Software quality evaluation is a challenging task in software engineering. A new group decision-making evaluation model is presented in this work. The new model is based on the Vlsekriterijumska optimizacija i KOmpromisno Resenje (VIKOR) technique, in which a group regret measurement and a group satisfaction measurement are provided to increase the number of reference criteria in the decision-making process. We choose the median to represent the center of the data. Based on this, an entropy-based weighting method is proposed and used to determine the weights of decision makers. A new normalized projection is explored to measure the closeness between two evaluation matrices in a Pythagorean fuzzy setting. Several experimental analyses demonstrate that the entropy-based weighting method developed in this study is superior to traditional weighting methods. The median-based data center provides support for stable decision outcomes. Four dynamic experiments are reported on in this paper: The first one shows that the decision results remain stable throughout the entire experimental range; the second one demonstrates that the proposed normalized projection measure outperforms traditional projection measure; the third one demonstrates that the newly developed VIKOR method outperforms the traditional VIKOR method; and the last one identifies the optimal range for the three parameters of the proposed comprehensive VIKOR model.

Although Convolutional Neural Networks (CNNs) have achieved remarkable success in image classification, most CNNs use image datasets in the Red-Green-Blue (RGB) color space (one of the most commonly used color spaces). The existing literature regarding the influence of color space use on the performance of CNNs is limited. This paper explores the impact of different color spaces on image classification using CNNs. We compare the performance of five CNN models with different convolution operations and numbers of layers on four image datasets, each converted to nine color spaces. We find that color space selection can significantly affect classification accuracy, and that some classes are more sensitive to color space changes than others. Different color spaces may have different expression abilities for different image features, such as brightness, saturation, hue, etc. To leverage the complementary information from different color spaces, we propose a pseudo-Siamese network that fuses two color spaces without modifying the network architecture. Our experiments show that our proposed model can outperform the single-color-space models on most datasets. We also find that our method is simple, flexible, and compatible with any CNN and image dataset.