Electricity price is a key influencer in the electricity market. Electricity market trades by each participant are based on electricity price. The electricity price adjusted with the change in supply ...and demand relationship can reflect the real value of electricity in the transaction process. However, for the power generating party, bidding strategy determines the level of profit, and the accurate prediction of electricity price could make it possible to determine a more accurate bidding price. This cannot only reduce transaction risk, but also seize opportunities in the electricity market. In order to effectively estimate electricity price, this paper proposes an electricity price forecasting system based on the combination of 2 deep neural networks, the Convolutional Neural Network (CNN) and the Long Short Term Memory (LSTM). In order to compare the overall performance of each algorithm, the Mean Absolute Error (MAE) and Root-Mean-Square error (RMSE) evaluating measures were applied in the experiments of this paper. Experiment results show that compared with other traditional machine learning methods, the prediction performance of the estimating model proposed in this paper is proven to be the best. By combining the CNN and LSTM models, the feasibility and practicality of electricity price prediction is also confirmed in this paper.
This paper focuses on the study of continuous age-structured models, or more general, physiologically structured models, which used for detailed and accurate study of population dynamics in many ...ecological, biological applications and medicine. In contrast to simpler unstructured models, these models allow us to relate the individual life-histories described as fertility and mortality rates of an individual at a given age with population dynamics. Depending from the particularity of reproduction mechanism continuous age-structured models are divided into monocyclic (reproduction occurs only at the one fixed age of individuals) and polycyclic (reproduction occurs with age-dependent probability at some age reproductive window) models. The linear monocyclic age-structured models are used often in cell cycles modelling, in population dynamics of plants, etc. In this case continuous age-structured models allow for obtaining the exact analytical solution. Since the linear and non-linear polycyclic age-structured models are more general then monocyclic models, they coverwider range of applications in life science. But in this case solution of model can be obtained only in the form of recurrent formulae and can be used only in numerical algorithms. Both solutions obtained in this work allow us to study numerically the important dynamical regimes population outbreaks of three types: oscillations with large magnitude, pulse sequence and single pulse. Thus, analysis of continuous age-structured models of population dynamics provides insight into features and particularities of complex dynamical regimes of populations in many applications in biology, ecology and medicine.
Brucellosis is a highly contagious zoonosis in the world caused by a group of bacteria from the genus brucella. It can infect both human and animals through eating contaminated food, breathing ...polluted air, and direct contact of the infected animals. The number of onset cases shows an increase tend in recent years, mainly in pastures and farms. To investigate the dynamics of brucellosis and capture the event of its spread, we propose a novel model that is an attempt for the first time ever to incorporate with both age-since-infection and spacial diffusion of the infection. We first analytically study the existence and uniqueness of the solution of the model, followed by positivity of the solutions. The location dependent reproduction number R(x) is explicitly calculated by a renewal process and the basic reproduction number R0 is defined by the spectral radius of R(x). The calculation method is novel and simple. It is shown that when R0<1 the infectious disease will die out; when R0>1 the disease will be prevalent. Parameter sensitivity analysis on the expression of R0 shows that certain parameters are more effective to impact the value of R0. Based on this analysis and our intensive numerical simulations, we recommend that the herdsmen should make efforts to keep the living environment of their animals clean, and eliminate infectious animals timely.
•We firstly propose a novel age–space structured brucellosis epidemic model.•We calculate an explicit formulation for the next generator operator R(x) by the renewal equation.•We give a general method to estimate the weighted coefficients for constructing Lyapunov functionals.•We show some effectively control strategies for herdsman by uncertainty analysis.
•This study suggested the discrete time age-structured model of hairtail in Korea Sea.•By using data for hairtail in Korea, the estimation of parameters were performed.•Sea surface temperature in the ...future was forecasted by wavelet-ARIMA method.•We investigated an optimal harvesting strategy for hairtail in the future.
Hairtail, Trichiurus Lepturus, is the major fishery resource in Korea and so has been occupying a large portion of total catches for a longtime. However, since the 1980s, the catch has fallen sharply. A climatic change and over-fishing of immature hairtails have decreased the resource in Korea Sea, which caused reduction in the catch. So, we should analyze this phenomenon and need to manage them. Thus, in this study, we first propose a discrete time age-structured model of hairtails from their biological features. Especially, since hairtail is the representative fish with characteristics of cannibalism in the marine ecosystem, we set the recruitment as Ricker type. Furthermore, for the environmental effect on its spawning, the sea surface temperature in the spawning ground is included in the model. Next, we find an optimal harvesting strategy for preserving the immature hairtails while simultaneously maximizing the corresponding profit of the fishing. The discrete-time optimal control problem is conducted as the extension of Pontryagin’s Maximum Principle to discrete system. Moreover, to suggest the optimal harvesting strategy in the future, the forecast of sea surface temperature should be accompanied. This is carried out by wavelet-ARIMA forecasting method. By using numerical simulations, we obtain that in the perspective of conservation, the limited fishing is the best for management of hairtails. On the other hand, in terms of balance between the conservation and economic profits, the optimal harvesting strategy is better than the limited fishing.
Microbially induced calcite precipitation (MICP) has applications in self-healing concrete, soil consolidation and bio-grouting. Development of models of processes involved in MICP is a step towards ...gaining mechanistic insights and building reliable predictive models of MICP. This work deals with understanding the reactions and transport processes involved in ureolysis mediated calcite precipitation in Sporosarcina pasteurii (S. pasteurii). Particularly, a simple structured model that describes urea uptake, ureolysis, ammonium assimilation and ammonium excretion processes is developed. The structured model describes extra-cellular processes like transport processes and important intra-cellular reactions involved in ureolysis. The model parameters are estimated using measured concentrations of extracellular and intracellular metabolites during experiments. In this work, The maximum specific growth rate and yield coefficient of S. pasteurii are found to be 0.78 d−1 and 4.93 gDW/g, respectively. The maximum urease activity of 1.79 μmoles/min/gDW biomass was observed during the fourth day of growth when grown in minimal media. It is shown that the urea uptake can be described by a first-order kinetics suggesting active transport. The estimated parameter of rate constant of first-order kinetics is 9.8 × 10−2d−1. On the other hand, the ammonium ion excretion takes place through free diffusion. The estimated parameter of permeability coefficient for ammonium ion diffusion is 9.2 × 10−3 m d−1.
•The developed structured kinetic model describes extra-and intra-cellular processes in ureolysis.•Urea uptake is described by first-order kinetics.•Ammonium ion excretion is described by passive transport.•The standard ureolysis stoichiometry is not followed by Sporosarcina pasteurii.•Urease activity of Sporosarcina pasteurii may be inducible.
We consider a (degenerate) cross-diffusion model of tumour growth structured by phenotypic trait. We prove the existence of weak solutions and the incompressible limit as the pressure becomes stiff ...extending methods recently introduced in the context of two-species cross-diffusion systems. In the stiff-pressure limit, the compressible model generates a free boundary problem of Hele-Shaw type. Moreover, we prove a new L
4
-bound on the pressure gradient.
Human behaviors in recommendation systems are driven by many high-level, complex, and evolving intentions behind their decision making processes. In order to achieve better performance, it is ...important for recommendation systems to be aware of user intentions besides considering the historical interaction behaviors. However, user intentions are seldom fully or easily observed in practice, so that the existing works are incapable of fully tracking and modeling user intentions, not to mention using them effectively into recommendation. In this paper, we present the I ntention-Aware S equential Rec ommendation ( ISRec ) method, for capturing the underlying intentions of each user that may lead to her next consumption behavior and improving recommendation performance. Specifically, we first extract the intentions of the target user from sequential contexts, then take complex intent transition into account through the message-passing mechanism on an intention graph, and finally obtain the future intentions of this target user from inference on the intention graph. The sequential recommendation for a user will be made based on the predicted user intentions, offering more transparent and explainable intermediate results for each recommendation. Extensive experiments on various real-world datasets demonstrate the superiority of our method against several state-of-the-art baselines in sequential recommendation in terms of different metrics.
Anthropogenic activities such as mining and the metallurgical industry are the main sources of mercury contamination. Mercury is one of the most serious environmental problems in the world. This ...study aimed to investigate, using experimental kinetic data, the effect of different inorganic mercury (Hg2+) concentrations on the response of microalga Desmodesmus armatus stress. Cell growth, nutrients uptake and mercury ions from the extracellular medium, and oxygen production were determined. A Compartment Structured Model allowed elucidating the phenomena of transmembrane transport, including influx and efflux of nutrients, metal ions and bioadsorption of metal ions on the cell wall, which are difficult to determine experimentally. This model was able to explain two tolerance mechanisms against mercury, the first one was the adsorption of Hg2+ions onto the cell wall and the second was the efflux of mercury ions. The model predicted a competition between internalization and adsorption with a maximum tolerable concentration of 5.29 mg/L of HgCl2. The kinetic data and the model showed that mercury causes physiological changes in the cell, which allow the microalga to adapt to these new conditions to counteract the toxic effects. For this reason, D. armatus can be considered as a Hg-tolerant microalga. This tolerance capacity is associated with the activation of the efflux as a detoxification mechanism that facilitates the maintenance of the osmotic balance for all the modeled chemical species. Furthermore, the accumulation of mercury in the cell membrane suggests the presence of thiol groups associated with its internalization, leading to the conclusion that metabolically active tolerance mechanisms are dominant over passive ones.