Search

The Beluga Whale Optimization (BWO) algorithm is a meta-heuristic optimization algorithm proposed to simulate the life behavior of the beluga whale population, which has the advantages of simple design and easy implementation, less parameter adjustment and fast convergence. This paper proposed a white whale optimization algorithm (TWBWO) based on chaotic backward learning and water wave algorithm improvement to address the problems that the original white whale algorithm has insufficient exploration and exploitation ability in the middle and late stages in some cases, the diversity and solution accuracy are reduced, and it is easy to fall into local optimality. Further improve the computational accuracy and convergence speed of Moby Dick algorithm, enhance the global search and jump out of local optimum capability. Combining chaotic mapping and backward learning strategies improves the quality and diversity of populations and speeds up the convergence rate. The refraction operation of the water wave algorithm (WWO) is introduced to avoid the algorithm from repeatedly falling into local optima and to improve the computational accuracy of the algorithm. The experimental results show that the TWBWO algorithm is superior to the original algorithm and other classical algorithms in terms of convergence speed and solution accuracy as well as stability,with better performance and better finding ability. [ABSTRACT FROM AUTHOR]

With the continuous economic growth, the number of power customers has increased significantly, and consumers in the field of power marketing will inevitably have a credit crisis. In order to reduce the business risk of relevant departments and improve the risk prediction ability of the system, this paper evaluates and reviews the user credit system. In this paper, the basic structure of BP neural network is described firstly, and then, the traditional BP neural network model is optimized after analyzing its algorithm flow. Based on this point, this paper analyzes the characteristics of customers in the energy and electricity market in the research area, and referring to local experts who have been engaged in power sales for many years, this paper puts forward a new set of directly scored power system load forecasting index system and algorithm improvement scheme and discusses the evaluation of power market credit rating based on the credit evaluation suggestions of power customers. After establishing the judgment criteria, in this paper, the power load data of the target area are studied by empirical analysis method and select three different customers from the production area, commercial and residential areas and residential areas as cases to analyze the determination of their credit rating and then, discuss the results of regional power load forecasting. Finally, this paper puts forward a kind of power management method based on the user's credit rating, and in order to complete the modernization transformation of power management system and promote the market development. In this paper, after improving and optimizing the traditional BP neural network, it is applied to the power market to predict the target user credit system, so as to achieve the improvement of forecasting ability. [ABSTRACT FROM AUTHOR]

Humans have the ability to quickly identify their own environment, understand, judge and analyze it, which is one of the important reasons why human beings can survive in nature for a long time and gradually develop it into a prosperous society today. The key to human's ability to perceive and understand the environment lies in the ability to accurately find and identify objects, understand and describe visual scenes, and even express emotions on this basis. And if computers can realize automatic and accurate image recognition, and even understand the semantics of images correctly, it will surely improve and facilitate human life. Based on this, the author integrated and optimized the computer image recognition system and applied it in this paper. The core technology of the system is to improve the image algorithm, which can complete the training, testing and classification of target images. The experimental data are available. Choosing this algorithm to improve the learning and training of the data generated by the original image processing is more effective than directly training the original image. [ABSTRACT FROM AUTHOR]

Precision marketing is faced with multiple levels of problems, such as pollution of the data environment and unscientific algorithms, which need to be sorted out urgently. Based on neural network technology, this paper constructs a neural network-based precision marketing model and focuses on data mining to study user churn prediction and user value enhancement, which are the two most important factors affecting marketing revenue. Moreover, this paper conducts an empirical test of the product strategy and market strategy adopted by big data precision marketing. According to the characteristics of the user population and the application scenarios of the product, this paper puts the corresponding precision marketing methods in a targeted manner and analyzes the performance of the model through experimental research. The research results show that precision marketing methods based on big data information platforms need to be more detailed and more comprehensive. At the same time, precision marketing methods need to correspond to the sensitive information characteristics of target users and consider the background and current situation of actual market execution to effectively play it role. [ABSTRACT FROM AUTHOR]

The feature extraction speed of the traditional athlete motion retrieval algorithm is slow, and it often takes dozens of minutes or even hours to analyze a video. The speed of this feature extraction obviously cannot meet the needs of big data video analysis. In response to these two problems exposed by Action Bank under large-scale data, this paper proposes to apply the template learning method based on spectral clustering to Action Bank, which replaces the cumbersome manual selection template step and is easy to generalize to different databases. Moreover, in view of the disadvantage of slow speed of extracting Action Bank features, this paper proposes a fast algorithm for accumulating Action Bank. In addition, this study uses the lookup table method instead of the time-consuming steps of the correlation distance calculation in template matching, which greatly accelerates the time of feature extraction. Finally, this study design experiments to analyze the performance of the algorithm. Through research, it can be seen that the algorithm of this study can be applied to athletes' sports retrieval and has certain recognition effects. [ABSTRACT FROM AUTHOR]

English part-of-speech intelligent recognition is the scientific and technological basis for the development of intelligent speech systems. The difficulty in the current English speech recognition system lies in the recognition of English parts of speech. In order to improve the effect of English part-of-speech recognition, this study builds the language rules and morphological models of English morphological forms based on machine learning algorithms. Moreover, this study proposes a stemming extraction algorithm and a syllable division algorithm based on English characteristic rules. By studying basic phrases in English, this study analyzes the compositional structure of phrases, and determines the basic phrase structure and composition rules of English such as noun, verb, and adjective. In addition, this research studies the basic English phrase recognition algorithm based on the rule method and the analysis of basic phrase ambiguity resolution. Finally, this study designs a control experiment to analyze the performance of the algorithm proposed in this paper model and confirm the classification algorithm. The research results show that the algorithm proposed in this paper has a certain practical effect. [ABSTRACT FROM AUTHOR]

Vehicle positioning and vehicle identification of natural scene images are an important part of intelligent transportation systems and unmanned driving research. In current situation, there are still some problems in vehicle intelligent wireless positioning. In order to improve the intelligent wireless positioning efficiency of vehicles, based on the convolutional neural network, this research combines the concept of deep learning to carry out algorithm innovation in the research. Moreover, this paper combines the actual vehicle positioning problem points to collect data, simulates the vehicle positioning situation in a variety of complex situations, and designs a controlled test to verify. The results show that the algorithm of this study has certain effects, which can provide reference for subsequent related research and has certain practical significance. [ABSTRACT FROM AUTHOR]

The classification of land cover is the first step in the analysis and application of remote sensing data in land resources. How to solve the multi-category image recognition and meet certain precision is a key issue in remote sensing image research, which has very important theoretical significance and practical application value. In this study, the algorithm is improved on the basis of convolutional neural network, and experiments are carried out on multi-source remote sensing images with different geomorphologies taken under three different weather conditions to verify the effectiveness and scalability of the improved convolutional neural network. The research results show that the improved algorithm proposed in this paper has certain results in remote sensing image classification and can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

The determination of the optimal measurement area of the articulated arm measuring machine belongs to the multi-dimensional function optimization problem under complex constraints. To realize high-precision measurement of low-precision articulated arm measuring machine, we analyze the working principle and error source of the measuring machine, and establish the optimization target model of the optimal measurement area in this paper. We propose a method for determining the optimal measurement area of an articulated arm measuring machine based on improved FOA. The basic FOA algorithm is improved, the historical optimal individual and population centroid information are added in the population iteration update process, and the fruit fly individuals in each iteration are directly used as the taste concentration judgment value, which increases cooperation and information sharing among fruit fly individuals, and improves the global optimization ability and stability of the algorithm. In the designated area of the measuring machine, we have carried out comparative experiments on the optimization results of improved FOA and basic FOA, ACO, PSO, AL-SC-FOA, LGMS-FOA, IPGS-FFO. Experimental results show that the improved FOA, ACO, PSO, and IPGS-FFO algorithms do not fall into local optimum, and the optimal measurement area determined by them is consistent with the optimization results of other algorithms, and is superior to other algorithms in convergence speed and stability, so it is more suitable for determining the optimal measurement area of articulated arm measuring machine. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of the basic bat algorithm such as slow convergence, low convergence precision and weak stability, this paper des igned an improved bat algorithm based on Gaussian disturbance and exponential decreasing strategy (GDEDBA). It introduced the exponential decreasing strategy into the speed update formula, which made the algorithm enter local optimization quickly and perform a precise search. It added the constructed Gaussian disturbance term to the local new solution generation formula, then made the information exchange and study between all particles in the local new solution and the current global optimal particles, prevented falling into local optimum and increased population diversity. It designed the disturbance control factor to control the disturbance range of Gaussian disturbance, enhanced the stability of the algorithm. The simulation results of 15 classical test functions show that the optimization performance of improved algorithm is significantly improved, the convergence speed is faster, the solution accuracy is higher, and the stability is stronger. [ABSTRACT FROM AUTHOR]

Highlights • A new pressure drop limit has been added into the optimization criteria. • The previous integrated optimization algorithm of NTCOC is improved. • The improved code has been applied on the HCSB blanket for CFETR Phase II. • The computational processes with two methods are compared. Abstract Blanket is the key component of Chinese Fusion Engineering Test Reactor (CFETR). In our previous work, considering that the radial arrangement of the internal functional zones has the greatest influence on the blanket performances and is also the most important basis of the 3D design, NTCOC, a Neutronics/Thermal-hydraulic Coupling Optimization Code which adopts 1D neutronics and 2D thermal-hydraulic simplified calculation models, has been independently developed for facilitating the radial build design and optimization of the CFETR helium cooled solid breeder (HCSB) blanket. Through setting three leading design requirements as the optimization criteria, this code has been applied on optimizing the radial build arrangement of a conceptual design of HCSB blanket for CFETR Phase I, which preliminarily verifies the reasonability of the code. However, recently, the design phase of CFETR has gradually changed from I to II, the fusion power of which will be quintuple to the previous I. This means that the internal nuclear power deposition in each blanket component under II operation condition will be much larger than the previous I. Therefore, much larger coolant inlet mass flowrate will be needed and more breeder units should to be inserted, both of which will make the total pressure drop of blanket for Phase II much larger than the previous I and even exceed the limit of CFETR HCSB blanket greatly. This can’t be sustained in CFETR, a power plant that should produce electricity. To solve this problem, in this paper, the previous integrated neutronics/thermal-hydraulic optimization algorithm is improved by adding the new pressure drop limit into the optimization criteria. Then the improved code has been applied on optimizing the radial build arrangement of a conceptual design of HCSB blanket for CFETR Phase II through constant and variable step length two methods. The calculation results verifies the feasibility and reasonability of the improved optimization algorithm preliminarily. [ABSTRACT FROM AUTHOR]

Because of the large mining thickness at one-time for extra thick seam using fully-mechanized top coal caving method and nearly shallow buried depth, the characteristics of surface movement and deformation particularity is obvious. Under this condition, its surface subsidence prediction has a certain degree of deviation with ihe actual situation. This paper analyzed the partic-ularity of surface movement and deformation for extra thick seam using fully-mechanized top coal caving method and nearly shallow buried depth of the test area. Considering thick-hard rock layer on surface subsidence control function,and based on layered elastic beam slab strata of subsidence control theory and random medium theory,the authors established a set of surface subsidence prediction model which is suitable for nearly shallow buried depth and extra thick seam using fully-mechanized top coal caving method. Practical application shows that degree of agreement for the prediction model algorithm with the experimental results is good,which is suitable for surface subsidence prediction application in extra thick seam mining using fully-mechanized top coal caving method. The prediction model algorithm preferably solved the problems such as rapid boundary convergence and unsymmetrical basin using probability integral method and improved the prediction accuracy of surface subsidence. [ABSTRACT FROM AUTHOR]

This paper analyzes the features and mechanism of the B algorithm proposed by Vincent D. Blondel et al., and discusses the possible impact of nodes' property on community structure detection. Then it proposes an improved algorithm for the B algorithm by reconstructing the initial network and controlling node (community) merging process in order to obtain better modularity and the corresponding network partition. The community structure detection experiments on computer simulation networks and actual networks, show that the improved algorithm we proposed is reliable and effective, which achieves a better network partition with a larger modularity and has shorter computation time. [ABSTRACT FROM AUTHOR]