Search

In this study, we compared the repeatability and reproducibility of radiomic features obtained from positron emission tomography (PET) images according to the reconstruction algorithm used—advanced reconstruction algorithms, such as HYPER iterative (IT), HYPER deep learning reconstruction (DLR), and HYPER deep progressive reconstruction (DPR), or traditional Ordered Subset Expectation Maximization (OSEM)—to understand the potential variations and implications of using advanced reconstruction techniques in PET-based radiomics. We used a heterogeneous phantom with acrylic spherical beads (4- or 8-mm diameter) filled with 18F. PET images were acquired and reconstructed using OSEM, IT, DLR, and DPR. Original and wavelet radiomic features were calculated using SlicerRadiomics. Radiomic feature repeatability was assessed using the Coefficient of Variance (COV) and intraclass correlation coefficient (ICC), and inter-acquisition time reproducibility was assessed using the concordance correlation coefficient (CCC). For the 4- and 8-mm diameter beads phantom, the proportion of radiomic features with a COV < 10% was equivocal or higher for the advanced reconstruction algorithm than for OSEM. ICC indicated that advanced methods generally outperformed OSEM in repeatability, except for the original features of the 8-mm beads phantom. In the inter-acquisition time reproducibility analysis, the combinations of 3 and 5 min exhibited the highest reproducibility in both phantoms, with IT and DPR showing the highest proportion of radiomic features with CCC > 0.8. Advanced reconstruction methods provided enhanced stability of radiomic features compared with OSEM, suggesting their potential for optimal image reconstruction in PET-based radiomics, offering potential benefits in clinical diagnostics and prognostics. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) is one of the fundamental imaging modalities used in medicine, allowing for the acquisition of accurate cross-sectional images of internal body tissues. However, during the acquisition and reconstruction process, various artifacts can arise, and one of them is ring artifacts. These artifacts result from the inherent limitations of CT scanner components and the properties of the scanned material, such as detector defects, non-uniform distribution of radiation from the source, or the presence of metallic elements within the scanning region. The purpose of this study was to identify and reduce ring artifacts in tomographic images using image decomposition and average filtering methods. In this study, tests were conducted on the effectiveness of identifying ring artifacts using wavelet decomposition methods for images. The test was performed on a Shepp–Logan phantom with implemented artifacts of different intensity levels. The analysis was performed using different wavelet families, and linear approximation methods were used to filter the image in the identified areas. Additional filtering was performed using moving average methods and empirical mode decomposition (EMD) techniques. Image comparison methods, i.e., RMSE, SSIM and MS-SSIM, were used to evaluate performance. The results of this study showed a significant improvement in the quality of tomographic phantom images. The authors obtained more than 50% improvement in image quality with reference to the image without any filtration. The different wavelet families had different efficiencies with relation to the identification of the induction regions of ring artifacts. The Haar wavelet and Coiflet 1 showed the best performance in identifying artifact induction regions, with comparative RMSE values for these wavelets of 0.1477 for Haar and 0.1469 for Coiflet 1. The applied additional moving average filtering and EMD permitted us to improve image quality, which is confirmed by the results of the image comparison. The obtained results allow us to assess how the used methods affect the reduction in ring artifacts in phantom images with induced artifacts. [ABSTRACT FROM AUTHOR]

Single photon emission tomography/computed tomography (SPECT/CT) is a mature imaging technology with a dynamic role in the diagnosis and monitoring of a wide array of diseases. This paper reviews the technological advances, clinical impact, and future directions of SPECT and SPECT/CT imaging. The focus of this review is on signal amplifier devices, detector materials, camera head and collimator designs, image reconstruction techniques, and quantitative methods. Bulky photomultiplier tubes (PMTs) are being replaced by position-sensitive PMTs (PSPMTs), avalanche photodiodes (APDs), and silicon PMs to achieve higher detection efficiency and improved energy resolution and spatial resolution. Most recently, new SPECT cameras have been designed for cardiac imaging. The new design involves using specialised collimators in conjunction with conventional sodium iodide detectors (NaI(Tl)) or an L-shaped camera head, which utilises semiconductor detector materials such as CdZnTe (CZT: cadmium–zinc–telluride). The clinical benefits of the new design include shorter scanning times, improved image quality, enhanced patient comfort, reduced claustrophobic effects, and decreased overall size, particularly in specialised clinical centres. These noticeable improvements are also attributed to the implementation of resolution-recovery iterative reconstructions. Immense efforts have been made to establish SPECT and SPECT/CT imaging as quantitative tools by incorporating camera-specific modelling. Moreover, this review includes clinical examples in oncology, neurology, cardiology, musculoskeletal, and infection, demonstrating the impact of these advancements on clinical practice in radiology and molecular imaging departments. [ABSTRACT FROM AUTHOR]

The capacity of Compressive Sensing (CS) to recreate original data from a limited number of samples has led to a surge in attention in recent years. As Deep Neural Networks (DNN) have emerged, the performance level of CS has also increased with the deployment of data-driven Autoencoders in it. But the lack of optimal parameters and hyperparameters, and inconsistent Autoencoder structures for more complex datasets cause inefficient resource utilization and limit the true potential of Autoencoders. In this paper, we propose the optimally designed structures and parameters of deep Autoencoder subnetworks for CS-based sampling and reconstruction of speech and image datasets to align with the desired objectives and available constraints. Furthermore, the impact of optimal types, structures, and hyperparameters of Autoencoders are assessed to match with their deployment for speech and image CS. Apart from the optimized levels of structure and hyperparameters, our work emphasized the usage of other types of Autoencoders – other than the Stacked Autoencoders- which are employed for the sampling and reconstruction of speech and image datasets. As a result, the optimally designed Autoencoders have demonstrated 18% improved performances for speech signals when compared with the baseline model. In this work, the novelty is associated with re-engineering the internal structure and layers of Convolutional layers to provide an optimized level of hyperparameters and layer architecture for image compressive sensing, which better suits a variety of compression ratios to better preserve bandwidth, power, and computational resources. We found the compression ratio of 0.4 to be the optimum value, which exhibited the structural similarity value of 0.85, for Convolutional Autoencoders. The novelty of our work lies in developing AI-driven, data-adaptive models that leverage optimally trained autoencoders for CS, significantly enhancing resource efficiency in terms of storage, hardware complexity, and computational cost.

Distance sensors are important for mobile robots to perceive surrounding environment. Typical sensors like LiDARs and depth cameras have been widely used, yet each has its limitations, such as LiDARs’ relatively high cost, depth cameras’ limitation to indoor use, and their poor performance in detecting transparent objects directly. On the other hand, ultrasonic phased array that integrates multiple ultrasonic sensors not only enables 3D ranging and imaging, but also provides advantages of strong environmental adaptability, being cost-effective and being able to detect transparent objects. To explore the application of in-air ultrasonic phased arrays for mobile robots, we simulate a 40 kHz $5\times 5$ non-uniform sparse ultrasonic phased array. The simulator emulates the process of phased array transmission and reception, and utilizes algorithms such as beamforming and matched filtering to obtain depth information in three-dimensional space. Then, a multi-view indoor 3D reconstruction method fusing the ultrasonic phased array and a monocular camera is proposed, where two scanning strategies are developed to handle different scenarios. Finally, the method is validated in different Gazebo scenarios and compared with other baseline methods like LiDARs and depth cameras. The experimental results reveal the method’s strong performance in terms of accuracy, consistency and completeness.

We study the decomposition of multivariate polynomials as sums of powers of linear forms. We give a randomised algorithm for the following problem: If a homogeneous polynomial f ∈ K [ x 1 ,... , x n ] (where K ⊆ C ) of degree d is given as a blackbox, decide whether it can be written as a linear combination of d-th powers of linearly independent complex linear forms. The main novel features of the algorithm are: For d = 3 , we improve by a factor of n on the running time from the algorithm in Koiran & Skomra (2021). The price to be paid for this improvement is that the algorithm now has two-sided error. For d > 3 , we provide the first randomised blackbox algorithm for this problem that runs in time poly (n , d) (in an algebraic model where only arithmetic operations and equality tests are allowed). Previous algorithms for this problem Kayal (2011) as well as most of the existing reconstruction algorithms for other classes appeal to a polynomial factorisation subroutine. This requires extraction of complex polynomial roots at unit cost and in standard models such as the unit-cost RAM or the Turing machine this approach does not yield polynomial time algorithms. For d > 3 , when f has rational coefficients (i.e. K = Q ), the running time of the blackbox algorithm is polynomial in n, d and the maximal bit size of any coefficient of f. This yields the first algorithm for this problem over C with polynomial running time in the bit model of computation. These results are true even when we replace C by R . We view the problem as a tensor decomposition problem and use linear algebraic methods such as checking the simultaneous diagonalisability of the slices of a tensor. The number of such slices is exponential in d. But surprisingly, we show that after a random change of variables, computing just 3 special slices is enough. We also show that our approach can be extended to the computation of the actual decomposition. In forthcoming work we plan to extend these results to overcomplete decompositions, i.e. decompositions in more than n powers of linear forms. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI)-based image enhancement has the potential to reduce scan times while improving signal-to-noise ratio (SNR) and maintaining spatial resolution. This study prospectively evaluated AI-based image enhancement in 32 consecutive patients undergoing clinical brain MRI. Standard-of-care (SOC) three-dimensional (3D) T1 precontrast, 3D T2 fluid-attenuated inversion recovery, and 3D T1 postcontrast sequences were performed along with 45% faster versions of these sequences using half the number of phase-encoding steps. Images from the faster sequences were processed by a Food and Drug Administration-cleared AI-based image enhancement software for resolution enhancement. Four board-certified neuroradiologists scored the SOC and AI-enhanced image series independently on a five-point Likert scale for image SNR, anatomic conspicuity, overall image quality, imaging artifacts, and diagnostic confidence. While interrater κ was low to fair, the AI-enhanced scans were noninferior for all metrics and actually demonstrated a qualitative SNR improvement. Quantitative analyses showed that the AI software restored the high spatial resolution of small structures, such as the septum pellucidum. In conclusion, AI-based software can achieve noninferior image quality for 3D brain MRI sequences with a 45% scan time reduction, potentially improving the patient experience and scanner efficiency without sacrificing diagnostic quality. Keywords: MR Imaging, CNS, Brain/Brain Stem, Reconstruction Algorithms © RSNA, 2022.

Computed tomography (CT) is one of the fundamental imaging modalities used in medicine, allowing for the acquisition of accurate cross-sectional images of internal body tissues. However, during the acquisition and reconstruction process, various artifacts can arise, and one of them is ring artifacts. These artifacts result from the inherent limitations of CT scanner components and the properties of the scanned material, such as detector defects, non-uniform distribution of radiation from the source, or the presence of metallic elements within the scanning region. The purpose of this study was to identify and reduce ring artifacts in tomographic images using image decomposition and average filtering methods. In this study, tests were conducted on the effectiveness of identifying ring artifacts using wavelet decomposition methods for images. The test was performed on a Shepp–Logan phantom with implemented artifacts of different intensity levels. The analysis was performed using different wavelet families, and linear approximation methods were used to filter the image in the identified areas. Additional filtering was performed using moving average methods and empirical mode decomposition (EMD) techniques. Image comparison methods, i.e., RMSE, SSIM and MS-SSIM, were used to evaluate performance. The results of this study showed a significant improvement in the quality of tomographic phantom images. The authors obtained more than 50% improvement in image quality with reference to the image without any filtration. The different wavelet families had different efficiencies with relation to the identification of the induction regions of ring artifacts. The Haar wavelet and Coiflet 1 showed the best performance in identifying artifact induction regions, with comparative RMSE values for these wavelets of 0.1477 for Haar and 0.1469 for Coiflet 1. The applied additional moving average filtering and EMD permitted us to improve image quality, which is confirmed by the results of the image comparison. The obtained results allow us to assess how the used methods affect the reduction in ring artifacts in phantom images with induced artifacts.

Single photon emission tomography/computed tomography (SPECT/CT) is a mature imaging technology with a dynamic role in the diagnosis and monitoring of a wide array of diseases. This paper reviews the technological advances, clinical impact, and future directions of SPECT and SPECT/CT imaging. The focus of this review is on signal amplifier devices, detector materials, camera head and collimator designs, image reconstruction techniques, and quantitative methods. Bulky photomultiplier tubes (PMTs) are being replaced by position-sensitive PMTs (PSPMTs), avalanche photodiodes (APDs), and silicon PMs to achieve higher detection efficiency and improved energy resolution and spatial resolution. Most recently, new SPECT cameras have been designed for cardiac imaging. The new design involves using specialised collimators in conjunction with conventional sodium iodide detectors (NaI(Tl)) or an L-shaped camera head, which utilises semiconductor detector materials such as CdZnTe (CZT: cadmium–zinc–telluride). The clinical benefits of the new design include shorter scanning times, improved image quality, enhanced patient comfort, reduced claustrophobic effects, and decreased overall size, particularly in specialised clinical centres. These noticeable improvements are also attributed to the implementation of resolution-recovery iterative reconstructions. Immense efforts have been made to establish SPECT and SPECT/CT imaging as quantitative tools by incorporating camera-specific modelling. Moreover, this review includes clinical examples in oncology, neurology, cardiology, musculoskeletal, and infection, demonstrating the impact of these advancements on clinical practice in radiology and molecular imaging departments.

Objective: To explore the influence of different CT acquisition and reconstruction parameters on the CT number of the chest in vivo. Methods: The CT number of the trachea, blood vessels, lungs, vertebral bodies, and muscles of the human chest were measured under different CT scanning parameters. Six groups of different scanning parameters and reconstruction algorithms were set respectively: slice thickness 5 mm, 50% multi-model adaptive statistical iterative reconstruction Veo (ASIR-V) and low-dose for S1; slice thickness 5 mm, filtered back projection (FBP) and standard-dose for S2; slice thickness 1.25 mm, 50% ASIR-V and low-dose for S3; slice thickness 1.25 mm, 50% ASIR-V and standard-dose for S4; slice thickness 1.25 mm, FBP, low-dose for S5; slice thickness 1.25 mm, FBP, standard-dose for S6. The radiation dose of the scan was controlled using two noise indexes (NI), including low-dose (NI=40) and standard-dose (NI=10). Differences in CT number between two groups were compared using t-test or rank-sum test. Results: Significant differences of CT number of the trachea were detected between low-dose and standard-dose, but no significant differences of CT number of other tissues were detected between low-dose and standard-dose. No significant differences of CT number of chest tissues were detected between either 5 mm thickness and 1.25 mm thickness or 50% ASIR-V and FBP. Conclusion: The CT number of human chest tissues showed well stability which was scarcely influenced by slices thickness, reconstruction algorithm and scan dose.

In X-ray computed tomography, discrete tomography (DT) algorithms have been successful at reconstructing objects composed of only a few distinct materials. Many DT-based methods rely on a divide-and-conquer procedure to reconstruct the volume in parts, which improves their run-time and reconstruction quality. However, this procedure is based on static rules, which introduces redundant computation and diminishes the efficiency. In this work, we introduce an update strategy framework that allows for dynamic rules and increases control for divide-and-conquer methods for DT. We illustrate this framework by introducing Tabu-DART, which combines our proposed framework with the Discrete Algebraic Reconstruction Technique (DART). Through simulated and real data reconstruction experiments, we show that our approach yields similar or improved reconstruction quality compared to DART, with substantially lower computational complexity. [ABSTRACT FROM AUTHOR]

Visual measurement methods are extensively used in various fields, such as aerospace, biomedicine, agricultural production, and social life, owing to their advantages of high speed, high accuracy, and non-contact. However, traditional camera-based measurement systems, relying on the pinhole imaging model, face challenges in achieving three-dimensional measurements using a single camera by one shot. Moreover, traditional visual systems struggle to meet the requirements of high precision, efficiency, and compact size simultaneously. With the development of light field theory, the light field camera has garnered significant attention as a novel measurement method. Due to its special structure, the light field camera enables high-precision three-dimensional measurements with a single camera through only one shot. This paper presents a comprehensive overview of light field camera measurement technologies, including the imaging principles, calibration methods, reconstruction algorithms, and measurement applications. Additionally, we explored future research directions and the potential application prospects of the light field camera. [ABSTRACT FROM AUTHOR]

Copyright of CT Theory & Applications is the property of Editorial Department of CT Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This letter proposes three new discriminators for dominant scattering mechanism (surface scattering or dihedral scattering) for the decomposition process of the compact polarimetric (CP) synthetic aperture radar (SAR) scattering model. Based on the covariance matrix of CP SAR under symmetry reflection assumption, a Re($\text{S}_{\text {HH}}\text {S}_{\text {VV}}^{\ast }$) reconstruction method based on the estimation of cross-polarization term is proposed, and three new discriminators, DISCREntropy, DISCREigen, and DISCRDoP, are obtained accordingly. Comparative experiments using real circular transmit linear receive (CTLR) CP SAR data for the three proposed discriminators as well as the commonly used discriminator $g_{3}$ demonstrate that the comprehensive decomposition results using the proposed three discriminators are better than the result using $g_{3}$ , and DISCRDoP is better than DISCREigen, DISCREigen is better than DISCREntropy. [ABSTRACT FROM AUTHOR]

Terahertz tomography is a non-contact inspection technique to image objects from multiple angles and reconstruct their 3D volume from intensity and time-of-flight transmission data, without the need for radiation protection measures. Unlike X-rays, terahertz radiation is subject to strong diffraction and refraction when propagating through dielectric materials, which often deteriorate the image reconstruction quality. Our solution to this problem applies ray tracing, considering the beam shape and an $a$ priori model of the sample under investigation to predict the beam paths of the terahertz radiation. We present two reconstruction methods based on the resulting beam path predictions yielding higher image quality. Method 1 filters out beams deviating strongly, thus removing induced artifacts and errors from the reconstruction image. Method 2 employs off-axis measurements that acquire data along the full detection plane and in this way detect even strongly deflected beams. Considering these beams and the information they carry in the reconstruction enhances the image quality. Applying these methods to terahertz tomography, even complicated structures can be imaged. We display the significant enhancements achieved with the two methods by comparing the reconstruction results of different polymeric samples.

The study aimed to improve the quality of the Y90 PET imaging by optimizing the reconstruction algorithm. Methods: Ten patients with metastatic neuroendocrine tumour to the liver or primary hepatocellular carcinoma who were qualified for Y90 labelled selective internal radiation therapy (SIRT) or peptide receptor radionuclide therapy (PRRT) were recruited. They underwent post-therapy PET/CT imaging using three different reconstruction parameters: (Algorithm A)Vue Point HD with 6.4mm filter cutoff, 24 subsets and 2 iterations, (Algorithm B)Vue Point FX with 6.0 mm filter cutoff, 18 subsets and 3 iterations using time of flight, and (Algorithm C)Vue Point HD LKYG with 5mm filter cutoff, 32 subsets and 1 iteration. The reconstructed PET/CT images were assessed by 10 nuclear medicine physicians using 4-point semi-qualitative scoring criteria. A P-value of less than 0.05 was considered significant. Results: The median quality assessment scores for Algorithm C were consistently scored the highest with algorithms A, B and C scoring 3, 2 and 4 respectively. The Y90 PET scans using Algorithm C were deemed diagnostic 91% of the time. There was a statistically significant difference in quality assessment scores between the algorithms by the Kruskal-Wallis rank sum test (χ2(2) = 86.5, P <0.001), with mean rank quality score (QS) of 130.03 for Algorithm A, 109.76 for Algorithm B and 211.71 for Algorithm C. Subgroup analysis for quality assessment score of post-PRRT imaging alone showed statistically significant difference between different scanning algorithms (χ2(2) = 35.35, P < 0.001), with mean rank QS of 45.85 for Algorithm A, 50.05 for Algorithm B and 85.6 for Algorithm C. Similar results were observed for quality assessment score of post-SIRT imaging (χ2(2) = 79.90, p<0.001), with mean rank of 82.33 for Algorithm A, 55.79 for Algorithm B and 133.38 for Algorithm C. Conclusion: The new LKYG algorithm that was featured by decreasing the number of iterations, decreasing the cutoff of the filter thickness, and increasing the number of the subsets had successfully improved the image quality. [ABSTRACT FROM AUTHOR]

To improve the performance of position sensorless control with a single current sensor in low-speed range, an improved current reconstruction method is proposed. High-frequency voltage is injected to estimate the rotor position. The time interval between two sampling moments is fixed as the minimum sampling window time. Therefore, the phase current can be compensated by an online adaptive one-step method. And the time-aligned three-phase currents can be reconstructed. The influence of the error between time-aligned reconstructed currents and the full sensors sampling currents on sensorless control is discussed. With the proposed method, the injection frequency can be improved to half the switching frequency. Finally, a permanent magnet synchronous motor is sensorless controlled with the proposed method in the experiments. [ABSTRACT FROM AUTHOR]

X‐ray‐based non‐destructive 3D grain mapping techniques are well established at synchrotron facilities. To facilitate everyday access to grain mapping instruments, laboratory diffraction contrast tomography (LabDCT), using a laboratory‐based conical polychromatic X‐ray beam, has been developed and commercialized. Yet the currently available LabDCT grain reconstruction methods are either ill‐suited for handling a large number of grains or require a commercial licence bound to a specific instrument. To promote the availability of LabDCT, grain reconstruction methods have been developed with multiple reconstruction algorithms based on both forward and back calculations. The different algorithms are presented in detail and their efficient implementation using parallel computing is described. The performance of different reconstruction methods is assessed on synthetic data. The code to implement all the described algorithms has been made publicly accessible with the intention of fostering the development of grain mapping techniques on widely available laboratory instruments. [ABSTRACT FROM AUTHOR]

Deep learning (DL)-based methods show great potential in computed tomography (CT) imaging field. The DL-based reconstruction methods are usually evaluated on the training and testing datasets which are obtained from the same distribution, i.e., the same CT scan protocol (i.e., the region setting, kVp, mAs, etc.). In this work, we focus on analyzing the robustness of the DL-based methods against protocol-specific distribution shifts (i.e., the training and testing datasets are from different region settings, different kVp settings, or different mAs settings, respectively). The results show that the DL-based reconstruction methods are sensitive to the protocol-specific perturbations which can be attributed to the noise distribution shift between the training and testing datasets. Based on these findings, we presented a low-dose CT reconstruction method using an unsupervised strategy with the consideration of noise distribution to address the issue of protocol-specific perturbations. Specifically, unpaired sinogram data is enrolled into the network training, which represents unique information for specific imaging protocol, and a Gaussian mixture model (GMM) is introduced to characterize the noise distribution in CT images. It can be termed as GMM based unsupervised CT reconstruction network (GMM-unNet) method. Moreover, an expectation-maximization algorithm is designed to optimize the presented GMM-unNet method. Extensive experiments are performed on three datasets from different scan protocols, which demonstrate that the presented GMM-unNet method outperforms the competing methods both qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

This article proposes a novel data reconstruction method, called projective cross-reconstruction (PCR) for cross-domain recognition. The intrinsic philosophy behind PCR is that the data from different domains but with the same label have a strong correlation and thus they can be reconstructed with each other. To this end, we first rearrange the data of source and target domains to form two new cross-data matrices, and the data with the same label but from different domains can be arranged together. Then, we use two different projection matrices to project the new cross-data into two approximate subspaces and perform the cross-reconstruction without introducing any extra matrix as the reconstruction coefficient matrix. This guarantees that the data from different domains can be interlaced well and the data from different domains but sharing the same label can be aligned together. In doing so, the problem of cross-domain distribution mismatch is solved and a discriminative and transferrable feature representation can be obtained. Moreover, PCR integrates the classifier learning and feature representation learning into a unified framework so that these two tasks can be iteratively improved until the termination condition is met. Extensive experiments on six datasets validate the effectiveness of our proposed PCR, compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Compressive sensing allows the reconstruction of original signals from a much smaller number of samples as compared to the Nyquist sampling rate. The effectiveness of compressive sensing motivated the researchers for its deployment in a variety of application areas. The use of an efficient sampling matrix for high-performance recovery algorithms improves the performance of the compressive sensing framework significantly. This paper presents the underlying concepts of compressive sensing as well as previous work done in targeted domains in accordance with the various application areas. To develop prospects within the available functional blocks of compressive sensing frameworks, a diverse range of application areas are investigated. The three fundamental elements of a compressive sensing framework (signal sparsity, subsampling, and reconstruction) are thoroughly reviewed in this work by becoming acquainted with the key research gaps previously identified by the research community. Similarly, the basic mathematical formulation is used to outline some primary performance evaluation metrics for 1D and 2D compressive sensing.

Recently, learning-based image inpainting has gained much attention. It widely utilizes an auto-encoder structure and can obtain compact feature representation in the encoder to achieve high-quality image inpainting. Although this approach has achieved encouraging inpainting results, it inevitably reduces the high-resolution representation due to interval downsampling. In order to solve this problem and achieve an excellent image inpainting effect, this paper proposes a brand-new generative network, Interactive Separation Network, which retains the high-resolution information and extracts the semantic features from corrupted images. Furthermore, this paper also discusses network designs with different complexity in different application scenarios. Finally, to improve the effectiveness and robustness of our proposal to large corrupted regions in the inpainting image, we further propose a flexible and highly reusable reconstruction scheme to complete the inpainting in the prediction process gradually. Experiments show that our proposed generation network and reconstruction scheme can significantly improve the quality of repaired images. The proposed method significantly outperforms the state-of-the-art image inpainting approaches in image quality.

Consider the compressed sensing setup where the support $\mathbf {s}^{\ast}$ of an $m$ -sparse $d$ -dimensional signal $\mathbf {x}$ is to be recovered from $n$ linear measurements with a given algorithm. Suppose that the measurements are such that the algorithm does not guarantee perfect support recovery and that true features may be missed. Can they efficiently be retrieved? We address this question through a simple error-correction module referred to as LiRE. LiRE takes as input an estimate $\mathbf {s}_{\text {in}}$ of the true support $\mathbf {s}^{\ast}$ , and outputs a refined support estimate $\mathbf {s}_{\text {out}}$. We establish sufficient conditions under which LiRE is guaranteed to recover the entire support, that is $\mathbf {s}_{\text {out}}\supseteq \mathbf {s}^{\ast} $. These conditions imply, for instance, that in high dimension LiRE can correct a sublinear in $m$ number of errors made by Orthogonal Matching Pursuit (OMP). The computational complexity of LiRE is ${\mathcal{O}}(m n d)$. Experimental results with random Gaussian design matrices show that LiRE substantially reduces the number of measurements needed for perfect support recovery via Compressive Sampling Matching Pursuit, Basis Pursuit (BP), and OMP. Interestingly, adding LiRE to OMP yields a support recovery procedure that is more accurate and significantly faster than BP. This observation carries over in the noisy measurement setup where the combination of LiRE and OMP is faster and more accurate than LASSO. Finally, as a standalone support recovery algorithm with a random initialization, experiments show that LiRE’s support recovery performance lies between OMP and BP. These results show that LiRE can be used generically, on top of any suboptimal baseline support recovery algorithm, to improve support recovery or to operate with a smaller number of measurements, at the cost of a relatively small computational overhead. Alternatively, LiRE may be used as a standalone support recovery algorithm that is competitive with respect to OMP. [ABSTRACT FROM AUTHOR]

Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms. The bottleneck lies in the reconstruction algorithms, resulting in rather limited reconstruction quality. To tackle this challenge, we propose a novel learning-based framework for the reconstruction of high-quality LFs from acquisitions via learned coded apertures. The proposed method incorporates the measurement observation into the deep learning framework elegantly to avoid relying entirely on data-driven priors for LF reconstruction. Specifically, we first formulate the compressive LF reconstruction as an inverse problem with an implicit regularization term. Then, we construct the regularization term with a deep efficient spatial-angular separable convolutional sub-network in the form of local and global residual learning to comprehensively explore the signal distribution free from the limited representation ability and inefficiency of deterministic mathematical modeling. Furthermore, we extend this pipeline to LF denoising and spatial super-resolution, which could be considered as variants of coded aperture imaging equipped with different degradation matrices. Extensive experimental results demonstrate that the proposed methods outperform state-of-the-art approaches to a significant extent both quantitatively and qualitatively, i.e., the reconstructed LFs not only achieve much higher PSNR/SSIM but also preserve the LF parallax structure better on both real and synthetic LF benchmarks. The code will be publicly available at https://github.com/MantangGuo/DRLF. [ABSTRACT FROM AUTHOR]

An effective electromagnetic interference (EMI) source reconstruction method based on dynamic differential evolution (DDE) is proposed in this article. In this method, an unknown EMI source is represented by an equivalent dipole array by using the scanned phaseless magnetic near fields. Different from the conventional differential evolution (CDE) method, DDE individually updates every equivalent dipole instead of the whole dipole array for each iteration. It converges faster and takes less computing time than CDE. The equivalent dipole model reconstructed by DDE can thereafter predict the near field and 3-m far field efficiently. The results of numerical and measurement examples have verified the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Entangled photon quantum imaging technology has become very promising for marine imaging due to its high resolution, anti-turbulence, and anti-interference properties. The turbulence and optical attenuation caused by oceanic water would impose severe limitations on conventional imaging equipment. Quantum imaging based on entangled light sources could make it possible to overcome the constraints of low imaging resolution, large maritime environmental impact and low confidentiality in traditional underwater target imaging. Hence, the recent technological developments in terms of quantum imaging in free space motivate our investigation into high-resolution quantum imaging based on spatially correlated properties of entangled photon pairs in a marine environment. Moreover we propose and design an innovative underwater quantum imaging optical path for experimental verification. We conduct extensive experiments to assess the effectiveness of our proposed quantum imaging approach in marine environments. In order to solve the problem of the slow quantum imaging process, we propose an innovative compressive sensing reconstruction algorithm. Experiments show that the compressive sensing method could be utilized to reduce the imaging time. Finally, we propose an underwater quantum target identification method based on deep learning, further providing the possibility for underwater quantum target identification of entangled light sources. [ABSTRACT FROM AUTHOR]

For massive multiple-input multiple-output systems operating in frequency-division duplex mode, downlink channel state information (CSI) acquisition will incur large overhead. This overhead is substantially reduced when sparse channel estimation techniques are employed, owing to the channel sparsity in the angular domain. When a sparse channel estimation method is implemented, the measurement matrix, which is related to the pilot matrix, is essential to the channel estimation performance. Existing sparse channel estimation schemes widely adopt random measurement matrices, which have been criticized for their suboptimal reconstruction performance. This paper proposes novel data-driven solutions to design the measurement matrix. Model-based autoencoders are customized to optimize the measurement matrix by unfolding the classical basis pursuit algorithm. The obtained data-driven measurement matrices are applied to existing sparse reconstruction algorithms, leading to flexible hybrid data-driven implementations for sparse channel estimation. Numerical results show that the proposed data-driven measurement matrices can achieve more accurate reconstructions and use fewer measurements than the existing random matrices, thereby leading to a higher achievable rate for CSI acquisition. Moreover, compared with existing pure deep learning-based sparse reconstruction methods, the proposed hybrid data-driven scheme, which uses the novel data-driven measurement matrices with conventional sparse reconstruction algorithms, can achieve higher reconstruction accuracy. [ABSTRACT FROM AUTHOR]

The inverse scattering problem related to the localization of metal bars embedded within a finite-dimensional dielectric was studied in two-dimensional geometry. The dielectric was placed in air and illuminated from the outside using a linear microwave source and a multi-monostatic configuration. The discontinuity at the interface between the air and the dielectric causes reflections that are neglected if a simple linear Born approximation of scattering is assumed. Herein, a new formulation was proposed based on a quadratic approximation of the scattering equation. The formulation maintained the interaction between the metal bars and the dielectric edge, whereas the mutual coupling between the bars was neglected. By exploiting the knowledge of the permittivity of the dielectric and the shape of its section, a relatively simple approximate expression for the scattered field was derived, which allowed for formulation of an inverse linear problem. Numerical examples demonstrated the feasibility of this approach. [ABSTRACT FROM AUTHOR]

Video snapshot compressive imaging (SCI) system enables high-frame-rate imaging by projecting multiple frames into a 2D snapshot measurement during a single exposure, and the original video frames can be reconstructed by solving an optimization problem. However, existing methods usually cannot achieve a good balance between reconstruction time and reconstruction quality, which has become a major obstacle for practical application of video SCI. In order to cope with this issue, we propose a residual ensemble network to learn the explicit inverse mapping from the 2D snapshot measurement to the original video. Specifically, the proposed network aims to exploit the spatiotemporal correlations between video frames for improving reconstruction quality. The spatiotemporal correlations of video frames demonstrate multiple types, including intra-frame spatial correlation, inter-frame forward and backward temporal correlation. With the purpose of fully capturing these differentiated correlations, we design four sub-networks, namely, a pseudo-3D U-shape sub-network, two residual sub-networks, and a serial forward and backward recurrent sub-network, and further assemble these four sub-networks into an ensemble network through alternate residual links. This ensemble network can effectively fuse the predictions of each sub-network and maintain spatiotemporal consistency between video frames. We further design a compound loss function to guide the network learning, and the new video can be fast reconstructed by simply feeding its 2D snapshot measurement into the learned network. The experimental results demonstrate that our network can significantly improve the reconstruction quality while maintaining low computational cost. [ABSTRACT FROM AUTHOR]

Optimizing k-space sampling trajectories is a promising yet challenging topic for fast magnetic resonance imaging (MRI). This work proposes to optimize a reconstruction method and sampling trajectories jointly concerning image reconstruction quality in a supervised learning manner. We parameterize trajectories with quadratic B-spline kernels to reduce the number of parameters and apply multi-scale optimization, which may help to avoid sub-optimal local minima. The algorithm includes an efficient non-Cartesian unrolled neural network-based reconstruction and an accurate approximation for backpropagation through the non-uniform fast Fourier transform (NUFFT) operator to accurately reconstruct and back-propagate multi-coil non-Cartesian data. Penalties on slew rate and gradient amplitude enforce hardware constraints. Sampling and reconstruction are trained jointly using large public datasets. To correct for possible eddy-current effects introduced by the curved trajectory, we use a pencil-beam trajectory mapping technique. In both simulations and in- vivo experiments, the learned trajectory demonstrates significantly improved image quality compared to previous model-based and learning-based trajectory optimization methods for $10\times $ acceleration factors. Though trained with neural network-based reconstruction, the proposed trajectory also leads to improved image quality with compressed sensing-based reconstruction. [ABSTRACT FROM AUTHOR]

High-quality measurement of temperature distribution information is of great significance for industrial production. As a typical non-contact temperature measurement method, acoustic tomography (AT) can obtain temperature distribution through reconstruction algorithms. To improve the reconstruction quality, a two-stage algorithm based on virtual observation (VO) and residual network (ResNet) was proposed. This algorithm combines the advantages of VO and ResNet. Aiming at total least squares, the VO method was adopted to reconstruct the ultrasonic time-of-flight (TOF) to obtain the temperature distribution under a coarse grid. Then, ResNet was built to predict the temperature distribution under the refined grid, and the dual-input model was used to improve the network generalization ability. At the same time, the sub-pixel convolution layer was introduced to reduce the network computing dimension, which improves the computing efficiency and the reconstruction quality. The numerical simulation of typical temperature field models was carried out, and the reconstruction results show that the average relative error and root mean square error are less than 0.86% and 1.21%, respectively. The noise immunity and reconstruction spatial resolution are better than traditional algorithms and the previous two-stage algorithm. [ABSTRACT FROM AUTHOR]

Miniaturized computational spectrometers have emerged as a promising strategy for miniaturized spectrometers, which breaks the compromise between footprint and performance in traditional miniaturized spectrometers by introducing computational resources. They have attracted widespread attention and a variety of materials, optical structures, and photodetectors are adopted to fabricate computational spectrometers with the cooperation of reconstruction algorithms. Here, a comprehensive review of miniaturized computational spectrometers, focusing on two crucial components: spectral encoding and reconstruction algorithms are provided. Principles, features, and recent progress of spectral encoding strategies are summarized in detail, including space-modulated, time-modulated, and light-source spectral encoding. The reconstruction algorithms are classified into traditional and deep learning algorithms, and they are carefully analyzed based on the mathematical models required for spectral reconstruction. Drawing from the analysis of the two components, cooperations between them are considered, figures of merits for miniaturized computational spectrometers are highlighted, optimization strategies for improving their performance are outlined, and considerations in operating these systems are provided. The application of miniaturized computational spectrometers to achieve hyperspectral imaging is also discussed. Finally, the insights into the potential future applications and developments of computational spectrometers are provided., (© 2024 The Author(s). Advanced Science published by Wiley‐VCH GmbH.)

Objective: We introduce a new treatment verification technique to estimate the primary particle’s stopping power from prompt gamma timing measurements in proton therapy.Approach: The starting point is the Spatio-temporal Emission Recostruction technique, which provides the time-depth distribution of the emitted prompt photons with a multiple Prompt-Gamma Timing detector setup based on Lanthanum Bromide crystals. A dedicated formalism based on an analytical approximation of the stopping power is developed to obtain the desired information. Its performance is evaluated in a proof of concept configuration via Monte Carlo simulations of monochromatic proton beams impinging on a homogeneous PMMA phantom.Main Results: Results indicate stopping power estimations as good as 3.8% with respect to NIST values, and range estimations within 0.3 cm (standard deviation), when considering 250 ps FWHM timing resolution.Significance: The current study shows, for the first time, the feasibility of evaluating the stopping power of primary beams with a technique that can be performed in-vivo, opening up new possibilities in the field of treatment verification and therapy optimization.

Visual measurement methods are extensively used in various fields, such as aerospace, biomedicine, agricultural production, and social life, owing to their advantages of high speed, high accuracy, and non-contact. However, traditional camera-based measurement systems, relying on the pinhole imaging model, face challenges in achieving three-dimensional measurements using a single camera by one shot. Moreover, traditional visual systems struggle to meet the requirements of high precision, efficiency, and compact size simultaneously. With the development of light field theory, the light field camera has garnered significant attention as a novel measurement method. Due to its special structure, the light field camera enables high-precision three-dimensional measurements with a single camera through only one shot. This paper presents a comprehensive overview of light field camera measurement technologies, including the imaging principles, calibration methods, reconstruction algorithms, and measurement applications. Additionally, we explored future research directions and the potential application prospects of the light field camera.

Steerable needles are a promising technology to provide safe deployment of tools through complex anatomy in minimally invasive surgery, including tumor-related diagnoses and therapies. For the 3-D localization of these instruments in soft tissue, fiber Bragg gratings (FBGs) based reconstruction methods have gained in popularity because of the inherent advantages of optical fibers in a clinical setting, such as flexibility, immunity to electromagnetic interference, nontoxicity, and the absence of line-of-sight issues. However, methods proposed thus far focus on shape reconstruction of the steerable needle itself, where accuracy is susceptible to errors in interpolation and curve fitting methods used to estimate the curvature vectors along the needle. In this study, we propose reconstructing the shape of the path created by the steerable needle tip based on the follow-the-leader nature of many of its variants. By assuming that the path made by the tip is equivalent to the shape of the needle, this novel approach paves the way for shape reconstruction through a single set of FBGs at the needle tip, which provides curvature information about every section of the path during navigation. We propose a Kalman-filter-based sensor fusion method to update the curvature information about the sections as they are continually estimated during the insertion process. The proposed method is validated through simulation, in vitro and ex vivo experiments employing a programmable bevel-tip steerable needle (PBN). The results show clinically acceptable accuracy, with 2.87-mm mean PBN tip position error, and a standard deviation of 1.63 mm for a 120-mm 3-D insertion. [ABSTRACT FROM AUTHOR]

Hyperspectral (HS) satellite data have been widely applied in many fields due to its numerous bands. Along with the advantages of high spectral resolution, HS satellite data are still limited by some disadvantages of high acquisition cost, low revisiting capability, and low spatial resolution. Compared with HS satellites, multispectral (MS) satellites have a large number, large width, strong coverage, and high spatial resolution. Therefore, MS data can be used as the input to the spectral reconstruction (SR) to obtain HS data with high temporal resolution. Better HS data can be obtained by spectral reconstructing with these continuous multitemporal data than with single-temporal data. A multitemporal spectral reconstruction network (MTSRN) is proposed in this article, which is used to reconstruct HS images from multitemporal MS images. The proposed MTSRN comprises multiple single-temporal spectral reconstruction networks (STSRN) for extracting temporal features and a multitemporal fusion network (MTFN). The parallel component alternative (PA) post-processing method enhances the physical plausibility of reconstructed HS data. To demonstrate performance of the proposed method in aspects of multitemporal reconstruction, experiments are conducted on four multitemporal HS and MS satellite datasets. The experimental results prove that the proposed MTSRN obtains better SR results compared with the SR method based on single-temporal information. [ABSTRACT FROM AUTHOR]

Monitoring the operating conditions of residential appliances by collecting the total power consumption data of households has a great significance for smart power utilization. In this study, a graph least squares reconstruction approach is proposed. First, the graph signal is constructed using the collected active power consumption data, providing unique appliance signature information. The signal smoothness of the graph and an iterative least squares reconstruction algorithm are utilized for classification. The proposed graph reconstruction method relies on only low-sampling data from installed smart meters. It aims to address some existing problems of event-based NILM methods like measurement noise, indistinguishable load signatures, and inaccurate power reconstruction. Also, extensive training and associated calculations are not required. Simulation results on the REDD benchmark dataset demonstrate that the proposed method outperforms some of the current state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Limited-angle CT is a challenging problem in real applications. Incomplete projection data will lead to severe artifacts and distortions in reconstruction images. To tackle this problem, we propose a novel reconstruction framework termed Deep Iterative Optimization-based Residual-learning (DIOR) for limited-angle CT. Instead of directly deploying the regularization term on image space, the DIOR combines iterative optimization and deep learning based on the residual domain, significantly improving the convergence property and generalization ability. Specifically, the asymmetric convolutional modules are adopted to strengthen the feature extraction capacity in smooth regions for deep priors. Besides, in our DIOR method, the information contained in low-frequency and high-frequency components is also evaluated by perceptual loss to improve the performance in tissue preservation. Both simulated and clinical datasets are performed to validate the performance of DIOR. Compared with existing competitive algorithms, quantitative and qualitative results show that the proposed method brings a promising improvement in artifact removal, detail restoration and edge preservation. [ABSTRACT FROM AUTHOR]

Missing data reconstruction is a classical, yet challenging problem in remote sensing (RS) image processing due to the complex atmospheric environment and variability of satellite sensors. Most of the contemporary reconstruction methods either handle only one specific task or require supplementary data, while the single input for multitask reconstruction has not been explored yet. In this article, we propose a novel generative adversarial network-based unified framework for missing RS image reconstruction, which is capable of various reconstruction tasks given only single-source data as input. Specifically, we first propose a mask extraction network (MEN) to obtain a united soft mask, which represents the intrinsic prior under various scenarios and indicates not only location, but also context information. The versatility of mask extraction enables the multitask reconstruction of RS images. Besides, we propose a unified inpainting network (UIN) to repair diverse degraded images. Being specifically tailored for RS images, dilated pyramidal convolutions (DPCs) and an attention fusion mechanism (AFM) are introduced to further improve the feature extraction ability and thus exhaustly leveraging the single-input information. Extensive experiments demonstrate the uncompromising performance of the proposed method against state-of-the-art multiinput methods on diverse missing restoration. Moreover, further exploration shows the potential of the proposed method to utilize joint spatial–spectral–temporal information, which is evaluated to outperform existing competitors on remote sense images. [ABSTRACT FROM AUTHOR]

Motivated by applications to DNA storage, we study reconstruction and list-reconstruction schemes for integer vectors that suffer from limited-magnitude errors. We characterize the asymptotic size of the intersection of error balls in relation to the code’s minimum distance. We also devise efficient reconstruction algorithms for various limited-magnitude error parameter ranges. We then extend these algorithms to the list-reconstruction scheme, and show the trade-off between the asymptotic list size and the number of required channel outputs. These results apply to all codes, without any assumptions on the code structure. Finally, we also study linear reconstruction codes with small intersection, as well as show a connection to list-reconstruction codes for the tandem-duplication channel. [ABSTRACT FROM AUTHOR]

As one of the most effective technologies for network reconstruction, compressive sensing can recover signals from a small amount of observed data through sparse search or greedy algorithms in the assumption that the unknown signal is sufficiently sparse on a specific basis. However, there often occurs loss of precision even failure in the process of reconstruction without enough prior information. Therefore, the purpose of this article is to solve the problem of low reconstruction accuracy by mining implicit structural information in the network. Specifically, we propose a novel and efficient algorithm (MCM_TRA) for reconstructing the structure of the $K$ -forked tree network. Based on evolutionary game dynamics, the modified clustering method (MCM) classifies all nodes into two sets, then a two-stage reconstruction algorithm (TRA) is illustrated to recover the node signals in different sets. The experimental results demonstrate that the MCM_TRA enhances the reconstruction accuracy prominently than previous algorithms. Moreover, extensive sensitivity analysis shows that the reconstruction effect can be promoted for a broad range of parameters, which further indicates the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Background: CT perfusion imaging (CTP) is used in the diagnostic workup of acute ischemic stroke (AIS). CTP may be performed within the angio suite using flat detector CT (FDCT) to help reduce patient management time. Purpose: In order to significantly improve FDCT perfusion (FDCTP) imaging, data‐processing algorithms need to be able to compensate for the higher levels of noise, slow rotation speed, and a lower frame rate of current FDCT devices. Methods: We performed a realistic simulation of FDCTP acquisition based on CTP data from seven subjects. We used the time separation technique (TST) as a model‐based approach for FDCTP data processing. We propose a novel dimension reduction in which we approximate the time attenuation curves by a linear combination of trigonometric functions. Our goal was to show that the TST can be used even without prior assumptions on the shape of the attenuation profiles. Results: We first demonstrated that a trigonometric basis is suitable for dimension reduction of perfusion data. Using simulated FDCTP data, we have shown that a trigonometric basis in the TST provided better results than the classical straightforward processing even with additional noise. Average correlation coefficients of perfusion maps were improved for cerebral blood flow (CBF), cerebral blood volume, mean transit time (MTT) maps. In a moderate noise scenario, the average Pearson's coefficient for the CBF map was improved using the TST from 0.76 to 0.81. For the MTT map, it was improved from 0.37 to 0.45. Furthermore, we achieved a total processing time from the reconstruction of FDCTP data to the generation of perfusion maps of under 5 min. Conclusions: In our study cohort, perfusion maps created from FDCTP data using the TST with a trigonometric basis showed equivalent perfusion deficits to classic CT perfusion maps. It follows, that this novel FDCTP technique has potential to provide fast and accurate FDCTP imaging for AIS patients. [ABSTRACT FROM AUTHOR]

As an innovative concept of high-resolution and wide-swath system, the low-oversampled staggered synthetic aperture radar (SAR) can not only deal with the blind ranges but also suppress range ambiguities and reduce the data volume. Due to the variation of pulse repetition interval (PRI), there will be echo pulse loss and nonuniform sampling in azimuth. Generally, the existing reconstruction algorithms mostly resample the nonuniformly sampled signal into a uniform grid and then perform conventional focused processing. However, the accuracy of the resampling is limited, and the advantage of the nonuniformity over uniform sampling in terms of reconstruction performance is ignored, especially with low oversampling factors. In this article, a reconstruction algorithm for low-oversampled staggered SAR is proposed based on the sparsity Bayesian learning (SBL) in the presence of a nonlinear PRI variation strategy. To ensure that the blind range distribution, which depends on the PRI variation strategy, brings a superior reconstruction performance, we define a novel objective function and optimize a sequence of nonlinear PRI variation with genetic algorithm (GA). On the basis of the optimized sequence, the proposed reconstruction algorithm performs the second-order keystone transform to achieve range curvature correction for nonuniformly sampled data in azimuth. Then, a nonuniform observation model is established. The SBL using a hierarchical form of the Laplace prior is applied to reconstruct the focused images directly with the nonuniform sampling. Simulations and experiments on raw data generated in the staggered SAR mode with low oversampling factors are performed to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Due to its strong performance in handling uncertain and ambiguous data, the fuzzy ${k}$ -nearest-neighbor method (FKNN) has realized substantial success in a wide variety of applications. However, its classification performance would be heavily deteriorated if the number k of nearest neighbors was unsuitably fixed for each testing sample. This study examines the feasibility of using only one fixed k value for FKNN on each testing sample. A novel FKNN-based classification method, namely, fuzzy KNN method with adaptive nearest neighbors (A-FKNN), is devised for learning a distinct optimal k value for each testing sample. In the training stage, after applying a sparse representation method on all training samples for reconstruction, A-FKNN learns the optimal ${k}$ value for each training sample and builds a decision tree (namely, A-FKNN tree) from all training samples with new labels (the learned optimal ${k}$ values instead of the original labels), in which each leaf node stores the corresponding optimal ${k}$ value. In the testing stage, A-FKNN identifies the optimal ${k}$ value for each testing sample by searching the A-FKNN tree and runs FKNN with the optimal ${k}$ value for each testing sample. Moreover, a fast version of A-FKNN, namely, FA-FKNN, is designed by building the FA-FKNN decision tree, which stores the optimal k value with only a subset of training samples in each leaf node. Experimental results on 32 UCI datasets demonstrate that both A-FKNN and FA-FKNN outperform the compared methods in terms of classification accuracy, and FA-FKNN has a shorter running time. [ABSTRACT FROM AUTHOR]

The problem of reconstructing nonlinear and complex dynamical systems from available data or time series is prominent in many fields, including engineering, physical, computer, biological, and social sciences. Many methods have been proposed to address this problem and their performance is satisfactory. However, none of them can reconstruct network structure from large-scale real-time streaming data, which leads to the failure of real-time and online analysis or control of complex systems. In this article, to overcome the limitations of current methods, we first extend the network reconstruction problem (NRP) to online settings, and then develop a follow-the-regularized-leader (FTRL)-Proximal style method to address the online complex NRP; we refer to it as Online-NR. The performance of Online-NR is validated on synthetic evolutionary game network reconstruction datasets and eight real-world networks. The experimental results demonstrate that Online-NR can effectively solve the problem of online network reconstruction with large-scale real-time streaming data. Moreover, Online-NR outperforms or matches nine state-of-the-art network reconstruction methods. [ABSTRACT FROM AUTHOR]