The prediction of security risk is a new problem in the field of *** value of food safety risk is dynamic,non-linear and *** order to improve the prediction accuracy of non-stationary sequences,this paper proposes an ...
详细信息
The prediction of security risk is a new problem in the field of *** value of food safety risk is dynamic,non-linear and *** order to improve the prediction accuracy of non-stationary sequences,this paper proposes an improved time series prediction model of bidirectional long short-term memory network based on NSADAM optimization *** using NS-ADAM optimization algorithm,the non-stationary series can be approximately regarded as stationary series in a fixed window *** with the advantages of two-way long-term and short-term network model to strengthen the correlation between current data and historical data,the combined network model significantly improves the prediction accuracy of non-stationary time *** experimental results show that compared with the traditional integrated moving average autoregressive model and the conventional long-term and short-term memory network model,the improved model has higher prediction accuracy and better fitting effect for non-stationary series.
Cyberbullying has emerged as a serious societal and public health problem that demands accurate methods for the detection of cyberbullying instances in an effort to mitigate the consequences. While techniques to autom...
详细信息
ISBN:
(纸本)9781538646595
Cyberbullying has emerged as a serious societal and public health problem that demands accurate methods for the detection of cyberbullying instances in an effort to mitigate the consequences. While techniques to automatically detect cyberbullying incidents have been developed, the scalability and timeliness of existing cyberbullying detection approaches have largely been ignored. We address this gap by formulating cyberbullying detection as a sequential hypothesis testing problem. Based on this formulation, we propose a novel algorithm designed to reduce the time to raise a cyberbullying alert by drastically reducing the number of feature evaluations necessary for a decision to be made. We demonstrate the effectiveness of our approach using a real-world dataset from Twitter, one of the top five networks with the highest percentage of users reporting cyberbullying instances. We show that our approach is highly scalable while not sacrificing accuracy for scalability.
Backgroud: Constraint-based flux analysis have been widely used in metabolic engineering to predict genetic optimization *** methods seek to find genetic manipulations that maximally couple the desired metabolite with...
详细信息
Backgroud: Constraint-based flux analysis have been widely used in metabolic engineering to predict genetic optimization *** methods seek to find genetic manipulations that maximally couple the desired metabolite with the cellular growth ***, such framework does not work well for overproducing chemicals that are not closely connected with biomass, for example non-native biochemical production by introducing synthetic pathways into heterologous host cells.
In the process of rotation, the total weight of the bridge structure is jointly supported by the spherical hinge and the supporting structure, and its lateral stability is poor. It is easy to lose stability under the ...
详细信息
In the process of rotation, the total weight of the bridge structure is jointly supported by the spherical hinge and the supporting structure, and its lateral stability is poor. It is easy to lose stability under the action of dynamic loads such as seismic action effect. The present paper takes a 10,000-ton continuous rigid frame swivel bridge as the re-search object, analyzes the dynamic response of the seismic action to the horizontal swivel system and establishes several structure simulation models. Eighteen seismic waves in three directions that meet the calculation requirements are screened for time history analysis and compared with the response spectrum method. Finally, an optimization algorithm for the seismic response of the bridge under horizontal swivel system is proposed based on the mode superposition method. The UHPC spherical hinge bears all the vertical forces and 20% of the bending moment caused by the seismic action, the support structure bearing the remaining 80% of the bending moment. The optimization algorithm proposed in this paper features high accuracy.
Network planning technology could be used to represent project plan management,such Critical Path Method(CPM for short) and Performance Evaluation Review Technique(PERT for short) *** at problem that how to find hypo-...
详细信息
Network planning technology could be used to represent project plan management,such Critical Path Method(CPM for short) and Performance Evaluation Review Technique(PERT for short) *** at problem that how to find hypo-critical path in network planning,firstly,properties of total *** float and safety float are analyzed,and total float theorem is deduced on the basis of above analysis;and secondly,simple algorithm of finding the hypo-critical path is designed by using these properties of float and total theorem,and correctness of the algorithm is analyzed. Proof shows that the algorithm could realize effect of whole optimization could be realized by part ***,one illustration is given to expatiate the algorithm.
In this paper a new optimization algorithm is proposed for optimal planning of the Distributed generation (DG's) with renewable bus available limit constraint. Distribution system objectives considered for optimiz...
详细信息
ISBN:
(纸本)9781479931026
In this paper a new optimization algorithm is proposed for optimal planning of the Distributed generation (DG's) with renewable bus available limit constraint. Distribution system objectives considered for optimization are Active and reactive power losses minimization, bus voltage profile improvement, and line flow capacity limits. Power system modeled Distributed generations such as wind, solar and fuel cell and some artificial models like micro turbines are used to study the proposed algorithm. To optimize the objective function with voltage limits and renewable DG bus available limit constraints, Shuffled Bat algorithm (ShBAT) is proposed and compared with Genetic algorithm (GA) and Bat algorithm (Bat). 84-bus distribution system testing with proposed algorithm is presented with results.
As an important energy source, lithium-ion batteries have vast applications in daily production and life. Therefore, the life prediction of such batteries is of great significance, which can help us maintain the effic...
详细信息
As an important energy source, lithium-ion batteries have vast applications in daily production and life. Therefore, the life prediction of such batteries is of great significance, which can help us maintain the efficacy and reliability of the system powered by lithium-ion batteries. In this paper, a hybrid battery model and an improved particle filter（PF） are developed to better estimate the remaining useful life（RUL） of lithium-ion battery. Firstly, a hybrid model is constructed as the degradation model of the battery. The developed hybrid model is a combination of the empirical battery model and neural network model such that it could characterize both the internal mechanism of the battery and the change of external environment in a more accurate ***, the beetle antennae search（BAS） based PF（BAS-PF） is utilized to compute the battery parameters online based on the proposed hybrid model. Compared with the existing PF based method, BAS-PF can well handle the problem of diversity loss and improve the estimation accuracy. Finally, the battery data set published by NASA is used as the experiment *** show that the proposed hybrid model can well represent the internal and external changes of the battery, and the BAS-PF based method has a great improvement in the estimation accuracy. Those results illustrate that the developed technique could achieve an improved life prediction for lithium-ion batteries.
In this paper, a new method is presented for double nonlinear analysis of the simply-supported beam with elastic-perfectly plastic model. The major character of the new method is that the equilibrium state with elasti...
详细信息
In this paper, a new method is presented for double nonlinear analysis of the simply-supported beam with elastic-perfectly plastic model. The major character of the new method is that the equilibrium state with elastic-plastic large deformation is chosen as the study object. The constitutive law adopts elastic-perfectly plastic model and the shearing deformation is taken into account. The endpoint coordinates are given by means of coordinate recursion formulae, and the objective function is defined by unknown endpoint coordinates of slight segments. The optimization problem is established for double nonlinear analysis of the simply-supported beam, and the optimization program is programmed. Typical numerical examples are calculated by optimization algorithm, and the results are in very good agreement with those by FEM. So this paper provides a new and effective idea for double nonlinear problem of the simply-supported beam.
In order to meet the urgent needs of upgrading the coal industry, energy exploitation of abandoned coal mines which may be rich in water resources and renewable resources brooks no delay. At present, the framework des...
详细信息
In order to meet the urgent needs of upgrading the coal industry, energy exploitation of abandoned coal mines which may be rich in water resources and renewable resources brooks no delay. At present, the framework design and simple energy flow analysis for the reuse of abandoned coal mine resources have been basically formed. However, profound studies on the complex interaction behavior and the coordinated optimal scheduling of the integrated power grid-abandoned coal mine energy system (IPGACMES) with distributed renewable energy and underground pumped hydro energy storage (UPHES) are still lacking. In this paper, a novel multi-objective optimal coordinated scheduling model of IPGACMES is proposed aiming to achieve the lowest operation cost and the minimal carbon emissions. Especially, load balance constraint as well as operation constraints of thermal units, wind/PV units, UPHES, power-to-gas (P2G), power to hydrogen (P2H) and hydrogen fuel cells (HFC) are all considered. Different case studies have been carried out to illustrate the feasibility and effectiveness of the presented optimal scheduling model. Better economic and environmental benefits are achieved in terms of a 3.52 % decline in operation cost and a 4.58 % reduction in carbon emissions. In addition, the renewable energy curtailment is decreased 83.7% whereby the use of P2G and P2H units.
This study aims to create a highly effective system for classifying email spam, with the key objective of improving performance and accuracy in classification. Rigorous pre-processing techniques, including lemmatizati...
详细信息
暂无评论