In this paper, the Towards High Performance Voxel-based 3D Object Detection (Voxel-RCNN) three-dimensional (3D) point cloud object detection model is used as the benchmark network. Aiming at the problems existing in the current mainstream 3D point cloud voxelization methods, such as the backbone and the lack of feature expression ability under the bird’s-eye view (BEV), a high-performance voxel-based 3D object detection network (Reinforced Voxel-RCNN) is proposed. Firstly, a 3D feature extraction module based on the integration of inverted residual convolutional network and weight normalization is designed on the 3D backbone. This module can not only well retain more point cloud feature information, enhance the information interaction between convolutional layers, but also improve the feature extraction ability of the backbone network. Secondly, a spatial feature-semantic fusion module based on spatial and channel attention is proposed from a BEV perspective. The mixed use of channel features and semantic features further improves the network’s ability to express point cloud features. In the comparison of experimental results on the public dataset KITTI, the experimental results of this paper are better than many voxel-based methods. Compared with the baseline network, the 3D average accuracy and BEV average accuracy on the three categories of Car, Cyclist, and Pedestrians are improved. Among them, in the 3D average accuracy, the improvement rate of Car category is 0.23%, Cyclist is 0.78%, and Pedestrians is 2.08%. In the context of BEV average accuracy, enhancements are observed: 0.32% for the Car category, 0.99% for Cyclist, and 2.38% for Pedestrians. The findings demonstrate that the algorithm enhancement introduced in this study effectively enhances the accuracy of target category detection.

Sparse-view CT reconstruction has gained significant attention due to the growing concerns about radiation safety. Although recent deep learning-based image domain reconstruction methods have achieved encouraging performance over iterative methods, effectively capturing intricate details and organ structures while suppressing noise remains challenging. This study presents a novel dual-stream encoder-decoder-based reconstruction network that combines global path reconstruction from the entire image with local path reconstruction from image patches. These two branches interact through an attention module, which enhances visual quality and preserves image details by learning correlations between image features and patch features. Visual and numerical results show that the proposed method has superior reconstruction capabilities to state-of-the-art 180-, 90-, and 45-view CT reconstruction methods.

We explore the maximum total number of edge crossings and the maximum geometric thickness of the Euclidean minimum-weight (k, ℓ)-tight graph on a planar point set P. In this paper, we show that (10/7－ε)|P| and (11/6－ε)|P| are lower bounds for the maximum total number of edge crossings for any ε ＞ 0 in cases (k,ℓ)=(2,3) and (2,2), respectively. We also show that the lower bound for the maximum geometric thickness is 3 for both cases. In the proofs, we apply the method of arranging isomorphic units regularly. While the method is developed for the proof in case (k,ℓ)=(2,3), it also works for different ℓ.

Negation scope resolution is the process of detecting the negated part of a sentence. Unlike the syntax-based approach employed in previous researches, state-of-the-art methods performed better without the explicit use of syntactic structure. This work revisits the syntax-based approach and re-evaluates the effectiveness of syntactic structure in negation scope resolution. We replace the parser utilized in the prior works with state-of-the-art parsers and modify the syntax-based heuristic rules. The experimental results demonstrate that the simple modifications enhance the performance of the prior syntax-based method to the same level as state-of-the-art end-to-end neural-based methods.

Compressed sensing is a rapidly growing research field in signal and image processing, machine learning, statistics, and systems control. In this survey paper, we provide a review of the theoretical foundations of compressed sensing and present state-of-the-art algorithms for solving the corresponding optimization problems. Additionally, we discuss several practical applications of compressed sensing, such as group testing, sparse system identification, and sparse feedback gain design, and demonstrate their effectiveness through Python programs. This survey paper aims to contribute to the advancement of compressed sensing research and its practical applications in various scientific disciplines.

Seen from the Internet Service Provider (ISP) side, network traffic monitoring is an indispensable part during network service provisioning, which facilitates maintaining the security and reliability of the communication networks. Among the numerous traffic conditions, we should pay extra attention to traffic anomaly, which significantly affects the network performance. With the advancement of Machine Learning (ML), data-driven traffic anomaly detection algorithms have established high reputation due to the high accuracy and generality. However, they are faced with challenges on inefficient traffic feature extraction and high computational complexity, especially when taking the evolving property of traffic process into consideration. In this paper, we proposed an online learning framework for traffic anomaly detection by embracing Gaussian Process (GP) and Sparse Representation (SR) in two steps: 1). To extract traffic features from past records, and better understand these features, we adopt GP with a special kernel, i.e., mixture of Gaussian in the spectral domain, which makes it possible to more accurately model the network traffic for improving the performance of traffic anomaly detection. 2). To combat noise and modeling error, observing the inherent self-similarity and periodicity properties of network traffic, we manually design a feature vector, based on which SR is adopted to perform robust binary classification. Finally, we demonstrate the superiority of the proposed framework in terms of detection accuracy through simulation.

Synthetic aperture radar (SAR) is a device for observing the ground surface and is one of the important technologies in the field of microwave remote sensing. In SAR observation, a platform equipped with a small-aperture antenna flies in a straight line and continuously radiates pulse waves to the ground during the flight. After that, by synthesizing the series of observation data obtained during the flight, one realize high-resolution ground surface observation. In SAR observation, there are two spatial resolutions defined in the range and azimuth directions and they are limited by the bandwidth of the SAR system. The purpose of this study is to improve the resolution of SAR by sparse reconstruction. In particular, we aim to improve the resolution of SAR without changing the frequency parameters. In this paper, we propose to improve the resolution of SAR using the deconvolution iterative shrinkage-thresholding algorithm (ISTA) and verify the proposed method by carrying out an experimental analysis using an actual SAR dataset. Experimental results show that the proposed method can improve the resolution of SAR with low computational complexity.

Glaucoma is a common high-incidence eye disease. The detection of the optic cup and optic disc in fundus images is one of the important steps in the clinical diagnosis of glaucoma. However, the fundus images are generally intensity inhomogeneity, and complex organizational structure, and are disturbed by blood vessels and lesions. In order to extract the optic disc and optic cup regions more accurately, we propose a segmentation method of the optic disc and optic cup in fundus image based on distance regularized two-layer level with sparse shape prior constraint. The experimental results show that our method can segment the optic disc and optic cup region more accurately and obtain satisfactory results.

To overcome the challenge in micro-expression recognition that it only emerge in several small facial regions with low intensity, some researchers proposed facial region partition mechanisms and introduced group sparse learning methods for feature selection. However, such methods have some shortcomings, including the complexity of region division and insufficient utilization of critical facial regions. To address these problems, we propose a novel Group Sparse Reduced Rank Tensor Regression (GSRRTR) to transform the fearure matrix into a tensor by laying blocks and features in different dimensions. So we can process grids and texture features separately and avoid interference between grids and features. Furthermore, with the use of Tucker decomposition, the feature tensor can be decomposed into a product of core tensor and a set of matrix so that the number of parameters and the computational complexity of the scheme will decreased. To evaluate the performance of the proposed micro-expression recognition method, extensive experiments are conducted on two micro expression databases: CASME2 and SMIC. The experimental results show that the proposed method achieves comparable recognition rate with less parameters than state-of-the-art methods.

This paper addresses short-length sparse superposition codes (SSCs) over the additive white Gaussian noise channel. Damped approximate message-passing (AMP) is used to decode short SSCs with zero-mean independent and identically distributed Gaussian dictionaries. To design damping factors in AMP via deep learning, this paper constructs deep-unfolded damped AMP decoding networks. An annealing method for deep learning is proposed for designing nearly optimal damping factors with high probability. In annealing, damping factors are first optimized via deep learning in the low signal-to-noise ratio (SNR) regime. Then, the obtained damping factors are set to the initial values in stochastic gradient descent, which optimizes damping factors for slightly larger SNR. Repeating this annealing process designs damping factors in the high SNR regime. Numerical simulations show that annealing mitigates fluctuation in learned damping factors and outperforms exhaustive search based on an iteration-independent damping factor.

This study considered an extension of a sparse regularization method with scaling, especially in thresholding methods that are simple and typical examples of sparse modeling. In this study, in the setting of a non-parametric orthogonal regression problem, we developed and analyzed a thresholding method in which soft thresholding estimators are independently expanded by empirical scaling values. The scaling values have a common hyper-parameter that is an order of expansion of an ideal scaling value to achieve hard thresholding. We simply refer to this estimator as a scaled soft thresholding estimator. The scaled soft thresholding method is a bridge method between soft and hard thresholding methods. This new estimator is indeed consistent with an adaptive LASSO estimator in the orthogonal case; i.e., it is thus an another derivation of an adaptive LASSO estimator. It is a general method that includes soft thresholding and non-negative garrote as special cases. We subsequently derived the degree of freedom of the scaled soft thresholding in calculating the Stein's unbiased risk estimate. We found that it is decomposed into the degree of freedom of soft thresholding and the remainder term connecting to the hard thresholding. As the degree of freedom reflects the degree of over-fitting, this implies that the scaled soft thresholding has an another source of over-fitting in addition to the number of un-removed components. The theoretical result was verified by a simple numerical example. In this process, we also focused on the non-monotonicity in the above remainder term of the degree of freedom and found that, in a sparse and large sample setting, it is mainly caused by useless components that are not related to the target function.

Sparse code division multiple access (SCMA) is a non-orthogonal multiple access (NOMA) technology that can improve frequency band utilization and allow many users to share quite a few resource elements (REs). This paper uses the modulation of lattice theory to develop a systematic construction procedure for the design of SCMA codebooks under Gaussian channel environments that can achieve near-optimal designs, especially for cases that consider large-scale SCMA parameters. However, under the condition of large-scale SCMA parameters, the mother constellation (MC) points will overlap, which can be solved by the method of the partial dimensions transformation (PDT). More importantly, we consider the upper bounded error probability of the signal transmission in the AWGN channels, and design a codeword allocation method to reduce the inter symbol interference (ISI) on the same RE. Simulation results show that under different codebook sizes and different overload rates, using two different message passing algorithms (MPA) to verify, the codebook proposed in this paper has a bit error rate (BER) significantly better than the reference codebooks, moreover the convergence time does not exceed that of the reference codebooks.

This paper evaluates the bluetooth low energy (BLE) positioning systems using the sparse-training data through the comparison experiments. The sparse-training data is extracted from the database including enough data for realizing the highly accurate and precise positioning. First, we define the sparse-training data, i.e., the data collection time and the number of smartphones, directions, beacons, and reference points, on BLE positioning systems. Next, the positioning performance evaluation experiments are conducted in two indoor environments, that is, an indoor corridor as a one-dimensionally spread environment and a hall as a twodimensionally spread environment. The algorithms for comparison are the conventional fingerprint algorithm and the hybrid algorithm (the authors already proposed, and combined the proximity algorithm and the fingerprint algorithm). Based on the results, we confirm that the hybrid algorithm performs well in many cases even when using sparse-training data. Consequently, the robustness of the hybrid algorithm, that the authors already proposed for the sparse-training data, is shown.

Millimeter wave synthetic aperture interferometric radiometers (SAIR) are very powerful instruments, which can effectively realize high-precision imaging detection. However due to the existence of interference factor and complex near-field error, the imaging effect of near-field SAIR is usually not ideal. To achieve better imaging results, a new fully connected imaging network (FCIN) is proposed for near-field SAIR. In FCIN, the fully connected network is first used to reconstruct the image domain directly from the visibility function, and then the residual dense network is used for image denoising and enhancement. The simulation results show that the proposed FCIN method has high imaging accuracy and shorten imaging time.

Visual Question Answering (VQA) is multi-task research that requires simultaneous processing of vision and text. Recent research on the VQA models employ a co-attention mechanism to build a model between the context and the image. However, the features of questions and the modeling of the image region force irrelevant information to be calculated in the model, thus affecting the performance. This paper proposes a novel dual self-guided attention with sparse question networks (DSSQN) to address this issue. The aim is to avoid having irrelevant information calculated into the model when modeling the internal dependencies on both the question and image. Simultaneously, it overcomes the coarse interaction between sparse question features and image features. First, the sparse question self-attention (SQSA) unit in the encoder calculates the feature with the highest weight. From the self-attention learning of question words, the question features of larger weights are reserved. Secondly, sparse question features are utilized to guide the focus on image features to obtain fine-grained image features, and to also prevent irrelevant information from being calculated into the model. A dual self-guided attention (DSGA) unit is designed to improve modal interaction between questions and images. Third, the sparse question self-attention of the parameter δ is optimized to select these question-related object regions. Our experiments with VQA 2.0 benchmark datasets demonstrate that DSSQN outperforms the state-of-the-art methods. For example, the accuracy of our proposed model on the test-dev and test-std is 71.03% and 71.37%, respectively. In addition, we show through visualization results that our model can pay more attention to important features than other advanced models. At the same time, we also hope that it can promote the development of VQA in the field of artificial intelligence (AI).

In this letter, we propose a novel transferable sparse regression (TSR) method, for cross-database facial expression recognition (FER). In TSR, we firstly present a novel regression function to regress the data into a latent representation space instead of a strict binary label space. To further alleviate the influence of outliers and overfitting, we impose a row sparsity constraint on the regression term. And a pairwise relation term is introduced to guide the feature transfer learning. Secondly, we design a global graph to transfer knowledge, which can well preserve the cross-database manifold structure. Moreover, we introduce a low-rank constraint on the graph regularization term to uncover additional structural information. Finally, several experiments are conducted on three popular facial expression databases, and the results validate that the proposed TSR method is superior to other non-deep and deep transfer learning methods.

As an emerging technology, device-free localization (DFL) using wireless sensor networks to detect targets not carrying any electronic devices, has spawned extensive applications, such as security safeguards and smart homes or hospitals. Previous studies formulate DFL as a classification problem, but there are still some challenges in terms of accuracy and robustness. In this paper, we exploit a generalized thresholding algorithm with parameter p as a penalty function to solve inverse problems with sparsity constraints for DFL. The function applies less bias to the large coefficients and penalizes small coefficients by reducing the value of p. By taking the distinctive capability of the p thresholding function to measure sparsity, the proposed approach can achieve accurate and robust localization performance in challenging environments. Extensive experiments show that the algorithm outperforms current alternatives.

Convolutional neural network (CNN) has a high recognition rate in image recognition and are used in embedded systems such as smartphones, robots and self-driving cars. Low-end FPGAs are candidates for embedded image recognition platforms because they achieve real-time performance at a low cost. However, CNN has significant parameters called weights and internal data called feature maps, which pose a challenge for FPGAs for performance and memory capacity. To solve these problems, we exploit a split-CNN and weight sparseness. The split-CNN reduces the memory footprint by splitting the feature map into smaller patches and allows the feature map to be stored in the FPGA's high-throughput on-chip memory. Weight sparseness reduces computational costs and achieves even higher performance. We designed a dedicated architecture of a sparse CNN and a memory buffering scheduling for a split-CNN and implemented this on the PYNQ-Z1 FPGA board with a low-end FPGA. An experiment on classification using VGG16 shows that our implementation is 3.1 times faster than the GPU, and 5.4 times faster than an existing FPGA implementation.

As scientific and technological resources are experiencing information overload, it is quite expensive to find resources that users are interested in exactly. The personalized recommendation system is a good candidate to solve this problem, but data sparseness and the cold starting problem still prevent the application of the recommendation system. Sparse data affects the quality of the similarity measurement and consequently the quality of the recommender system. In this paper, we propose a matrix factorization recommendation algorithm based on similarity calculation(SCMF), which introduces potential similarity relationships to solve the problem of data sparseness. A penalty factor is adopted in the latent item similarity matrix calculation to capture more real relationships furthermore. We compared our approach with other 6 recommendation algorithms and conducted experiments on 5 public data sets. According to the experimental results, the recommendation precision can improve by 2% to 9% versus the traditional best algorithm. As for sparse data sets, the prediction accuracy can also improve by 0.17% to 18%. Besides, our approach was applied to patent resource exploitation provided by the wanfang patents retrieval system. Experimental results show that our method performs better than commonly used algorithms, especially under the cold starting condition.

Recent trends in designing filters involve development of sparse filters with coefficients that not only have real but also zero values. These sparse filters can achieve a high performance through optimizing the selection of the zero coefficients and computing the real (non-zero) coefficients. Designing an infinite impulse response (IIR) sparse filter is more challenging than designing a finite impulse response (FIR) sparse filter. Therefore, studies on the design of IIR sparse filters have been rare. In this study, we consider IIR filters whose coefficients involve zero value, called sparse IIR filter. First, we formulate the design problem as a linear programing problem without imposing any stability condition. Subsequently, we reformulate the design problem by altering the error function and prepare several possible denominator polynomials with stable poles. Finally, by incorporating these methods into successive thinning algorithms, we develop a new design algorithm for the filters. To demonstrate the effectiveness of the proposed method, its performance is compared with that of other existing methods.