Dynamic Weighting Method Research Articles

Research on occlusion block face recognition based on feature point location

AbstractAiming at improving the poor face recognition accuracy under occlusion, a multipose block occlusion face recognition method based on feature point location is proposed. Face segmentation is carried out according to the location results of face feature points and occlusion areas. The local features of each face block are extracted by deep convolution neural network. The dynamic adaptive weighting method is used to give different weights to the face block information, and the occluded face recognition is completed according to the results of face segmentation, which effectively reduces the impact of pose change and occlusion on face recognition. The experiment is analyzed from two aspects: frontal occlusion and multipose face occlusion. The results show that fewer blocks in the frontal occlusion experiment are conducive to maintaining good local integrity and relatively good recognition performance; When the proportion of frontal occlusion reaches 50%, the recognition rate of our algorithm can still be up to 92.68%, which is significantly better than other algorithms.

Distributed process monitoring for large‐scale processes based on MJMI‐weighted DKPCA

AbstractAlthough the distributed monitoring model has been widely employed in monitoring large‐scale processes, the dynamic nonlinear property in process data is rarely investigated. Given the complex dynamic nature of industrial processes, different process variables interact with each other over time. In order to describe the correlation of dynamic variables more accurately, this work proposes a novel dynamic nonlinear fault detection framework based on maximum joint mutual information (MJMI)‐weighted dynamic kernel principal component analysis (WDKPCA). After dividing the process variables using the MJMI scheme, the proposed dynamic weighting method defines the weight of time‐delayed variables, which allows the dynamic characteristics of these variables to be characterized more comprehensively. By these means, the processes can be decomposed into multiple subblocks, and a distributed monitoring scheme based on DKPCA is thus established. Then, the Bayesian fusion strategy is used to fuse the monitoring results of different subblocks. Through a series of experiments on the Tennessee Eastman (TE) process, the results indicate that MJMI‐WDKPCA has superior process monitoring performance.

A Novel βSA Ensemble Model for Forecasting the Number of Confirmed COVID-19 Cases in the US

In December 2019, Severe Special Infectious Pneumonia (SARS-CoV-2)–the novel coronavirus (COVID-19)– appeared for the first time, breaking out in Wuhan, China, and the epidemic spread quickly to the world in a very short period time. According to WHO data, ten million people have been infected, and more than one million people have died; moreover, the economy has also been severely hit. In an outbreak of an epidemic, people are concerned about the final number of infections. Therefore, effectively predicting the number of confirmed cases in the future can provide a reference for decision-makers to make decisions and avoid the spread of deadly epidemics. In recent years, the α-Sutte indicator method is an excellent predictor in short-term forecasting; however, the α-Sutte indicator uses fixed static weights. In this study, by adding an error-based dynamic weighting method, a novel β-Sutte indicator is proposed. Combined with ARIMA as an ensemble model (βSA), the forecasting of the future COVID-19 daily cumulative number of cases and the number of new cases in the US are evaluated from the experiment. The experimental results show that the forecasting accuracy of βSA proposed in this study is better than other methods in forecasting with metrics MAPE and RMSE. It proves the feasibility of adding error-based dynamic weights in the β-Sutte indicator in the area of forecasting.

Complex Network Construction and Pattern Recognition of China’s Provincial Low-Carbon Economic Development with Long Time Series: Based on the Detailed Spatial Relationship

Low-carbon economic development has become the orientation of high-quality economic construction in the era of climate change. Because it involves multi-dimensional elements and is driven by the concept of regional integration and common development, the development pattern among China’s provinces should show the characteristics of complex networked spatial correlation. However, most of the existing research are for is based on attribute data and combined with traditional spatial econometric models, which cannot describe the complex networked spatial correlation. Concurrently, the network construction is mainly based on undirected-unweighted sparseness, which makes it difficult to truly restore the asymmetric detailed spatial relationship, making the related research about development pattern recognition and its evolution based on the detailed spatial relationship relatively lacking. Therefore, based on the perspective of relational data, this study constructs a multi-dimensional gravity model by using the comprehensive quality of China’s provincial low-carbon economic development, measured by the multi-dimensional evaluation index system and dynamic weight method, and the comprehensive distance based on geography, society, economy, and adjacency. And then the spatial correlation strength among China’s provincial low-carbon economic development is determined, and constructs a directed-weighted complex network. Then, it further explores the inter-provincial detailed spatial relationship of low-carbon economy development from the three dimensions of overall, individual and group, to recognize the development patterns and evolution rules of low-carbon economic development in different provinces, and clarify the development orientation. The results show that, during the study period, the spatial correlation of China’s provincial low-carbon economic development has become increasingly close, showing a complex networked correlation structure with multi-linearity, asymmetry, and geographical proximity as a whole. The division of general structure is consistent with China’s regional economic development strategy. The unbalanced development of China’s provincial low-carbon economy is the result of multi-center drive in the eastern and central regions, and the distance from the network center in the western regions. In general, China’s provincial low-carbon economic development patterns can be roughly divided into spillover, main bridge, auxiliary bridge, and benefit type. In the future, we should make full use of the power source role of spillover provinces, and the bridge support role of bridge provinces to drive the development of benefit provinces. Among them, Chongqing, Shaanxi, Hebei and Sichuan are expected to become new regional growth poles. The research on the inter-provincial spatial correlation effect and development pattern recognition of low-carbon economic development is expected to provide guidance for the sustainable development of low-carbon economy in China.

Spatial Equilibrium Evaluation of Regional Water Resources Carrying Capacity Based on Dynamic Weight Method and Dagum Gini Coefficient

With the rapid economic development and the acceleration of urbanization, the pressure on the water resources system is becoming intense. As an important indicator of water resources security and sustainable development, the water resources carrying capacity has become a hot issue. To overcome the limitation of commonly used methods for weight determination and to evaluate the regional water resources carrying capacity reasonably, the index weight determined by the Analytic Hierarchy Process method was revised by the subtraction set pair potential to calculate the dynamic index weight. Then, the dynamic weight was combined with the set pair analysis method to evaluate the regional water resources carrying capacity dynamically. In addition, the Dagum Gini coefficient and its decomposition method were used to analyze the overall difference of water resources carrying capacity in the whole region and the differences within and between subregions considering the lack of quantitative research in spatial equilibrium. Finally, a case study was carried out in Anhui Province, China. The results showed that from 2011 to 2018, most of the water resources carrying capacity for 16 cities in Anhui Province were in a critical state, with the strongest in the south of Anhui Province and the weakest in the north. The overall spatial difference of carrying capacity in Anhui Province showed an increasing trend from 2011 to 2018. Furthermore, the slightest difference within the subregion was in the north of Anhui Province, while the largest was in the south. The most significant difference between the subregions was between the south and the north of Anhui Province. The primary source of carrying capacity spatial difference in Anhui Province was from the difference between subregions. The results of the case study suggested that the method proposed in this paper are conducive to the early find of possible disadvantages of spatial equilibrium and can effectively identify the main source of regional spatial difference in water resources carrying capacity, which means that the method can be widely applied to similar issues.

Comparison of several model updating methods based on full-scale model test of track beam

The response surface model updating method uses the objective function to fit the finite element model, which improves the optimization efficiency of the model. In order to make up for the shortcoming of weights selection in traditional model updating, a dynamic weight method based on response surface is proposed in this paper. Combined with the static and dynamic test results of a full-scale test of track beam, the response surface is fitted and the accuracy is tested. Then, the effects of static method, dynamic method and combined method on model updating are compared and analyzed. The effects of two different objective function construction methods, equal weight and dynamic weight, on the model updating are discussed. The results show that the model updating of the response surface method can effectively improve the accuracy of the finite element model. In the static response updating results, the static method is the best, the combined method is the second, and the dynamic method is the worst. Among the dynamic response updating results, the dynamic method and the combined method have better correction effect, while the static method has worse correction effect. The dynamic weight method can effectively improve the accuracy of model updating.

Design of dynamic load balancing algorithm for heterogeneous clusters based on energy consumption

In order to reduce energy waste and improve the dynamic load balancing of heterogeneous clusters, sensor technology is introduced into the Internet of Things technology to build a channel transmission model for heterogeneous clusters. Then use the dynamic weighting method to configure the output channel to complete the decomposition of the channel characteristics. In addition, based on the establishment of the channel fuzzy recombination structure model, the noise interference suppression method is used to suppress the multipath interference of heterogeneous cluster communication channels, and the equalization of the channel output is controlled by the baud interval equalization sampling method. At the same time, through the fuzzy balance configuration and spatial balance scheduling process, the dynamic load balancing processing of heterogeneous clusters is realized. The simulation results show that the method proposed in this paper has better balance for the load scheduling of heterogeneous clusters and reduces the bit error rate of the output signal. More importantly, the output balance and adaptive control capabilities of heterogeneous clusters have also been improved.

Dynamic Pythagorean fuzzy probabilistic linguistic TOPSIS method with psychological preference and its application for COVID-19 vaccination

The probabilistic linguistic term set (PLTS) has been widely used in multiple criteria group decision making (MCGDM) problems where the linguistic information is uncertain and hesitant. To reflect the different preferences and uncertainties, we propose a new PLTS with probability in the form of Pythagorean fuzzy set (PFS), called Pythagorean fuzzy probabilistic linguistic term set (PFPLTS). In addition, considering the information integrity, uncertainty and DMs' preferences, the operation and aggregation operators for PFPLTS are introduced. Then, the weight method based on minimum deviation and dual ideal point-vector projection is proposed, which considers the time-varying characteristics of the weights and combines multi-dimensional influencing factors. Next, the psychological distance measure is proposed by dividing the psychological space into multiple vectors. Based on the proposed dynamic weight method, three psychological distance measures and TOPSIS method, we develop a dynamic Pythagorean fuzzy probabilistic linguistic TOPSIS method with psychological distance (Psy-TOPSIS), the psychological index ranges from 1 to 40. Finally, a practical case, site selecting of COVID-19 vaccination center, is given and compared with three approaches to illustrate the effectiveness and practicality of PFPLTS and the proposed decision-making method.

An Ensemble of Recurrent Neural Networks for Real Time Performance Modeling of Three-Spool Aero-Derivative Gas Turbine Engine

Abstract Gas turbine is a complex system operating in nonstationary operation conditions for which traditional model-based modeling approaches have poor generalization capabilities. To address this, an investigation of a novel data driven neural networks based model approach for a three-spool aero-derivative gas turbine engine (ADGTE) for power generation during its loading and unloading conditions is reported in this paper. For this purpose, a nonlinear autoregressive network with exogenous inputs (NARX) is used to develop this model in matlab environment using operational closed-loop data collected from Siemens (SGT-A65) ADGTE. Inspired by the way biological neural networks process information and by their structure which changes depending on their function, multiple-input single-output (MISO) NARX models with different configurations were used to represent each of the ADGTE output parameters with the same input parameters. First, data preprocessing and estimation of the order of these MISO models were performed. Next, a computer program code was developed to perform a comparative study and to select the best NARX model configuration, which can represent the system dynamics. Usage of a single neural network to represent each of the system output parameters may not be able to provide an accurate prediction for unseen data and as a consequence provides poor generalization. To overcome this problem, an ensemble of MISO NARX models is used to represent each output parameter. The major challenge of the ensemble generation is to decide how to combine results produced by the ensemble's components. In this paper, a novel hybrid dynamic weighting method (HDWM) is proposed. The verification of this method was performed by comparing its performance with three of the most popular basic methods for ensemble integration: basic ensemble method (BEM), median rule, and dynamic weighting method (DWM). Finally, the generated ensembles of MISO NARX models for each output parameter were evaluated using unseen data (testing data). The simulation results based on datasets consisting for experimental data as well as data provided by Siemens high fidelity thermodynamic transient simulation program show improvement in accuracy and robustness by using the proposed modeling approach.

Research on Quality Management Evaluation Method of Intelligent Robot Upgrade and R&D Project

In order to promote the high-quality development of intelligent robot upgrade R&D projects, promote the progress of social and economic intelligence, and improve production efficiency, a dynamic weighted evaluation method based on network cohesion of balanced groups is proposed. This method is based on balanced grouping of evaluation groups to ensure the relative homogeneity of evaluation groups. It uses dynamic interactive evaluation to construct a network adjacency matrix based on the consistency of pairwise evaluations within the group. And it collects Horizontal information based on the concept of network cohesion. A stage planning function is constructed to calculate the weights of multiple rounds of evaluation, Finally, a comprehensive evaluation result is obtained after vertical merging. This paper provides a new evaluation method for improving the quality management of intelligent robot upgrade R&D projects.

Research on PID Control of Water Level in Pile Legs Based on Improved PSO

Aiming at the problem of poor water level control effect during mud dredging in pile legs, based on the research of traditional PID algorithm and particle swarm algorithm, a PID parameter optimization method based on improved PSO(IPSO)was proposed. This paper adopts a nonlinear dynamic adaptive inertial weight (ω) method and introduces a time factor to adjust the position update time. In this paper, a mathematical model of the water level control system in the leg is established, and the system is simulated by MATLAB / Simulink. By comparing the simulation results, PID controller optimized by improved PSO is better than traditional PID controller. The proposed method provides a theoretical reference for the water level control system during the mud dredging operation in the pile legs.

Novel Online Optimized Control for Underwater Pipe-Cleaning Robots

Due to the particularity of the jacket structure of offshore platforms and the complexity of the marine environment, there have been few effective localization and autonomous control methods for underwater robots that are designed for cleaning tasks. To improve this situation, a fusion bat algorithm (BA) online optimized fuzzy control method using vision localization was developed based on the constraints of the underwater operational environment. Vision localization was achieved based on images from a catadioptric panoramic imaging system. The features of the pipe edge and the boundary of the area covered by biofouling were obtained by image processing and feature extraction. The feature point chosen as the “highest” point of the boundary was calculated by projection transformation to generate the reference path. The specialized fuzzy controller was designed to drive the robot to track the reference path, and an improved bat algorithm with dynamic inertia weight and differential evolution method was developed to optimize the scale factors of the fuzzy controller online. The control method was simulated and further implemented on an underwater pipe-cleaning robot (UPCR), and the results indicate its rationality and validity.

Risk assessment of the UPIoT construction in China using combined dynamic weighting method under IFGDM environment

Large-scale integration of renewable energy systems poses challenges to the ubiquitous power Internet of things (UPIoT) construction in China. This paper aims to study beyond these challenges from a risk assessment perspective, using the combined dynamic weighting evidence fusion (CDWEF) method under the intuitionistic fuzzy group decision-making (IFGDM) environment. The UPIoT construction risk is identified and characterized by a 17-indicator system which is scored by intuitionistic fuzzy relations (IFRs) from experts. The IFRs are corrected by the dynamic expert weight determined from both the intuitionistic fuzzy entropy and conflicts among IFRs. The IF-AHP-DEMATEL method is adopted to determine the combined indicator weight for correcting the risk mass functions, which are obtained from the IFRs with the evidence fusion theory. The proposed risk assessment method is validated in a case study, indicating that the UPIoT construction risk in China is high in communication networks and business innovation.

HWSMCB: A community-based hybrid approach for identifying influential nodes in the social network

Influence Maximization is concerned with identifying a set of influential nodes in the social network that aims to maximize the spread of information, disease, and influence. Such a set of nodes is responsible for optimizing the influence in the network and is NP-Hard problem. To address this issue, different centrality measures have been proposed such as betweenness centrality, closeness centrality, degree centrality, but all of them suffered from some drawbacks. Some recent research works found that the dynamics of the network are greatly affected by the group structure, which is an important topological property of the social network. This paper proposes a novel framework, named, a community-based hybrid approach for identifying influential nodes in the social network (HWSMCB), to deal with the influence maximization problem. A dynamic Weighted Sum Method (D-WSM), a multi-criteria decision making method (MCDM), is introduced to take into account the node’s topological features simultaneously. The proposed HWSMCB is based on D-WSM and exploits community structure to identify influential nodes from the underlying social network. To establish the efficacy of the HWSMCB, experiments are conducted on real-world networks under the SIR epidemic model. The results obtained from HWSMCB are compared with some competitive methods such as Hybrid community based approach using K-means(HKM), W-Topsis (WT), betweenness centrality, page rank, closeness centrality, and degree centrality based on two parameters: diffusion speed and diffusion quality.

Empirical Study on Coupling and Coordinated Development of “Energy-Finance-Environment” in the Middle Reaches of Yangtze River

In the important transition period of high-quality development in China, it is of great significance to explore the coordinated development among finance, energy and environment. In this paper, the dynamic average weight method with improved entropy value is used, and the index system of “energy-finance-environment” three-dimensional system (hereinafter referred to as “EFE system”) is established to explore the coordinated development and dynamic evolution of the coupling. The results show that the newly constructed dynamic average weighting method is reasonable and effective, and can reflect the time-varying characteristics of each subsystem index weight; from 2009 to 2017, the EFE values of the four provinces in the middle reaches of the Yangtze river present different development trends, and the trend of finance shows an overall upward trend, while the trend of environment and energy show twists and turns; the coupling degrees of the four provinces are high, but the coordination degrees are generally low, failing to reach the coordination level; the restricting factors of coordinated development are mainly the backward type of financial development and energy efficiency. This conclusion provides a reference for a more rational grasp of the coordinated development of EFE system in the middle reaches of Yangtze river.

Weight Value and Map Complexity in Theta*

A performance of an experiment to analyze the relationship between weight value and map complexity. That means there is a trial to find which weight value performs the best on maps with different complexity. And then in this article there is an application of hierarchical and dynamic weight method into Theta* path-finding algorithm. The dynamic weight value is picked from the first experiment. For different abstract map, a weight value is changed base on the complexity of the abstract map. This article contains a re-test of new implementation of Theta* and compare to the Mr. Nash’s Theta* to collect the positive outcome. And by applying the dynamic weight method with different weight based on map complexity, the dynamic weight theta* perform better in time costing

Development of an Optimal Operation Approach in the MPC Framework for Heavy-Haul Trains

An operation control approach for heavy-haul trains to optimize their performance, including operation safety, service quality, and energy consumption, is proposed. Following a model predictive control method, the controller is capable of scheduling a train to operate optimally during a long section of the rail track. In the cost function, two penalty factors are presented, i.e., one for the braking forces and one for coupler damping effects. The penalty for braking forces is employed to reduce the energy waste incurred by braking. The penalty for coupler damping is introduced to alleviate the cyclic vibration of couplers, which link adjacent cars in the train. The damping penalty is also expected to reduce energy wasted by coupler damping and corresponding maintenance/replacement cost of the dampers. In addition, the weight of the velocity tracking term in the objective function is modified to vary dynamically, according to the train's velocity, to improve the train's overall performance. Simulations verify the effectiveness of the proposed control approach. Discussions over the impacts of the two penalty factors and the dynamic weight method are provided, together with some suggestions on their applications.

Time Sharing Algorithm with Dynamic Weighted Harmonic Round Robin

In operating system is an important issue, Allocates processor time to processes, to be fair. We presented in This paper proposed methods to reduce Average waiting time, average response time, Switch Counts process, through the design of a time sharing non-exclusive scheduling algorithm based on the round Robin and determined accurate time quantum . Among the proposed approaches, weight harmonic- dynamic weight and Subtraction Method are achieved better and more accurate results.

Evaluating intelligent residential communities using multi-strategic weighting method in China

Many residential communities are claimed to be “intelligent”, but their level of intelligence noticeably varies corresponding to the functionality and operational efficiency of the installed intelligent systems. This raises the need for having an effective and practicable method that would allow decision-makers to measure the degree of intelligence of one residential community against another. To achieve this objective, this paper elicits a general list of intelligence indicators of residential communities in China by means of system modeling as a base. Then, focusing in particular on the importance of these intelligence indicators’ weights, this paper proposes a dynamic multi-strategic weighting method to facilitate the evaluation of intelligent residential communities. The analytic network process (ANP), entropy method and their combination are proposed as three weighting strategies to meet the need of evaluation at different stages of intelligent residential community's development in China. An experimental case study has been presented to demonstrate how to use the multi-strategic method to confront real-world design tasks. The research aims to provide a practical method to enable the evaluation of intelligent residential communities on more fair ground.

An adaptive online safety assessment method for mechanical system with pre-warning function

The safety status of a dynamic mechanical system is determined by its historical, current and future states together. Therefore the safety assessment process of such system should have dynamic and diachronic characteristics, which helps to track the dynamic states of system and predict future probable danger in advance. In order to overcome the disadvantages of traditional static safety assessment approaches, the results from which are often delayed and prone to produce false alarms, an adaptive online safety assessment method is proposed in this paper, which consists of two steps. A dynamic adaptive weighting method is first introduced and an aggregation scheme based on “3-D” time perspective is further presented to integrate system’s historical, current and future safety performance in a unit framework, considering both of assessment and pre-warning functions. The proposed method is able to track and predict the safety status of system dynamically and discover the potential fault in time. Its feasibility and benefits are investigated with a field case study of gas turbine compressor system, which validates that the proposed method improves the accuracy of safety assessment in dynamic conditions, and finally helps to restrain the fault symptom by proactive maintenance successfully.