Browse Articles
Discover research articles across all indexed journals
Hybrid neural network method for damage localization in structural health monitoring
Abstract The detection of cracks in large structures is of critical importance, as such damage can result not only in significant financial costs but also pose serious risks to public safety. Many existing methods for crack detection rely on deep learning algorithms or traditional approaches that typically use image data. In this study, however, we explore an innovative approach based on numerical data, which is characterized by greater cost efficiency and offers intriguing research implications. This study emphasizes the evaluation of hybrid RNN-CNN models in comparison to the pure CNN models previously utilized in related research. Our proposed model incorporates a single RNN layer, complemented by essential supporting layers, which contributes to a reduction in complexity and a decrease in the number of parameters. This design choice results in a more streamlined and efficient architecture. Our experimental results reveal an accuracy of 78.9%, which, while slightly lower than the performance of conventional CNN models, underscores the potential of RNN layers in crack detection tasks. Importantly, this work demonstrates that integrating additional RNN layers can effectively enhance crack detection capabilities, particularly given the significance of preserving spatial information for accurate crack segmentation. These findings open avenues for further exploration and optimization of RNN-based methods in structural damage analysis, suggesting that the strategic use of RNNs can complement CNN models to achieve robust performance in this domain.
Combined indicator assists in early recognition of retinopathy of prematurity
Abstract This research aimed to investigate the value of clinical data in preterm infants on admission for the early prediction of retinopathy of prematurity (ROP). 98 preterm infants (66 males and 32 females) with an average gestational age of 30.42 ± 1.20 weeks were included. Basic vital signs, clinical tests, and maternal information were collected at admission. Preterm infants were divided into a non-ROP group and a ROP group based on whether they eventually developed ROP. The receiver operating characteristic (ROC) curve was used to evaluate the predictive value of the above indexes and the combined indexes in the ROP of preterm infants. (1) The differences in systolic blood pressure (SBP), red blood cell count (RBC), hemoglobin (HGB), direct bilirubin (DBIL), and total bilirubin (TBIL) were statistically significant between the non-ROP group and ROP group (all P < 0.05). (2) RBC, HGB, DBIL, and TBIL, all of which have diagnostic value for ROP [area under curve (AUC) 0.643, 0644, 0.887, and 0.744, respectively, all P < 0.05]. (3) The combined indicator possessed a good diagnostic value for ROP (AUC of 0.962, P < 0.05), with a sensitivity and specificity of 88.64% and 91.49%, respectively. (4) Combined indicator (body temperature, body weight, heart rate, SBP, diastolic blood pressure, mean arterial pressure, RBC, HGB, red blood cell distribution width, DBIL, TBIL) has better diagnostic value for ROP than each of RBC, HGB, DBIL, and TBIL alone (Z-value 5.386, 5.475, 2.410 and 4.420, respectively, all P < 0.05). Combined indicator has good predictive value for ROP in preterm infants.
Author Correction: Monocytes to Apolipoprotein A1 ratio is associated with metabolic dysfunction-associated fatty liver disease in type 2 diabetes mellitus
A real-world pharmacovigilance study of omalizumab using disproportionality analysis in the FDA adverse drug events reporting system database
Application of machine learning techniques in GlaucomAI system for glaucoma diagnosis and collaborative research support
Improvement of carboplatin chemosensitivity in lung cancer cells by siRNA-mediated downregulation of DLGAP1-AS2 expression
Author Correction: Hydropower Station diversion tunnel layered excavation deformation mechanism under high crustal stress
Increased activation of the WNT pathway in brain tissue from patients with cortical dysplasia type IIb
Measurement of axial dose profile for wide detector CT using radiochromic films
A comparative analysis of supraharmonic emission by DC fast chargers used for electric vehicle charging
Spectroscopic and molecular docking studies on binding interactions of camptothecin drugs with bovine serum albumin
Abstract This study investigates the binding interactions between bovine serum albumin (BSA) and camptothecin (CPT) drugs (camptothecin, 10-hydroxycamptothecin, topotecan, and irinotecan) using UV–Vis spectroscopy, fluorescence spectroscopy, three-dimensional fluorescence spectroscopy, and molecular docking techniques. The fluorescence quenching of BSA by CPT drugs follows a static mechanism, with binding constants (Kb) ranging from 4.23 × 103 M− 1 (CPT) to 101.30 × 103 M− 1 (irinotecan), demonstrating significant drug binding selectivity. Thermodynamic analysis reveals distinct interaction mechanisms: topotecan binding is driven by hydrogen bonding (ΔH = − 10.96 kJ·mol− 1) and hydrophobic interactions (ΔS = 0.066 kJ·mol− 1·K− 1), while irinotecan exhibits stronger binding dominated by electrostatic forces (ΔH = − 86.77 kJ·mol− 1) with significant entropy loss (ΔS = − 0.161 kJ·mol− 1·K− 1). Molecular docking confirms preferential binding at Sudlow site I of BSA, with hydrophobic interactions and hydrogen bonding as the primary driving forces. These findings provide a comprehensive understanding of CPT-BSA interactions, offering valuable insights for the design of albumin-based drug delivery systems with optimized pharmacokinetic profiles.
Parameter calibration for discrete element simulation of Leymus chinensis seeds based on RSM optimization
Integrating transcriptome and metabolome analyses to characterize flower development in Salix variegata franch., a typical dioecious plant
Bias dependent band alignment in Ga2O3 ferroelectric interface by operando HAXPES
Early prediction of postpartum dyslipidemia in gestational diabetes using machine learning models
Correlation free large-scale probabilistic computing using a true-random chaotic oscillator p-bit
A lagrangian particle tracking approach of evapotranspiration partitioning to explore evaporation and transpiration travel time distributions in the root zone
Single-stage versus two-stage resection for large anterior midline skull base meningiomas with bihemispheric peritumoral edema
Abstract Resection of large anterior midline skull base meningiomas with extensive peritumoral edema poses high risks due to postoperative edema decompensation leading to increased intracranial pressure. Initial craniectomy prevents intracranial pressure decompensation but requires secondary cranioplasty. This study compares single-stage osteoplastic craniotomy with tumor resection to a two-stage approach using bifrontal craniectomy, tumor resection and subsequent cranioplasty after edema recovery in a second surgical step. Patients with large anterior midline skull base meningiomas (> 50 mm) and extensive peritumoral edema were included. Group 1 underwent single-stage resection (2002–2016), while Group 2 had a two-stage approach (2012–2022). The primary outcome was the Karnofsky Performance Scale (KPS) at three months post-surgery. Secondary outcomes included preoperative KPS, KPS at discharge and last follow-up, ICU stay, hospital stay length and complication rates. A total of 25 patients were analyzed (Group 1: n = 9; Group 2: n = 16). Group 2 demonstrated significantly improved KPS at three months postoperatively (median KPS 70% vs. 50%; p = 0.0204) with a non-significant reduction in ICU stay (10 vs. 6.5 days; p = 0.3284). Although no significant differences were observed in KPS at discharge (Group 1: KPS 30% vs. Group 2: KPS 50%; p = 0.1829) or last follow-up (Group 1: KPS 60% vs. Group 2: KPS 80%; p = 0.1630), Group 2 patients required fewer postoperative interventions for complications unrelated to cranioplasty. Overall complication rates were comparable in both groups (Group 1: 67% vs. Group 2: 56%; p = 0.6274). Two-stage resection of large anterior midline skull base meningiomas with extensive edema provides superior clinical outcomes at three months postoperatively without increasing overall complication rates. These findings support the use of a two-stage surgical strategy for highly selected patients. However, further multicenter studies are warranted to validate these results in larger cohorts.