Accelerates Bayesian optimization using learned weight-prior.
problem Optimizing expensive functions with limited auxiliary data.
method Constructs a GP covariance from auxiliary data to model a more appropriate weight prior.
result Accelerates Bayesian optimization on test functions and real-world applications.
Novel method constructs covariance functions for Bayesian optimisation.
problem Bayesian optimisation with existing knowledge.
method Uses m-kernels to convert existing covariance functions to problem-specific ones.
result Constructs covariance functions matching the problem at hand.
Bayesian optimisation for expensive experiments with shape prior.
problem Expensive experiments with time-varying control variables.
method Developed a novel Bayesian optimisation framework using Bernstein polynomial basis and dynamic polynomial degree adjustment.
result Demonstrated effectiveness on polymer fibre design and learning rate optimisation.
Machine learning optimizes polymer fiber synthesis.
problem Complex material synthesis requires impractical experimentation.
method Bayesian optimisation using machine learning.
result Efficiently directs synthesis to achieve material and process objectives.
This paper proposes AI-based solutions for optimizing semiconductor manufacturing processes.
problem Optimizing semiconductor manufacturing processes with advanced analytics.
method Evolutionary Computing and Deep Learning algorithms for feature selection and neural networks.
result Advanced algorithm for intelligent feature selection in semiconductor manufacturing.
End-to-end framework diagnoses manufacturing faults.
problem General framework for diagnosis and monitoring in manufacturing.
method Data-driven, deep learning techniques for fused sensory measurements.
result Framework performs well in diverse manufacturing applications.
A new system detects and classifies defects in semiconductor manufacturing.
problem Detecting and classifying novel defect patterns in high-resolution imagery.
method Stacked hybrid convolutional neural networks (SH-CNN) with visual attention.
result SH-CNN outperforms current approaches in automated visual inspection.
Paper proposes RL for efficient dispatching in dynamic manufacturing environments.
problem Efficient dispatching in dynamic, stochastic manufacturing environments.
method Reinforcement learning (RL) with policy transfer for dynamic shop floor settings.
result Proposed RL approach outperforms other methods in terms of total discounted reward and average lateness, tardiness.
MFRL-BI controls manufacturing processes without needing accurate models.
problem Model inaccuracies in complex manufacturing systems.
method Model-free reinforcement learning with Bayesian inference.
result Demonstrated to perform well in a nonlinear CMP process.
An encoder-decoder model detects anomalies in manufacturing data.
problem Detecting and predicting anomalies in sequential sensor data.
method Encoder-decoder architecture for unsupervised anomaly detection.
result The model identifies anomalies and predicts future states in manufacturing processes.
New method uses SEMs to uncover cause-effect in manufacturing processes.
problem Complex cause-and-effect relationships in manufacturing processes.
method Using Structural Equation Models with non-linear relationships.
result More informative cause-effect relationships derived from data.
Bayesian method predicts runtime metrics for fog manufacturing.
problem Accurate prediction of runtime performance metrics in fog manufacturing.
method Bayesian sparse regression for multivariate mixed responses.
result Enhanced prediction and statistical inferences of runtime metrics.
3D-CNN learns local geometric features for manufacturability analysis of drilled holes.
problem Capturing distinguishing local features in 3D CAD geometry.
method 3D-CNN with voxel data augmented by surface normals, using 3D gradient-weighted class activation maps.
result Identification of local features critical for manufacturability analysis.
3D-CNN method visualizes localized geometric features for manufacturability analysis.
problem Interpreting 3D-CNN decisions for complex geometries.
method 3D-CNN with surface normals, 3D-GradCAM for feature visualization.
result Identifies critical local features for manufacturability.
Study examines cash conversion cycle in manufacturing firms, finding negative relationships with profitability and size.
problem Understanding cash conversion cycle in manufacturing firms and its impact on profitability and size.
method Empirical study of 30 manufacturing firms in Dhaka Stock Exchanges, categorizing them into six industries, analyzing industry averages and relationships with size and profitability.
result Negative relationship between cash conversion cycle and profitability, especially ROE; negative relationship with firm size in terms of net sales.
Framework optimizes expensive manufacturing processes efficiently.
problem Optimizing input parameters for advanced manufacturing methods.
method Bayesian optimization with tailored acquisition function and parallel acquisition.
result Framework efficiently finds optimal parameters with minimal process cost.
AI monitors social distancing and masks at manufacturing plants.
problem Ensuring safety of workers during post-COVID production.
method Computer vision and AI techniques for social distancing and mask detection.
result Real-time alerts prevent violations of social distancing and mask-wearing.
New framework uses machine learning for better product design.
problem Design for manufacturability challenges in product design.
method Machine learning applied to optimize product design.
result Enhanced design process for improved manufacturing efficiency.
Paper proposes tensor-based method for semiconductor manufacturing process control.
problem Challenges of traditional process control methods in high-dimensional image-based overlay errors.
method Builds a high-dimensional process model, proposes tensor-on-vector regression algorithms, designs EWMA controller for tensor data.
result The method reduces overlay errors using limited control recipes and is superior especially when disturbances are not stable.
A new framework optimizes manufacturing decisions with less data and time.
problem Optimizing complex systems with multiple conflicting objectives.
method Data-driven Bayesian optimization using sequential learning.
result The proposed algorithm achieves the actual Pareto front with less data.
Paper introduces a hybrid GPR model for more interpretable RUL prediction in aeroengine.
problem Challenges in interpreting and modeling uncertainty in RUL prediction models.
method Modified Gaussian Process Regression (GPR) with temporal feature extraction.
result Effective prediction of RUL intervals with transparent feature significance.
New methods improve tool-to-tool matching in semiconductor manufacturing.
problem Challenges in obtaining static configuration data and extending methods to heterogeneous equipment.
method Novel TTTM analysis pipelines hypothesizing higher variance and modes for mismatched equipment.
result Best univariate method achieves correlation coefficients >0.95 and >0.5 with variance and modes, respectively.
Labor productivity was studied at the microscopic level in terms of distributions based on individual firm financial data from Japan and the US. A power-law distribution in terms of firms and sector productivity was found in both countries' data. The labor productivities were not equal for nation and sectors, in contra…
Framework predicts melt pool geometry with AI, improving manufacturing quality.
problem Achieving consistent product quality in Metal Additive Manufacturing.
method Surprise-guided sequential learning framework integrating CTGAN for limited data.
result Enhanced predictive accuracy for melt pool dimensions.
The paper uses causal machine learning to optimize rework decisions in manufacturing.
problem Optimizing rework policies in manufacturing systems to balance yield improvement and rework costs.
method Proposes a causal model using double/debiased machine learning (DML) techniques to estimate conditional treatment effects and derive rework policies.
result Achieved a yield improvement of 2-3% during the color-conversion process of white LEDs.
Describes spectral data for singular fibres of a specific Hitchin system.
problem Characterizing singular fibres of the SL(2,C)-Hitchin system. method Using Hecke transformations and analysis of parameter spaces, the paper stratifies and compactifies the singular spaces.
result Large classes of singular fibres are shown to be fibre bundles over Prym varieties.
We classify semi-Riemannian submersions with connected totally geodesic fibres from a real pseudo-hyperbolic space onto a semi-Riemannian manifold under the assumption that the dimension of the fibres is less than or equal to three and the metrics induced on fibres are negative definite. Also, we obtain the classificat…
Ozsváth and Szabó conjectured that knot Floer homology detects fibred links. We will verify this conjecture for closed 3-braids, by classifying fibred closed 3-braids. In particular, given a nontrivial closed 3-braid, either it is fibred, or it differs from a fibred link by a half twist. The proof uses Gabai's method o…
Study proposes explainable analytics for manufacturing process planning.
problem Improving data-driven decision-making in manufacturing.
method Combines process mining, machine learning, and XAI. Uses deep learning for prediction and Shapley values/ICE plots for explanations.
result Enhanced decision-making capabilities through local post-hoc explanations.
Given a (smooth) complex analytic family of compact complex manifolds, we prove that the central fibre must be Moishezon if the other fibres are Moishezon. Using a "strongly Gauduchon metric" on the central fibre whose existence was proved in our previous work on limits of projective manifolds, we show that the irreduc…
Following on from work of Dunfield, we determine the fibred status of all the unknown hyperbolic 3-manifolds in the cusped census. We then find all the fibred hyperbolic 3-manifolds in the closed census and use this to find over 100 examples each of closed and cusped virtually fibred non-fibred census 3-manifolds, incl…
This paper evaluates data enrichment techniques for rare event detection in manufacturing.
problem Rare events in manufacturing lead to unplanned downtime and high energy consumption.
method Time series data augmentation, sampling, and imputation techniques combined with supervised machine learning.
result Data enrichment enhances rare failure event detection and prediction by up to 48%.
Develops a framework for continual learning in anomaly detection.
problem Deterioration of monitoring performance due to new defect categories.
method Pseudo replay-based class incremental learning with oversampling.
result Enhanced monitoring performance and flexibility in model architecture.
We consider vector fields on knot/link complements in S3 which are transverse to the fibres of a fibration of the complement over a circle. We prove that a large class of fibred knots/links, including all non-torus fibred 2-bridge knots, has the following property: any vector field transverse to the fibres of the fi…
The paper uses machine learning to optimize rework policies in semiconductor manufacturing.
problem Optimizing rework steps to increase yield without increasing costs.
method Applied double/debiased machine learning (DML) to estimate treatment effects.
result Derived optimal rework policies and estimated their value empirically.
Profinite rigidity studied for algebraic fibring of groups.
problem Profinite rigidity of groups through algebraic fibring.
method Introducing TAP groups and proving algebraic fibring is a profinite property.
result Algebraic fibring is a profinite property for LERF groups.
The stabilisation height of a fibre surface in the 3-sphere is the minimal number of Hopf plumbing operations needed to attain a stable fibre surface from the initial surface. We show that families of fibre surfaces related by iterated Stallings twists have unbounded stabilisation height.
Study shows volume and genus unrelated for hyperbolic fibred knots.
problem Volume and genus of hyperbolic fibred knots are unrelated.
method Analyzes hyperbolic fibred knots in three-sphere.
result Volume and genus are unrelated for hyperbolic fibred knots.
Survey on fibring in manifolds and groups, focusing on recent developments and conjectures.
problem Understanding fibring phenomena in manifolds and groups.
method Discussion of state of the art and explanation of recent developments.
result Many conjectures about fibring in higher dimensions, some plausible, some dubious.
Any leafwise connection on a fibre bundle over a foliated manifold is proved to come from a connection on this fibre bundle.
Study Laplace operators in adiabatic limit of fibre bundles.
problem Understanding Laplace-type operators in the adiabatic limit of complex vector bundles.
method Analyse the adiabatic limit of fibre bundles with compact fibres, proving existence of effective operators providing asymptotics.
result Existence of effective operators providing asymptotics to any order in ε for Laplace-type operators H on an almost-invariant subspace of L^2(E).
Defines and parametrizes sl(2)-type singular fibres in symplectic and odd orthogonal Hitchin systems.
problem Characterizing and understanding singular fibres in Hitchin systems.
method Stratification by semi-abelian spectral data, study of irreducible components, global description of degenerations.
result Extension of Langlands duality to sl(2)-type Hitchin fibres. Study compares deterministic and probabilistic ML for precise AM component dimensions.
problem Accurately estimate dimensions of additively manufactured parts with variability.
method Employed models integrating continuous and categorical factors, tested deterministic and probabilistic ML methods.
result Gaussian Process Regression and Bayesian Neural Networks provide strong predictive performance and uncertainty quantification.
We explore algebraic characterizations of 2-knots whose associated knot manifolds fibre over lower-dimensional orbifolds, and consider also some issues related to the groups of higher-dimensional fibred knots.
Study uses machine learning, linear, and Bayesian models for logistic regression in manufacturing failures detection.
problem Manufacturing failures detection using logistic regression models.
method Machine learning (XGBoost), linear, and Bayesian approaches for logistic regression.
result Bayesian approach provides statistical distribution for model parameters, useful for probabilistic analysis.
We consider Schrödinger operators H=−Δgε+V on a fibre bundle M→πB with compact fibres and a metric gε that blows up directions perpendicular to the fibres by a factor ε−1≫1. We show that for an eigenvalue λ of the fibre-wise part of H, satisfying a l…
Ano-SuPs detects anomalies in images of manufactured products by identifying suspected patches.
problem Challenges in detecting anomalies in image-based manufacturing systems, including complexity of background and various anomaly patterns.
method Two-stage strategy anomaly detection method: first, remove suspected patches; second, refine anomaly identification using normal patches.
result Demonstrated effectiveness through simulation and case studies, identifying key parameters and steps impacting model performance and efficiency.
Manufacturing infinite sets of knotted and unknotted surfaces in 4-manifolds.
problem Creating infinite sets of knotted and unknotted surfaces in 4-manifolds.
method Recent constructions of inequivalent smooth structures.
result Infinite sets of pairwise smoothly non-isotopic nullhomologous 2-tori and spheres.