There has been relatively little emphasis on describing the common features that are important if an algorithm is to have good performance. This paper describes the key features, with particular emphasis on alg
One example in Excel is how it determines what to paint on the screen after some arbitrary edit. It starts with a known top-left cell and then can incrementally walk through the column widths and row heights until the screen is filled. This algorithm scales with the size of the screen (w...
(2001), thismachine learning methodenables prediction and interpretation of data on computers. The GBDT is an iterative decision tree algorithm that is widely used in rail transit passenger flow prediction and the influence mechanism of metro stations on the built environment and traffic efficiency (...
3.2. NMR inversion algorithm The important step of NMR data processing is to extract T2 relaxation time distribution from the measurement data using Eq. (21). Generally, Eq. (21) can be written as the matrix form: M=Af+r (r denotes the fitting error), and the solution of the equation...
Let a fuzzy quality characteristic expressed as multiple levels {good, general, bad, very bad}; each term set corresponds to a fuzzy function μ (x). Fuzzy functions are expressed by trapezoidal membership functions. If other types of fuzzy functions are selected, the processing methods are ...
It is known for its fast execution speed and good convergence of solution sets and is often used as a benchmark for the performance of other algorithms31. Previous research has shown the potential of the NSGA-II algorithm for CFRP layup optimization32. Sun et al. used the NSGA-II ...
Wu et al.22 investigated the creep and mechanical properties of cemented waste rock backfill (CWRB). They used the Burgers model to characterize the creep behavior of the backfill material, validated the creep model using a genetic algorithm, and investigated the effect of the creep behavior ...
Specifically, the ensemble algorithm demonstrated an AUC of 0.94, accuracy of 0.87, precision of 0.74, recall of 0.87, F1-score of 0.80, sensitivity of 0.87, specificity of 0.88, PPV of 0.74, and NPV of 0.94 in the training cohort. In the validation cohort, the ensemble algorithm maintained...
Goupee and Senthil [6] proposed a genetic algorithm methodology to optimize the natural frequencies of functionally graded structures by tailoring their material distribution for three model problems. In the first problem, the material distributions that maximize each of the first three natural ...
A 7 × 7 convolution filter was applied to the 38 and 120 kHz clean echosounder data from below the surface exclusion (mean depth = 10 m) to a maximum depth of 250 m. The shoal analysis and patch estimation system (SHAPES58) algorithm implemented in Echoview was run on...