Skip to search formSkip to main contentSkip to account menu
Remaining Useful Life Estimation Using Functional Data Analysis
TLDR
A novel Functional Data Analysis method called functional Multilayer Perceptron (functional MLP) for RUL estimation, which treats time series data from multiple equipment as a sample of random continuous processes over time and shows the superiority of this algorithm over all the other state-of-the-art methods.
View on IEEE
Silver Circulation Worldwide: Initial Steps in Comprehensive Research
TLDR
Estimates from 1400 through 1900, showing annual flows of production, cumulative stocks (accounting for various levels of wear and tear), and the long-term rate of growth in silver stocks, indicate that, while world population grew at an annual rate of 0.45% per year, 1700– 1900, silver stock rose at an approximate 0.7%" per year.
View via Publisher
Multilayer Perceptron for Sparse Functional Data
TLDR
A novel algorithm for generalizing Multilayer Perceptron to handle sparse functional data, wherein for a given subject there are multiple observations available over time and these observations are sparsely and irregularly distributed within the considered time range is proposed.
View on IEEE
Bayesian Optimization Algorithm with Agent-based Supply Chain Simulator for Multi-echelon Inventory Management
TLDR
A Bayesian optimization approach along with an agent-based supply chain simulator is proposed to solve a constrained multi-echelon inventory optimization problem that requires fewer number of interactions with the simulator and converges to the optimal solution significantly faster than GA.
View on IEEE
What Maintenance is Worth the Money? A Data-Driven Answer
TLDR
This paper formally defines the problem of estimating the effectiveness of a single or a group of maintenance actions, and proposes a systemic way of solving the problem.
View on IEEE
Deep Time Series Models for Scarce Data
View PDF on arXiv
A Non-linear Function-on-Function Model for Regression with Time Series Data
TLDR
A general functional mapping that embraces the function-on-function linear model as a special case is proposed, using the fully connected neural network to learn the mapping from data, which addresses the aforementioned concerns in the existing approaches.
View on IEEE
TWO-SAMPLE INFERENCE AND CHANGE POINT DETECTION FOR SPARSE FUNCTIONAL DATA
TLDR
Three topics within the field of sparse functional data inference are focused on: two-sample inference of mean functions of two independent groups of functional data, one-way functional ANOVA (FANOVA), and change point detection in mean functions for sparse functional time series.
1st Place Solution to ICDAR 2021 RRC-ICTEXT End-to-end Text Spotting and Aesthetic Assessment on Integrated Circuit
TLDR
This paper presents the proposed methods to ICDAR 2021 Robust Reading Challenge Integrated Circuit Text Spotting and Aesthetic Assessment and adds a classification branch of 3 classes to differentiate the aesthetic classes of each character.
View PDF on arXiv
Health Indicator Forecasting for Improving Remaining Useful Life Estimation
TLDR
A new ‘generative + scenario matching' algorithm for health indicator forecasting to first non-parametrically fit the underlying health indicator curve with a continuous Gaussian Process using a sample of run-to-failure health indicator curves and generates a rich set of random curves from the learned distribution.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License