A Clustering-Based Approach for Features Extraction in Spectro-Temporal Domain Using Artificial Neural Network

Esfandian, Nafiseh; Hosseinpour, K.

doi:10.5829/ije.2021.34.02b.17

Cited by 3 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering was based on similarity in only the critical properties of the data. As the results of implementation on three data sets from R package (Esoph, Diabetes, and KosteckiDillon) revealed, the cluster-based approach [20] is more competent than the other detection method. Furthermore, the results indicate that the F-score and likelihood values do not change with random data object removals.…”

Section: Related Workmentioning

confidence: 99%

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Mohseni¹,

Nematzadeh²,

Akbarib³

et al. 2023

IJE

View full text Add to dashboard Cite

Outlier detection is a technique to identify and remove significantly different data from the more correct and consistent data in a data set. Outlier data can have negative impact on classification and clustering performance; that should be identified and removed to improve the classification efficiency. Regardless of whether a classifying technique classifies an outlier correctly, the very notion of identifying a data as outlier is of great significance. In this paper, a new approach is proposed for outlier data detection within a test data set along with unsupervised training set selection. The selected training set is used for two-step classification. After unsupervised clustering the training set, the closest cluster to a test sample is selected using the Euclidean distance measure. Then, the outlier in the test sample is identified with the concepts of standard deviation and mean value. The results showed by evaluating the distance of each sample of the test set with the new selected data set. the accuracy of the classifiers is enhanced after detection and elimination of outlier data.

show abstract

Section: Related Workmentioning

confidence: 99%

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Mohseni¹,

Nematzadeh²,

Akbarib³

et al. 2023

IJE

View full text Add to dashboard Cite

show abstract

“…Furthermore, for the plucking position of a fruit picking robot, a visual positioning method was proposed by Lei and Lu [11]. Besides, attention model [12], Artificial Neural Network [13,14], Kalman Filter [14],Genetic Algorithm [15], Ant Colony Algorithm *Corresponding Author Institutional Email: liukaidiligent@gmail.com (Kai liu) [16,17], R-CNN [18], GAN model [19], Greedy Algorithm [20], Synovium Control [21], Deep Learning [22,23] and Lightweight deep learning methods [24,25] are also used in object perception and control.…”

Section: Introductionmentioning

confidence: 99%

Bionic Perception Method of Navel Orange Plucking Position Based on Fmincon and PD Angle Control

Liu

Lai

2022

IJE

View full text Add to dashboard Cite

In this paper, a bionic perception method of navel orange plucking position based on Fmincon and Proportional Differential (PD) angle control is proposed to solve the problems of wind disturbance and green branches in dynamic unstructured environment. Different from these algorithms that limited to two-dimensional images, this method realizes picking position perception in three-dimensional. Meanwhile, the perception method and the picking robot control algorithm are achieved simultaneously. Firstly, an optimal solution model of the global target rotation angle of the control system based on Fmincon is established to solve the angle optimization problem of robot target approach motion. Secondly, a bionic perception system of plucking position based on PD angle control is constructed to solve specific perception problems. Finally, a joint simulation platform for picking robots based on Solidworks, Adams, and Simulink is given; the validity and accuracy of the algorithm were verified. The experimental results show that the picking accuracy rate is 95%, the angle error of each mechanism and the displacement error are less than 0.5 degrees and 10mm, respectively. The total time from the optimized angle calculation to the system's stability is only about 0.33s. This method is suitable for the rapid perception of plucking position and active angle control of picking robots under dynamic unstructured environment.

show abstract

“…Recently, clustering-based methods are used for feature extraction [19,20]. A supervised method named PSBS has been proposed based on k-means clustering of bands for band selection of HIs [21].…”

Section: Introductionmentioning

confidence: 99%

Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

Beirami

Mokhtarzade

2021

IJE

View full text Add to dashboard Cite

Nowadays, hyperspectral images (HIs) are widely used for land cover land use (LCLU) mapping. Hyperspectral sensors collect spectral data in numerous adjacent spectral bands, which are usually redundant. Hyperspectral data processing comes with important challenges such as huge processing time, difficulties in transfer, and storage. In this study, two supervised and unsupervised dimensionality reduction methods are proposed for hyperspectral feature extraction based on the band clustering technique. In the first method, the unsupervised method, after the unsupervised band clustering stage with some statistical attributes, the principal component transform is used in each cluster, and the first PC component is considered an extracted feature. In the second method, the supervised method, bands are clustered based on training samples mean vectors of each class, and the weighted mean operator is used for feature extraction in each cluster. The experiment is conducted on the classification of real famous HI named Indian Pines. Comparing the obtained results and some other state of art methods proved the proposed method's efficiency.

show abstract

A Clustering-Based Approach for Features Extraction in Spectro-Temporal Domain Using Artificial Neural Network

Cited by 3 publications

References 25 publications

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Bionic Perception Method of Navel Orange Plucking Position Based on Fmincon and PD Angle Control

Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

Contact Info

Product

Resources

About