Facial beauty prediction (FBP) is a burgeoning issue for attractiveness evaluation, which aims to make assessment consistent with human opinion. Since FBP is a regression problem, to handle this issue, there are data-driven methods for finding the relations between facial features and beauty assessment. Recently, deep learning methods have shown its amazing capacity for feature representation and analysis. Convolutional neural networks (CNNs) have shown tremendous performance on facial recognition and comprehension, which are proved as an effective method for facial feature exploration. Lately, there are well-designed networks with efficient structures investigated for better representation performance. However, these designs concentrate on the effective block but do not build an efficient information transmission pathway, which led to a sub-optimal capacity for feature representation. Furthermore, these works cannot find the inherent correlations of feature maps, which also limits the performance. In this paper, an elaborate network design for FBP issue is proposed for better performance. A residual-in-residual (RIR) structure is introduced to the network for passing the gradient flow deeper, and building a better pathway for information transmission. By applying the RIR structure, a deeper network can be established for better feature representation. Besides the RIR network design, an attention mechanism is introduced to exploit the inner correlations among features. We investigate a joint spatial-wise and channel-wise attention (SCA) block to distribute the importance among features, which finds a better representation for facial information. Experimental results show our proposed network can predict facial beauty closer to a human’s assessment than state-of-the-arts.

The vibration and sound signals get widely applications in fault diagnosis of rolling bearing systems, but the detection accuracy is unstable at different measuring positions. This paper puts forward a two-step vibration-sound signal fusion method, in which sound signal fusion and vibration-sound signal fusion are executed respectively. The sound signals are fused through weighting to the vibration signal to reduce the influence by measuring positions, and the phase difference is eliminated by a sliding window on the time axis. Then a second fusion between the vibration signal and sound signal is conducted after normalization and superposition, and the performance of two-step fusion is compared with the existing direct fusion. Results show that the two-step fusion provides a larger signal-to-noise ratio, and the amplitudes of characteristic frequencies are also higher. A cascaded bistable stochastic resonance system is applied in the post-processing of the fusion signal to make the signal features more clear, and it is proved that the fault detection effect has an obvious improvement after the whole process. This method provides a new approach for weak fault feature detection in vibration and sound signals, and is of great significance for the maintenance of rolling bearing systems.

No abstract

Single image super-resolution (SISR) is a traditional image restoration problem. Given an image with low resolution (LR), the task of SISR is to find the homologous high-resolution (HR) image. As an ill-posed problem, there are works for SISR problem from different points of view. Recently, deep learning has shown its amazing performance in different image processing tasks. There are works for image super-resolution based on convolutional neural network (CNN). In this paper, we propose an adaptive residual channel attention network for image super-resolution. We first analyze the limitation of residual connection structure and propose an adaptive design for suitable feature fusion. Besides the adaptive connection, channel attention is proposed to adjust the importance distribution among different channels. A novel adaptive residual channel attention block (ARCB) is proposed in this paper with channel attention and adaptive connection. Then, a simple but effective upscale block design is proposed for different scales. We build our adaptive residual channel attention network (ARCN) with proposed ARCBs and upscale block. Experimental results show that our network could not only achieve better PSNR/SSIM performances on several testing benchmarks but also recover structural textures more effectively.

For the multiple automated guided vehicle (multi-AGV) routing problems in the warehousing link of logistics, where the optimization objective is to minimize both the number of AGVs used and the maximum pickup time simultaneously, a nondominant sorting differential evolution (NSDE) algorithm is proposed. In the encoding and decoding stages, the pickup point area is divided. AGVs are allocated to each region according to the proposed rule based on avoiding duplicate paths. Meanwhile, the pickup points within the region can be adjusted to optimize the pickup paths and improve the pickup efficiency. The fast nondominated sorting method and elitist selection strategy in the nondominated sorting genetic algorithm II (NSGA-II) are introduced into the differential evolution algorithm, which sorts all the regions to obtain the best Pareto solution set. Lastly, the domination of the proposed NSDE algorithm in Pareto frontier evaluation indicators is verified by some numerical experiments.