Ever-increasing demands for lower power loss, shorter transmission delay, and higher communication capacity have been a challenge in optical networks-on-chips (ONoCs). To address this, various multiplexing technologies have been proposed and applied to optical interconnection networks. Among these, Mode-Division Multiplexing (MDM) technology stands out for its ability to significantly enhance network throughput and reduce communication delays by simultaneously transmitting multiple-mode optical signals through a multi-mode waveguide, making it a compelling research area. In this paper, we propose a flexible and scalable multi-mode optical switching element (MOSE) that adjusts transmitted optical signals by modifying its structure. A multi-mode optical router (MOR) based on the proposed MOSE is introduced, followed by the design of MDM-based optical mesh networks-on-chip (MMONoCs) that support parallel transmission of multiple TE-polarization mode optical signals. Additionally, loss and crosstalk models for multi-mode optical devices, including MOSE and MOR, are systematically established. In conclusion, the loss, OSNR, and BER for three TE-polarization modes (TE0, TE1, and TE2) at different network scales are analyzed using MOR as a specific example. The findings indicate that the scalability of MMONoC and its communication quality are mainly influenced by mode crosstalk noise. Furthermore, network performance metrics, including End-to-End (ETE) delay and throughput, are discussed based on two-mode (TE0, TE1) and three-mode (TE0, TE1, and TE2) optical signals at 1550 nm in 4 × 4 and 5 × 5 optical mesh networks. Simulation results demonstrate that MMONoC exhibits significant improvements in ETE delay and throughput compared to traditional single-mode optical modes.

Reversible data hiding in encrypted image (RDHEI) is a powerful security technology that aims to hide data into the encrypted image without any distortions of data extraction and image recovery. Most existing RDHEI methods using vacated room-based data embedding algorithms face challenges in improving embedding capacity and security. In this paper, we develop a novel data hiding strategy via fusion based on reservoir computing (RC) system, upon which a new RDHEI scheme is further proposed. In the proposed scheme, the original image is first encrypted by the stream cipher-based encryption algorithm using the secret keys generated by an optical chaotic system. Then, by means of the RC system, the generated encrypted image can be fused with the secret data to produce the final masked image. Unlike the existing data embedding algorithms based on vacating rooms, the RC-based fusion strategy allows for hiding secret data comparable to the volume of the cover image into the encrypted image so that a higher embedding capacity can be greatly afforded. Moreover, the proposed strategy involves a chaotic transformation via the reservoir of RC system during data hiding, producing a masked image that is completely different from the encrypted image, thus the security is greatly enhanced. Experimental results show the contributions in improving the embedding capacity and security, and also demonstrate the superiority of the proposed scheme compared to some existing RDHEI methods.

The rapid development of big data and artificial intelligence technology has given new vitality and value to smart cities, which provide rich algorithm models and knowledge computing capabilities. Since the recognition results of the traditional Convolutional Neural Network (CNN) model in the face database are prone to over-fitting, this paper proposes a face recognition algorithm based on an improved CNN model and deep learning. The improved CNN model has a good network image recognition performance, improves the data training speed, and optimizes the network structure parameters. Based on an improved CNN model, using the facial expression recognition (FER2013) data to test the model performance, to achieve more accurate face recognition. Experimental results show that the recognition rate of the improved model and deep learning algorithm on the FER2013 dataset reaches 98.36%, which is 4.63% higher than before the improvement.

Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning , but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined to a local window, so it cannot capture information from other locations, and its sampled shapes is fixed. On the other hand, the size of the convolutional kernel is fixed to k × k, which is a fixed square shape, and the number of parameters tends to grow squarely with size. Although Deformable Convolution (Deformable Conv) address the problem of fixed sampling of standard convolutions, the number of parameters also tends to grow in a squared manner, and Deformable Conv do not explore the effect of different initial sample shapes on network performance. In response to the above questions, the Linear Deformable Convolution (LDConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance. In LDConv, a novel coordinate generation algorithm is defined to generate different initial sampled positions for convolutional kernels of arbitrary size. To adapt to changing targets, offsets are introduced to adjust the shape of the samples at each position. LDConv corrects the growth trend of the number of parameters for standard convolution and Deformable Conv to a linear growth. Compared to Deformable Conv, LDConv provides richer choices and can be equivalent to deformable convolution when the number of parameters of LDConv is set to the square of K. Differently, this paper also explores the effect of neural networks by using LDConv with the same size and different initial sampling shapes. LDConv completes the process of efficient feature extraction by irregular convolutional operations and brings more exploration options for convolutional sampled shapes. Object detection experiments on representative datasets COCO2017, VOC 7 + 12, and VisDrone-DET2021 fully demonstrate the advantages of LDConv. LDConv is a plug-and-play convolutional operation that can replace the convolutional operation to improve network performance. The code for the relevant tasks can be found at https://github.com/CV-ZhangXin/LDConv .

Convolutional Neural Networks (CNNs) are widely adopted in object recognition, speech processing and machine translation, due to their extremely high inference accuracy. However, it is challenging to compute massive computationally expensive convolutions of deep CNNs on traditional CPUs and GPUs. Emerging Nanophotonic technology has been employed for on-chip data communication, because of its CMOS compatibility, high bandwidth and low power consumption. In this paper, we propose a nanophotonic accelerator, HolyLight, to boost the CNN inference throughput in datacenters. Instead of an all-photonic design, HolyLight performs convolutions by photonic integrated circuits, and process the other operations in CNNs by CMOS circuits for high inference accuracy. We first build HolyLight-M by microdisk-based matrix-vector multipliers. We find analog-to-digital converters (ADCs) seriously limit its inference throughput per Watt. We further use microdisk-based adders and shifters to architect HolyLight-A without ADCs. Compared to the state-of-the-art ReRAM-based accelerator, HolyLight-A improves the CNN inference throughput per Watt by 13× with trivial accuracy degradation.