scholarly journals Classification of Objects by Shape Applied to Amber Gemstone Classification

2021 ◽  
Vol 11 (3) ◽  
pp. 1024
Author(s):  
Armantas Ostreika ◽  
Marius Pivoras ◽  
Alfonsas Misevičius ◽  
Tomas Skersys ◽  
Linas Paulauskas
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Feedforward Neural Network ◽  
Classification Algorithms ◽  
Machine Learning Classification ◽  
Parametric Description ◽  
Real Time Applications ◽  
Time Required ◽  
Computational Resources

To properly and quickly evaluate an object’s shape, in a manner that is suitable for real-time applications, a set of parameters has been created and the shape parametric description (SPD) has been elaborated. This solution is focused on the classification of amber gemstones according to shape. To improve the results obtained by SPD, the most popular machine learning classification algorithms were applied and tested. The proposed method (i.e., SPD) achieved the fastest classification, requiring the least computational resources, while providing an accuracy of approximately 80%. The best results were achieved when the SPD parameters were used in a feedforward neural network (FFNN), and an accuracy of 91.5% was obtained, while the time required for the computations remained in a range that is acceptable for real-time applications.

scholarly journals Machine learning classification of new asteroid families members

2020 ◽  
Author(s):  
Valerio Carruba
Keyword(s):  
Machine Learning ◽  
Family Members ◽  
Classification Algorithms ◽  
New Members ◽  
Machine Learning Classification ◽  
New Family ◽  
Robotic Telescope ◽  
Traditional Approaches ◽  
Asteroid Families

<p>Asteroid families are groups of asteroids that are the product of collisions or of the rotational fission of a parent object.  These groups are mainly identified in proper elements or frequencies domains.   Because of robotic telescope surveys, the number of known asteroids has increased from about 10,000 in the early 90's to more than 750,000 nowadays. Traditional approaches for identifying new members of asteroid families, like the hierarchical clustering method (HCM), may   struggle to keep up with the growing rate of new discoveries. Here we used machine learning classification algorithms to identify new family members based on the orbital distribution in proper (a,e,sin(i)) of previously known family constituents. We compared the outcome of nine classification algorithms from stand alone and ensemble approaches.  The Extremely Randomized Trees (ExtraTree) method had the highest precision, enabling to  retrieve up to 97% of family members identified with standard HCM.</p>

scholarly journals Research on Sentiment Classification Algorithms on Online Review

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Ruixia Yan ◽  
Zhijie Xia ◽  
Yanxi Xie ◽  
Xiaoli Wang ◽  
Zukang Song
Keyword(s):  
Neural Network ◽  
Sentiment Classification ◽  
Online Review ◽  
Support Vector ◽  
Classification Algorithms ◽  
Evaluation Indexes ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Reinforcement Learning Models

The product online review text contains a large number of opinions and emotions. In order to identify the public’s emotional and tendentious information, we present reinforcement learning models in which sentiment classification algorithms of product online review corpus are discussed in this paper. In order to explore the classification effect of different sentiment classification algorithms, we conducted a research on Naive Bayesian algorithm, support vector machine algorithm, and neural network algorithm and carried out some comparison using a concrete example. The evaluation indexes and the three algorithms are compared in different lengths of sentence and word vector dimensions. The results present that neural network algorithm is effective in the sentiment classification of product online review corpus.

scholarly journals Real-time Neural Networks Implementation Proposal for Microcontrollers

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1597
Author(s):  
Caio José B. V. Guimarães ◽  
Marcelo A. C. Fernandes
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Intelligent Systems ◽  
Implementation Strategy ◽  
Processing Time ◽  
Mean Squared Error ◽  
Low Cost ◽  
Real Time Applications ◽  
Time Required ◽  
Process Classification

The adoption of intelligent systems with Artificial Neural Networks (ANNs) embedded in hardware for real-time applications currently faces a growing demand in fields such as the Internet of Things (IoT) and Machine to Machine (M2M). However, the application of ANNs in this type of system poses a significant challenge due to the high computational power required to process its basic operations. This paper aims to show an implementation strategy of a Multilayer Perceptron (MLP)-type neural network, in a microcontroller (a low-cost, low-power platform). A modular matrix-based MLP with the full classification process was implemented as was the backpropagation training in the microcontroller. The testing and validation were performed through Hardware-In-the-Loop (HIL) of the Mean Squared Error (MSE) of the training process, classification results, and the processing time of each implementation module. The results revealed a linear relationship between the values of the hyperparameters and the processing time required for classification, also the processing time concurs with the required time for many applications in the fields mentioned above. These findings show that this implementation strategy and this platform can be applied successfully in real-time applications that require the capabilities of ANNs.

Implementation of Frequency-Based Classification of Damages in Composites Using Real-Time FPGA-Based Hardware Framework

2017 ◽  
Author(s):  
Adauto P. A. Cunha ◽  
Sebastian F. Wirtz ◽  
Dirk Söffker ◽  
Nejra Beganovic
Keyword(s):  
Signal Processing ◽  
Real Time ◽  
Time Signal ◽  
Discrete Wavelet ◽  
Ae Signal ◽  
Technical Systems ◽  
Time Required ◽  
Guaranteed Service ◽  
System Variables

Structural Health Monitoring (SHM) systems become an integral part of most technical systems in recent years. An integration of SHM in technical systems is closely related to: i) providing the guaranteed service lifetime of a system, ii) scheduled/planned maintenance actions, and iii) optimized system operation. For these purposes, different system variables can be monitored and utilized for an estimation of aging level of the system. Monitored system variables are therefore correlated to stochastically occurring damage, indirectly also to Remaining Useful Lifetime (RUL). Among challenges related to SHM, high attention is given to the reduction of a large amount of measured data and its real-time signal processing. In this contribution, classification of damages in composite materials using measurements of Acoustic Emission (AE) is proposed. Here, Discrete Wavelet Transform (DWT) is applied to AE signal to identify different damages in composites. As AE-signal is found in high frequency bandwidth, the amount of data captured in a short time period is enormous. Consequently, the calculation of DWT of such signal requires processing time quite far from real time and delays the entire classification procedure. Due to this, real-time implementation of DWT is proposed to cope with huge amount of captured data in this case and to reduce the time required for signal processing. Using FPGA-based system, real-time implementation of DWT is shown. Obtained results are compared with the results of offline DWT calculation to prove the efficiency and accuracy of real-time implementation.

scholarly journals Deep learning model for metagenome fragment classification using spaced k-mers feature extraction

2020 ◽  
Vol 8 (3) ◽  
pp. 234-238
Author(s):  
Nur Choiriyati ◽  
Yandra Arkeman ◽  
Wisnu Ananta Kusuma
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Language Processing ◽  
Computational Time ◽  
Genus Level ◽  
Computational Resources ◽  
Learning Architectures ◽  
Deep Learning Model

An open challenge in bioinformatics is the analysis of the sequenced metagenomes from the various environments. Several studies demonstrated bacteria classification at the genus level using k-mers as feature extraction where the highest value of k gives better accuracy but it is costly in terms of computational resources and computational time. Spaced k-mers method was used to extract the feature of the sequence using 111 1111 10001 where 1 was a match and 0 was the condition that could be a match or did not match. Currently, deep learning provides the best solutions to many problems in image recognition, speech recognition, and natural language processing. In this research, two different deep learning architectures, namely Deep Neural Network (DNN) and Convolutional Neural Network (CNN), trained to approach the taxonomic classification of metagenome data and spaced k-mers method for feature extraction. The result showed the DNN classifier reached 90.89 % and the CNN classifier reached 88.89 % accuracy at the genus level taxonomy.

Modified single-output Chebyshev-polynomial feedforward neural network aided with subset method for classification of breast cancer

2019 ◽  
Vol 350 ◽  
pp. 128-135 ◽  
Author(s):  
Long Jin ◽  
Zhiguan Huang ◽  
Liangming Chen ◽  
Mei Liu ◽  
Yuhe Li ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Chebyshev Polynomial ◽  
Feedforward Neural Network ◽  
Single Output
Sign in / Sign up

Export Citation Format

Share Document