Transport-based pattern recognition versus deep neural networks in underwater OAM communications.

Charts are often used for the graphical representation of tabular data. Due to their vast expansion in various fields, it is necessary to develop computer algorithms that can easily retrieve and process information from chart images in a helpful way. Convolutional neural networks (CNNs) have succeeded in various image processing and classification tasks. Nevertheless, the success of training neural networks in terms of result accuracy and computational requirements requires careful construction of the network layers’ and networks’ parameters. We propose a novel Shallow Convolutional Neural Network (SCNN) architecture for chart-type classification and image generation. We validate the proposed novel network by using it in three different models. The first use case is a traditional SCNN classifier where the model achieves average classification accuracy of 97.14%. The second use case consists of two previously introduced SCNN-based models in parallel, with the same configuration, shared weights, and parameters mirrored and updated in both models. The model achieves average classification accuracy of 100%. The third proposed use case consists of two distinct models, a generator and a discriminator, which are both trained simultaneously using an adversarial process. The generated chart images are plausible to the originals. Extensive experimental analysis end evaluation is provided for the classification task of seven chart classes. The results show that the proposed SCNN is a powerful tool for chart image classification and generation, comparable with Deep Convolutional Neural Networks (DCNNs) but with higher efficiency, reduced computational time, and space complexity.

Orbital Angular Momentum (OAM) based wireless communications can greatly increase the channel capacity due to its mode degree of freedom (DOF) besides time and frequency. Currently, OAM generation based on Uniform Circular Arrays (UCAs) draws much attention because it can flexibly perform OAM mode multiplexing. Channel models of UCA based OAM communications in the previous researches were built without consideration of radiation patterns of antenna elements in the UCA. In order to further explore the impact of UCA element’s radiation pattern on the OAM communication performance, in this paper, we consider the radiation pattern of antenna elements in both the transmit and receive UCAs and reconstruct the channel model of UCA based OAM communications in the line of sight (LOS) and coaxial scenarios. For the antenna element’s radiation pattern function $G(\theta,\phi)$, we theoretically prove that only when $G(\theta,\phi)$ is symmetric in the dimension of $\phi$ can the orthogonality among each OAM mode be maintained. The simulations indicate that the mode isolation, the channel capacity and the bit error rate (BER) performance all decline sharply when $G(\theta,\phi)$ is not symmetric in the dimension of $\phi$. Our research provides useful insights for the designing of antenna elements for CA based OAM communications.

Physical layer security is a cross research hotspot of information security and wireless communications. Recently, orbital angular momentum (OAM) technology has attracted widespread attention due to its potential of improving capacity and spectrum efficiency. However, there are few researches on system security based on OAM technology. In this work, we studied the security of the proposed OAM wiretap system by applying physical layer security theory to OAM communications. Firstly, we proposed a uniform circular array-based multi-mode OAM system and derived the secrecy capacity. Secondly, the phase profiles, channel capacity and received power of OAM beams are analyzed in terms of various system parameters in oblique scenarios at 30GHz. Thirdly, we discussed the security of the proposed OAM wiretap system. The results show that the system using vortex waves is superior to conventional communication systems using planar electromagnetic waves in terms of system security due to the inherent divergence and spiral phase structure of OAM beams. Moreover, we found that the distortion of OAM beams during transmission and the center shift at receiving end will occur and that system is more stable for high-mode OAM propagation in oblique scenarios. This work can provide an effective guidance for the research and application of OAM communications.

Angular momentum of light can be divided into spin angular momentum and orbital angular momentum (OAM). Due to the theoretically unlimited orthogonal states, the physical dimension of OAM provides a potential solution to boost the information capacity. The OAM multiplexing and modulation techniques have been implemented to meet the continuous growth of bandwidth requirements, resulting in the concept of OAM optical communication. However, the performances of the traditional optical OAM detection techniques degrade seriously in the practical application of OAM optical communications. Thanks to the powerful data analysis advantages, the cutting-edge machine learning (ML) algorithms have been widely used in the field of image processing, laying the technical foundation for OAM recognition. This paper reviews the recent advances on OAM optical communications that are enhanced by ML methods. More than the traditional OAM detection methods, the OAM demodulation methods based on multiple network architectures, including the support vector machine, self-organizing map, feed-forward neural network, convolutional neural network, and diffractive deep optical neural network (D2NN), have been summarized. We also discuss the development of the spiking neural network and on-chip D2NN, opening a possible way to facilitate the future ultra-low power and ultra-fast OAM demodulation technology.

Orbital angular momentum (OAM) holography is becoming a promising technology for image encryption, optical transmission, and storage because of its excellent fidelity, orthogonality, and security. Benefiting from the powerful ability of machine learning to learn from big data features, a computational holographic orbital angular momentum (OAM) communication method using OAM hologram encoding and machine learning decoding is proposed. The OAM information representing the grayscale of the images is encoded into different holograms. Subsequently, using a well-trained convolutional neural network, the holograms carrying arbitrary image information can be accurately transmitted and translated, and the hidden OAM information is readout quickly and accurately as an added confidential channel. Topological charge digits can be arranged to form grayscale images or serial codes. Such a computational holographic OAM communication method can be used for extended channels with high security and complexity. In addition, this method can be applied in areas of confidential digital modulation/demodulation and encrypted communication, as well as expand the transmission capacity.

A fingerprint is an impression left by the friction ridges of a human finger. A fingerprint classification system groups fingerprint according to their characteristics and therefore helps to match a fingerprint against an extensive database of fingerprints. The Henry classification system is widely used among fingerprint classification systems. Some researchers have used traditional machine learning or deep learning for fingerprint classification. Nevertheless, traditional algorithms cannot extract the depth features of the fingerprint, and most deep learning algorithms lack fingerprint image enhancement. So, this paper combined the Gabor Filter and Convolutional Neural Network to extract fingerprint features. The model has two channels, one is a Deep Convolutional Neural Network (DCNN), and the other is a Shallow Convolutional Neural Network (SCNN). The DCNN consists of a neural network with eight layers, which can extract deep features of the fingerprint. The SCNN consists of Gabor Filter and a neural network with two layers that can extract features from clear fingerprint images. This paper uses NIST Special Database 4 for experiments. Experimental results show that the model proposed in this paper has achieved 91.4% accuracy. Compared with other algorithms, this model has higher accuracy than others. It shows that combined with the Gabor Filter and Convolutional Neural Network can better extract the ridge features of fingerprint images.

Shallow convolutional neural networks (CNNs) have successfully been used to classify polarimetric synthetic aperture radar (PolSAR) imagery. However, one drawback of the existing deep CNN-based techniques is that the input PolSAR training data are often insufficient due to their need for a significant number of training data compared to shallow CNN models utilized in PolSAR image classification. In this paper, we propose using Haar wavelet transform in deep CNNs for effective feature extraction to improve the classification accuracy of PolSAR imagery. Based on the results, the proposed deep CNN model obtained better average accuracy in the San Francisco region with an accuracy of 93.3% and produced more homogeneous classification maps with less noise compared to the two much shallower CNN models of AlexNet (87.8%) and a 2D CNN network (91%). The proposed algorithm is efficient and may be applied over large areas to support regional wetland mapping and monitoring activities using PolSAR imagery. The codes are available at (https://github.com/aj1365/DeepCNN_Polsar).

Orbital angular momentum (OAM) at radio frequency (RF) provides a novel approach of multiplexing a set of orthogonal modes on the same frequency channel to achieve high spectral efficiencies. However, OAM communication system requires perfect alignment of the transmit and the receive antennas and this harsh precondition greatly challenges practical application of OAM mode multiplexing gain. In this paper, we first investigate the effect of non- parallel misalignment on the inter-mode interference of the RF-OAM communication system equipped with uniform circular array (UCA). Then, large-scale system analysis shows that increasing the number of antennas has little effect on the inter-mode interference induced by oblique angle, but beam steering approach could eliminate the inter-mode interference completely. Numerical simulations validate our conclusion on the effect of beam steering.

Automatic eyeglasses detection plays a major role in many facial analysis systems. To improve the robustness of these systems and cope with real-world applications, a high-speed eyeglasses detector that can achieve high accuracy is needed. Recent studies indicate that the features extracted from convolutional neural networks are compelling. Therefore, this paper presents an effective and efficient method for eyeglasses detection in facial images based on extracting deep features from a well-designed shallow convolutional neural network (CNN). The main contribution of this paper is to address the two essential aspects of CNN: (1) the size of the training dataset required and (2) the depth of the network architecture. To this end, we initialize the learning parameters of the shallow CNN by the parameters of a deep CNN which is fine-tuned on a small dataset. The depth of the neural network is then decreased by removing some convolutional layers after testing its performance on the validation dataset. As a result, a significantly more accurate shallow CNN architecture, Shallow-GlassNet, is obtained, which achieves not only high accuracy but also high speed in eyeglasses detection. Evaluation experiments have been conducted on two large unconstrained facial image databases, LFW and Celeb Faces. The results have demonstrated the superior performance of the proposed framework which achieves a mean accuracy of 99.73%.

Self-mixing interferometry (SMI) is superior to other laser interferometry methods due to its simplicity and compactness. However, SMI signals are often complex and difficult to process due to interference in the form of variations in the effective reflectivity of the target, noisy signals, complex signal shapes, and other dependencies. Deep neural networks have been a very popular area of research in computer artificial intelligence in recent years, allowing more implicit features to be uncovered than traditional shallow machine learning. It has been shown that convolutional and back-propagation neural networks can be used for SMI signal processing. There are also studies that have used machine learning genetic algorithms for absolute distance measurement. Based on the above, this study used convolutional neural networks to form a deep neural network for absolute distance measurement based on SMI technology. We first trained the deep convolutional neural network at different feedback strengths. The results of the Convolutional Neural Network (CNN) model showed a coefficient of determination of 0.9987. which is consistent with the required model. The trained network was then used to estimate absolute distances with and without the addition of noise. The comparison proves that the proposed method is noise-proof and has high adaptability for measurements under different conditions.

Video hyperlinking represents a classical example of multimodal problems. Common approaches to such problems are early fusion of the initial modalities and crossmodal translation from one modality to the other. Recently, deep neural networks, especially deep autoencoders, have proven promising both for crossmodal translation and for early fusion via multimodal embedding. A particular architecture, bidirectional symmetrical deep neural networks, have been proven to yield improved multimodal embeddings over classical autoencoders, while also being able to perform crossmodal translation. In this work, we focus firstly at evaluating good single-modal continuous representations both for textual and for visual information. Word2Vec and paragraph vectors are evaluated for representing collections of words, such as parts of automatic transcripts and multiple visual concepts, while different deep convolutional neural networks are evaluated for directly embedding visual information, avoiding the creation of visual concepts. Secondly, we evaluate methods for multimodal fusion and crossmodal translation, with different single-modal pairs, in the task of video hyperlinking. Bidirectional (symmetrical) deep neural networks were shown to successfully tackle downsides of multimodal autoencoders and yield a superior multimodal representation. In this work, we extensively tests them in different settings, with different single-modal representations, within the context of video-hyperlinking. Our novel bidirectional symmetrical deep neural networks are compared to classical autoencoders and are shown to yield significantly improved multimodal embeddings that significantly (alpha=0.0001) outperform multimodal embeddings obtained by deep autoencoders with an absolute improvement in precision at 10 of 14.1% when embedding visual concepts and automatic transcripts and an absolute improvement of 4.3% when embedding automatic transcripts with features obtained with very deep convolutional neural networks, yielding 80% of precision at 10.

Identification of crops is an important topic in the agricultural domain. Hyperspectral remote sensing data are very useful for crop feature extraction and classification. Remote sensing data is an unstructured data and Convolutional Neural Network (CNN) can work on unstructured data efficiently. This paper presents an evaluation of CNN for crop classification using the Indian Pines standard dataset obtained from the AVIRIS sensor and the study area dataset obtained from the EO-1hyperion sensor. Optimized CNN has been tuned by training the model on different parameters. It has been compared with two classification algorithms: Deep Neural Network (DNN) and Convolutional Autoencoder. According to the test results, the proposed optimized CNN model provided better results as compared to the other two methods. CNN has given 97 ± 0.58% overall accuracy for the Indian Pines standard dataset and 78 ± 2.43% for our study area dataset.

We propose a metasurface to evaluate the polarization, chirality and orbital angular momentum of the incident light. By employing the weak measurement mechanism, an aperture with a set orientation is utilized to filter the incident polarization components and enhance the polarization contrast. We demonstrate theoretically and numerically that the mechanism can detect the weak quantities of the incident field by evaluating the orientation angle of the azimuthal polarized component in the back focal plane or imaging plane. Using the aperture as the cell of metasurface, the enhancement can also be realized in the imaging plane. Moreover, by constructing a phase gradient through a couple of mirror symmetric apertures in the cell, the metasurface can produce orbit induced rotation in the imaging plane. Our results could find wide application in the polarization, chirality detection and orbital angular momentum communications.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

Manifold causes of image blurring make the no-reference evaluation of realistic blurred images very challenging. Previous studies indicate that handcrafted features suffer from poor representation of the intrinsic characteristics of image blurring and thus blind image sharpness assessment (BISA) is unsatisfactory. This paper explores a shallow convolutional neural network (CNN) to address this problem facilitated by data augmentation. Superior to algorithms that necessitates considerable expertise and efforts to handcraft features for optimal representation of perceptual image quality, CNN directly integrates the retrieval of intrinsic features and the prediction of image blur quality into an optimization process. Moreover, experiments on Realistic Blurring Image Database have verified that CNN advances in retrieving intrinsic features and obtains good correlation with subjective image blurring evaluations.