scholarly journals Research on Segmentation Experience of Music Signal Improved Based on Maximization of Negative Entropy

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Qin Yao ◽  
Zhencong Li ◽  
Wanzhi Ma
Keyword(s):  
Objective Function ◽  
Automatic Segmentation ◽  
Separation Performance ◽  
Initial Value ◽  
Entropy Maximization ◽  
Negative Entropy ◽  
Music Signal ◽  
Number Of Iterations ◽  
Iteration Time ◽  
Improved Algorithm

With the rapid growth of digital music today, due to the complexity of the music itself, the ambiguity of the definition of music category, and the limited understanding of the characteristics of human auditory perception, the research on topics related to automatic segmentation of music is still in its infancy, while automatic music is still in its infancy. Segmentation is a prerequisite for fast and effective retrieval of music resources, and its potential application needs are huge. Therefore, topics related to automatic music segmentation have important research value. This paper studies an improved algorithm based on negative entropy maximization for well-posed speech and music separation. Aiming at the problem that the separation performance of the negative entropy maximization method depends on the selection of the initial matrix, the Newton downhill method is used instead of the Newton iteration method as the optimization algorithm to find the optimal matrix. By changing the descending factor, the objective function shows a downward trend, and the dependence of the algorithm on the initial value is reduced. The simulation experimental results show that the algorithm can separate the source signal well under different initial values. The average iteration time of the improved algorithm is reduced by 26.2%, the number of iterations is reduced by 69.4%, and the iteration time and the number of iterations are both small. Fluctuations within the range better solve the problem of sensitivity to the initial value. Experiments have proved that the new objective function can significantly improve the separation performance of neural networks. Compared with the existing music separation methods, the method in this paper shows excellent performance in both accompaniment and singing in separated music.

scholarly journals An Iteration-Time Combination Method to Reduce the Dynamic Degradation of Digital Chaotic Maps

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Yao Wu ◽  
Lingfeng Liu
Keyword(s):  
Chaotic Maps ◽  
Control Function ◽  
Chaotic Map ◽  
Combination Method ◽  
Control Parameters ◽  
Improved Method ◽  
Dynamical Degradation ◽  
Dynamic Degradation ◽  
Number Of Iterations ◽  
Iteration Time

A new and improved method based on the number of iterations is proposed to reduce the dynamical degradation of the digital chaotic map in this study. We construct a control function by introducing iteration time instead of external systems, thereby replacing the control parameters in the original chaotic map. Experimental results show that the chaotic map based on the iteration-time combination method is more complicated and effective. The period is extended without completely destroying the phase space, which indicates that our method is effective and can compete with other proposed techniques. A type of pseudorandom bit generator based on the iteration-time combination method is proposed to demonstrate its simple application.

scholarly journals Music Signal Separation Using Supervised Robust Non-Negative Matrix Factorization with β-divergence

2021 ◽  
Vol 15 ◽  
pp. 149-154
Author(s):  
Feng Li ◽  
Hao Chang
Keyword(s):  
Prior Knowledge ◽  
Matrix Factorization ◽  
Signal Separation ◽  
Separation Performance ◽  
Effective Strategy ◽  
Music Signal ◽  
Training Sequences ◽  
Conventional Methods ◽  
Music Signals ◽  
Non Negative Matrix Factorization

We propose a supervised method based on robust non-negative matrix factorization (RNMF) for music signal separation with β-divergence called supervised robust non-negative matrix factorization (SRNMF). Although RNMF method is an effective method for separating music signals, its separation performance degrades due to has no prior knowledge. To address this problem, in this paper, we develop SRNMF that unifying the robustness of RNMF and the prior knowledge to improve such separation performance on instrumental sound signals (e.g., piano, oboe and trombone). Application to the observed instrumental sound signals is an effective strategy by extracting the spectral bases of training sequences by using RNMF. In addition, β-divergence based on SRNMF be extended. The results obtained from our experiments on instrumental sound signals are promising for music signal separation. The proposed method achieves better separation performance than the conventional methods.

scholarly journals ON TACTICS OF DEVELOPING ARCHITECTURE OF THE GENERALIZED ALGORITHM OF ENERGY-ORIENTED POWER CONSUMPTION CONTROL AT IRON ORE UNDERGROUND MINING COMPANIES

2021 ◽  
Vol 1 (53) ◽  
pp. 51-63
Author(s):  
I. Sinchuk ◽  
◽  
A. Kupin ◽  
V. Baranovskyi ◽  
Keyword(s):  
Power Consumption ◽  
Objective Function ◽  
Iron Ore ◽  
Underground Mining ◽  
Time Of Day ◽  
Total Power ◽  
Positive Trend ◽  
Technological Parameters ◽  
Consumption Control ◽  
Number Of Iterations

Purpose. The article substantiates and confirms the thesis about the need for energy-oriented power consumption control levels in power complexes: the system of power supply at iron ore underground mining enterprises on the basis of experiment data analysis. Methodology. It is estimated that along with the current positive trend suitable for developing architecture of power consumption control levels when a limited number of energy-intensive enterprises consume about 80 % of the total power produced, their functioning modes in day hours vary. Analysis of varied realtime modes of power consumption in hours indicates absence of enterprises’ control over this process. Results. The suggested methods enable forecasting efficiency of power consumption control in hours in any variant of time-of-day tariff integration. In non-standard and changeable conditions of technological parameters in mining production, on the basis of the results of stochastic optimization analysis, it is proven that even when applying a small number of iterations N = 10, it is possible to improve the initial solution by over 60 % (the initial value of the objective function is I* = 27.7 and the final value on the last iteration is I* = 10.7). There are determined required vectors to specify a connection of the time-of-day tariff of ore mining (Р*) and the corresponding power consumption (Е*) which corresponds to the suboptimal value of the objective function (I*). The obtained results can be applied to developing recommendations for a more efficient planning of an enterprise’s performance. Practical value. The suggested algorithm implemented in power consumption control systems enables receiving a final result with any quality required for the level. If the quality of the obtained results needs improving, the number of iterations is to be increased by two or three orders of magnitude.

scholarly journals Penerapan Algoritma Kunang-Kunang pada Open Vehicle Routing Problem (OVRP)

2019 ◽  
Vol 1 (1) ◽  
pp. 46
Author(s):  
Ihda Septiyafi ◽  
Herry Suprajitno ◽  
Asri Bekti Pratiwi
Keyword(s):  
Objective Function ◽  
Vehicle Routing ◽  
Vehicle Routing Problem ◽  
Firefly Algorithm ◽  
Initial Population ◽  
Small Data ◽  
Routing Problem ◽  
Open Vehicle Routing Problem ◽  
Number Of Iterations ◽  
Open Vehicle Routing

This paper aims to solve Open Vehicle Routing Problem using Firefly Algorithm. Open Vehicle Routing Problem (OVRP) is a variant of Vehicle Routing Problem (VRP)  where vehicles used to serve customers do not return to the depot after serving the last customer on each route. The steps of the Firefly Algorithm to handle OVRP are data input and initialization parameters, generating the initial population for each firefly, sorting population sources, calculating the value of the objective function and light intensity, comparing the intensity of light, performing movement, setting the best fireflies as g-best, doing random movement in the best fireflies as long as the maximum number of iterations has not been met. The program used to complete OVRP using the Firefly Algorithm is Borland C ++ and implemented in 3 case examples, namely small data with 18 customers, moderate data with 50 customers, and large data with 100 customers with the best total mileage of 211, 344 , 970.62, and 2531.83. The results obtained from the program output indicate that the more the number of iterations and the number of fireflies, then the results of the objective function (total mileage) obtained tend to be better so that these parameters affect the value of the objective function. While the absorption coefficient value (g) does not give effect to the value of the objective function.

scholarly journals Single-Valued Neutrosophic Clustering Algorithm Based on Tsallis Entropy Maximization

Axioms ◽  
2018 ◽  
Vol 7 (3) ◽  
pp. 57 ◽  
Author(s):  
Qiaoyan Li ◽  
Yingcang Ma ◽  
Florentin Smarandache ◽  
Shuangwu Zhu
Keyword(s):  
Objective Function ◽  
Data Clustering ◽  
Clustering Algorithm ◽  
Real Life ◽  
Neutrosophic Set ◽  
Entropy Maximization ◽  
Fuzzy C Means ◽  
Promising Tool ◽  
Life Problems ◽  
Benchmark Datasets

Data clustering is an important field in pattern recognition and machine learning. Fuzzy c-means is considered as a useful tool in data clustering. The neutrosophic set, which is an extension of the fuzzy set, has received extensive attention in solving many real-life problems of inaccuracy, incompleteness, inconsistency and uncertainty. In this paper, we propose a new clustering algorithm, the single-valued neutrosophic clustering algorithm, which is inspired by fuzzy c-means, picture fuzzy clustering and the single-valued neutrosophic set. A novel suitable objective function, which is depicted as a constrained minimization problem based on a single-valued neutrosophic set, is built, and the Lagrange multiplier method is used to solve the objective function. We do several experiments with some benchmark datasets, and we also apply the method to image segmentation using the Lena image. The experimental results show that the given algorithm can be considered as a promising tool for data clustering and image processing.

Modeling of Planar Flexible Link Manipulators: Parameter Identification Using Genetic Algorithm

2000 ◽  
Author(s):  
S. M. Megahed ◽  
K. T. Hamza
Keyword(s):  
Experimental Data ◽  
Genetic Algorithm ◽  
Objective Function ◽  
Natural Frequencies ◽  
Model Parameters ◽  
Flexible Link ◽  
Algorithm Optimization ◽  
Initial Value ◽  
Experimental Procedure ◽  
Experimental Response

Abstract In this paper, a model for simulation of planar flexible link manipulators is presented. Identification of the model parameters is done based on experimental results obtained from separate experiments performed on every link in the manipulator. A simple experimental procedure is used to determine the first three natural frequencies and damping ratios corresponding to them. The experimental data provides guidance in selecting an appropriate number of elements per link for modeling, mass and stiffness parameters and an initial value of damping parameters. Further enhancement of the model is performed through Genetic Algorithm optimization of the damping parameters with the objective function to be minimized defined as the sum of squares of errors between the experimental response and the simulated one. After optimization, the simulated response and the experimental one are closely matching.

scholarly journals Research on Multi-Alternatives Problem of Finite Element Model Updating Based on IAFSA and Kriging Model

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4274 ◽  
Author(s):  
Juntao Kang ◽  
Xueqiang Zhang ◽  
Hongyou Cao ◽  
Shiqiang Qin
Keyword(s):  
Finite Element ◽  
Finite Element Model ◽  
Objective Function ◽  
Model Updating ◽  
Optimal Solution ◽  
Element Model ◽  
Kriging Model ◽  
Finite Element Model Updating ◽  
Global Optimal ◽  
Improved Algorithm

Due to insufficient test data, insufficient constraint equations and uncertain objective function, the local optimal solution and the global optimal solution of the objective function in finite element model updating may represent the actual parameters of the structure. Based on this, this paper proposes an improved artificial fish school algorithm. By combining the niche technology with the artificial fish school algorithm, the improved algorithm can systematically find multiple global optimal solutions and local optimal solutions of the objective function. Aiming at the difficulty of determining the niche radius, an adaptive niche radius mechanism is proposed. The improved algorithm is used to study the multi-alternatives problem of finite element model updating after verifying its feasibility through numerical simulation analysis. In the case of benchmark framework model updating, it is confirmed that multi-alternative problems exist and the global optimal solution of the objective function does not necessarily represent the true parameters of the structure. In case 2, the improved algorithm combined with the Kriging model is applied to the model updating of a cable-stayed footbridge, and 15 sets of solutions are obtained, in which the error objective function values of the measured and theoretical values of the bridge modes are close but the solutions are completely different. Combining with the actual bridge condition and reanalysis technology, the author takes the suboptimal solution 2 as the most representative solution of the bridge parameters, which reduces the possibility of misjudgment of structural parameters.

A New Method Based on Interation Algorithm to Extract Parameters of Constitutive Equations

2013 ◽  
Vol 281 ◽  
pp. 505-510
Author(s):  
Yong Zhi Hua ◽  
Li Wen Guan ◽  
Xin Jun Liu ◽  
Yu Hui Zhang
Keyword(s):  
Evolutionary Algorithms ◽  
Convergence Rate ◽  
Objective Function ◽  
Constitutive Equations ◽  
Orthogonal Cutting ◽  
New Method ◽  
Iteration Algorithm ◽  
Experiment Data ◽  
Initial Value ◽  
Gradient Based

These methods that extract parameters of constitutive equations can be divided into three groups: direct search-based strategies, gradient-based methods and evolutionary algorithms. By analyzing these strategies, a new method based on iteration algorithm was proposed. To obtain parameters of JC and ZA model for Ti-6Al-4V, the error between prediction data and SHPB experiment data was set as objective function, then initial value was calculated using iteration algorithm. The effect of convergence rate and precision at various steps and experiment data was invested. The main advantage of the method are as follows：fast calculation; compatible with SHPB data and orthogonal cutting data; compatible with the decoupling and coupling constitutive equations. Finally, it has shown that the algorithm is stable, and acceptable results can be obtained.

scholarly journals A Sparsity Preestimated Adaptive Matching Pursuit Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Xinhe Zhang ◽  
Yufeng Liu ◽  
Xin Wang
Keyword(s):  
Compressed Sensing ◽  
Matching Pursuit ◽  
Reconstruction Algorithm ◽  
Initial Value ◽  
Step Size ◽  
Matching Pursuit Algorithm ◽  
Run Speed ◽  
Number Of Iterations

In the matching pursuit algorithm of compressed sensing, the traditional reconstruction algorithm needs to know the signal sparsity. The sparsity adaptive matching pursuit (SAMP) algorithm can adaptively approach the signal sparsity when the sparsity is unknown. However, the SAMP algorithm starts from zero and iterates several times with a fixed step size to approximate the true sparsity, which increases the runtime. To increase the run speed, a sparsity preestimated adaptive matching pursuit (SPAMP) algorithm is proposed in this paper. Firstly, the sparsity preestimated strategy is used to estimate the sparsity, and then the signal is reconstructed by the SAMP algorithm with the preestimated sparsity as the iterative initial value. The method reconstructs the signal from the preestimated sparsity, which reduces the number of iterations and greatly speeds up the run efficiency.

Classification of Ship’ Magnetic Field and Feature Selection Based on the Improved Weighted Fuzzy Clustering Algorithm

2013 ◽  
Vol 401-403 ◽  
pp. 1353-1357
Author(s):  
Wu Di Wen ◽  
Zhong Le Liu ◽  
Zhi Qiang Zhang
Keyword(s):  
Magnetic Field ◽  
Feature Selection ◽  
Objective Function ◽  
Fuzzy Clustering ◽  
Field Data ◽  
Clustering Algorithm ◽  
Magnetic Field Data ◽  
Fuzzy Clustering Algorithm ◽  
Improved Algorithm

Magnetic field data of ship has three-component,and traditional weighted fuzzy clustering algorithm(FCA) can’t deal with the three-component data. We improve the traditional FCA by changing the objective function and added weights calculation of three-component of magnetic field in the function.Give the equation to compute the weights of three-component.Put forward new steps for improved algorithm.Use ships’ data to test the improved algorithm and giving the conclusion.

Sign in / Sign up

Export Citation Format

Share Document