Spatial Domain Information Research Articles

SleepPrintNet: A Multivariate Multimodal Neural Network Based on Physiological Time-Series for Automatic Sleep Staging

Sleep is one of the most fundamental physiological activities of human beings. Sleep assessment based on physiological time-series can efficiently assist human experts to diagnose the sleep health of people. However, most of the existing methods only considered one or two kinds of time-domain, frequency-domain, and spatial-domain information from electroencephalogram (EEG). Besides, existing deep learning methods share the feature extraction module of EEG with other modalities, which ignore the discriminative features of electrooculogram (EOG) and electromyography (EMG). Therefore, how to make full use of the complementarity of different features of EEG and capture the discriminative features from other modalities is challenging. To tackle this challenge, we design SleepPrintNet to capture the SleepPrint in physiological time-series, which represents the complementarity among different features of EEG and discriminative features from other modalities in different sleep stages. SleepPrintNet consists of an EEG temporal feature extraction module, an EEG spectral-spatial feature extraction module for the temporal-spectral-spatial representation of EEG signals, and two multimodal feature extraction modules including EOG and EMG feature extraction module. To the best of our knowledge, it is the first attempt to integrate EEG temporal-spectral-spatial as well as the multimodal features simultaneously in a unified model for sleep staging. Experiments on the benchmark dataset MASS-SS3 demonstrate that SleepPrintNet outperforms all baseline models. The implementation code of SleepPrintNet is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/xiyangcai/SleepPrintNet</uri> . <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>Impact Statement–</i> Sleep staging helps sleep experts assess sleep quality and diagnose sleep health. The polysomnography, which contains the physiological signal recordings during sleep, is a kind of multimodal multivariant physiological time-series for sleep staging. However, existing methods treat physiological time-series from different parts of the body equally, which ignore the abundant information in multimodal signals. The SleepPrintNet proposed in this article has improved the accuracy of sleep staging with the help of the discriminative characteristics from different physiological time-series, which is made up of several independent modules for the extraction of different modalities signals. SleepPrintNet is also a universal framework for the classification of multivariate and multimodal signals. It can be applied in the diagnosis and treatment of other diseases based on physiological signals. The high-accuracy classification of physiological signals has great significance in the field of intelligent medical diagnostics.

Spectral-spatial joint sparsity unmixing of hyperspectral images based on framelet transform

The purpose of hyperspectral unmixing is to estimate the spectral signatures composing the data (endmembers) and their abundance fractions. However, the conventional sparse unmixing involves finding the optimal subset of signatures for the observed data in a very large standard spectral library in the spatial domain and the spatial domain information has many drawbacks which are very scattered, redundancy, and susceptible to noise. In this paper, a new sparse unmixing algorithm is based on framelet domain, namely spectral-spatial joint sparsity unmixing of hyperspectral images based on framelet transform (SSFSU), is proposed to complete the unmixing task of hyperspectral remote sensing images. SSFSU can improve the efficiency of data feature extraction and enhance the anti-noise performance by using the framelet transform information. the experimental results of synthetic and real data show that the SSFSU algorithm has better anti-noise performance and unmixing results compared with other advanced sparse unmixing methods.

Exploiting Level 1 and Level 3 features of fingerprints for liveness detection

Fingerprint-based biometric systems are designed to authenticate and provide authorized access to the users in various security applications. However, such systems can be jeopardized by different kinds of presentation and spoof attacks by using different spoof materials. In this paper, an improved feature descriptor named as Quantized Fundamental Fingerprint Features (Q-FFF) is proposed for live fingerprint detection. The proposed feature descriptor integrates Level 1 and Level 3 features of fingerprints. Level 3 features of fingerprints such as ridge contours are extracted by the weighted linear combination (WLC) of magnitude of perceived stimuli and local contrast information in spatial domain. The novel magnitude of perceived stimuli with modified Weber law is proposed to compute the perceived stimuli of initial pixel intensities. The weights are explicitly determined by sigmoid function to interpolate the sparse information. Level 1 features such as ridge orientation is computed by retaining only the significant frequency components in frequency domain. Both ridge contours and ridge orientation are explicitly quantized into predefined intervals. The quantized feature sets are then integrated to populate a 2-D histogram. Performance evaluation of Q-FFF is determined on the three standard datasets of LivDet competition i.e. LivDet 2011, 2013 and 2015. Results comparison showed a reduction of Average Error Rates (AER) to 5.28, 2.0 and 4.62 on LivDet 2011, LivDet 2013 and LivDet 2015, respectively.

Quantum image encryption algorithm based on Arnold scrambling and wavelet transforms

Based on the modified flexible representation of quantum images, a novel quantum image encryption algorithm was proposed in this paper. The encryption process performs Arnold scrambling operation to disturb the quantum image information in spatial domain first. Then, quantum wavelet transforms are employed to decompose the scrambled quantum image into multiscale resolution (i.e., a sequence of subimages) in the frequency domain, which are mainly divided into two parts: the low-frequency component (i.e., the approximation) and high-frequency detail information (i.e., the horizontal details, vertical details and diagonal details in each decomposition level). Following that, Arnold scrambling operations are implemented to encrypt the wavelet coefficients within each subimage in the frequency domain once again. Finally, based on inverse quantum wavelet transforms, the encrypted wavelet coefficients can affect the pixel values of the entire reconstructed quantum images. Due to the fact that all the quantum operations are invertible, the decryption process of the encrypted image is performed in a straightforward manner by reversing all of the quantum operations within quantum image encryption process. The proposed encryption algorithm is simulated on a classical computer with MATLAB environments. Experimental results and numerical analysis indicate that the presented algorithm has a good encrypted effect and high security.

Medical Image Coloring Based on Gabor Filtering for Internet of Medical Things

Color medical images better reflect a patient's lesion information and facilitate communication between doctors and patients. The combination of medical image processing and the Internet has been widely used for clinical medicine on Internet of medical things. The classical Welsh method uses matching pixels to achieve color migration of grayscale images, but it exists problems such as unclear boundary and single coloring effect. Therefore, the key information of medical images after coloring can't be reflected efficiently. To address this issue, we propose an image coloring method based on Gabor filtering combined with Welsh coloring and apply it to medical grayscale images. By using Gabor filtering, which is similar to the visual stimulus response of simple cells in the human visual system, filtering in 4 directions and 6 scales is used to stratify the grayscale images and extract local spatial and frequency domain information. In addition, the Welsh coloring method is used to render the image with obvious textural features in the layered image. Our experiments show that the color transboundary problem can be solved effectively after the layered processing. Compared to images without stratification, the coloring results of the processed images are closer to the real image.

QNet: An Adaptive Quantization Table Generator Based on Convolutional Neural Network.

The JPEG is one of the most widely used lossy image-compression standards, whose compression performance depends largely on a quantization table. In this work, we utilize a Convolutional Neural Network (CNN) to generate an image-adaptive quantization table in a standard-compliant way. We first build an image set containing more than 10,000 images and generate their optimal quantization tables through a classical genetic algorithm, and then propose a method that can efficiently extract and fuse the frequency and spatial domain information of each image to train a regression network to directly generate adaptive quantization tables. In addition, we extract several representative quantization tables from the dataset and train a classification network to indicate the optimal one for each image, which further improves compression performance and computational efficiency. Tests on diverse images show that the proposed method clearly outperforms the state-of-the-art method. Compared with the standard table at the compression rate of 1.0 bpp, the regression and classification network provide average Peak Signal-to-Noise Ratio (PSNR) gains of nearly 1.2 and 1.4 dB. For the experiment under Structural Similarity Index Measurement (SSIM), the improvements are 0.4% and 0.54%, respectively. The proposed method also has competitive computational efficiency, as the regression and classification network only take 15 and 6.25 milliseconds, respectively, to process a 768 W 512 image on a single CPU core at 3.20 GHz.

Paradox Elimination in Dempster-Shafer Combination Rule with Novel Entropy Function: Application in Decision-Level Multi-Sensor Fusion.

Multi-sensor data fusion technology in an important tool in building decision-making applications. Modified Dempster–Shafer (DS) evidence theory can handle conflicting sensor inputs and can be applied without any prior information. As a result, DS-based information fusion is very popular in decision-making applications, but original DS theory produces counterintuitive results when combining highly conflicting evidences from multiple sensors. An effective algorithm offering fusion of highly conflicting information in spatial domain is not widely reported in the literature. In this paper, a successful fusion algorithm is proposed which addresses these limitations of the original Dempster–Shafer (DS) framework. A novel entropy function is proposed based on Shannon entropy, which is better at capturing uncertainties compared to Shannon and Deng entropy. An 8-step algorithm has been developed which can eliminate the inherent paradoxes of classical DS theory. Multiple examples are presented to show that the proposed method is effective in handling conflicting information in spatial domain. Simulation results showed that the proposed algorithm has competitive convergence rate and accuracy compared to other methods presented in the literature.

Digital Orthogonal-Filters Enhanced Spatial Modulation for High-Speed Indoor Optical Wireless Communications

Spatial modulation (SM) has been proposed and studied in high-speed indoor optical wireless communication systems to improve the spectral efficiency and system capacity by exploring the spatial domain information of transmitters. However, the correct detection of active transmitter(s) is critical, and it typically requires precise channel state information (CSI) and low correlation between channel gains. To overcome this limit, in this paper an orthogonal-filters enhanced SM scheme is proposed for high-speed indoor optical wireless communication systems, where the use of orthogonal-filters can improve the correct detection of active transmitter(s) significantly. The proposed scheme is experimentally demonstrated, and results show that with 4-pulse amplitude modulation (PAM-4) and two transmitters, 7.5 Gb/s optical wireless data transmission is achieved with 2.5 GS/s symbol rate. The power penalty of proposed scheme on the receiver sensitivity is negligible, and the active transmitter(s) can be correctly detected even under high channel correlations and without CSI. The scalability of proposed orthogonal-filters enhanced SM scheme is also studied, and it is shown that higher dimensions can be realized to achieve higher spectral efficiency, which provides a promising solution in indoor optical wireless communications to achieve ultra-high bit rate.

DIMENSION: Dynamic MR imaging with both k-space and spatial prior knowledge obtained via multi-supervised network training.

Dynamic MR image reconstruction from incomplete k-space data has generated great research interest due to its capability in reducing scan time. Nevertheless, the reconstruction problem is still challenging due to its ill-posed nature. Most existing methods either suffer from long iterative reconstruction time or explore limited prior knowledge. This paper proposes a dynamic MR imaging method with both k-space and spatial prior knowledge integrated via multi-supervised network training, dubbed as DIMENSION. Specifically, the DIMENSION architecture consists of a frequential prior network for updating the k-space with its network prediction and a spatial prior network for capturing image structures and details. Furthermore, a multi-supervised network training technique is developed to constrain the frequency domain information and the spatial domain information. The comparisons with classical k-t FOCUSS, k-t SLR, L+S and the state-of-the-art CNN-based method on in vivo datasets show our method can achieve improved reconstruction results in shorter time.

Practical multi-class event classification approach for distributed vibration sensing using deep dual path network.

Influenced by severe ambient noises and nonstationary disturbance signals, multi-class event classification is an enormous challenge in several long-haul application fields of distributed vibration sensing technology (DVS), including perimeter security, railway safety monitoring, pipeline surveillance, etc. In this paper, a deep dual path network is introduced into solving this problem with high learning capacity. The spatial time-frequency spectrum datasets are built by utilizing the multidimensional information of DVS signal, especially the spatial domain information. With the novel datasets and a high-parameter-efficiency network, the proposed scheme presents good reliability and robustness. The feasibility is verified in an actual railway safety monitoring field test, as a proof-of-concept. Seven types of real-life disturbances were implemented and their f1-scores all reached up to 97% in the test. The performance of this proposed approach is fully evaluated and discussed. The presented approach can be employed to improve the performance of DVS in actual applications.

A Multichannel LSTM‐CNN Method for Fault Diagnosis of Chemical Process

The identification and classification of faults in chemical processes can provide decision basis for equipment maintenance personnel to ensure the safe operation of the production process. In this paper, we combine long short‐term memory neural network (LSTM) with convolutional neural network (CNN) and propose a new fault diagnosis method based on multichannel LSTM‐CNN (MCLSTM‐CNN). The primary methodology here includes three aspects. In the initial state, the fault data are input into the LSTM to obtain the output of the hidden layer, which stores the relevant temporal and spatial domain information. Due to the diversity of data features, convolutional kernels with different sizes are utilized to form multiple channels to extract the output characteristics of the hidden layer simultaneously. Finally, the fault data are classified by fully connected layers. The Tennessee Eastman (TE) chemical process is used for experimental analysis, and the MCLSTM‐CNN model is compared with the LSTM‐CNN, LSTM, CNN, RF and KPCA + SVM models. The experimental results show that the MCLSTM‐CNN model has higher diagnostic accuracy, and the fault classification results are superior to other models.

Copyright protection method for 3D model of geological body based on digital watermarking technology

In the continuous development of Internet technology and geological information technology, problems such as illegal possession, copying, modification and dissemination of unauthorized digital products have occurred in the field of geological information technology. In the field of geological information technology, not only traditional digital products such as text, image, audio and video are produced, but also 3D model digital products unique to geological information technology, which are geological bodies, geological phenomena, geological structures, geological processes and geology. Regular 3D visualization analysis and the foundation and platform for comprehensive decision making of 3D visualization, the 3D model of geological body plays an increasingly important role in the field of geological information technology. Of course, it also faces the problems faced by traditional digital products and copyright protection. In this paper, the advantages and disadvantages of digital watermarking technology in copyright protection and the characteristics of geological body 3D model itself, and the current mature 3D model digital watermarking algorithm are introduced. The research idea of 3D geological body digital watermarking algorithm based on point cloud model is proposed. According to the spatial characteristics of the point cloud model of geological body, the spatial characteristic variables of the point cloud model are obtained by using the spatial characteristic analysis algorithm. The spatial domain information represented by the spatial characteristic variables is transformed into the frequency domain information, and then the frequency domain information is analyzed by means of mathematical statistics to extract the digital watermarking information of the whole geological body point cloud model. The feasibility of the algorithm is analyzed and verified by the experimental analysis. The digital watermark information before and after the attack is extracted by geometric attacks such as affine transformation and shearing. The extracted digital watermark information is correlated with the coefficient analysis and the robustness of the algorithm is obtained. A better robustness effect can effectively protect the copyright of the owner of the 3D model of the geological body.

Spatial–spectral preprocessing for spectral unmixing

ABSTRACT Most techniques available in the endmember extraction rely on exploiting the spectral information of the data alone. In this paper, we improve the utilization of data information by dividing a pixel into four subpixels which are redefined by the scalar factor related to the spatial–spectral similarity. The spatial information is integrated into the spectral information in a certain spatial neighbourhood domain, which can make extracted endmembers more precisely, because the effect of noise and outliers can be suppressed with preprocessing (PP). Meanwhile, the accuracy of spectral unmixing will be improved without modification to the conventional methods applied to spectral-based endmember extraction. Experimental results with both synthetic and real hyperspectral images demonstrate the unmixing accuracy is better than that without PP.

Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks.

Spiking neural networks (SNNs) are promising in ascertaining brain-like behaviors since spikes are capable of encoding spatio-temporal information. Recent schemes, e.g., pre-training from artificial neural networks (ANNs) or direct training based on backpropagation (BP), make the high-performance supervised training of SNNs possible. However, these methods primarily fasten more attention on its spatial domain information, and the dynamics in temporal domain are attached less significance. Consequently, this might lead to the performance bottleneck, and scores of training techniques shall be additionally required. Another underlying problem is that the spike activity is naturally non-differentiable, raising more difficulties in supervised training of SNNs. In this paper, we propose a spatio-temporal backpropagation (STBP) algorithm for training high-performance SNNs. In order to solve the non-differentiable problem of SNNs, an approximated derivative for spike activity is proposed, being appropriate for gradient descent training. The STBP algorithm combines the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD), and does not require any additional complicated skill. We evaluate this method through adopting both the fully connected and convolutional architecture on the static MNIST dataset, a custom object detection dataset, and the dynamic N-MNIST dataset. Results bespeak that our approach achieves the best accuracy compared with existing state-of-the-art algorithms on spiking networks. This work provides a new perspective to investigate the high-performance SNNs for future brain-like computing paradigm with rich spatio-temporal dynamics.

Multi-focus image fusion based on block matching in 3D transform domain

Fusion methods based on multi-scale transforms have become the mainstream of the pixel-level image fusion. However, most of these methods cannot fully exploit spatial domain information of source images, which lead to the degradation of image. This paper presents a fusion framework based on block-matching and 3D (BM3D) multi-scale transform. The algorithm first divides the image into different blocks and groups these 2D image blocks into 3D arrays by their similarity. Then it uses a 3D transform which consists of a 2D multi-scale and a 1D transform to transfer the arrays into transform coefficients, and then the obtained low- and high- coefficients are fused by different fusion rules. The final fused image is obtained from a series of fused 3D image block groups after the inverse transform by using an aggregation process. In the experimental part, we comparatively analyze some existing algorithms and the using of different transforms, e.g. non-subsampled Contourlet transform (NSCT), non-subsampled Shearlet transform (NSST), in the 3D transform step. Experimental results show that the proposed fusion framework can not only improve subjective visual effect, but also obtain better objective evaluation criteria than state-of-the-art methods.

Phase-encoded xSPEN: A novel high-resolution volumetric alternative to RARE MRI.

To develop a rapid, non-CPMG high-resolution volumetric imaging approach, exhibiting a speed and in-plane resilience to field inhomogeneities comparable to RARE/turbo-spin-echo (TSE) while endowed with unique downsampling characteristics. A multi-scan extension of cross-term spatiotemporal encoding (xSPEN) is introduced and analyzed. The method simultaneously yields ky /kz data containing low and high frequency components, as well as transposed, low-resolution z/y images. This dual k-/spatial-domain information is captured by a multi-scan procedure that phase-encodes ky while simultaneously slice-selecting z. A reconstruction scheme converting this information into high resolution 3D images with fully multiplexed volumetric coverage is introduced and exemplified. Phase-encoded xSPEN was tested by human brain imaging at sub-mm resolutions. The method exceeded 2D TSE's sensitivity by factors of ≈3-4, while providing similar resolution and SNR as 3D TSE in ≈50% acquisition times. The method's contrast is dominated by T2 and is free from "bright-fat" effects associated to spin-echo trains. Further acceleration is enabled by the method's downsampling abilities. Tradeoffs between encoding time, number of measurements, spatial resolution, SNR, and artifact levels are also laid out. A new MRI strategy is introduced delivering high in- and through-plane resolutions while enjoying full Fourier multiplexing, leading to fast acquisitions with high SNR.

Rotation-covariant tissue analysis for interstitial lung diseases using learned steerable filters: Performance evaluation and relevance for diagnostic aid

A novel method to detect and classify several classes of diseased and healthy lung tissue of interstitial lung diseases is presented, as these diseases are hard to diagnose and differentiate. Local organizations of image directions at several scales drive the process of creating discriminative lung tissue texture signatures using spatial and Fourier domain information extracted from the images. The signatures are generated for four diseased tissue classes and healthy tissue, all of which appear in the Interstitial Lung Disease (ILD) database, using a novel one-versus-one approach for learning discriminative filter signatures. A multiclass tissue classification accuracy of 80.31% is observed using Radial Basis Function (RBF) Support Vector Machines (SVMs). The presented method compares well against a variety of state-of-the-art approaches. Another strong feature of our approach is the ability to access the individual class probabilities before a final classification decision is made. This enables an analysis of the causes of misclassification in this paper. We also make the case against total reliance on the accuracy of the ground truth given that the ILD database only contains a single label for a specific region and sometimes more than one pattern can be present, particularly for regions classified as healthy tissue. Measures to address misclassifications in this context are also proposed.

A Novel Hybrid Dimming Control Scheme for Visible Light Communications

A dimming control scheme that combines analog dimming and spatial dimming is proposed. The basic idea of the combined scheme is that both the direct current bias level of each individual light-emitting diode (LED) and the number of glared LEDs are simultaneously adjusted to achieve a required dimming level. Besides, we design a space constellation to transmit additional information in spatial domain without compromising uniform illumination constraint, and this essentially improves the performance of the system. A maximum-a-posteriori probability estimator is also designed to estimate the received time domain and spatial domain signals. Since two degree of freedoms are simultaneously exploited for dimming control, the proposed scheme outperforms conventional dimming schemes, which only focus on signal domain design, and this is verified by simulation results. To the best of authors’ knowledge, this is the first design that effectively utilizes multidomain resources to achieve dimming control for visible light communications.

Automatic Relevance Determination of Adaptive Variational Bayes Sparse Decomposition for Micro-Cracks Detection in Thermal Sensing

Induction thermography has been applied as an emerging non-destructive testing and evaluation technique for a wide range of conductive materials. The infrared vision sensing acquired image sequences contain valuable information in both spatial and time domain. However, automatic and precisely extracting defect pattern from thermal video remains a challenge. In order to accurately find anomalous patterns for defect detection and further quantitative nondestructive evaluation, we propose an automatic relevance determination approach with adaptive variational Bayes for sub-group sparse decomposition. A subset of scale parameters is driven to a small low bound in the inference, with the pruning the corresponding spurious components. In addition, an internal sub-sparse grouping as well as adaptive fine-tuned is built into the proposed algorithm to control the sparsity. Experimental tests on both artificially and nature defects and comparisons with other methods have been conducted to verify the efficacy of the proposed method.

Small dim object tracking using frequency and spatial domain information

Small dim target tracking is an active and important research area in image processing and pattern recognition. Recently, there has been an emphasis on the development of algorithms based on spatial domain Constant False Alarm Rate (CFAR) detection. This paper presents a novel algorithm for detecting and tracking small dim targets in Infrared (IR) image sequences with low Signal to Noise Ratio (SNR) based on the frequency and spatial domain information. Using a Dual-Tree Complex Wavelet Transform (DT-CWT), a CFAR detector is applied in the frequency domain to find potential positions of objects in a frame. Following this step, a Support Vector Machine (SVM) classification is applied to accept or reject each potential point based on the spatial domain information of the frame. The combination of the frequency and spatial domain information demonstrates the high efficiency and accuracy of the proposed method which is supported by the experimental results.