AbstractConvolutional neural networks (CNNs) are a branch of deep learning which have been turned into one of the popular methods in different applications, especially medical imaging. One of the significant applications in this category is to help specialists make an early detection of skin cancer in dermoscopy and can reduce mortality rate. However, there are a lot of reasons that affect system diagnosis accuracy. In recent years, the utilization of computer-aided technology for this purpose has been turned into an interesting category for scientists. In this research, a meta-heuristic optimized CNN classifier is applied for pre-trained network models for visual datasets with the purpose of classifying skin cancer images. However there are different methods about optimizing the learning step of neural networks, and there are few studies about the deep learning based neural networks and their applications. In the present work, a new approach based on whale optimization algorithm is utilized for optimizing the weight and biases in the CNN models. The new method is then compared with 10 popular classifiers on two skin cancer datasets including DermIS Digital Database Dermquest Database. Experimental results show that the use of this optimized method performs with better accuracy than other classification methods.

The experiment adopted the method of cultivating Hydrilla verticillata and algae in coexistence systems to study the inhibitory effect of Hydrilla verticillata on planktonic algae in eutrophic water. The results showed that allelopathic and competition of nutrition inhibitory effect were both affect the inhibition of Hydrilla verticillata on planktonic algae at initial concentration of 105 cells·mL-1, and the highest inhibition ratio on was 79% at undernutrition condition; opposite, allelopathic inhibitory effect played a major role at nutritional sufficiency, the highest inhibition ratio was 39%. Hydrilla verticillata played a role of “promoting with low biomass while inhibiting with high biomass” on planktonic algae, the optimal biological dosage of Hydrilla verticillata on inhibiting planktonic algae at initial concentration of 105 cells·mL-1 was 12g·L-1. Hydrilla verticillata allproduced inhibitory effect on planktonic algae at different initial concentrations, and the greater the initial concentration of planktonic algae, the higher the inhibition ratio of Hydrilla verticillata on planktonic algae.

No abstract