Search Results (3,886)

Coronary artery disease (CAD) remains a leading cause of global morbidity and mortality. Accurate diagnosis of ischemia-causing coronary stenoses is essential for guiding revascularization and improving outcomes. Although invasive fractional flow reserve (FFR) remains the gold standard for functional lesion assessment, its use is limited by procedural invasiveness, cost, and complexity. CT-derived FFR (FFRct), based on computational fluid dynamics (CFD), was the first major advance in noninvasive physiological assessment, but its adoption has been hindered by intensive off-site computation and dependence on high-quality imaging. This review summarizes the evolution from invasive FFR to AI-driven functional assessment of coronary lesions. We examine the principles and validation of CFD-based FFRct and then focus on the shift toward artificial intelligence, including both machine learning (ML) and deep learning (DL) approaches. These methods range from models using engineered geometric and plaque features trained on large synthetic datasets to end-to-end systems that learn directly from imaging data. We discuss key validation studies evaluating diagnostic accuracy, prognostic value, and clinical utility, with attention to performance in challenging settings such as intermediate stenoses, heavy calcification, and patients with comorbidities. We also highlight major barriers to widespread adoption, including dependence on input data quality, limited explainability, regulatory hurdles, and integration into clinical workflows. Finally, we outline future directions, including AI-enabled virtual PCI planning, multimodal risk stratification, and broader access to functional cardiac assessment. AI has the potential to transform noninvasive coronary imaging by enabling a single CCTA scan to provide rapid, integrated evaluation of anatomy, plaque characteristics, and physiological significance, supporting more personalized care and better clinical outcomes. Full article

Urban Unmanned Aerial Vehicle (UAV) logistics operations are frequently constrained by the intersection of limited battery endurance and dynamic ground traffic. When mobile depots are delayed by congestion, onboard drone fleets experience extended idling periods, leading to constrained sortie generation and reduced asset utilization. To address this bottleneck, this paper introduces a traffic-predictive multi-UAV dispatch framework for deterministic day-ahead planning under modeled urban operating conditions. By coupling a count-derived macroscopic speed surrogate learned using XGBoost with a Particle Swarm Optimization (PSO)–Mixed-Integer Linear Programming (MILP) optimization architecture, the framework synchronizes mobile depot trajectories with forecasted low-congestion windows and pre-allocates endurance-feasible parallel aerial sorties. Controlled computational experiments across 30 synthetic routing instances demonstrate the potential value of this approach within the stated modeling assumptions. Compared to baseline clustered deployments, the traffic-aware framework raises mean fleet utilization from 0.43 to 0.63—a 46.2% relative improvement driven by temporal compression of the mission window rather than an absolute increase in flight hours. Furthermore, the proposed framework reduces total mission completion time by 69.87% relative to the conventional truck-only baseline, while achieving a 29.58% incremental gain over static speed drone deployments. These findings suggest that incorporating predictive ground traffic information into day-ahead UAV scheduling can improve modeled fleet efficiency; however, field validation with measured route-level speeds, real delivery demand, and operational constraints remains necessary before deployment-level claims can be made. Full article

The study investigated the tensile strength and elongation properties of abaca fiber-reinforced polymer (AFRP) composites after varying durations of seawater soaking, with a focus on their potential for reinforcing fiber-optic cables. It aims to bridge industrial technology education, experiential learning, and green technology by evaluating abaca fiber as a sustainable alternative to synthetic aramid yarn. Conducted at Caraga State University, Cabadbaran Campus (CSUCC), the research utilized a quasi-experimental product development design involving industrial technology students and instructors. Tensile strength testing and comparative analysis were performed on abaca fiber samples (A, B, and C) subjected to different seawater soaking durations. Results show that soaking time significantly affects the fiber strength, with Sample A achieving the highest tensile strength (5631.5 MPa) and Sample C the lowest (1679.8 MPa). Findings indicate that prolonged exposure to seawater weakens abaca fiber, emphasizing the need for controlled treatment to optimize its industrial applications. This study emphasizes the importance of hands-on learning in industrial technology education, promoting critical thinking and technical skills while underscoring sustainability. The research advocates for eco-friendly materials in industrial applications and highlights the potential of abaca fiber composites. Future studies should investigate pre-treatment methods to enhance fiber durability, assess the long-term environmental performance, and conduct large-scale pilot testing to evaluate commercial viability. By integrating sustainable innovations into industrial technology education, this study contributes to advancing natural fiber composites for manufacturing and telecommunications infrastructure. Full article

Background/Objectives: Successful revascularization following extremity arterial injury is critical for survival and limb salvage. Graft repair is required in ~45% of patients, with the autologous vein preferred for its efficacy and safety. When unavailable, synthetic or non-autologous grafts are associated with infection, amputation, and reduced durability. Extremity arterial injury-specific cost data are lacking, with estimates extrapolated from the general trauma literature. This study characterized the costs and post-discharge healthcare resource utilization (HCRU) for U.S. adults with extremity arterial injury undergoing graft repair. Methods: Adults with extremity arterial injury undergoing graft repair (January 2018 to March 2023) were identified from the linked PINC AI Healthcare Database and Inovalon all-payer claims. Hospitalization charges, costs, and 18-month post-discharge HCRU and costs were assessed. Two-part models estimated cost drivers, adjusted for demographics, clinical characteristics, and complications. Results: Among 964 patients, grafts were autologous (74%), synthetic (14%), other (6%), or multiple (6%). Mean initial hospitalization charges and reimbursed costs were $316,600 and $75,947, respectively. Charges/costs increased with orthopedic fracture (+$639,558/+$91,462), graft infection (+$589,921/+$84,598), and amputation (+$492,986/+$116,611) (all p < 0.05). Mean post-discharge costs were $70,222 at 6 months and $93,639 at 18 months. Initial hospitalization complications predicted increased post-discharge costs: orthopedic fracture ($138,683–$145,360) and graft infection ($389,376–$422,224) (both p < 0.01). Post-discharge aneurysm, graft infection, and thrombectomy were also associated with higher costs (all p < 0.05). Post-discharge HCRU was lowest and most stable with the autologous vein. Conclusions: In-hospital and post-discharge complications are major cost drivers following arterial graft repair. Graft infection was associated with significantly increased costs across both periods, and non-autologous graft use was associated with disproportionately higher 18-month HCRU. Full article

Due to the indispensable use of the internet, malicious actors have exploited URLs as a threat source of network information security and integrity. URL detection based on traditional methods has become inefficient against the uncontrolled increase of URLs, especially when facing dynamic and large-scale threats. To address the limitations of traditional methods and to provide intelligent and scalable detection of malicious URLs, this study proposes the hybrid framework (NetGuard) by integrating probabilistic data structures (PDSs) with machine learning (ML) capabilities. The proposed NetGuard utilizes PDSs to develop a Hybrid Scalable Detection Filter (HSDF), which combines the strengths of counting Bloom filters (CBFs) (deletion capability) and Scalable Bloom filters (SBFs). The proposed HSDF provides efficient membership queries under bounded false-positive rates (approximately 0.01) and ensures efficient data management and low-latency lookups on a scale of 10⁻⁵ s. On the other hand, NetGuard leverages the ML classifier capabilities to train and package a learned classifier for detecting malicious URLs. The proposed framework utilizes Decision Trees (DTs) and Random Forest (RF) classifiers. The proposed classifiers are trained by a novel SupURLsIdDs dataset which includes fifteen distinctive lexical and structural URL features extracted from four URL classes: benign, defacement, malware, and phishing URLs. The experimental results indicated the effectiveness of the HSDF in insertion and deletion operations, with minimal memory consumption (approximately 2.7 MB for 222,000 URLs) while maintaining a controlled false-positive rate (approximately 0.01 on Real-only subset up to 0.12 with synthetic data). The HSDF memory footprint represents a 99.88% enhancement compared to the RF model (which demands 2253.17 MB); thus, the HSDF complements RF as an ultra-lightweight first line of defense. The ML classifiers showed the superiority of RF, which achieved an overall classification accuracy of approximately 96% on large-scale URL data. These experiments are conducted using benchmark datasets constructed from aggregated real and synthetic data to demonstrate the scalability, adaptability, and resource efficiency of the first phase of NetGuard as a practical foundation for real-time web threat detection. The real-time integration and dynamic updates are presented as a deployment architecture and constitute future work. Full article

With the development of Internet of Things (IoT) technology, fire detection systems based on multi-sensor fusion have become critical infrastructure to ensure public safety. Due to environmental noise and sensor heterogeneity, these systems often suffer from high rates of false alarms and missed detections. Although existing machine learning approaches have partially improved classification accuracy, their overall performance remains limited. Inspired by the cognitive mechanisms of the human brain, we developed an improved mind-linked continuous-coupled neural network (ML-CCNN) based on the existing continuous-coupled neural network (CCNN). We propose a parameter adaptation mechanism that modulates neural activations through a global threshold. We utilized the synthetic minority oversampling technique (SMOTE) to mitigate data imbalance and transformed sample feature vectors into matrices for training. Our model achieved an accuracy of 99.96% on our own dataset and 99.97% on the public Smoke Detection Dataset (SDD), which highlights ML-CCNN’s potential for fire detection. Full article

One of the major obstacles in early cancer detection in dogs is the limited sensitivity in detecting circulating tumor DNAs (ctDNAs) with low abundances. Standard next-generation sequencing (NGS) without error correction typically achieves detection limits around ~1% mutant allele frequency (MAF). We sought to improve the detection sensitivity using a sequential CRISPR-EspCas9 enrichment strategy in which iterative in vitro cleavage (IVC) was combined with PCR amplification to selectively deplete wild-type DNA and enrich rare tumor mutations. Applying the strategy to genomic DNA and cell-free DNA mimics from canine mammary gland tumor cell lines demonstrated that IVC enrichment enabled the detection of cancer-associated PIK3CA H1047R mutations that were undetectable by conventional Sanger sequencing. To evaluate detection sensitivity, we characterized enrichment using synthetic templates for PIK3CA H1047R and other cancer-related mutations, BRAF V596E, and KRAS G12C. We observed that three iterations of sequential IVC achieved ~160, ~15, and ~2.2-fold enrichment for PIK3CA H1047R, BRAF V596E, and KRAS G12C, respectively. Under the present synthetic-template conditions, the analytical LOD reached 0.001% MAF for PIK3CA and 0.01% MAF for BRAF, whereas KRAS showed only modest enrichment and remained practically limited under the current guide design. Together, the results show that the CRISPR-EspCas9 IVC strategy enables selective enrichment of low-frequency single-nucleotide mutant alleles. We anticipate that the finding could be utilized to develop a highly sensitive veterinary liquid biopsy application with further optimization and validation using canine plasma cfDNA. Full article

Nowadays, approximately 50% of chemical surfactants come from petrochemical sources and pose environmental risks due to poor biodegradability, affecting microbial communities, aquatic organisms, and terrestrial ecosystems. Biosurfactants are eco-friendly alternatives, thanks to their strong surface tension-reducing activity, stability, low toxicity, and biodegradability, but their large-scale production is still limited by high costs and low yields. In this study, rice husk was evaluated as a renewable substrate from the agro-industrial field for lipopeptide production by the endophytic Bacillus subtilis AC7. Medium optimization through Plackett–Burman designs identified nitrogen sources and pH 6.5 as key factors enhancing biosurfactant production. Under optimized conditions, surfactin production increased from 4.2 mg/L in untreated rice husk to 266–276 mg/L with NaNO₃ and NH₄NO₃ supplementation, respectively. Combined laccase–amylolytic pretreatment further improved substrate utilization, enhancing sugar availability and supporting higher biomass and metabolic activity. In bench-scale fermentation, this condition yielded the highest surfactin concentration (237.5 mg/L). LC-MS/MS analysis confirmed surfactin as the main product, with C15 as the dominant homologue, in both shake-flask and bench-scale fermentations. These findings highlight a novel, sustainable process for surfactin production, offering a renewable alternative to synthetic surfactants while addressing both environmental and economic concerns. Full article

Triple-negative breast cancer (TNBC) poses a significant therapeutic challenge owing to its aggressiveness and limited treatment options. Here, we integrated genome-scale metabolic modeling with machine learning to improve gene essentiality prediction and identify candidate therapeutic targets for TNBC. Cell-line-specific genome-scale metabolic models were reconstructed for 50 breast cancer cell lines using RNA-sequencing from Cancer Dependency Map (DepMap). Metabolic reaction flux distributions derived from minimization of metabolic adjustment (MOMA) were used as features to train a random forest classifier, with DepMap gene dependency scores as ground truth labels. This integrative approach outperformed the MOMA alone for gene essentiality prediction, increasing sensitivity from 0.37 to 0.55. The model identified 57 TNBC-specific essential genes, including Enolase 1 (ENO1), that were missed by MOMA-based prediction. Furthermore, 30 synthetic lethal partners of succinate dehydrogenase subunit A (SDHA) were predicted in TNBC cell lines. This framework demonstrates the utility of combining metabolic modeling with machine learning for identifying context-specific cancer vulnerabilities. Full article

To address the lack of long-term, wide-area surface deformation observations along the geologically complex Dangxiong–Yangbajing section of the G6 Expressway in the frozen-ground region of the Qinghai–Tibet Plateau, where conventional monitoring is insufficient, we applied Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) to retrieve surface deformation within a 2.0 km corridor on both sides of the highway from 24 November 2021 to 26 December 2024, and to characterize the spatiotemporal evolution of deformation. We then integrated eight explanatory factors (slope, surface roughness, distance to rivers, distance to faults, surface soil moisture, precipitation, land surface temperature (LST), and fractional vegetation cover (FVC)). Geodetector was used to quantify their explanatory power and spatial heterogeneity with respect to deformation. The results show pronounced spatially uneven settlement along this highway segment, with maximum annual settlement rates exceeding −45 mm/a. Five settlement centers were identified, including two major pavement subsidence zones. Distance to faults and soil moisture showed higher single-factor explanatory power, whereas FVC, precipitation, and LST also contributed to deformation heterogeneity. Interaction detection further indicated that the interactions between fault-related conditions with vegetation, soil moisture, precipitation, and LST substantially enhanced the explanatory power, suggesting that the deformation pattern was associated with multi-factor coupling rather than a single dominant environmental factor. These findings demonstrate the utility of integrating SBAS-InSAR with Geodetector analysis for corridor-scale highway deformation assessment and provide a remote sensing basis for targeted hazard assessment and risk mitigation for highways in frozen-ground environments. Full article

Quasi-static ultrasound elastography (USE) is a promising imaging technique for detecting malignancies by assessing tissue stiffness, but its accuracy heavily depends on the quality of radio-frequency (RF) frame pairs used for displacement estimation. A major challenge in quasi-static USE is signal decorrelation, which is primarily caused by out-of-plane motion during manual probe compression, leading to unreliable displacement fields and degraded elastography images. This paper introduces a novel, displacement estimator-agnostic method for assessing RF frame pair quality by measuring the similarity between the measured post-compression RF frame and a warped version of the pre-compression frame generated using the estimated displacement field. The proposed approach employs computationally efficient metrics such as mean squared error (MSE) and correlation, demonstrating robustness against signal decorrelation in both synthetic and clinical datasets. Additionally, we present a method to simulate realistic RF data corruption via controlled out-of-plane displacements, facilitating the development of robust motion-tracking algorithms. Validation using in silico phantoms, tissue-mimicking phantoms and clinical breast cancer and liver cancer cases confirm the method’s efficacy in identifying high-quality frame pairs, significantly improving strain image accuracy. Threshold values of 1.4 and 0.5 were determined for MSE and correlation, respectively, as being effective to differentiate between good vs. bad RF data frame pairs. This work lays the foundation for automated frame selection in USE, enhancing its diagnostic reliability and clinical utility. Full article

Interpreting complex, non-linear Interferometric Synthetic Aperture Radar (InSAR) displacement time-series data for infrastructure risk assessment remains a significant geotechnical challenge. This is particularly evident in regions with established road and railway infrastructures, where the primary objective is monitoring the entire network to ensure safety and operational continuity. Because landslide displacement is a highly complex process affected by a combination of internal geological conditions and external triggers, time-series data inherently encode non-linear trends and periodic fluctuations. To address this, a data-driven framework utilizing a sliding-window transformation to engineer temporal-kinematic features is proposed, providing a broader framework for the contextualization of slope stability assessment from a network perspective. This is paired with Principal Component Analysis (PCA) for dimensionality reduction and evaluated across four unsupervised architectures: K-means, Self-Organising Maps (SOMs), Hybrid SOM-K-means, and PCA-K-means. The comparative evaluation reveals that the PCA-K-means pipeline performed best, offering a highly efficient and scalable workflow. The analysis revealed that the optimized PCA-K-means architecture successfully captured 79.20% of the kinematic variance across the first two principal components. Furthermore, it achieved a robust Between-Cluster-to-Total-Sum-of-Squares (BCSS/TSS) ratio of 71.70%, an optimal Silhouette Score of 0.320, and a low Quantisation Error (QE) of 0.90, demonstrating superior spatial separation and geometric accuracy compared to traditional heuristic methods. When cross-validated against static topographic susceptibility models, the dynamic kinematic clusters exhibited a 23% spatial convergence at the polar bounds of risk, successfully grounding the algorithm’s predictions in physically verified geomorphological features. Relying on the statistical volatility of displacements, this optimal model successfully partitioned the data into five distinct geotechnical risk classes, ranging from stable (Class A) to extreme risk (Class E). The results demonstrate that the developed dynamic framework provides a highly reliable, actionable tool for proactive, large-scale slope stability and infrastructure risk assessment. Full article

Bioethanol production from lignocellulosic biomass remains energy-intensive, and its energy performance can be affected by equipment degradation, utility disturbances, and operating variability. This study developed a degradation-aware mechanistic–AI framework for energy forecasting, anomaly detection, maintenance-oriented interpretation, and multi-objective optimization in bioethanol production under limited-data conditions. Reduced-order energy models were formulated for pretreatment, hydrolysis–fermentation, and ethanol purification. Equipment deterioration was represented through heat-transfer fouling, column-efficiency decline, and pump-efficiency decay. Condition-dependent modifiers were introduced to account for load-related degradation and intervention-related partial recovery. Benchmark-constrained synthetic time-series datasets were generated under baseline, accelerated-degradation, condition-dependent, stress, and data-quality perturbation scenarios. Empirical baselines and machine-learning models were compared for specific energy consumption prediction, with uncertainty reported using confidence intervals. The long short-term memory model achieved the lowest prediction errors under both baseline and stress conditions. Robustness testing showed that sensor drift, missing values, and outliers increased forecasting and anomaly-detection uncertainty. Sensitivity analysis identified degradation coefficients, seasonal disturbance, and anomaly-threshold selection as influential factors. Multi-objective optimization revealed trade-offs among specific energy consumption, ethanol purity, and equipment-health penalty. The proposed framework should be interpreted as a benchmarked methodological platform rather than a plant-validated maintenance or control system. Plant-specific deployment requires calibration with operating records, maintenance logs, cleaning records, and sensor-quality assessment. Full article

In high-stakes settings, the most consequential failure of a language model is not a wrong answer but an answer it was not entitled to give. Existing retrieval-augmented generation (RAG) pipelines retrieve context, generate text, and perhaps add citations, but they do not decide whether the evidence justifies answering, how uncertain the answer is, or at what level the system should intervene. We argue that LLMs should not only generate answers; they should be embedded inside a selective decision architecture that jointly estimates answerability, quantifies uncertainty, verifies structural validity, and chooses among direct response, escalation, abstention, or failure. We introduce BRAG (Bayesian Retrieval-Augmented Generation), a framework that operationalises this shift from answer generation to evidence-governed decision support. BRAG estimates an answerability posterior, decomposes uncertainty into epistemic and aleatoric components, and applies a structural validity gate prior to answer emission. Evaluation is conducted using controlled Monte Carlo simulation (n = 2400 queries) and a calibrated statistical pilot (N = 500), both parametric models of the pipeline’s output distribution, together with a governed operational validation that executes the full released pipeline end-to-end on independently generated MIMIC-IV-schema records (N = 100; not credentialed patient records), expert adjudication on a stratified subset (N = 200), and secondary transfer experiments on SEC EDGAR and CUAD. In simulation, BRAG reduces hallucination from 0.257 to 0.016 (93.8%) and achieves the highest coverage-adjusted utility (0.632) among five systems. In the synthetic MIMIC-IV-schema pilot, hallucination decreases from 0.292 to 0.020 (93.2%), with utility 0.538 at 89.6% coverage and an answerability AUROC of 0.692, which is moderate in absolute terms and is therefore positioned as a routing signal that operates jointly with the deterministic validity gate rather than as a stand-alone clinical classifier. Expert adjudication yields substantial agreement (Cohen’s κ = 0.778) and 93.5% concordance with BRAG decisions. Cross-domain transfer demonstrates 96–97% hallucination reduction without retriever modification, while ablation identifies the structural validity gate as the primary safety mechanism and the answerability posterior as the primary coverage and routing-precision mechanism. These results show that combining answerability estimation with structural validity enforcement can substantially reduce unsupported outputs. All findings are methodological rather than clinical: every evaluation tier uses synthetic or schema-conformant data, and validation on credentialed de-identified patient records remains necessary before any clinical deployment. Full article

In long-horizon multi-party conversations, human-centric AI agents face a persistent structural problem: similarity-based retrieval may fail to reconnect semantically dispersed fragments of the same evolving event. This problem severely weakens causal continuity and multi-hop context recovery. To improve attribution trust and reduce structural erasure, we propose MemLoom, a dual-loop causality-traceable retrieval framework that organizes conversational history as an event memory graph. MemLoom decouples latency-sensitive online interaction from off-peak structural curation through online event formation, sentence-level buffering, asynchronous neuro-symbolic graph synthesis, and bounded dual-stream retrieval. Evaluations across QMSum, LoCoMo, and the synthetic causal diagnostic suite (SCDS) support the structural utility of MemLoom. For LoCoMo, under our unified local evaluation setup, MemLoom shows favorable temporal and multi-hop reasoning results (J = 65.77 and 58.14) relative to contemporary agentic baselines, such as Mem0, Zep, and A-Mem. For SCDS, within a controlled diagnostic setting, it recovers demanded causal chains more reliably than GraphRAG (SCR = 0.72 vs. 0.35) and maintains stronger answer-level auditability (AA = 0.80 vs. 0.50). This is achieved with a bounded online P95 latency of 1.67 s. These results indicate that asynchronous dual-loop stewardship has practical value for causality-traceable, event-centric conversational memory in multi-party settings. Full article