Pattern Recognition of Grating Perimeter Intrusion Behavior in Deep Learning Method

Developments in X‐ray photoelectron spectroscopy (XPS) instrumentation and the need for spatial information in surface characterization have led to advances in XPS imaging and related image processing techniques. In this Insight Note, we demonstrate the use of summary statistics as simple, but effective, tools for understanding XPS hyperspectral images (data cubes) prior to more advanced image processing. An XPS image obtained from a silicon surface patterned with different thicknesses of oxide was analyzed with three summary statistics: a tool in the MATLAB programming environment, the mean, and pattern recognition entropy (PRE). The MATLAB tool largely separates the spectra into two groups. The mean does a somewhat better job differentiating between the spectra, and PRE is even more effective. The results of the MATLAB summary statistic are confirmed by plotting the average and standard deviation spectra of different regions of the image it produces. The results of the mean and PRE summary statistics are confirmed by evenly segmenting the results and examining the average and standard deviation spectra of these segments. Fitting these average spectra demonstrates the greater effectiveness of the PRE summary statistic in segmenting the spectra into chemically distinct groups.

show abstract

“…The PRE summary statistic is based on Shannon's entropy. 24,25,[32][33][34][35][36][37][38][39] It is defined as follows:…”

Section: Theorymentioning

confidence: 99%

“…The PRE summary statistic is based on Shannon's entropy 24,25,32–39 . It is defined as follows:

PRE goodbreak= goodbreak- \sum_{i = 1}^{n} normalp ((), x_{i}) \log_{2} normalp ((), x_{i}),

where

normalp ((), x_{i})

is the “probability” of observing a signal (intensity value) in a spectrum.…”

Section: Theorymentioning

confidence: 99%

Surface analysis insight note: Analysis of X‐ray photoelectron spectroscopy images with summary statistics

Moeini

Linford

2023

Surface & Interface Analysis

View full text Add to dashboard Cite

show abstract

“…(14)(15)(16)(17) They are also applied to the research of electromagnetic waves, such as those in optical gratings, optical ring resonator sensors, and photonic crystals. (18)(19)(20)(21) For example, artificial neural networks are used to predict the diffractive efficiencies of optical gratings. (18) The diffractive efficiencies of each order of an optical grating are strongly related to the geometric shape of the grating.…”

Section: Introductionmentioning

confidence: 99%

Using Autoencoder Artificial Neural Network to Predict Photonic Crystal Band Structure

Chang,

Tsai,

Chiang

et al. 2023

Sensors and Materials

View full text Add to dashboard Cite

A photonic crystal is an artificial material with a periodic optical refractive index. The band structure of photons can be tailored by adjusting the geometric parameters spatially. By properly designing the configuration, the photonic crystal can generate an optical forbidden band within the structure. To choose an appropriate geometric configuration that can generate a photonic band gap in the desired frequency range, traditionally, the band structure of such structure has been obtained by applying Floquet periodic boundary conditions and performing the eigen analysis calculation. However, a great amount of testing is required and consumes a great amount of time. In our study, the top view of the unit cell is converted to a binary bitmap and encoded to downgrade the bitmap for forming the input data of the artificial neural network. We adopted the finite element method to calculate the band structure training data set, which contained various geometric parameters and corresponding band structures. Our neural network shows high accuracy and is less time-consuming. The results are useful for the inverse design of photonic crystals.

show abstract

“…Mališa and Lazarević [19] discussed the length and cardinality of block codes over L-fuzzy sets. e concepts of fuzzy codes and codes of ordered fuzzy sets are relatively new, but crucial for modifying the data communication and pattern recognition in deep learning [20] and fault detection for distributed components [21,22]. However, these codes are unable to identify and handle any expected error in the information process while codes are transmitted in a noisy channel, for example, a spell checker and machine reader.…”

Section: Introductionmentioning

confidence: 99%

Codes over Lattice‐Valued Intuitionistic Fuzzy Set Type‐3 with Application to the Complex DNA Analysis

et al. 2022

View full text Add to dashboard Cite

In this article codes over lattice valued intuitionistic fuzzy set type-3 (LIFS-3) are defined. Binary block codes and linear codes are constructed over LIFS-3. Hamming distance and related properties of these newly established codes are examined. The research findings are applied to genetic codes. The set L of sixty-four codons is converted into a lattice and then codes are created over the set S of twenty amino acids by defining membership and nonmembership functions from the set of twenty amino acids to the sixty-four codon set. Comparison of codes over L -fuzzy set and LIFS-3 conducted in terms of hamming distance for codon system that ensures the efficiency of newly established codes.

show abstract

Pattern Recognition of Grating Perimeter Intrusion Behavior in Deep Learning Method

Cited by 7 publications

References 16 publications

Surface analysis insight note: Analysis of X‐ray photoelectron spectroscopy images with summary statistics

Surface analysis insight note: Analysis of X‐ray photoelectron spectroscopy images with summary statistics

Using Autoencoder Artificial Neural Network to Predict Photonic Crystal Band Structure

Codes over Lattice‐Valued Intuitionistic Fuzzy Set Type‐3 with Application to the Complex DNA Analysis

Contact Info

Product

Resources

About