Prediction of chemical reproductive toxicity to aquatic species using a machine learning model: An application in an ecological risk assessment of the Yangtze River, China

A QSAR–ICE–SSD model prediction of the PNECs for alkylphenol substances and application in ecological risk assessment for rivers of a megacity

“…To further evaluate the consistency and predictive ability of the selected ICE models, the MSE cutoffs linked to cross- validation success rates of 70% and 60% were identified and were assumed to have high reliability and moderate reliability, respectively ( Fan et al, 2021 ). All MSE values were<0.95, ranged from 0.044 to 0.575.…”

“…Model predictions as used here for QSAR-ICE minimizes the use of experimental animals in toxicity experiments. The use of in silico methods to derive water quality criteria of pollutants is the future of water quality criteria development ( Bejarano et al, 2017 ; Dyer et al, 2008 ; Fan et al, 2021 ; Fan et al, 2019 ; Gredelj et al, 2018 ; Van den Berg et al, 2019 ). The application of QSAR-ICE models has recently expanded to include toxicity data for species native to China (about 60 native species of amphibians and fish), which can broaden application of QSAR- ICE models to be used to derive HC 5 for China ( He et al, 2017 ).…”

Market Risk Early Warning Based on Deep Learning and Fruit Fly Optimization

“…For the unbalanced classification samples, the Synthetic Minority Oversampling Technique (SMOTE) is used to deal with them from the data level [21]:…”

“…rough references [21,27,28], there are a total of 20 financial indicators selected as credit risk warning indicators of listed companies, including 6 first-level indicators such as enterprise operation capacity, growth capacity, profitability, and so on, and 20 second-level indicators such as total asset turnover rate, net asset growth rate, return on net asset, and so on. e indicators are listed in detail in Table 1.…”

Sports-Assisted Education Based on a Support Vector Machine and Genetic Algorithm

“…Among them, the test dataset contains 111 video frames with a resolution of 320 * 240 and a frame rate of 25 fps, and the competition dataset contains 396 video frames with a resolution of 720 * 480 and a frame rate of 29 fps. KTH, Weizmann, and UCF-Sport datasets, which are commonly used for human motion pose recognition, are selected as experimental data [19,20] Mathematical Problems in Engineering removed in this experiment. Taking the KTH dataset as an example, we first calculate the area of the motion target silhouette area in each frame of a video, set 1/2 of the maximum area value as the threshold value, and then classify the video frames smaller than the threshold value as invalid video for deletion processing.…”