scholarly journals Palm print recognition based on harmony search algorithm

2021 ◽  
Vol 11 (5) ◽  
pp. 4113
Author(s):  
Raniah Ali Mustafa ◽  
Haitham Salman Chyad ◽  
Rafid Aedan Haleot
Keyword(s):  
Hong Kong ◽  
Gaussian Distribution ◽  
Search Algorithm ◽  
Harmony Search ◽  
Region Of Interest ◽  
Recognition System ◽  
Harmony Search Algorithm ◽  
Identification Methods ◽  
Palm Print ◽  
College Of Engineering

Due to its stabilized and distinctive properties, the palmprint is considered a physiological biometric. Recently, palm print recognition has become one of the foremost desired identification methods. This manuscript presents a new recognition palm print scheme based on a harmony search algorithm by computing the Gaussian distribution. The first step in this scheme is preprocessing, which comprises the segmentation, according to the characteristics of the geometric shape of palmprint, the region of interest (ROI) of palmprint was cut off. After the processing of the ROI image is taken as input related to the harmony search algorithm for extracting the features of the palmprint images through using many parameters for the harmony search algorithm, Finally, Gaussian distribution has been used for computing distance between features for region palm print images, in order to recognize the palm print images for persons by training and testing a set of images, The scheme which has been proposed using palmprint databases, was provided by College of Engineering Pune (COEP), the Hong Kong Polytechnic University (HKPU), Experimental results have shown the effectiveness of the suggested recognition system for palm print with regards to the rate of recognition that reached approximately 92.60%.

scholarly journals Design of CAD System of Solitary Pulmonary Nodule with Harmony Classification and Fuzzy System

2017 ◽  
Vol 1 (4) ◽  
pp. 102-102
Author(s):  
Maryam Sadat Mahmoodi ◽  
Seyed Abbas Mahmoodi
Keyword(s):  
Lung Cancer ◽  
Fuzzy System ◽  
Search Algorithm ◽  
Harmony Search ◽  
Lung Nodule ◽  
Region Of Interest ◽  
Harmony Search Algorithm ◽  
Cad System ◽  
Nodule Detection ◽  
Base Method

Introduction: Lung cancer is the most wide spread from of cancer, with the highest mortality rate worldwide. In this study, a computer-aided detection (CAD) system was developed for lung nodule detection, segmentation and recognition using CT images. So, we use a highly accurate supervised that uses lung images with the aim of assisting physicians in early detection of lung cancer. Methods: First, we segmented the lung area by masking techniques to isolated nodules and determined region of interest. Then, 24 features were extracted from images that included morphological, statistical and histogram. Important features  were derived from the images for their posterior analysis with the aid of a harmony search algorithm and fuzzy systems. Results: In order to evaluate the performance of the proposed method, we used the LIDC database. the number of images included a database of  97 images whom 47 were diagnosed with lung cancer. Results of the base method show a sensitivity of 93%. Conclusion: The harmony search algorithm is optimized using fuzzy system for classification. The CAD system provides 93.1%  accuracy.

scholarly journals Hyperparameter Optimization Method Based on Harmony Search Algorithm to Improve Performance of 1D CNN Human Respiration Pattern Recognition System

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3697 ◽  
Author(s):  
Seong-Hoon Kim ◽  
Zong Woo Geem ◽  
Gi-Tae Han
Keyword(s):  
Pattern Recognition ◽  
Search Algorithm ◽  
Harmony Search ◽  
Recognition Rate ◽  
Recognition System ◽  
Harmony Search Algorithm ◽  
Optimal Combination ◽  
Dense Layer ◽  
Human Respiration ◽  
Respiration Pattern

In this study, we propose a method to find an optimal combination of hyperparameters to improve the accuracy of respiration pattern recognition in a 1D (Dimensional) convolutional neural network (CNN). The proposed method is designed to integrate with a 1D CNN using the harmony search algorithm. In an experiment, we used the depth of the convolutional layer of the 1D CNN, the number and size of kernels in each layer, and the number of neurons in the dense layer as hyperparameters for optimization. The experimental results demonstrate that the proposed method provided a recognition rate for five respiration patterns of approximately 96.7% on average, which is an approximately 2.8% improvement over an existing method. In addition, the number of iterations required to derive the optimal combination of hyperparameters was 2,000,000 in the previous study. In contrast, the proposed method required only 3652 iterations.

Optimal linear cooperation spectrum sensing method based on chaos harmony search algorithm

2013 ◽  
Vol 32 (9) ◽  
pp. 2412-2417
Author(s):  
Yue-hong LI ◽  
Pin WAN ◽  
Yong-hua WANG ◽  
Jian YANG ◽  
Qin DENG
Keyword(s):  
Spectrum Sensing ◽  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm ◽  
Optimal Linear

Performance Study of Harmony Search Algorithm for Multilevel Thresholding

2016 ◽  
Vol 25 (4) ◽  
pp. 473-513 ◽  
Author(s):  
Salima Ouadfel ◽  
Abdelmalik Taleb-Ahmed
Keyword(s):  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm ◽  
Computational Time ◽  
Multilevel Thresholding ◽  
Performance Study ◽  
Bacterial Foraging Optimization ◽  
Bee Colony ◽  
Fitness Value ◽  
Multiple Thresholds

AbstractThresholding is the easiest method for image segmentation. Bi-level thresholding is used to create binary images, while multilevel thresholding determines multiple thresholds, which divide the pixels into multiple regions. Most of the bi-level thresholding methods are easily extendable to multilevel thresholding. However, the computational time will increase with the increase in the number of thresholds. To solve this problem, many researchers have used different bio-inspired metaheuristics to handle the multilevel thresholding problem. In this paper, optimal thresholds for multilevel thresholding in an image are selected by maximizing three criteria: Between-class variance, Kapur and Tsallis entropy using harmony search (HS) algorithm. The HS algorithm is an evolutionary algorithm inspired from the individual improvisation process of the musicians in order to get a better harmony in jazz music. The proposed algorithm has been tested on a standard set of images from the Berkeley Segmentation Dataset. The results are then compared with that of genetic algorithm (GA), particle swarm optimization (PSO), bacterial foraging optimization (BFO), and artificial bee colony algorithm (ABC). Results have been analyzed both qualitatively and quantitatively using the fitness value and the two popular performance measures: SSIM and FSIM indices. Experimental results have validated the efficiency of the HS algorithm and its robustness against GA, PSO, and BFO algorithms. Comparison with the well-known metaheuristic ABC algorithm indicates the equal performance for all images when the number of thresholds M is equal to two, three, four, and five. Furthermore, ABC has shown to be the most stable when the dimension of the problem is too high.

Sign in / Sign up

Export Citation Format

Share Document