In an effort to address the problem of the insufficient accuracy of existing orbital angular momentum (OAM) detection systems for vortex optical communication, an OAM mode detection technology based on an attention pyramid convolution neural network (AP-CNN) is proposed. By introducing fine-grained image classification, the low-level detailed features of the similar light intensity distribution of vortex beam superposition and plane wave interferograms are fully utilized. Using ResNet18 as the backbone of AP-CNN, a dual path structure with an attention pyramid is adopted to detect subtle differences in the light intensity in images. Under different turbulence intensities and transmission distances, the detection accuracy and system bit error rate of basic CNN with three convolution layers and two full connection layers, i.e., ResNet18 and ResNet18, with a specified mapping relationship and AP-CNN, are numerically analyzed. Compared to ResNet18, AP-CNN achieves up to a 7% improvement of accuracy and a 3% reduction of incorrect mode identification in the confusion matrix of superimposed vortex modes. The accuracy of single OAM mode detection based on AP-CNN can be effectively improved by 5.5% compared with ResNet18 at a transmission distance of 2 km in strong atmospheric turbulence. The proposed OAM detection scheme may find important applications in optical communications and remote sensing.

To improve the robustness of vortex beam transmission and detection in the face of atmospheric turbulence and to guarantee accurate recognition of orbital angular momentum (OAM), we present an end-to-end dynamic compensation technique for vortex beams using an improved cycle-consistent generative adversarial network (CycleGAN). This approach transforms the problem of vortex beam distortion compensation into one of image translation. The Pix2pix and CycleGAN models were extended with a structural similarity loss function to constrain turbulence distortion compensation in luminance, contrast and structure. Experiments were designed to evaluate the compensation performance from subjective and objective indicators. The simulation results demonstrate that the optical OAM intensity map is very similar to that of the target OAM light after compensation. The mean value of structural similarity is close to 1. The recognition accuracy of the OAM is improved by 4.4% compared to no distortion compensation, demonstrating that the improved CycleGAN-based compensation scheme can guarantee excellent detection accuracy without reconstructing the wavefront and saving optical hardware. The method can be implemented in real-time optical communications in atmospheric turbulence environments.

This book addresses advancement in nanomaterials to design and develop non-invasive healthcare sensors including a combination of hybrid nanocomposites to design non-invasive devices for diagnosing human diseases. The cost-effectiveness is addressed with the methodologies to increase the scalability of the fabrication process. It aims to provide a complete end-to-end solution for smart non-invasive diagnosis developed indigenously and is a cost-effective complete guide to implement a deployable healthcare solution in real-time scenarios. Key Features: Focuses on the design and development of healthcare sensor devices. Reviews different AI techniques using senors for healthcare. Focuses on the application of nanomaterials in different biosensing applications. Explores non-invasive and painless diagnosis with remote healthcare. Discusses remote healthcare with IoMT integration and smart app communication. This book is aimed at graduate students and researchers in biomedical engineering, medical devices, machine learning/pattern recognition, and nanotechnology. <!----> <!----> <!----> <!---->

Due to its orbital angular momentum (OAM), optical vortex has been widely used in communications and LIDAR target detection. The OAM mode recognition based on deep learning is mostly based on the basic convolutional neural network. To ensure high-precision OAM state detection, a deeper network structure is required to overcome the problem of similar light intensity distribution of different superimposed vortex beams and the effect of atmospheric turbulence disturbance. However, the large number of parameters and the computation of the OAM state detection network conflict with the requirements of deploying optical communication system equipment. In this paper, an online knowledge distillation scheme is selected to achieve an end-to-end single-stage training and the inter-class dark knowledge of similar modes are fully utilized. An optical vortex OAM state detection technique based on deep mutual learning (DML) is proposed. The simulation results show that after mutual learning training, a small detection network with higher accuracy can be obtained, which is more suitable for terminal deployment. Based on the scalability of the number of networks in the DML queue, it provides a new possibility to further improve the detection accuracy of the optical communication.