Multimodal Sentiment Analysis Using BiGRU and Attention-Based Hybrid Fusion Strategy

Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.

Adaptive Agent Model with Hybrid Routing Selection Strategy for Improving the Road-Network Congestion Problem

This paper proposes an adaptive agent model with a hybrid routing selection strategy for studying the road-network congestion problem. We focus on improving those severely congested links. Firstly,a multi-agent system is built,where each agent stands for a vehicle,and it makes its routing selection by considering the shortest path and the minimum congested degree of the target link simultaneously. The agent-based model captures the nonlinear feedback between vehicle routing behaviors and road-network congestion status.Secondly,a hybrid routing selection strategy is provided,which guides the vehicle routes adapting to the realtime road-network congestion status. On this basis, we execute simulation experiments and compare the simulation results of network congestion distribution,by Floyd agent with shortest path strategy and our proposed adaptive agent with hybrid strategy. The simulation results show that our proposed model has reduced the congestion degree of those seriously congested links of road-network. Finally,we execute our model on a real road map. The results finds that those seriously congested roads have some common features such as located at the road junction or near the unique road connecting two areas. And,the results also show an effectiveness of our model on reduction of those seriously congested links in this actual road network. Such a bottom-up congestion control approach with a hybrid congestion optimization perspective will have its significance for actual traffic congestion control.

DEVELOPMENT OF THE ENERGY MANAGEMENT STRATEGY FOR PARALLEL HYBRID ELECTRIC URBAN BUSES

A novel parallel hybrid electrical urban bus （PHEUB） configuration consisting of an extra one-way clutch and an automatic mechanical transmission （AMT） is taken as the study subject. An energy management strategy combining a logic threshold approach and an instantaneous optimization algorithm is proposed for the investigated PHEUB. The objective of the energy management strategy is to achieve acceptable vehicle performance and drivability requirements while simultaneously maximizing the engine fuel consumption and maintaining the battery state of charge in its operation range at all times. Under the environment of Matlab/Simulink, a computer simulation model for the PHEUB is constructed by using the model building method combining theoretical analysis and bench test data. Simulation and experiment results for China Typical Bus Driving Schedule at Urban District （CTBDS_UD） are obtained, and the results indicate that the proposed control strategy not only controls the hybrid system efficiently but also improves the fuel economy significantly.

A Novel Polymorphic Topology with Hybrid Control Strategy Based LLC Resonant Converter for Ultra-Wide Input Voltage Range Applications

To realize effective utilization of renewable energy sources,a novel polymorphic topology with hybrid control strategy based LLC resonant converter was analyzed and designed in this paper.By combining the merits of a full bridge LLC resonant converter,three-level half bridge LLC resonant converter,and variable frequency control mode,the converter realizes an intelligent estimation of input voltage by automatically changing its internal cir-cuit topology.Under this control strategy,different input voltages determine different operation modes.This is achieved in full bridge LLC mode when the input voltage is low.If the input voltage rises to a certain level,it operates in three-level half bridge LLC mode.These switches are digital and entirely carried out by the DSP(Digi-tal Signal Processor),which means that an auxiliary circuit is unnecessary,where a simple strategy of software modification can be utilized.Experimental results of a 500W prototype with 100V~600V input voltage and full load efficiency of up to 92%are developed to verify feasibility and practicability.This type of converter is suitable for applications with an ultra-wide input voltage range,such as wind turbines,photovoltaic generators,bioenergy,and other renewable energy sources.

Hybrid Control Strategy for Matrix Converter Fed Wind Energy Conversion System

In this paper, a hybrid control strategy for a matrix converter fed wind energy conversion system is presented. Since the wind speed may vary, output parameters like power, frequency and voltage may fluctuate. Hence it is necessary to design a system that regulates output parameters, such as voltage and frequency, and thereby provides a constant voltage and frequency output from the wind energy conversion system. Matrix converter is used in the proposed solution as the main power conditioner as a more efficient alternative when compared to traditional back-back converter structure. To control the output voltage, a vector modulation based refined control structure is used. A power tracker is included to maximize the mechanical output power of the turbine. Over current protection and clamp circuit input protection have been introduced to protect the system from over current. It reduces the spikes generated at the output of the converter. The designed system is capable of supplying an output voltage of constant frequency and amplitude within the expected ranges of input during the operation. The matrix converter control using direct modulation method, modified Venturini modulation method and vector modulation method was simulated, the results were compared and it was inferred that vector modulation method was superior to the other two methods. With the proposed technique, voltage transfer ratio and harmonic profile have been improved compared to the other two modulation techniques. The behaviour of the system is corroborated by MATLAB Simulink, and hardware is realized using an FPGA controller. Experimental results are found to be matching with the simulation results.

Designing an automated FAQ answering system for farmers based on hybrid strategies

Purpose: The purpose of this study is to develop an automated frequently asked question(FAQ) answering system for farmers. This paper presents an approach for calculating the similarity between Chinese sentences based on hybrid strategies.Design/methodology/approach: We analyzed the factors influencing the successful matching between a user's question and a question-answer(QA) pair in the FAQ database. Our approach is based on a combination of multiple factors. Experiments were conducted to test the performance of our method.Findings: Experiments show that this proposed method has higher accuracy. Compared with similarity calculation based on TF-IDF,the sentence surface forms and the semantic relations,the proposed method based on hybrid strategies has a superior performance in precision,recall and F-measure value.Research limitations: The FAQ answering system is only capable of meeting users' demand for text retrieval at present. In the future,the system needs to be improved to meet users' demand for retrieving images and videos.Practical implications: This FAQ answering system will help farmers utilize agricultural information resources more efficiently.Originality/value: We design the algorithms for calculating similarity of Chinese sentences based on hybrid strategies,which integrate the question surface similarity,the question semantic similarity and the question-answer similarity based on latent semantic analysis(LSA) to find answers to a user's question.

Hybridization of iron phthalocyanine and MoS_(2)for high-efficiency and durable oxygen reduction reaction

Hybrid catalysts based on iron phthalocyanine(FePc)have raised much attention due to their promising applications in electrocatalytic oxygen reduction reaction(ORR).Various hybridization strategies have been developed for improving their activity and durability.However,the influence of different hybridization strategies on their catalytic performance remains unclear.In this study,Fe Pc was effectively distributed on molybdenum disulfide(MoS_(2))forming Fe Pc-based hybrid catalysts,namely Fe Pc-MoS_(2),Fe Pc*-MoS_(2),and Fe Pc-Py-MoS_(2),respectively,to disclose the related influence.Through direct hybridization,the stacked and highly dispersed Fe Pc on MoS_(2)resulted in Fe Pc-MoS_(2),and Fe Pc*-MoS_(2),respectively,in which the substrate and Fe Pc are mainly bound through van der Waals interactions.Through covalent hybridization strategy using pyridyl(Py)as a linker,Fe Pc-Py-MoS_(2)hybrid catalyst was prepared.Experimental and theoretical results disclosed that the linker hybridization of Fe Pc and MoS_(2)facilitated the exposure of Fe-N4 sites,maintained the intrinsic activity of Fe Pc by forming a more dispersed phase and increased the durability via Fe-N bonding,rendering the Fe Pc-Py-MoS_(2)an excellent ORR hybrid catalyst.Compared with van der Waals hybridized Fe Pc-MoS_(2)and Fe Pc*-MoS_(2)in alkaline media,the linker hybridized Fe Pc-Py-MoS_(2)showed an obviously enhanced ORR activity with a half-wave potential(E_(1/2))of 0.88 V vs RHE and an ultralow Tafel slope of 26 m V dec-1.Besides,the Fe Pc-Py-MoS_(2)exhibited a negligible decay of E_(1/2) after 50,000 CV cycles for ORR,showing its superior durability.This work gives us more insight into the influence of different hybrid strategies on Fe Pc catalysts and provides further guidance for the development of highly efficient and durable ORR catalysts.

Fuzzy Hybrid Coyote Optimization Algorithm for Image Thresholding

In order to address the problems of Coyote Optimization Algorithm in image thresholding,such as easily falling into local optimum,and slow convergence speed,a Fuzzy Hybrid Coyote Optimization Algorithm(here-inafter referred to as FHCOA)based on chaotic initialization and reverse learning strategy is proposed,and its effect on image thresholding is verified.Through chaotic initialization,the random number initialization mode in the standard coyote optimization algorithm(COA)is replaced by chaotic sequence.Such sequence is nonlinear and long-term unpredictable,these characteristics can effectively improve the diversity of the population in the optimization algorithm.Therefore,in this paper we first perform chaotic initialization,using chaotic sequence to replace random number initialization in standard COA.By combining the lens imaging reverse learning strategy and the optimal worst reverse learning strategy,a hybrid reverse learning strategy is then formed.In the process of algorithm traversal,the best coyote and the worst coyote in the pack are selected for reverse learning operation respectively,which prevents the algorithm falling into local optimum to a certain extent and also solves the problem of premature convergence.Based on the above improvements,the coyote optimization algorithm has better global convergence and computational robustness.The simulation results show that the algorithmhas better thresholding effect than the five commonly used optimization algorithms in image thresholding when multiple images are selected and different threshold numbers are set.

A HYBRID METHOD FOR SOLVING VARIATIONAL INEQUALITY PROBLEMS

By using Fukushima's differentiable merit function,Taji,Fukushima and Ibaraki have given a globally convergent modified Newton method for the strongly monotone variational inequality problem and proved their method to be quadratically convergent under certain assumptions in 1993.In this paper a hybrid method for the variational inequality problem under the assumptions that the mapping F is continuously differentiable and its Jacobian matrix Δ F(x) is positive definite for all x∈S rather than strongly monotone and that the set S is nonempty,polyhedral,closed and convex is proposed.Armijo type line search and trust region strategies as well as Fukushima's differentiable merit function are incorporated into the method.It is then shown that the method is well defined and globally convergent and that,under the same assumptions as those of Taji et al.,the method reduces to the basic Newton method and hence the rate of convergence is quadratic.Computational experiences show the efficiency of the proposed method.

Accuracy improvement of the traditional rolling force and torque model powered by an industrial data platform

The calculation results of the rolling force and torque model based on Orowan's differential equation numerical solution method do not fit with the industrial measurements very well.In particular,a quite large deviation on the torque model was found.On the basis of analyzing the shortcomings of the existing method,an improved rolling force and torque model algorithm aided by the Process Integrated Data Application System platform is proposed.Accordingly,the calculation accuracy of the rolling torque model is improved.The improved models are verified by 1711136 records of a data platform.The improved models are also based on Orowan's differential equation.Two coefficients,namely,friction factor and forward slip,are recognized as the crucial factors to be determined from industrial measurements to improve the accuracy.Therefore,the proposed method is a hybrid method that can be used to deeply understand the rolling process and improve the model's accuracy by combining traditional plastic mechanics and data-driving global optimization algorithms.This paper proposes a new approach to studying theoretical rolling deformation models powered by the industrial data platform.

Solving algorithm for TA optimization model based on ACO-SA

An ant colony optimization （ACO）-simulated annealing （SA）-based algorithm is developed for the target assignment problem （TAP） in the air defense （AD） command and control （C2） system of surface to air missile （SAM） tactical unit. The accomplishment process of target assignment （TA） task is analyzed. A firing advantage degree （FAD） concept of fire unit （FU） intercepting targets is put forward and its evaluation model is established by using a linear weighted synthetic method. A TA optimization model is presented and its solving algorithms are designed respectively based on ACO and SA. A hybrid optimization strategy is presented and developed synthesizing the merits of ACO and SA. The simulation examples show that the model and algorithms can meet the solving requirement of TAP in AD combat.

A hybrid brain-computer interface control strategy in a virtual environment

This paper presents a hybrid brain-computer interface (BCI) control strategy,the goal of which is to expand control functions of a conventional motor imagery or a P300 potential based BCI in a virtual environment.The hybrid control strategy utilizes P300 potential to control virtual devices and motor imagery related sensorimotor rhythms to navigate in the virtual world.The two electroencephalography (EEG) patterns serve as source signals for different control functions in their corresponding system states,and state switch is achieved in a sequential manner.In the current system,imagination of left/right hand movement was translated into turning left/right in the virtual apartment continuously,while P300 potentials were mapped to discrete virtual device control commands using a five-oddball paradigm.The combination of motor imagery and P300 patterns in one BCI system for virtual environment control was tested and the results were compared with those of a single motor imagery or P300-based BCI.Subjects obtained similar performances in the hybrid and single control tasks,which indicates the hybrid control strategy works well in the virtual environment.

Energy Management Strategy for Hybrid Electric Vehicle Based on System Efficiency and Battery Life Optimization

A novel method to calculate fuel-electric conversion factor for full hybrid electric vehicle（HEV）equipped with continuously variable transmission（CVT）is proposed.Based on consideration of the efficiency of pivotal components,electric motor,system efficiency optimization models are developed.According to the target of instantaneous optimization of system efficiency,operating ranges of each mode of power-train are determined,and the corresponding energy management strategies are established.The simulation results demonstrate that the energy management strategy proposed can substantially improve the vehicle fuel economy,and keep battery state of charge（SOC）change in a reasonable variation range.

Hybrid Adaptive Event‑Triggered Platoon Control with Package Dropout

A novel hybrid adaptive event-triggered platoon control strategy is proposed to achieve the balanced coordination between communication resource utilization and vehicle-following performance considering the effect of package dropout.To deal with the disturbance caused by the event-triggered scheme,the parameter space approach is adopted to derive the feasible region from which cooperative adaptive cruise control controller satisfies internal stability,distance accuracy,and string stability.Subsequently,the Bernoulli random distribution process is employed to depict the phenomenon of package drop-out,and the hybrid coefficient is proposed to realize the allocation between the adaptive trigger threshold strategy and the adaptive headway strategy.The simulation of a six-vehicle platoon is carried out to verify the effectiveness of the designed control strategy.Results show that about 78.76%of communication resources have been saved by applying the event-triggered scheme,while guaranteeing the desired vehicle-following performance.And in the non-ideal communication environment with frequent package dropouts,the hybrid adaptive strategy achieves the coordination among communication resource utilization,string stability margin,distance accuracy,and traffic efficiency.

Distributed hybrid optimization for multi-agent systems

This paper addresses the distributed optimization problems of multi-agent systems using a distributed hybrid impulsive protocol.The objective is to ensure the agents achieve the state consensus and optimize the aggregate objective functions assigned for each agent with distributed manner. We establish two criteria related to the optimality condition and the impulsive gain upper estimation, and propose a distributed hybrid impulsive optimal protocol, which includes two terms: the local averaging term in the continuous interval and the term involving the gradient information at impulsive instants. The simulation results show that the optimal consensus can be realized under the distributed hybrid impulsive optimization algorithm.

Optimization management of hybrid energy source of fuel cell truck based on model predictive control using traffic light information

Energy optimization management can make fuel cell truck(FCT)power system more efficient,so as to improve vehicle fuel economy.When the structure of power source system and the torque distribution strategy are determined,the essence is to find the reasonable distribution of electric power between the fuel cell and other energy sources.The paper simulates the assistance of the intelligent transport system(ITS)and carries out the eco-velocity planning using the traffic signal light.On this basis,in order to further improve the energy efficiency of FCT,a model predictive control(MPC)-based energy source optimization management strategy is innovatively developed,which uses Dijkstra algorithm to achieve the minimization of equivalent hydrogen consumption.Under the scenarios of signalized intersections,based on the planned eco-velocity,the off-line simulation results show that the proposed MPC-based energy source management strategy(ESMS)can reduce hydrogen consumption of fuel cell up to 7%compared with the existing rule-based ESMS.Finally,the Hardware-in-the-Loop(HiL)simulation test is carried out to verify the effectiveness and real-time performance of the proposed MPC-based energy source optimization management strategy for the FCT based on eco-velocity planning with the assistance of traffic light information.

Estimation of distribution algorithm enhanced particle swarm optimization for water distribution network optimization

The optimization of a water distribution network （WDN） is a highly nonlinear, multi-modal, and constrained combinatorial problem. Particle swarm opti- mization （PSO） has been shown to be a fast converging algorithm for WDN optimization. An improved estimation of distribution algorithm （EDA） using historic best positions to construct a sample space is hybridized with PSO both in sequential and in parallel to improve population diversity control and avoid premature conver- gence. Two water distribution network benchmark exam- ples from the literature are adopted to evaluate the performance of the proposed hybrid algorithms. The experimental results indicate that the proposed algorithms achieved the literature record minimum （6.081 MS） for the small size Hanoi network. For the large size Balerma network, the parallel hybrid achieved a slightly lower minimum （1.921M） than the current literature reported best minimum （1.923MC）. The average number of evaluations needed to achieve the minimum is one order smaller than most existing algorithms. With a fixed, small number of evaluations, the sequential hybrid outperforms the parallel hybrid showing its capability for fast convergence. The fitness and diversity of the populations were tracked for the proposed algorithms. The track record suggests that constructing an EDA sample space with historic best positions can improve diversity control significantly. Parallel hybridization also helps to improve diversity control yet its effect is relatively less significant.

High Order Finite Difference Hermite WENO Fixed-Point Fast Sweeping Method for Static Hamilton-Jacobi Equations

In this paper, we combine the nonlinear HWENO reconstruction in [43] andthe fixed-point iteration with Gauss-Seidel fast sweeping strategy, to solve the staticHamilton-Jacobi equations in a novel HWENO framework recently developed in [22].The proposed HWENO frameworks enjoys several advantages. First, compared withthe traditional HWENO framework, the proposed methods do not need to introduceadditional auxiliary equations to update the derivatives of the unknown function φ.They are now computed from the current value of φ and the previous spatial derivatives of φ. This approach saves the computational storage and CPU time, which greatlyimproves the computational efficiency of the traditional HWENO scheme. In addition,compared with the traditional WENO method, reconstruction stencil of the HWENOmethods becomes more compact, their boundary treatment is simpler, and the numerical errors are smaller on the same mesh. Second, the fixed-point fast sweeping methodis used to update the numerical approximation. It is an explicit method and doesnot involve the inverse operation of nonlinear Hamiltonian, therefore any HamiltonJacobi equations with complex Hamiltonian can be solved easily. It also resolves someknown issues, including that the iterative number is very sensitive to the parameterε used in the nonlinear weights, as observed in previous studies. Finally, to furtherreduce the computational cost, a hybrid strategy is also presented. Extensive numerical experiments are performed on two-dimensional problems, which demonstrate thegood performance of the proposed fixed-point fast sweeping HWENO methods.