated ensure responsible development

Language: Английский

---

Artificial intelligence and personalized diagnostics in periodontology: A narrative review

Periodontology 2000, Journal Year: 2024, Volume and Issue: 95(1), P. 220 - 231

Published: June 1, 2024

Periodontal diseases pose a significant global health burden, requiring early detection and personalized treatment approaches. Traditional diagnostic approaches in periodontology often rely on "one size fits all" approach, which may overlook the unique variations disease progression response to among individuals. This narrative review explores role of artificial intelligence (AI) diagnostics periodontology, emphasizing potential for tailored strategies enhance precision medicine periodontal care. The begins by elucidating limitations conventional techniques. Subsequently, it delves into application AI models analyzing diverse data sets, such as clinical records, imaging, molecular information, its training. Furthermore, also discusses research community policymakers integrating Challenges ethical considerations associated with adopting AI-based tools are explored, need transparent algorithms, safety privacy, ongoing multidisciplinary collaboration, patient involvement. In conclusion, this underscores transformative advancing toward paradigm, their integration practice holds promise ushering new era

Language: Английский

---

Deep learning in fringe projection: A review

Neurocomputing, Journal Year: 2024, Volume and Issue: 581, P. 127493 - 127493

Published: March 7, 2024

Language: Английский

---

Deep Learning in Oral Hygiene: Automated Dental Plaque Detection via YOLO Frameworks and Quantification Using the O’Leary Index

Diagnostics, Journal Year: 2025, Volume and Issue: 15(2), P. 231 - 231

Published: Jan. 20, 2025

Background: Oral diseases such as caries, gingivitis, and periodontitis are highly prevalent worldwide often arise from plaque. This study focuses on detecting three plaque stages—new, mature, over-mature—using state-of-the-art YOLO architectures to enhance early intervention reduce reliance manual visual assessments. Methods: We compiled a dataset of 531 RGB images 177 individuals, captured via multiple mobile devices. Each sample was treated with disclosing gel highlight types, then preprocessed for lighting color normalization. YOLOv9, YOLOv10, YOLOv11, in various scales, were trained detect categories, their performance evaluated using precision, recall, mean Average Precision (mAP@50). Results: Among the tested models, YOLOv11m achieved highest mAP@50 (0.713), displaying superior detection over-mature Across all variants, older generally easier than newer plaque, which can blend gingival tissue. Applying O’Leary index indicated that over half population exhibited severe levels. Conclusions: Our findings demonstrate feasibility automated advanced models varied imaging conditions. approach offers potential optimize clinical workflows, support diagnoses, mitigate oral health burdens low-resource communities.

Language: Английский

---

Systematic review of predictive maintenance and digital twin technologies challenges, opportunities, and best practices

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e1943 - e1943

Published: April 22, 2024

Background Maintaining machines effectively continues to be a challenge for industrial organisations, which frequently employ reactive or premeditated methods. Recent research has begun shift its attention towards the application of Predictive Maintenance (PdM) and Digital Twins (DT) principles in order improve maintenance processes. PdM technologies have capacity significantly profitability, safety, sustainability various industries. Significantly, precise equipment estimation, enabled by robust supervised learning techniques, is critical efficacy conjunction with DT development. This study underscores DT, exploring transformative potential across domains demanding real-time monitoring. Specifically, it delves into emerging fields healthcare, utilities (smart water management), agriculture farm), aligning latest frontiers these areas. Methodology Employing Preferred Reporting Items Systematic Review Meta-Analyses (PRISMA) criteria, this highlights diverse modeling techniques shaping asset lifetime evaluation within context from 34 scholarly articles. Results The revealed four important findings: modelling their approaches, predictive outcomes, implementation management. These findings align ongoing exploration applications farm). In addition, sheds light on functions emphasising extraordinary ability drive revolutionary change dynamic challenges. results highlight methodologies’ flexibility many industries, providing vital insights revolutionise management practice Conclusions Therefore, systematic review provides current essential resource academics, practitioners, policymakers refine strategies expand applicability sectors.

Language: Английский

---

Computerized diagnosis of knee osteoarthritis from x‐ray images using combined texture features: Data from the osteoarthritis initiative

International Journal of Imaging Systems and Technology, Journal Year: 2024, Volume and Issue: 34(2)

Published: March 1, 2024

Abstract The prevalence of knee osteoarthritis (KOA) cases has witnessed a significant increase on global scale in recent years, emphasizing the need for automated diagnostic computer systems to aid early‐stage (OA) diagnosis. accurate characterization KOA stages through feature extraction poses research challenges due complexity identifying relevant attributes. In this study, development system is presented, leveraging combination Gabor, and Tamura parameters using Canonical Correlation Analysis algorithm. Two selection algorithms, namely Principal Component Relief, were employed classification. Furthermore, various classifiers, including K‐Nearest Neighbors, AdaBoost, Bagging, Random Forest, used assess proposed approach. was assessed dataset comprising 688 x‐ray images sourced from OA initiative (OAI) dataset, consisting 344 healthy subjects (Grade 0) pathological patients 2). To mitigate overfitting, 10‐fold cross‐validation method utilized. experimental results indicate that Gabor with Forest classifier achieved remarkable performance diagnosis, yielding an accuracy 94.59%, area under curve 98.3%. Notably, combined models exhibited superior compared individual models, as well existing techniques reported literature.

Language: Английский

---

DeMambaNet: Deformable Convolution and Mamba Integration Network for High-Precision Segmentation of Ambiguously Defined Dental Radicular Boundaries

Sensors, Journal Year: 2024, Volume and Issue: 24(14), P. 4748 - 4748

Published: July 22, 2024

The incorporation of automatic segmentation methodologies into dental X-ray images refined the paradigms clinical diagnostics and therapeutic planning by facilitating meticulous, pixel-level articulation both structures proximate tissues. This underpins pillars early pathological detection meticulous disease progression monitoring. Nonetheless, conventional frameworks often encounter significant setbacks attributable to intrinsic limitations imaging, including compromised image fidelity, obscured delineation structural boundaries, intricate anatomical constituents such as pulp, enamel, dentin. To surmount these impediments, we propose Deformable Convolution Mamba Integration Network, an innovative 2D architecture, which amalgamates a Coalescent Structural Encoder, Cognitively-Optimized Semantic Enhance Module, Hierarchical Convergence Decoder. Collectively, components bolster management multi-scale global features, fortify stability feature representation, refine amalgamation vectors. A comparative assessment against 14 baselines underscores its efficacy, registering 0.95% enhancement in Dice Coefficient diminution 95th percentile Hausdorff Distance 7.494.

Language: Английский

---

A novel deep learning-based pipeline architecture for pulp stone detection on panoramic radiographs

Oral Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 14, 2025

Language: Английский

---

Assessment of using transfer learning with different classifiers in hypodontia diagnosis

BMC Oral Health, Journal Year: 2025, Volume and Issue: 25(1)

Published: Jan. 15, 2025

Hypodontia is the absence of one or more teeth in primary permanent dentition during development, and radiographic imaging most common method diagnosis. However, recent years, artificial intelligence-based decision support systems have been employed to make highly accurate diagnoses. The aim this study was classify single premolar agenesis, multiple without tooth agenesis using various intelligence approaches. One thousand sixty-eight panoramic radiographs from pediatric patients aged between 6 12 years systemic disease were sorted into three separate classes: (n = 336), 324), 408). Pretrained convolutional neural network models (AlexNet, DarkNet-19, DarkNet-53, DenseNet-201, EfficientNet, GoogLeNet, InceptionV3, IncResV2, MobileNetV2, NasNet-Mobile, Places365, ResNet-18, ResNet-50, ResNet-101, ShuffleNet, SqueezeNet, VGG-16, VGG-19, Xception) used for training with fine-tuning different machine learning classifiers (decision trees, discriminant analysis, logistic regression, naive Bayes, vector machines, nearest neighbor, ensemble method, network). dataset divided 80% 20% testing. Performance evaluated via accuracy, recall, precision, F1-score, specificity area under curve (AUC) parameters. All data classified a VGG-19 model bilayered classifier, which achieved 95.63% 93.26% 93.34% 96.73% specificity, 93.25% F1-score 95.03% AUC identified as successful model. accuracy values distributed follows: 96.72% 95.79% 94.39% agenesis. Successful results pretrained demonstrated diagnosis hypodontia patients. It expected that approaches will facilitate hypodontia.

Language: Английский

---