No abstract

Deep learning models have achieved success in image recognition and have shown great potential for interpretation of ground penetrating radar (GPR) data. However, training reliable deep learning models requires massive labeled data, which are usually not easy to obtain due to the high costs of data acquisition and field validation. This paper proposes an improved least square generative adversarial networks (LSGAN) model which employs the loss functions of LSGAN and convolutional neural networks (CNN) to generate GPR images. This model can generate high-precision GPR data to address the scarcity of labelled GPR data. We evaluate the proposed model using Frechet Inception Distance (FID) evaluation index and compare it with other existing GAN models and find it outperforms the other two models on a lower FID score. In addition, the adaptability of the LSGAN-generated images for GPR data augmentation is investigated by YOLOv4 model, which is employed to detect rebars in field GPR images. It is verified that inclusion of LSGAN-generated images in the training GPR dataset can increase the target diversity and improve the detection precision by 10%, compared with the model trained on the dataset containing 500 field GPR images.

No abstract

No abstract

In mobile phone supply chains, consumers can choose handsets and telecommunication services as a bundled package or buy handsets and services independently. This article develops a multi-agent simulation model to explore price, subsidy and bundling decisions for competing mobile phone supply chains with network externality, where each chain includes one mobile phone manufacturer and one service operator. There are two bundling strategies: free or bundled. The results indicate that: 1) if the impact of network externality is not too small, then competitive differentiation can be formed when one party adopts a bundled one. If bundled scenario is adopted by both, the total profit is reduced. Consequently, both service operators and manufacturers choose (accept) different bundling strategies; 2) network externality and consumer heterogeneity both increase the advantage of bundled scenario in the asymmetric setting; 3) when the effect of network externality is sufficiently small, free scenario is dominant; and 4) consumer heterogeneity can alleviate competition in the symmetric settings.