Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.     

Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

IRS辅助的SWIPT系统中基于能效优先的波束成形设计与优化

以智能反射面(intelligent reflecting surface,IRS)辅助的无线携能通信(simultaneous wireless information and power transfer,SWIPT)系统为背景,研究了该系统中基于能效优先的多天线发送端有源波束成形与IRS无源波束成形联合设计与优化方法。以最大化接收端的最小能效为优化目标,构造在发送端功率、接收端能量阈值、IRS相移等多约束下的非线性优化问题,用交替方向乘子法(alternating direction method of multipliers,ADMM)求解。采用Dinkelbach算法转化目标函数,通过奇异值分解(singular value decomposition,SVD)和半定松弛(semi-definite relaxation,SDR)得到发送端有源波束成形向量。采用SDR得到IRS相移矩阵与反射波束成形向量。结果表明,该系统显著降低了系统能量收集(energy harvesting,EH)接收端的能量阈值。当系统总电路功耗为?15 dBm时,所提方案的用户能效为300 KB/J。当IRS反射阵源数与发送天线数均为最大值时,系统可达最大能效。     

Robust optical flow estimation via edge preserving filtering

It is known that optical flow estimation techniques suffer from the issues of ill-defined edges and boundaries of the moving objects. Traditional variational methods for optical flow estimation are not robust to handle these issues since the local filters in these methods do not hold the robustness near the edges. In this paper, we propose a non-local total variation NLTV-$L^1$ optical flow estimation method based on robust weighted guided filtering. Specifically, first, the robust weighted guided filtering objective function is proposed to preserve motion edges. The proposed objective function is based on the linear model which is computationally efficient and edge-preserving in complex natural scenarios. Second, the proposed weighted guided filtering objective function is incorporated into the non-local total variation NLTV-$L^1$ energy function. Finally, the novel NLTV-$L^1$ optical flow method is performed using the coarse-to-fine process. Additionally, we modify some state-of-the-art variational optical flow estimation methods by the robust weighted guided filtering objective function to verify the performance on Middlebury, MPI-Sintel, and Foggy Zurich sequences. Experimental results show that the proposed method can preserve edges and improve the accuracy of optical flow estimation compared with several state-of-the-art methods.     

Rapid screening of DON contamination in whole wheat meals by Vis/NIR spectroscopy and computer vision coupling technology

This work intends to develop an online experimental system for screening of deoxynivalenol (DON) contamination in whole wheat meals by visible/near-infrared (Vis/NIR) spectroscopy and computer vision coupling technology. Spectral and image information of samples with various DON levels was collected at speed of 0.15 m s⁻¹ on a conveyor belt. The two-type data were then integrated and subjected to chemometric analysis. Discriminant analysis showed that samples could be classified by setting 1000 μg kg⁻¹ as the cut-off value. The best correct classified rate obtained in prediction was 93.55% based on fusion of spectral and image features, with reduced prediction uncertainty as compared to single feature. However, quantification of DON by quantitative analysis was not successful due to poor model performance. These results indicate that, although not accurate enough to provide conclusive result, this coupling technology could be adopted for rapid screening of DON contamination in cereals and feeds during processing.     

Distributed two‐stage state estimation with event‐triggered strategy for multirate sensor networks

This paper investigates the state estimation issue for a class of wireless sensor networks (WSNs) with the consideration of limited energy resources. First, a multirate estimation model is established, and then, a new event‐triggered two‐stage information fusion algorithm is developed based on the optimal fusion criterion weighted by matrices. Compared with the existing methods, the presented fusion algorithm can significantly reduce the communication cost in WSNs and save energy resources of sensors efficiently. Furthermore, by presetting a desired containment probability over the interval [0,1] with the developed event‐triggered mechanism, one can obtain a suitable compromise between the communication cost and the estimation accuracy. Finally, a numerical simulation for the WSN tracking system is given to demonstrate the effectiveness of the proposed method.     

基于数据运营安全的个人信息保护

个人信息因其自身携带隐私特性,与每个个体息息相关。个人信息保护不当,影响公众权益、企业利益以及社会秩序。在互联网、大数据、5G万物互联的时代,个人信息被广泛收集和使用,必须妥善解决个人信息保护问题,才能保障整个数据产业健康发展。而现有的个人信息保护方法或技术,不足以应对新形势下的保护诉求。基于数据运营安全的个人信息保护,针对当前个人信息保护的新形势和新诉求,提出结合人工智能,通过数据运营安全对结构化、半结构化、非结构化的个人信息流动的保护,涵盖从生产到运维,从采集、传输、存储、处理、分析、共享、销毁全生命周期保护,深入数据运营中内嵌防护,同时与业务解耦,达到保护个人信息安全的目标。     

A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

A double laser filtering approach to vibration noise rejection for hot-rolled strip flatness measurement

This paper proposes a new filtering method based on the Kalman filtering algorithm for hot-rolled strip flatness measurement system. The system involves processing slowly changing signal, which can be considered as a bounded random process, and its model parameters are completely unknown. The noise rejection strategy in double lasers can generate a compensation signal. Since the initial and accumulative error would lead to negative filter effect or even cause divergence, Kalman filter is integrated to effectively deal with the initial error and enhance convergence. In this setting, the noise rejection strategy is used as a prediction model to constitute a similar Kalman filter. The correlated error caused by measurement error is coped with by a compensation model based on the feature of correlated error to enhance the filter effect. Both theoretical analysis and simulations show that the new algorithm has a better filter effect than the traditional Kalman filtering algorithm for the system.     

Training visual attention in a naturalistic visual environment

The efficiency of training visual attention in the central and peripheral visual field was investigated by means of a visual detection task that was performed in a naturalistic visual environment including numerous, time-varying visual distractors. We investigated the minimum number of repetitions of the training required to obtain the top performance and whether intra-day training improved performance as efficiently as inter-day training. Additionally, our research aimed to find out whether exposure to a demanding task such as a microsurgical intervention may cancel out the effects of training.

Results showed that performance in visual attention peaked within three (for tasks in the central visual field) to seven (for tasks in the periphery) days subsequent to training. Intra-day training had no significant effect on performance. When attention training was administered after exposure to stress, improvement of attentional performance was more pronounced than when training was completed before the exposure. Our findings support the implementation of training in situ at work for more efficient results.

Practitioner Summary: Visual attention is important in an increasing number of workplaces, such as with surveillance, inspection, or driving. This study shows that it is possible to train visual attention efficiently within three to seven days. Because our study was executed in a naturalistic environment, training results are more likely to reflect the effects in the real workplace.