No abstract

Tuna resources are an important part of China’s pelagic fishery production. However, for China’s tuna fishery, tuna species caught at sea are still manually classified, which is a time-consuming and inefficient process, so China’s tuna fishery needs to develop towards automation. This study uses GLCM (gray level co-occurrence matrix) and VGG16 to visualize phenotypic texture through local images of three Thunnus species. At the same time, texture feature index data (TFD), deep feature data (DFD) and their combined feature data (CFD) are obtained from texture images. SVM with different kernel functions is used to classify phenotypic texture of tuna automatically. The study shows that visualized texture images of different tuna using GLCM and VGG16 have biological characteristics. In the classification results without cross-validation, the average classification accuracy of TFD in polynomial was 83%, the average classification accuracy of DFD in RBF was 93%, and the average classification accuracy of CFD in RBF was 95%. It is concluded that tuna phenotype texture can be efficiently classified by using SVM with different kernel functions.

We consider a standard splitting algorithm for the rare-event simulation of overflow probabilities in any subset of stations in a Jackson network at level n, starting at a fixed initial position. It was shown in [8] that a subsolution to the Isaacs equation guarantees that a subexponential number of function evaluations (in n) suffices to estimate such overflow probabilities within a given relative accuracy. Our analysis here shows that in fact O(n 2β V +1 ) function evaluations suffice to achieve a given relative precision, where βV is the number of bottleneck stations in the subset of stations under consideration in the network. This is the first rigorous analysis that favorably compares splitting against directly computing the overflow probability of interest, which can be evaluated by solving a linear system of equations with O(n d ) variables.

We consider a standard splitting algorithm for the rare-event simulation of overflow probabilities in any subset of stations in a Jackson network at level n, starting at a fixed initial position. It was shown in [8] that a subsolution to the Isaacs equation guarantees that a subexponential number of function evaluations (in n) suffices to estimate such overflow probabilities within a given relative accuracy. Our analysis here shows that in fact O(n 2β V +1 ) function evaluations suffice to achieve a given relative precision, where βV is the number of bottleneck stations in the subset of stations under consideration in the network. This is the first rigorous analysis that favorably compares splitting against directly computing the overflow probability of interest, which can be evaluated by solving a linear system of equations with O(n d ) variables.

Rare events in heavy-tailed systems are challenging to analyze using splitting algorithms because large deviations occur suddenly. So, every path prior to the rare event is viable and there is no clear mechanism for rewarding and splitting paths that are moving towards the rare event of interest. We propose and analyze a splitting algorithm for the tail distribution of a heavy-tailed random walk. We prove that our estimator achieves the best possible performance in terms of the growth rate of the relative mean squared error, while controlling the population size of the particles.