1592 papers
This paper proposes a cascaded inverse-forward deep learning framework that estimates unknown initial and boundary conditions from early-time temperature fields to enable real-time, uncertainty-quantified prediction of the degree of cure in frontal polymerization, achieving high accuracy with minimal inference latency.
This paper analyzes 53,860 production snapshots from high-mix semiconductor equipment manufacturing to demonstrate that schedule credibility is primarily constrained by capacity-limited attention and administrative latency rather than structural complexity, leading to a dual-timescale Lean Six Sigma framework that prioritizes simple temporal heuristics over complex rules for effective intervention.
This paper proposes a low-data decision screen for urban curb management that determines optimal vehicle priority sequences based on social waiting costs relative to dwell times and calculates the maximum operating budget justified by the resulting welfare gains, thereby helping agencies decide both which vehicle class should be prioritized and whether such intervention is economically viable.
This paper proposes a closed-loop active sampling method that combines a label-extension algorithm with an iterative geometric selection process to efficiently and accurately characterize the static voltage stability region of multi-terminal HVDC systems, overcoming the computational inefficiency of random sampling and the conservatism of approximation-based approaches.
This paper presents a novel Wheatstone bridge-inspired microfluidic trap that immobilizes large droplets while enabling automated, high-precision medium exchange and chemical control, demonstrating its versatility for biomedical applications through successful experiments with bacterial and mammalian cells.
This study demonstrates that the effectiveness of choropleth map comparison layouts depends on the interaction between task complexity and spatial discretization geometry, revealing that slider-based transitions improve efficiency in high-complexity tasks while hexagonal grids consistently outperform irregular polygons in both response time and accuracy.
This study combines experimental analysis of PVDF hollow fiber membrane degradation in direct contact membrane distillation with a deep learning-based LSTM model to accurately predict performance decline under varying operational conditions, enabling proactive maintenance and optimized water purification strategies.
This study demonstrates that 3D-printed sandwich panels with anti-trichiral cores made from sustainable PLA/flax composites exhibit tunable mechanical performance and enhanced energy absorption, where increasing node radius and core thickness or decreasing ligament length significantly improves stiffness and load-bearing capabilities for protective applications.
This paper proposes a resilient frequency control strategy for low-inertia islanded microgrids under false data injection attacks by employing an augmented-state Kalman filter observer to simultaneously estimate system states, load disturbances, and attack signals, thereby significantly reducing frequency deviations and estimation errors across various inertia levels.
This study presents an explainable artificial intelligence framework that utilizes a literature-calibrated simulation of 1,200 building archetypes to accurately predict construction waste and embodied carbon intensity through advanced regression algorithms and SHAP-based feature analysis, demonstrating how integrating material data enhances predictive accuracy for early-stage decision support.