Modified Adam to Update Control Parameters of Crow Search Algorithm in Transformation Technique Based Dementia MRI Image Classification

2022 ◽  
pp. 121-131
Author(s):  
N. Bharanidharan ◽  
Harikumar Rajaguru
Keyword(s):  
Image Classification ◽  
Search Algorithm ◽  
Control Parameters ◽  
Transformation Technique ◽  
Mri Image

scholarly journals Minimization of Risks of Voltage and Frequency Violations in Islanded Microgrids using Robust Probabilistic Optimal Power Flow

2021 ◽  
Author(s):  
Elton A. Chagas ◽  
Anselmo B. Rodrigues ◽  
Maria G. Silva
Keyword(s):  
Power Flow ◽  
Optimal Power Flow ◽  
Search Algorithm ◽  
Gravitational Search Algorithm ◽  
Computational Cost ◽  
Forecast Errors ◽  
Droop Control ◽  
Control Parameters ◽  
Distributed Generators ◽  
Optimal Power

The main aim of this paper is to propose a robust probabilistic optimal power flow model to determine the droop control parameters for the Distributed Generators (DG) of a islanded microgrid. The term robust is related to the droop control parameters being immune to uncertainties associated with: load forecast errors, DG outages and variability of power output in renewable DG. This optimization problem is solved by an improved gravitational search algorithm (GSA). The test results demonstrated that the proposed method can achieve significant reductions in the load curtailments due to frequency and voltage violations. In addition, a comparison between GSA and the Particle Swarm Optimization (PSO) demonstrated that GSA is more suitable for evaluating the droop control parameters than PSO in relation to the computational cost and the optimal quality of the solution.

scholarly journals Image Classification Based on Automatic Neural Architecture Search Using Binary Crow Search Algorithm

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 189891-189912
Author(s):  
Mobeen Ahmad ◽  
Muhammad Abdullah ◽  
Hyeonjoon Moon ◽  
Seong Joon Yoo ◽  
Dongil Han
Keyword(s):  
Image Classification ◽  
Search Algorithm ◽  
Neural Architecture

Experimental Assessment of Effect of Backlash Control Parameters on Quadrant Protrusions of Circular Tests for CNC Machine Tools

2020 ◽  
Vol 19 (01) ◽  
pp. 65-85
Author(s):  
Chuan-Hsun Hsu ◽  
Chi-Hsiang Wang ◽  
Syh-Shiuh Yeh
Keyword(s):  
Machine Tool ◽  
Feed Rate ◽  
Machine Tools ◽  
Search Algorithm ◽  
Cnc Machine Tools ◽  
Control Parameters ◽  
Cnc Machine ◽  
Circular Test ◽  
Binary Search Algorithm ◽  
The Relationship

Backlash, friction, and servo lag factors often result in protrusion or segment difference phenomenon in the moving speed reversal of a machine tool’s moving table. This phenomenon can be improved by adjusting the backlash control parameters of the machine tool controller, but the control parameters must vary with the feed rate and payload of the moving table. Therefore, this study performed the circular test process for CNC machine tools, and used different feed rate, radius, and payload motion conditions to discuss the effect of backlash control parameters on quadrant protrusions. First, this study used parameter-range reduction combined with the Taguchi method and the binary search algorithm to search for the optimal backlash control parameters in the parameter setting range, so that the machine tool could have preferable quadrant protrusion performance when executing circular tests. Afterward, the correlation of the moving table feed rate, radius, and payload to the quadrant protrusion was analyzed according to the experimental results. The results indicated that the machine tool moving table feed rate had the most apparent effect on quadrant protrusions, and the relationship between the payload and quadrant protrusion was influenced by the moving table feed rate and circular radius simultaneously.

scholarly journals INTERRELATIONSHIP BETWEEN CONTROL PARAMETERS AND TUMOR/BONE CONDITIONS FOR EXTERNAL ULTRASOUND HYPERTHERMIA

2001 ◽  
Vol 13 (04) ◽  
pp. 199-212 ◽  
Author(s):  
CHIHNG-TSUNG LIAUH ◽  
WIN-LI LIN ◽  
YUNG-YAW CHEN ◽  
JIA-YUSH YEN
Keyword(s):  
Tumor Size ◽  
Search Algorithm ◽  
Window Size ◽  
Blood Perfusion ◽  
Control Parameters ◽  
Tumor Depth ◽  
Acoustic Window ◽  
Ultrasound Frequency ◽  
Ultrasound Hyperthermia ◽  
The Relationship

The purpose of this paper is to examine the relationship between the control parameters and the tumor/bone conditions, and also to determine the domain determined by the treatable tumor size and tumor depth for an external ultrasound hyperthermia. This work employs computer simulation programs based on a simplified model of a scanned ultrasound transducer power deposition, the steadystate bio-heat transfer equation, and a search algorithm. The low bounds of SR (specific absorption rate ratio) and f · SR (f : ultrasound frequency) are determined based on the temperature distributions for large ranges of blood perfusion and ultrasound frequencies. These low bounds of SR and f · SR are then used to investigate the relationship between the control parameters and the tumor/bone conditions and to determine the treatable domain. The control parameters considered are the acoustic window size, ultrasound frequency; and the tumor/bone conditions are tumor size, tumor depth, and the depth of post-target bone. Simulation results demonstrate that a) the low bounds of SR and f · SR are functions of blood perfusion; b) the ultrasound frequency to obtain the largest treatable tumor size depends on the tumor depth and the depth of post-target bone, however it is independent of the acoustic window size; and c) the treatable domain is proportional to the acoustic window size and the depth of post-target bone, and a proper frequency can result in a larger treatable domain. The results of this study can be a guideline for designing an optimal ultrasound heating system, arranging the transducers, and implementing further treatment planning for the external ultrasound hyperthermia.

scholarly journals Composite Differential Search Algorithm

2014 ◽  
Vol 2014 ◽  
pp. 1-15 ◽  
Author(s):  
Bo Liu
Keyword(s):  
Convergence Rate ◽  
Optimization Problem ◽  
Search Algorithm ◽  
Search Algorithms ◽  
Control Parameters ◽  
Original Algorithm ◽  
New Space ◽  
Random Method ◽  
Better Than

Differential search algorithm (DS) is a relatively new evolutionary algorithm inspired by the Brownian-like random-walk movement which is used by an organism to migrate. It has been verified to be more effective than ABC, JDE, JADE, SADE, EPSDE, GSA, PSO2011, and CMA-ES. In this paper, we propose four improved solution search algorithms, namely “DS/rand/1,” “DS/rand/2,” “DS/current to rand/1,” and “DS/current to rand/2” to search the new space and enhance the convergence rate for the global optimization problem. In order to verify the performance of different solution search methods, 23 benchmark functions are employed. Experimental results indicate that the proposed algorithm performs better than, or at least comparable to, the original algorithm when considering the quality of the solution obtained. However, these schemes cannot still achieve the best solution for all functions. In order to further enhance the convergence rate and the diversity of the algorithm, a composite differential search algorithm (CDS) is proposed in this paper. This new algorithm combines three new proposed search schemes including “DS/rand/1,” “DS/rand/2,” and “DS/current to rand/1” with three control parameters using a random method to generate the offspring. Experiment results show that CDS has a faster convergence rate and better search ability based on the 23 benchmark functions.

scholarly journals DenseNet-Based Classification of MRI Images for Detecting the Difference before and after Treating Liver Cancer

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Jianbo Peng
Keyword(s):  
Side Effects ◽  
Liver Cancer ◽  
Image Classification ◽  
Clinical Application ◽  
Tumor Volume ◽  
Saline Group ◽  
Classification Algorithm ◽  
The Body ◽  
Raw Material ◽  
Mri Image

This study aimed to explore the evaluation of Adriamycin-loaded microspheres in the treatment of liver cancer under DenseNet-based magnetic resonance imaging (MRI) image classification algorithm. According to different treatment methods, the research objects were classified into a normal saline (saline) group, a doxorubicin raw material (DOX) group, and a chitosan cross-linked pectin-doxorubicin conjugate macromolecular (CS-PDC-M) group. DenseNet’s migration learning was employed to analyze the dynamic enhanced MRI characteristics and classify the MRI images. The CS-PDC-M-targeted nanotransfer system was examined with its apparent morphology, drug absorption, and cytotoxicity. Tumor volume was monitored using MRI, and alanine aminotransferase (ALT) and creatine kinase isoenzyme (CK-MB) values were detected. Results showed that the classification accuracy of liver cancer MRI image based on DenseNet model reached 80% at the arterial hepatobiliary stage. The DOX and CS-PDC-M group had obviously smaller tumor volume than that of the saline group P < 0.05 with a statistical meaning. The mortality in the DOX group was 30%, while there was no death in the saline and CS-PDC-M groups. Compared with the saline and CS-PDC-M groups, ALT and CK-MB from the DOX group increased substantially P < 0.05 . Therefore, DOX had an inhibitory effect on tumor but damaged the heart and liver. DOX was used to construct CS-PDC-M that could maintain the original treatment effect of DOX and inhibit its side effects on the body, so CS-PDC-M had a clinical application value. In conclusion, Adriamycin-loaded microspheres could not only maintain the original therapeutic effect of Adriamycin but also inhibit its toxic and side effects on the body. The  DenseNet model was applied in the liver cancer MRI dynamic image classification algorithm, and the normalization algorithm could improve the accuracy of the liver cancer microvessel classification, thus promoting the diagnostic efficiency of liver cancer diagnosis, which had clinical application value.

Sign in / Sign up

Export Citation Format

Share Document