Optical nonlinearity impairments have been a major obstacle for high-speed, long-haul and large-capacity optical transmission. In this paper, we propose a novel convolutional neural network (CNN)-based perturbative nonlinearity compensation approach in which we reconstruct a feature map with two channels that rely on first-order perturbation theory and build a classifier and a regressor as a nonlinear equalizer. We experimentally demonstrate the CNN equalizer in 375 km 120-Gbit/s dual-polarization 64-quadrature-amplitude modulation (64-QAM) coherent optical communication systems. We studied the influence of the dropout value and nonlinear activation function on the convergence of the CNN equalizer. We measured the bit-error-ratio (BER) performance with different launched optical powers. When the channel size is 11, the optimum BER for the CNN classifier is 0.0012 with 1 dBm, and for the CNN regressor, it is 0.0020 with 0 dBm; the BER can be lower than the 7 $\%$ hard decision-forward threshold of 0.0038 from −3 dBm to 3 dBm. When the channel size is 15, the BERs at −4 dBm, 4 dBm and 5 dBm can be lower than 0.0020. The network complexity is also analyzed in this paper. Compared with perturbative nonlinearity compensation using a fully connected neural network (2392-64-64), we can verify that the time complexity is reduced by about 25 $\%$ , while the space complexity is reduced by about 50 $\%$ .

In recent years, the number of devices and terminals connected to the smart city has increased significantly. Edge networks face a greater variety of connected objects and massive services. Considering that a large number of services have different QoS requirements, it has always been a huge challenge for smart city to optimally allocate limited computing resources to all services to obtain satisfactory performance. In particular, delay is intolerable for services in certain applications, such as medical, industrial applications, etc, that such applications require the high priority. Therefore, through flexibly dynamic scheduling, it is crucial to schedule services to the optimal node to ensure user experience. In this paper, we propose a resource allocation scheme for hierarchical edge computing network in smart city based on attention mechanism, for extracting a small number of features that can represent services from a large amount of information collected from edge nodes. The attention mechanism is used to quickly determine the priority of the services. Based on this, task deployment and resource allocation for different task priorities are developed to ensure the quality of service in smart cities by introducing Q-learning. Simulation results show that the proposed scheme can effectively improve the edge network resource utilization, reduce the average delay of task processing, and effectively guarantee the quality of service.

Nonlinear impairments caused by devices and fiber transmission links in a coherent optical communication system can severely limit its transmission distance and achievable capacity. In this paper, we propose a low-complexity pruned-convolutional-neural-network-(CNN)-based nonlinear equalizer, to compensate nonlinear signal impairments for coherent optical communication systems. By increasing the size of the effective receptive field with an 11 × 11 large convolutional kernel, the performance of feature extraction for CNNs is enhanced and the structure of the CNN is simplified. And by performing the channel-level pruning algorithm, to prune the insignificant channels, the complexity of the CNN model is dramatically reduced. These operations could save the important component of the CNN model and reduce the model width and computation amount. The performance of the proposed CNN-based nonlinear equalizer was experimentally evaluated in a 120 Gbit/s 64-quadrature-amplitude-modulation (64-QAM) coherent optical communication system over 375 km of standard single-mode fiber (SSMF). The experimental results showed that, compared to a CNN-based nonlinear equalizer with a 6 × 6 normal convolutional kernel, the proposed CNN-based nonlinear equalizer with an 11 × 11 large convolutional kernel, after channel-level pruning, saved approximately 15.5% space complexity and 43.1% time complexity, without degrading the equalization performance. The proposed low-complexity pruned-CNN-based nonlinear equalizer has great potential for application in realistic devices and holds promising prospects for coherent optical communication systems.

In this paper, we propose an image denoising algorithm based on the quaternion wavelet transform (QWT) to address sinusoidal fringe images under strong noise in structured light 3D profilometry. The analysis of a quaternion wavelet shows that the amplitude image of the quaternion wavelet is easily affected by noise. However, the three phase images, which mainly reflect edge and texture information, are randomly and disorderly distributed with respect to noise. The QWT denoising algorithm is suitable for processing sinusoidal fringe images of complex structures in a high-accuracy 3D measurement system. Sinusoidal fringe images are collected and denoised by using the QWT algorithm and classical Gaussian smoothing (GS) denoising algorithm, and GS is used as a reference for the QWT algorithm. The results indicate that the standard deviation is reduced from 0.1448 for raw sinusoidal fringe images to 0.0192, and the signal-to-noise ratio is improved from 4.6213 dB to 13.3463 dB by using the QWT algorithm. The two algorithms have the same denoising effect for a surface with less information. For a surface with rich information, the details of the 3D contour are lost because of the image “blurring” caused by using the GS algorithm, while all edge details of the 3D contour are reconstructed by using the QWT denoising algorithm because of its characteristic of information and noise being separated from the source. For the measured face mask, the error is less than ±0.02 mm. In addition, it takes less than 20 s to run the QWT algorithm to process eight sinusoidal fringe images, which meets the requirements of high-precision measurements.

The probability distribution of probabilistic shaping 64 quadrature amplitude modulation (PS-64QAM) is uneven. The traditional M-ary support vector machine (SVM) algorithm is incompatible with the data set with uneven distribution. In order to solve the problem, we propose a novel nonlinear equalizer (NLE) for PS-64QAM based on constellation segmentation (CS) and SVM, called CS M-ary SVM NLE. The performance of CS M-ary SVM NLE has been demonstrated in a 120 Gb/s PS-64QAM coherent optical communication system. The experimental results show that after employing the proposed scheme, the launched optical power dynamic range (LOPDR) of PS-64QAM can be increased by 1.6 dBm compared with the situation without NLE. In addition, aided by the proposed scheme, the LOPDR of PS-64QAM is increased by 0.6 dBm than M-ary SVM NLE. Compared with employing M-ary SVM NLE and without employing NLE, when employing the proposed scheme, the Q factor is improved about 0.50 dB and 0.96 dB, respectively. The number of support vectors (SVs) and CPU running time for both NLE schemes are collected to measure the complexity of the two NLE schemes. The results show that the complexity of the proposed scheme is lower than that of the M-ary SVM scheme under the entire measured launched optical power range from −5 dBm to +5 dBm.