scholarly journals Quantitative Spectral Data Analysis Using Extreme Learning Machines Algorithm Incorporated with PCA

Algorithms ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 18
Author(s):  
Michael Li ◽  
Santoso Wibowo ◽  
Wei Li ◽  
Lily D. Li
Keyword(s):  
Data Analysis ◽  
Conceptual Framework ◽  
Spectral Data ◽  
Learning Algorithm ◽  
Structural Parameters ◽  
Inverse Function ◽  
Principal Component ◽  
Learning Task ◽  
Classification Problems ◽  
Spectral Data Analysis

Extreme learning machine (ELM) is a popular randomization-based learning algorithm that provides a fast solution for many regression and classification problems. In this article, we present a method based on ELM for solving the spectral data analysis problem, which essentially is a class of inverse problems. It requires determining the structural parameters of a physical sample from the given spectroscopic curves. We proposed that the unknown target inverse function is approximated by an ELM through adding a linear neuron to correct the localized effect aroused by Gaussian basis functions. Unlike the conventional methods involving intensive numerical computations, under the new conceptual framework, the task of performing spectral data analysis becomes a learning task from data. As spectral data are typical high-dimensional data, the dimensionality reduction technique of principal component analysis (PCA) is applied to reduce the dimension of the dataset to ensure convergence. The proposed conceptual framework is illustrated using a set of simulated Rutherford backscattering spectra. The results have shown the proposed method can achieve prediction inaccuracies of less than 1%, which outperform the predictions from the multi-layer perceptron and numerical-based techniques. The presented method could be implemented as application software for real-time spectral data analysis by integrating it into a spectroscopic data collection system.

scholarly journals Multi-manufacturer drug identification based on near infrared spectroscopy and deep transfer learning

2020 ◽  
Vol 13 (04) ◽  
pp. 2050016
Author(s):  
Lingqiao Li ◽  
Xipeng Pan ◽  
Wenli Chen ◽  
Manman Wei ◽  
Yanchun Feng ◽  
...  
Keyword(s):  
Data Analysis ◽  
Spectral Data ◽  
Transfer Learning ◽  
Near Infrared ◽  
Learning Strategy ◽  
Classification Performance ◽  
Classification Problems ◽  
Learning Methods ◽  
Effective Transfer ◽  
Spectral Data Analysis

Near infrared (NIR) spectrum analysis technology has outstanding advantages such as rapid, nondestructive, pollution-free, and is widely used in food, pharmaceutical, petrochemical, agricultural products production and testing industries. Convolutional neural network (CNN) is one of the most successful methods in big data analysis because of its powerful feature extraction and abstraction ability, and it is especially suitable for solving multi-classification problems. CNN-based transfer learning is a machine learning technique, which migrates parameters of trained model to the new one to improve the performance. The transfer learning strategy can speed up the learning efficiency of the model instead of learning from scratch. In view of the difficulty in acquisition of drug NIR spectral data and high labeling cost, this paper proposes three simple but very effective transfer learning methods for multi-manufacturer identification of drugs based on one-dimensional CNN. Compared with the original CNN, the transfer learning method can achieve better classification performance with fewer NIR spectral data, which greatly reduces the dependence on labeled NIR spectral data. At the same time, this paper also compares and discusses three different transfer learning methods, and selects the most suitable transfer learning model for drug NIR spectral data analysis. Compared with the current popular methods, such as SVM, BP, AE and ELM, the proposed method achieves higher classification accuracy and scalability in multi-variety and multi-manufacturer NIR spectrum classification experiments.

Chemical components of the rhizomes of Drynaria fortunei (KUNZE) J. Sm. (polypodiaceae) in Vietnam

2011 ◽  
Vol 76 (9) ◽  
pp. 1133-1139 ◽  
Author(s):  
Pham Thi Nhat Trinh ◽  
Nguyen Cong Hao ◽  
Phan Thanh Thao ◽  
Le Tien Dung
Keyword(s):  
Data Analysis ◽  
Spectral Data ◽  
Phenolic Acid ◽  
Ethanol Extract ◽  
Chemical Components ◽  
Spectroscopic Methods ◽  
Phenylpropanoid Glycoside ◽  
Spectral Data Analysis ◽  
First Time

From the ethanol extract of Drynaria fortunei (KUNZE) J. Sm., a new phenylpropanoid glycoside, fortunamide (1), was isolated and characterized by spectroscopic methods. Together with a new glycoside, 9 known compounds, including three curcuminoids (2–4), two isoprenylated flavonoids (5, 6), two flavonoids (7, 8), one monoterpenoid (9) and one phenolic acid (10) were isolated and identified by spectral data analysis from the rhizomes of Drynaria fortunei (KUNZE) J. Sm. Eight of them were isolated from Drynaria fortunei (KUNZE) J. Sm. for the first time.

Coumarins and a Naphthyl Labdanoate Diarabinoside from the Fruits of Peucedanum grande C. B. Clarke

2012 ◽  
Vol 67 (11-12) ◽  
pp. 580-586 ◽  
Author(s):  
Mohammad Aslam ◽  
Mohammed Ali ◽  
Rameshwar Dayal ◽  
Kalim Javed
Keyword(s):  
Data Analysis ◽  
Spectral Data ◽  
Chemical Reactions ◽  
Wistar Rats ◽  
Methanolic Extract ◽  
Nephroprotective Activity ◽  
Coumarin 1 ◽  
Spectral Data Analysis

Phytochemical investigations of the methanolic extract of the fruits of Peucedanum grande C. B. Clarke (Apiaceae) led to the identification of three coumarins and a naphthyl labdanoate diarabinoside characterized as 5-hydroxy-6-isopranyl coumarin (1), 5,6-furanocoumarin (2), 7-methoxy-5,6-furanocoumarin (3), and labdanyl-3α-ol-18-(3’’’-methoxy-2’’’- naphthyl-oate)-3α-L-arabinofuranosyl-(2’→1’’)-α-L-arabinofuranoside (4). The structures of these compounds were identified on the basis of spectral data analysis and chemical reactions. The methanolic extract and 4 showed nephroprotective activity against gentamicininduced nephrotoxicity in Wistar rats.

scholarly journals A Novel on Transmission Line Tower Big Data Analysis Model Using Altered K-means and ADQL

2019 ◽  
Vol 11 (13) ◽  
pp. 3499 ◽  
Author(s):  
Se-Hoon Jung ◽  
Jun-Ho Huh
Keyword(s):  
Big Data ◽  
Data Analysis ◽  
Transmission Line ◽  
Clustering Algorithm ◽  
Learning Algorithm ◽  
Principal Component ◽  
Big Data Analysis ◽  
Standard Normal Distribution ◽  
Analysis Model ◽  
Q Learning

This study sought to propose a big data analysis and prediction model for transmission line tower outliers to assess when something is wrong with transmission line tower big data based on deep reinforcement learning. The model enables choosing automatic cluster K values based on non-labeled sensor big data. It also allows measuring the distance of action between data inside a cluster with the Q-value representing network output in the altered transmission line tower big data clustering algorithm containing transmission line tower outliers and old Deep Q Network. Specifically, this study performed principal component analysis to categorize transmission line tower data and proposed an automatic initial central point approach through standard normal distribution. It also proposed the A-Deep Q-Learning algorithm altered from the deep Q-Learning algorithm to explore policies based on the experiences of clustered data learning. It can be used to perform transmission line tower outlier data learning based on the distance of data within a cluster. The performance evaluation results show that the proposed model recorded an approximately 2.29%~4.19% higher prediction rate and around 0.8% ~ 4.3% higher accuracy rate compared to the old transmission line tower big data analysis model.

Spectral data analysis approaches for improved provenance classification

2015 ◽  
Author(s):  
Kellen J. Sorauf ◽  
Amy J. R. Bauer ◽  
Andrzej W. Miziolek ◽  
Frank C. De Lucia
Keyword(s):  
Data Analysis ◽  
Spectral Data ◽  
Spectral Data Analysis

scholarly journals Mumunine - A New Carbazole Alkaloid from Murraya koenigii (Linn.) Spreng

2020 ◽  
Vol 12 (4) ◽  
pp. 665-672
Author(s):  
M. Chakraborty
Keyword(s):  
Data Analysis ◽  
Spectral Data ◽  
Structure Elucidation ◽  
2D Nmr ◽  
Rich Source ◽  
Murraya Koenigii ◽  
Spectral Data Analysis ◽  
Carbazole Alkaloids

The plant Murraya koenigii, commonly known as curry leaf tree is a rich source of carbazole alkaloids. A number of monomeric as well as dimeric carbazoles with C13, C18 and C23 skeleton have been isolated from the plant. In my present work, a new carbazole alkaloid, designated as mumunine, was isolated from the bark of Murraya koenigii (Linn) Spreng, along with a known carbazole alkaloid, viz. mahanimbine. The structure of the new alkaloid 1 was elucidated on the basis of 1D and 2D NMR spectral data analysis. In this paper, the isolation and structure elucidation of the new compound will be discussed in detail.

scholarly journals Phenolic Derivatives with an Irregular Sesquiterpenyl Side Chain from Macaranga pruinosa

2010 ◽  
Vol 5 (2) ◽  
pp. 1934578X1000500 ◽  
Author(s):  
Yana M. Syah ◽  
Emilio L. Ghisalberti
Keyword(s):  
Data Analysis ◽  
Spectral Data ◽  
Natural Compounds ◽  
Acetone Extract ◽  
Side Chain ◽  
Phenolic Derivatives ◽  
Spectral Data Analysis

A stilbene and two flavonoid derivatives, macapruinosins A-C (1-3), together with two known flavonoids, papyriflavonol A and nymphaeol C, have been isolated from the acetone extract of the leaves of Macaranga pruinosa. The structures of these compounds were identified based on spectral data analysis. Compounds 1 and 2 are the first examples of natural compounds containing an irregular sesquiterpenyl side chain with a cyclobutane skeleton.

Sign in / Sign up

Export Citation Format

Share Document