Search

Driven by a wide range of essential applications, significant achievements are made to explore WiFi-based Human Activity Recognition (HAR) techniques that utilize the information collected by commercial off-the-shelf WiFi infrastructures to infer human activities without the need for subjects to carry any devices. Although existing WiFi-based HAR systems achieve satisfactory performance in some instances, they are faced with a severe challenge that the impacts of ubiquitous Co-channel Interference (CCI) on WiFi signals are inevitable. This downgrades the performance of these HAR systems significantly. To address this challenge, we propose PhaseAnti, a novel WiFi-based HAR system to exploit the CCI-independent phase component, Nonlinear Phase Error Variation (NLPEV), of WiFi Channel State Information to cope with the negative effects of CCI. The stability of NLPEV data and the sensibility of this component to motions are rigorously analyzed. Furthermore, validated by extensive properly designed experiments, this phase component across subcarriers is invariant under various CCI scenarios while sufficiently distinct for different motions. Therefore, the NLPEV data can be used and processed effectively to perform HAR in CCI scenarios. Extensive experiments with various daily activities in different indoor rooms demonstrate the superior effectiveness and generalizability of the proposed PhaseAnti system under various CCI scenarios.

The scene graph is a symbolic data structure that comprehensively describes the objects and visual relations in a visual scene, while ignoring the inherent perceptual saliency of each visual relation (i.e., relation saliency). However, humans often quickly allocate attention to important/salient visual relations in a scene. To align with such human perception of a scene, we explicitly model the perceptual saliency of visual relation in scene graph by upgrading each graph edge (i.e., visual relation) with an attribute of relation saliency. We present a new design, named as Saliency-guided Message Passing (SMP), that boosts the generation of such scene graph structure with the guidance from the visual relation saliency. Technically, an object interaction encoder is first utilized to strengthen object relation representations by jointly exploiting the appearance, semantic, and spatial relations in between. A branch is further leveraged to estimate the relation saliency of each visual relation by ordinal regression. Next, conditioned on the object and relation features (coupled with the estimated relation saliency), our SMP enhances scene graph generation by performing message passing over the objects and the most salient relations. Extensive experiments on VG-KR and VG150 datasets demonstrate the superiority of SMP for the scene graph generation. Moreover, we empirically validate the compelling generalizability of the learned scene graphs via SMP on downstream tasks like cross-model retrieval and image captioning.

We present an analysis to extract kaon parton distribution functions (PDFs) for the first time using meson-induced Drell-Yan and quarkonium production data. Starting from the statistical model first developed for determining the partonic structure of spin-1/2 nucleon and later applied to the spin-0 pion, we have extended this approach to perform a global fit to existing kaon-induced Drell-Yan and $J/\psi$ production data. These data are well described by the statistical model, allowing a first extraction of the kaon PDFs. We find that both the Drell-Yan and the $J/\psi$ data favor a harder valence distribution for strange quark than for up quark in kaon. The kaon gluon distribution is further constrained by the $J/\psi$ production data. In particular, the momentum fraction carried by gluons is found to be similar for pion and kaon., Comment: 6 pages, 3 figures. arXiv admin note: text overlap with arXiv:2202.12547

Cytomegalovirus (CMV) viremia is associated with a higher mortality rate and prolonged intensive care unit (ICU) stay for critically ill patients. CMV infection causes transient but substantial immunosuppression for transplant recipients, increasing risk of fungal infection. The association between CMV viremia and invasive pulmonary aspergillosis (IPA) for critically ill patients is still unknown.We retrospectively analyzed patients received bronchoalveolar lavage (BAL), galactomannan test, influenza survey and blood CMV viral load test in ICUs of a university hospital between April 2017 and May 2020. Independent risks for IPA were analyzed by multivariable logistic regression.A total of 136 patients were included. Twenty-one patients had IPA, 48 patients had CMV viremia and 22 patients had influenza. In a multivariable logistic regression model, patients with CMV viremia or influenza had higher IPA risk (adjusted odds ratio, 3.98 and 8.72; 95% CI, 1.26-12.60 and 2.64-28.82; p value = 0.019 and0.001, respectively.). Patients with detectable CMV in BAL fluid did not have higher IPA risk (crude odds ratio, 0.95; 95% CI, 0.33-2.79; p value = 0.933). After stratifying patients by CMV viral load, the IPA risk is higher for patients with higher viral loads. There is an additive synergistic effect on IPA risk between CMV viremia and influenza infection.For critically ill patients, CMV viremia is an independent risk factor of IPA. Patients with higher blood CMV viral loads have a higher risk of IPA. CMV viremia and influenza have an additive synergistic effect for IPA risk in critically ill patients.

Bud dormancy is crucial for winter survival and is characterized by the inability of the bud meristem to respond to growth-promotive signals before the chilling requirement (CR) is met. However, our understanding of the genetic mechanism regulating CR and bud dormancy remains limited. This study identified PpDAM6 (DORMANCY-ASSOCIATED MADS-box) as a key gene for CR using a GWAS (Genome-Wide Association Study) analysis based on structural variations (SVs) in 345 peach (Prunus persica (L.) Batsch) accessions. The function of PpDAM6 in CR regulation was demonstrated by transiently silencing the gene in peach buds and stably overexpressing the gene in transgenic apple (Malus × domestica) plants. The results showed an evolutionarily conserved function of PpDAM6 in regulating bud dormancy release, followed by vegetative growth and flowering, in peach and apple. The 30-bp deletion in the PpDAM6 promoter was substantially associated with reducing PpDAM6 expression in low-CR accessions. A PCR marker based on the 30-bp indel was developed to distinguish peach plants with non-low and low CR. Modification of the H3K27me3 marker at the PpDAM6 locus showed no apparent change across the dormancy process in low- and non-low-chilling requirement cultivars. Additionally, H3K27me3 modification occurred earlier in low-CR cultivars on a genome-wide scale. PpDAM6 could mediate cell-cell communication by inducing the expression of the downstream genes PpNCED1 (9-cis-epoxycarotenoid dioxygenase 1), encoding a key enzyme for ABA biosynthesis, and CALS (CALLOSE SYNTHASE), encoding callose synthase. We shed light on a gene regulatory network formed by PpDAM6-containing complexes that mediate CR underlying dormancy and budbreak in peach. A better understanding of the genetic basis for natural variations of CR can help breeders develop cultivars with different CR for growing in different geographical regions.

As a technically challenging topic, visual storytelling aims at generating an imaginary and coherent story with narrative multi-sentences from a group of relevant images. Existing methods often generate direct and rigid descriptions of apparent image-based contents, because they are not capable of exploring implicit information beyond images. Hence, these schemes could not capture consistent dependencies from holistic representation, impairing the generation of reasonable and fluent story. To address these problems, a novel knowledge-enriched attention network with group-wise semantic model is proposed. Three main novel components are designed and supported by substantial experiments to reveal practical advantages. First, a knowledge-enriched attention network is designed to extract implicit concepts from external knowledge system, and these concepts are followed by a cascade cross-modal attention mechanism to characterize imaginative and concrete representations. Second, a group-wise semantic module with second-order pooling is developed to explore the globally consistent guidance. Third, a unified one-stage story generation model with encoder-decoder structure is proposed to simultaneously train and infer the knowledge-enriched attention network, group-wise semantic module and multi-modal story generation decoder in an end-to-end fashion. Substantial experiments on the popular Visual Storytelling dataset with both objective and subjective evaluation metrics demonstrate the superior performance of the proposed scheme as compared with other state-of-the-art methods.

Generative Adversarial Networks (GAN) has become more and more popular these years. However, it is difficult to train and suffers from the training instability problem. To tackle this difficulty, this paper proposes a novel approach. Our idea is intuitive but proven to be very useful. In essence, it combines saturating loss and non-saturating loss into the loss function. Thus it will exploit the complementary statistical properties from two kinds of loss functions to effectively improve the training stability. We term our method twin discriminator Generative Adversarial Networks (TWGAN) which, unlike GAN, has a generator and a twin discriminator. The twin discriminator consists of two discriminators with identical architecture and both of them aim to distinguish whether the samples are from real data or fake data. We develop theoretical analysis to show that, given the optimal discriminators, optimizing the generator of TWGAN reduces to minimizing the Kullback-Leibler (KL) divergence between the distribution of generated data (Pg) and the distribution of real data (Pdata), hence effectively addressing the training instability problem. Extensive experiments on MNIST, Fashion MNIST, CIFAR-10/100 and STL-10 datasets demonstrate that the competitive performance of our TWGAN in generating good quality and diverse samples over baselines. The obtained highest inception score (IS) and lowest Frechet Inception Distance (FID), compared with other state-of-the-art GANs, show the superiority of our TWGAN.

In this paper, we present LensCast, a novel cross-layer video transmission framework for wireless networks, which seamlessly integrates millimeter wave (mmWave) lens multiple-input multiple-output (MIMO) with robust video transmission. LensCast is designed to exploit the video content diversity at the application layer, together with the spatial path diversity of lens antenna array at the physical layer, to achieve graceful video transmission performance under varying channel conditions. In LensCast, a transmission distortion minimization problem is formulated with the consideration of video chunk scheduling, path matching and power allocation, which is an intractable mixed integer non-linear programming (MINLP) problem. The solution of this MINLP problem is converted into resource allocation (i.e., joint path matching and power allocation) plus chunk scheduling. First, resource allocation is investigated with given chunk scheduling results. By analyzing the optimality of the resource allocation problem, a winner-takes-all assignment is obtained to guide resource allocation. After that, a greedy water-filling algorithm is proposed as a near-optimal solution. Second, we propose a low-complexity chunk scheduling algorithm to schedule chunks for each transmission. Simulation results demonstrate that the proposed LensCast achieves an improved performance in terms of both peak signal-to-noise ratio and visual quality comparing with reference schemes.

Limited backhaul bandwidth and blockage effects are two main factors limiting the practical deployment of millimeter wave (mmWave) networks. To tackle these issues, we study the feasibility of relaying as well as caching in mmWave networks. A user association and relaying (UAR) criterion dependent on both caching status and maximum biased received power is proposed by considering the spatial correlation caused by the coexistence of base stations (BSs) and relay nodes (RNs). A joint UAR and caching placement problem is then formulated to maximize the backhaul offloading traffic. Using stochastic geometry tools, we decouple the joint UAR and caching placement problem by analyzing the relationship between UAR probabilities and caching placement probabilities. We then optimize the transformed caching placement problem based on polyblock outer approximation by exploiting the monotonic property in the general case and utilizing convex optimization in the noise-limited case. Accordingly, we propose a BS and RN selection algorithm where caching status at BSs and maximum biased received power are jointly considered. Experimental results demonstrate a significant enhancement of backhaul offloading using the proposed algorithms, and show that deploying more RNs and increasing cache size in mmWave networks is a more cost-effective alternative than increasing BS density to achieve similar backhaul offloading performance.

Background Pendelluft occurs in patients with acute respiratory distress syndrome (ARDS) during spontaneous breaths. Quantifying pendelluft in ARDS patients has not been performed before. We combined electrical impedance tomography (EIT) and respiratory mechanics monitoring to quantitatively examine pendelluft in trigger and reverse triggering breaths in mechanically ventilated patients with ARDS. Methods EIT and respiratory mechanics measurements were analyzed in 20 mechanically ventilated patients with ARDS during transitioning from controlled to spontaneous breaths following discontinuance of myorelaxant under volume-cycled ventilation. Breath selection was based on 4 levels of esophageal pressure swing (∆Pes). These were rest (0 cm H2O, breaths = 200), low (2O, breaths = 471), moderate (≥ 5, < 10cm H2O, breaths = 906), and high effort (≥ 10cm H2O, breaths = 565). A total of 2,142 breaths were analyzed. Results The pendelluft response to breathing efforts varied and was significantly greater in trigger versus reverse triggering breaths (3.9 ± 6.8 vs 1.9 ± 2.8 ml, respectively, p es slope (ml/cmH2O). For trigger breaths, high pendelluft group (n = 9, slope 0.7 to 2.4 ml/cmH2O) was significantly associated with lower peak airway/plateau pressure and lower respiratory system/lung elastance than low pendelluft group (n = 11, slope − 0.1 to 0.3 ml/cmH2O). For reverse triggering breaths, there was no difference in respiratory mechanics between high (n = 4, 0.49 to 2.53 ml/cmH2O) and low pendelluft (n = 12, -0.22 to 0.25 ml/cmH2O) groups. The prediction of pendelluft by ∆Pes was characterized by a low positive predictive value. ARDS cases with high effort-related pendelluft were uncommon. The prediction of pendelluft was not significant in reverse triggering breaths. Conclusions Effort-related pendelluft should be individualized. Pendelluft is higher in trigger breaths than reverse triggering breaths. For trigger breaths, high pendelluft is likely to occur in ARDS patients with lower lung elastance and lower peak airway/plateau pressure. However, ARDS cases with high effort-related pendelluft were uncommon in our study population.

The pion, as the Goldstone boson of the strong interaction, is the lightest QCD bound state and responsible for the long-range nucleon-nucleon interaction inside the nucleus. Our knowledge on the pion partonic structure is limited by the existing Drell-Yan data which are primarily sensitive to the pion valence-quark distributions. The recent progress of global analysis of pion's parton distribution functions (PDFs) utilizing various experimental approaches are introduced. From comparisons between the pion-induced $J/\psi$ and $\psi(2S)$ production data with theoretical calculations using the CEM and NRQCD models, we show how these charmonium production data could provide useful constraints on the pion PDFs., Comment: 17 pages, 6 figures; invited review. arXiv admin note: text overlap with arXiv:2006.06947, arXiv:2209.04072

We present an analysis to extract kaon parton distribution functions (PDFs) for the first time using meson-induced Drell-Yan and quarkonium production data. Starting from the statistical model first developed for determining the partonic structure of spin-1/2 nucleon and later applied to the spin-0 pion, we have extended this approach to perform a global fit to existing kaon-induced Drell-Yan and $J/ψ$ production data. These data are well described by the statistical model, allowing a first extraction of the kaon PDFs. We find that both the Drell-Yan and the $J/ψ$ data favor a harder valence distribution for strange quark than for up quark in kaon. The kaon gluon distribution is further constrained by the $J/ψ$ production data. In particular, the momentum fraction carried by gluons is found to be similar for pion and kaon., 6 pages, 3 figures. arXiv admin note: text overlap with arXiv:2202.12547

Recently, robust video transmission system that can eliminate the cliff effect in digital video transmission has attracted great interest from both academia and industry. By linearizing the whole system, robust video transmission is intrinsically scalable to channel conditions in mobile networks. However, the heterogeneity of user devices in terms of viewing resolution has not been well studied for robust video broadcast systems. In this paper, we propose a spatial scalability enabled robust video broadcast (SSRVB) system, aiming at accommodating diverse users with both heterogeneous resolutions and heterogeneous channel conditions. In SSRVB, a novel spatial decomposition method based on linear projection is first designed for robust video transmission. Then the transmission distortion minimization problem with joint subcarrier matching and power allocation is formulated. A near-optimal low-complexity subcarrier matching algorithm based on auction theory and an optimal power allocation strategy are also proposed. Furthermore, an iterative algorithm is designed to solve the problem of joint resource allocation. Simulation results demonstrate that SSRVB can achieve an average of 3 dB gain when compared with the reference schemes (i.e., ECast, MCast, discrete wavelet transform (DWT) based scheme, and scalable video coding (SVC) scheme) in terms of average peak signal-to-noise ratio under heterogeneous scenarios.

Purpose The positive end-expiratory pressure (PEEP) level with best respiratory system compliance (Crs) is frequently used for PEEP selection in acute respiratory distress syndrome (ARDS) patients. On occasion, two similar best Crs (where the difference between the Crs of two PEEP levels is 2O) may be identified during decremental PEEP titration. Selecting PEEP under such conditions is challenging. The aim of this study was to provide supplementary rationale for PEEP selection by assessing the global and regional ventilation distributions between two PEEP levels in this situation. Methods Eight ARDS cases with similar best Crs at two different PEEP levels were analyzed using examination-specific electrical impedance tomography (EIT) measures and airway stress index (SIaw). Five Crs were measured at PEEP values of 25 cm H2O (PEEP25), 20 cm H2O (PEEP20), 15 cm H2O (PEEPH), 11 cm H2O (PEEPI), and 7 cm H2O (PEEPL). The higher PEEP value of the two PEEPs with similar best Crs was designated as PEEPupper, while the lower designated as PEEPlower. Results PEEPH and PEEPI shared the best Crs in two cases, while similar Crs was found at PEEPI and PEEPL in the remaining six cases. SIaw was higher with PEEPupper as compared to PEEPlower (1.06 ± 0.10 versus 0.99 ± 0.09, p = 0.05). Proportion of lung hyperdistension was significantly higher with PEEPupper than PEEPlower (7.0 ± 5.1% versus 0.3 ± 0.5%, p = 0.0002). In contrast, proportion of recruitable lung collapse was higher with PEEPlower than PEEPupper (18.6 ± 4.4% versus 5.9 ± 3.7%, p lower than PEEPupper (34.4 ± 19.3% versus 16.0 ± 9.1%, p = 0.046). The intratidal gas distribution (ITV) index was also significantly higher at PEEPlower than PEEPupper (2.6 ± 1.3 versus 1.8 ± 0.7, p = 0.042). Conclusions PEEPupper is a rational selection in ARDS cases with two similar best Crs. EIT provides additional information for the selection of PEEP in such circumstances.

Acute respiratory distress syndrome (ARDS) is characterized by acute-onset rapid-deteriorating inflammatory lung injury. Although the preservation of spontaneous breathing may have physiological benefits in oxygenation, increasing evidence shows that vigorous spontaneous breathing may aggravate lung injury (i.e., patient self-inflicted lung injury). Increased lung stress and pendelluft, which is defined as intrapulmonary gas redistribution without a significant change in tidal volume, are important mechanisms of patient self-inflicted lung injury. The presence of pendelluft may be considered a surrogate marker of vigorous inspiratory effort, which can cause the dependent lung to overstretch. In this review, we summarized three major methods for electrical impedance tomography–based pendelluft monitoring. Future studies are warranted to compare and validate the different methods of pendelluft estimation in patients with ARDS.

In this paper, the backward-compatible coding schemes are explored to achieve the near-capacity performances in dynamic LDPC-coded Gaussian multiple access channels (GMAC). Specifically, some user-load-compatible (ULC) masked edges in a raptor-like protograph are masked with the variation of user load $u$ . To distinguish the edges in a protograph, a multi-user protograph-based extrinsic information transfer (MU-PEXIT) chart is developed. Based on this chart, an iterative edge selection algorithm combined with a theoretical simplification is proposed to facilitate the selection of independent masked edge sets (MESs) for varying $u$ . To further decrease the complexity of the independent masking scheme, a nested version is presented, where the MESs for varying $u$ are nested and derived from the same mother MES. Meanwhile, nested selection algorithms are provided to select the nested MESs. Extensive simulation results demonstrate that the masked 5G-NR LDPC codes can maintain near-capacity performances regardless of the variation of $u$ . Besides, these ULC masked codes achieve comparable performances with the state-of-the-art LDPC codes which are specially re-designed in a static GMAC.

Nowadays, the Internet of Video Things (IoVT) is growing rapidly in terms of quantity and computation demands. In spite of the higher local computation capability on visual processing compared to conventional Internet of Things devices, IoVT devices need to offload partial visual processing tasks to the mobile edge computing (MEC) server wirelessly due to its larger computation demands. However, visual processing task offloading is limited by uplink throughput and computation capability of the MEC server. To break through these limitations, a novel non-orthogonal multiple access (NOMA)-assisted IoVT framework with multiple MEC servers is proposed, where NOMA is exploited to improve uplink throughput, and MEC servers are co-located with base stations to provide enough computation capability for off-loading. In the proposed framework, the association strategy, uplink visual data transmission assisted by NOMA, and division of the visual processing tasks as well as computation resource allocation at the MEC servers are jointly optimized to minimize the total delay of all visual processing tasks, while meeting the delay requirements of all IoVT devices. Simulation results demonstrate that significant performance gains can be achieved by proposed joint optimization with NOMA transmission and multi-MEC offloading in the heterogeneous IoVT network.

This letter explores shortening technology for achieving near Gaussian multiple access channel (GMAC) capacity in low-density parity-check coded multi-user systems. To optimize the shortening patterns, a hybrid extrinsic information transfer (H-EXIT) tool, which integrates EXIT and protograph-based EXIT, is firstly developed. Based on this analysis, H-EXIT priority (HEP) algorithm is proposed to facilitate the optimization of shortening patterns. It can be observed that columns with larger degrees are prior to be selected, which differs from those for point-to-point scenarios. Inspired by this finding, we further propose largest-column-degree priority (LCDP) algorithm, which narrows the selection space to lower the complexity while maintains a comparable performance. Extensive simulation results demonstrate the superiority of proposed shortening schemes from two aspects: 1) Proposed shortening can bring nonnegligible gain over unshortening with consistent sum rate; 2) HEP and LCDP algorithms outperform benchmark algorithms.

To cope with rapid growth of video services, we propose a non-orthogonal multiple access (NOMA) based scalable video multicast (NOMA-SVM) framework for mobile networks, by exploiting NOMA's specific potential in scalable video multicast transmission. We consider statistical channels, instead of channels with perfect estimation, in the proposed NOMA-SVM framework in order to capture the realistic channel behaviors. As quality of experience (QoE) is a better metric than throughput for video transmission, QoE-driven power allocation is performed among multiple video layers in the proposed NOMA-SVM framework, in which users can decode video with quality proportional to their channel conditions. Specifically, we formulate the power allocation problem with the goal to maximize the average QoE over all users while guaranteeing the basic services of these users. To solve such a non-convex discrete problem, an optimal algorithm is developed based on the hidden monotonicity of the problem. A suboptimal algorithm is also proposed with much lower complexity in order to meet the practical needs. Simulation results show that the proposed algorithms outperform existing orthogonal multiple access (OMA) and NOMA based algorithms under various multicast scenarios in terms of QoE.

In this paper, we present a novel learning-based scheme for vehicle logo recognition (VLR). This scheme is termed Multilayer Pyramid Network Based on Learning (MLPNL) and is based on the principle that considering multiple resolutions is helpful for extracting valuable features that benefit the final recognition performance. The innovations of this scheme include (1) a multilayer pyramid network, with pixel difference matrices (PDMs) as its input and output and feature parameters mapping one PDM to another; (2) an objective function and a corresponding optimization method designed to facilitate the learning of the feature parameters of the proposed multilayer pyramid network; and (3) a multi-codebook-based encoding method that makes best use of the features extracted from PDMs corresponding to different resolutions. Extensive experiments conducted with an open dataset, HFUT-VL, demonstrate that the proposed MLPNL scheme outperforms state-of-the-art handcrafted descriptors and non-deep-learning-based learning methods when fewer training samples exist. Experiments conducted with a benchmark dataset, XMU, demonstrate that MLPNL outperforms existing state-of-the-art VLR methods. Experiments conducted both on HFUT-VL and XMU demonstrate that MLPNL is faster than most deep-learning-based learning methods while maintaining nearly the same recognition rate. Code has been made available at: https://github.com/HFUT-CV/MLPNL .

Network morphism is an effective learning scheme to morph a well-trained neural network to a new one with the network function completely preserved. However, existing network morphism scheme addresses only basic morphing types on the layer level. In this research, we address the central problem of network morphism at a higher level, i.e., how a convolutional layer can be morphed into an arbitrary module of a neural network. To simplify the representation of a network, we abstract a module as a graph with blobs as vertices and convolutional layers as edges. Based on this graph, the morphing process can be formulated as a graph transformation problem. Two atomic morphing operations are introduced to construct the graphs, based on which modules are classified into two families, i.e., simple morphable modules and complex modules. We present practical morphing solutions for both families, and prove that any module can be morphed from a single convolutional layer. Extensive experiments have been conducted based on the state-of-the-art ResNet on benchmarks to verify the effectiveness of the proposed solution.

Non-orthogonal multiple access (NOMA) is promising to enable growing video services with requirements of massive traffic and low latency. In this paper, we investigate a novel multi-user NOMA system design for video delivery. Different from data delivery considered in existing NOMA systems, video distortion is taken into consideration for the design and optimization of the proposed scheme. We first propose a cross-layer scalable video delivery scheme over NOMA wireless networks based on given user grouping. By adopting a semi-analytical rate distortion model for encoded video sequences and investigating the physical layer model for the multi-carrier NOMA network, the distortion-aware power allocation problem is formulated with the goal to minimize the system end-to-end distortion with quality-of-service requirements. To solve such a non-convex problem, we design an efficient algorithm by exploiting its hidden monotonic property to approximate the optimal solution. Inspired by the decoding order in NOMA, a fast algorithm is developed by combining water-filling and greedy strategies to further tame the computational complexity. Simulations results have verified the advantages of the proposed cross-layer scheme with distortion-aware power allocation algorithms, against two existing NOMA schemes and an OMA scheme.

Face super-resolution is a domain-specific super-resolution (SR) problem of generating high-resolution (HR) face images from low-resolution (LR) inputs. Even though existing face SR methods have achieved great performance on the global region evaluation, most of them cannot restore local attributes and structure reasonably, especially to ultra-resolve tiny LR face images (16 × 16 pixels) to its larger version (8 × upscaling factor). In this paper, we propose an open source face SR framework based on facial semantic attribute transformation and self-attentive structure enhancement. Specifically, the proposed framework introduces face semantic information ( i.e. , face attributes) and face structure information ( i.e. , face boundaries) in a successive two-stage fashion. In the first stage, an Attribute Transformation Network (AT-Net) is established. It upsamples LR face images to HR feature maps and then combines facial attributes with these features to generate the intermediate HR results with rational attributes. In the second stage, a Structure Enhancement Network (SE-Net) is built. It simultaneously extracts face features and estimates facial boundary heatmaps from the inputs, and then fuses them to output the final HR face images. Extensive experiments demonstrate that our method achieves superior super-resolved results and outperforms the state-of-the-art methods.

Convolutional neural network-based (CNN-based) method has shown its superior performance on the image super-resolution (SR) task. However, several researches have shown that obtaining a better reconstruction result often leads to the significant increase in parameters and computation. To alleviate the burden in computational needs, we propose a novel global-local adjusting dense super-resolution network (GLADSR) to build a powerful yet lightweight CNN-based SR model. To enhance the network capacity, we present a global-local adjusting module (GLAM) which can adaptively reallocate the processing resources with local selective block (LSB) and global guided block (GGB). The GLAMs are linked with nested dense connections to make better use of the global-local adjusted features. In addition, we also introduce a separable pyramid upsampling (SPU) module to replace the regular upsampling operation, which thus brings a substantial reduction of its parameters and obtains better results. Furthermore, we show that the proposed refinement structure is capable of reducing image artifacts in SR processing. Extensive experiments on benchmark datasets show that the proposed GLADSR outperforms the state-of-the-art methods with much fewer parameters and much less computational cost.

Many semantic events in team sport activities e.g. basketball often involve both group activities and the outcome (score or not). Motion patterns can be an effective means to identify different activities. Global and local motions have their respective emphasis on different activities, which are difficult to capture from the optical flow due to the mixture of global and local motions. Hence it calls for a more effective way to separate the global and local motions. When it comes to the specific case for basketball game analysis, the successful score for each round can be reliably detected by the appearance variation around the basket. Based on the observations, we propose a scheme to fuse global and local motion patterns (MPs) and key visual information (KVI) for semantic event recognition in basketball videos. Firstly, an algorithm is proposed to estimate the global motions from the mixed motions based on the intrinsic property of camera adjustments. And the local motions could be obtained from the mixed and global motions. Secondly, a two-stream 3D CNN framework is utilized for group activity recognition over the separated global and local motion patterns. Thirdly, the basket is detected and its appearance features are extracted through a CNN structure. The features are utilized to predict the success or failure. Finally, the group activity recognition and success/failure prediction results are integrated using the kronecker product for event recognition. Experiments on NCAA dataset demonstrate that the proposed method obtains state-of-the-art performance.

Mobile displays have been recognized as the major contributors to the energy consumption of contemporary mobile video services. Existing display energy reduction (DER) algorithms focus on local video/image processing by utilizing the computation resources on the mobile devices. As such, a per-device DER strategy is highly inefficient from the systematic perspective since the same computation is repeated among millions of individual mobile devices. In this new era of cloud-based video streaming, a natural question to ask is can ubiquitous cloud resources be exploited to overcome these drawbacks. It is based on this motivation that we design a paradigm-shifting strategy to integrate the display energy saving engine into cloud-based video streaming in order to simultaneously benefit massive mobile devices with a one-time video processing in the cloud. By taking full advantage of the computational and storage resources in the cloud, a family of Rate-Distortion-Display Energy (R-D-DE) profiles can be created for a given video source and for different types of mobile devices. The preliminary experimental results with OLED displays prove that we can achieve the desired DER performance through jointly managing the display energy and user experience by implementing the proposed R-D-DE integrated video encoding engine in the cloud.

To offer commercial LDPC decoders with better performance, in this paper, multi-edge-type (MET) normalized scheme is proposed to improve the performance of traditional min-sum algorithm (MSA) and its modified versions. With respect to sum-product algorithm (SPA), we firstly analyze and find out that the degradations of convergence in different edge types are distinct in MSA theoretically. To compensate the different degradations above, proposed MET-normalized scheme is used in normalized min-sum algorithm (MET-NMSA). In addition, MET-based density evolution (MET-DE) is also presented to search optimized MET-scaling factors for MET-NMSA. To further verify the validity of MET-normalized scheme, Advanced Television Systems Committee (ATSC) 3.0 LDPC codes are used to evaluate MET-NMSA in comparison with the conventional algorithms, i.e., normalized min-sum algorithm (NMSA), offset min-sum algorithm (OMSA) and variable-scaling normalized min-sum algorithm (VS-NMSA). Extensive simulation results show that MET-NMSA for ATSC 3.0 LDPC decoders has at most 1.53dB, 0.21dB and 0.35dB gain over NMSA, OMSA and VS-NMSA respectively when frame error rate (FER) is at 10-4 level over additive white Gaussian noise (AWGN) channels using QPSK modulation.

The worldwide flourishing of the Internet of Things (IoT) in the past decade has enabled numerous new applications through the internetworking of a wide variety of devices and sensors. More recently, visual sensors have seen their considerable booming in IoT systems because they are capable of providing richer and more versatile information. Internetworking of large-scale visual sensors has been named Internet of Video Things (IoVT). IoVT has its own unique characteristics in terms of sensing, transmission, storage, and analysis, which are fundamentally different from the conventional IoT. These new characteristics of IoVT are expected to impose significant challenges to existing technical infrastructures. In this article, an overview of recent advances in various fronts of IoVT will be introduced and a broad range of technological and system challenges will be addressed. Several emerging IoVT applications will be discussed briefly to illustrate the potentials of IoVT in a broad range of practical scenarios.

In Cache-enabled dense small cell networks (DSCNs), energy consumption and file delivery delay are two critical performance metrics. On the other hand, power control is an essential mechanism to mitigate inter-cell interference in DSCNs. However, the impact of power control at small base stations (SBSs) on the system performance when caches are involved has not been well studied. Observing energy consumption and file delivery delay are coupled with each other in cache-enabled DSCNs, different from existing studies, we attempt to optimize these two performance metrics at the same time, taking into account sophisticated power control at SBSs. Firstly, we formulate the energy-delay optimization problem as a utility maximization problem, where cooperative power control among SBSs, file placement and user association are considered. Then, we solve the optimization problem in two stages (i.e., caching stage and delivery stage), based on the fact that caching is performed during off-peak time. At the caching stage, a local popular file placement policy is proposed by estimating user preference at each SBS. At the delivery stage, with given caching status at SBSs, the optimization problem is further decomposed by Benders’ decomposition method. An efficient algorithm is proposed to approach the optimal association and power solution by iteratively shrinking the gap of the upper and lower bounds. Finally, extensive simulations are performed to validate our analytical and algorithmic work. The results demonstrate that the proposed algorithms can achieve a better tradeoff between energy consumption and file delivery delay than the existing algorithms.

BackgroundA cessation program for hospitalized smokers is an effective strategy to achieve smoking abstinence. The effects of multiple in-hospital counseling sessions on 6-month smoking abstinence require further investigation.MethodsWe retrospectively analyzed the data of smokers who participated in hospital-initiated cessation programs at a medical center between 2017 and 2019. Data on age, sex, comorbidities, daily number of cigarettes, cessation motivation, nicotine dependence, cessation medications, discharge diagnosis, length of hospitalization, and intensive care unit admission were collected. We conducted multiple logistic regression analysis to investigate the effect of multiple in-hospital counseling sessions on 6-month sustained smoking abstinence. Sensitivity analyses were carried out excluding participants who underwent post-discharge cessation programs and assuming that the loss to follow-up participants had failure in 6-month smoking abstinence.ResultsA total of 1943 participants aged ≥ 20 years were analyzed. Compared with single in-hospital counseling session, the adjusted odds ratios (ORs) for 2 and ≥ 3 counseling sessions were 1.44 (95% confidence interval [CI] 1.05 to 1.98) and 2.02 (95% CI 1.27 to 3.22), respectively, with a significant trend for increasing the number of counseling sessions (P ConclusionMultiple in-hospital counseling sessions were associated with a higher 6-month sustained smoking abstinence rate. This strategy could be used to reduce the prevalence of smoking.

BackgroundSmoking behavior differs between the sexes. Weight control is one of the main reasons leading to tobacco abuse in women but not in men. Studies on the predictive factors of cessation failure between sexes are scarce. This study is aim to investigate whether there are sex differences in the effect of weight gain on smoking cessation rate.MethodsParticipants in the smoking-cessation program at a Medical Center in Taiwan between 2018 and 2019 were included. Details of age, sex, comorbidities, depression screening, nicotine dependence, body weight, and cessation medications of the participants were collected. The participants were classified based on their sex, and multivariable logistic regression analyses were conducted. Multivariable logistic regression analyses were performed for sensitivity analysis after stratifying the participants according to their weight loss (weight loss ≥ 1.5 kg and weight loss ≥ 3.0 kg).ResultsA total of 1,475 participants were included. The body-weight gain in women was associated with failed abstinence (adjusted odds ratio (OR): 3.10, 95% CI: 1.10–9.04). In contrast, body-weight gain in men was associated with successful 6-month prolonged abstinence (adjusted OR: 0.77, 95% CI: 0.61–0.98). The adjusted ORs for any body-weight loss, body-weight loss ≥1.5 kg, and body-weight loss ≥3.0 kg were 0.28 (95% CI: 0.09–0.88), 0.14 (95% CI: 0.03–0.55), and 0.03 (95% CI: 0.01–0.42), respectively.ConclusionBody-weight gain in women during a hospital-based smoking-cessation program is associated with abstinence failure. Further multicenter studies, including participants of different races and cultural backgrounds, are warranted.

We present a new analysis to extract pion parton distribution functions (PDFs) within the framework of the statistical model. Starting from the statistical model first developed for the spin-1/2 nucleon, we extend this model to describe the spin-0 pion. Based on a combined fit to both the pion-induced Drell-Yan data and the pion-induced J/Ψ production data, a new set of pion PDFs has been obtained. The inclusion of the J/Ψ production data in the combined fit has provided additional constraints for better determining the gluon distribution in the pion. We also compare the pion PDFs obtained in the statistical model with other existing pion PDFs.

Objectives: In order to predict the European Quality of Life-5 Dimensions three-Level (EQ-5D-3L) questionnaire utility from the chronic obstructive pulmonary disease (COPD) assessment test (CAT).Methods: The EQ-5D-3L and CAT data from 323 patients were collected. At first, response mapping under a backward elimination procedure was used for the EQ-5D score predictions from the CAT scores. A multinomial logistic regression (MLR) model was used to identify the association between the score and the covariates using a minimized quasi-information criterion (QIC). Afterwards, the predicted scores were transformed to the utility. Validation in the model selection depended on the mean absolute error (MAE) and the root mean squared error (RMSE) for the validation group. We also compared the developed formula with previous models based on an ordinary least squares (OLS) regression. Results: Using response mapping with the MLR model to predict EQ-5D utility from CAT in this study performed as well as OLS regression models in previous studies using MAE and RMSE evaluations (all MAEs ≤ 0.100). In addition, the overestimation for low utility patients (utility ≤ 0.6) and underestimation for near health (utility > 0.9) in previous developed OLS models was improved in this study using a bubble chart analysis. Conclusions: Response mapping with the MLR model led to performance comparable to that using the OLS model for predicting EQ-5D utility from CAT data. In addition, the bubble charts revealed that the model constructed in this study was a better predictive model than other alternatives.

Recent high-performing Human-Object Interaction (HOI) detection techniques have been highly influenced by Transformer-based object detector (i.e., DETR). Nevertheless, most of them directly map parametric interaction queries into a set of HOI predictions through vanilla Transformer in a one-stage manner. This leaves rich inter- or intra-interaction structure under-exploited. In this work, we design a novel Transformer-style HOI detector, i.e., Structure-aware Transformer over Interaction Proposals (STIP), for HOI detection. Such design decomposes the process of HOI set prediction into two subsequent phases, i.e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer. The structure-aware Transformer upgrades vanilla Transformer by encoding additionally the holistically semantic structure among interaction proposals as well as the locally spatial structure of human/object within each interaction proposal, so as to strengthen HOI predictions. Extensive experiments conducted on V-COCO and HICO-DET benchmarks have demonstrated the effectiveness of STIP, and superior results are reported when comparing with the state-of-the-art HOI detectors. Source code is available at \url{https://github.com/zyong812/STIP}., Comment: CVPR 2022; Code is publicly available at: https://github.com/zyong812/STIP

We present a new analysis to extract pion parton distribution functions (PDFs) within the framework of the statistical model. Starting from the statistical model first developed for the spin-1/2 nucleon, we extend this model to describe the spin-0 pion. Based on a combined fit to both the pion-induced Drell-Yan data and the pion-induced $J/Ψ$ production data, a new set of pion PDFs has been obtained. The inclusion of the $J/Ψ$ production data in the combined fit has provided additional constraints for better determining the gluon distribution in the pion. We also compare the pion PDFs obtained in the statistical model with other existing pion PDFs., 8 pages, 6 figures

This study delineated the characteristics of 24 (11.2%) culture-positive, influenza-associated pulmonary aspergillosis (IAPA) patients out of 215 patients with severe influenza during 2016–2019 in a medical center in southern Taiwan. Twenty (83.3%) patients did not have EORTC/MSG-defined host factors. The mean time from influenza diagnosis to Aspergillus growth was 4.4 days, and 20 (83.3%) developed IAPA within seven days after influenza diagnosis. All patients were treated in intensive care units and all but one (95.8%) received mechanical ventilation. Aspergillus tracheobronchitis was evident in 6 (31.6%) of 19 patients undergoing bronchoscopy. Positive galactomannan testing of either serum or bronchoalveolar lavage was noted in all patients. On computed tomography imaging, IAPA was characterized by peribronchial infiltrates, multiple nodules, and cavities superimposed on ground-glass opacities. Pure Aspergillus growth without bacterial co-isolation in culture was found in 17 (70.8%) patients. A. fumigatus (15, 62.5%), A. flavus (6, 25.0%), and A. terreus (4, 16.7%) were the major causative species. Three patients had mixed Aspergillus infections due to two species, and two had mixed azole-susceptible and azole-resistant A. fumigatus infection. All patients received voriconazole with an all-cause mortality of 41.6%. Of 14 survivors, the mean duration of antifungal use was 40.5 days. In conclusion, IAPA is an early and rapidly deteriorating complication following influenza that necessitates clinical vigilance and prompt diagnostic workup.

The movements of articulators, such as lips, tongue and teeth, play an important role in increasing the language expression capability by unmasking the information hid in text or speech. Hence, it is necessary to deeply mine and visualize the relationship between text, speech and articulatory movements for understanding language in multi-modality and multi-level. As a case study, given text and audio of President Donald John Trump, this paper synthesizes a high quality 3D animation of him speaking with accurate synchronicity between speech and articulators. First, visual co-articulation is modeled by predicting the mapping from text/speech to articulatory movements. Then, based on a reconstructed 3D head model, physiological characteristics and statistical learning are combined to visualize each phoneme. Finally, the visualization results of consecutive phonemes are fused by visual co-articulation model to generate synchronized articulatory animations. Experiments show that the system can not only produce photo-realistic results in front but also distinguish the visual differences among phonemes from unconstrained views.

We address the issues of 3-D head pose estimation and face modeling from a depth image. Given a depth image, random forests are effective for estimating the location and orientation of a person's head. However, the accuracy of the estimation is not high enough. We propose using corrected regression votes. The corrected votes are obtained by considering the cooperation of all trees, leading to significant improvement of head pose estimation accuracy. Based on the head pose estimator, we present a face modeling system. In our system, the face model is generated by aligning a deformable face model to a depth image using an iterative closest point (ICP) algorithm. The novelty of our approach is that an optimal weight for each vertex is incorporated into the ICP algorithm with point to plane constraints. Experiments show that our system can automatically estimate the head pose and generate a realistic face model from a single depth image. We also provide a detailed evaluation that shows the benefits of our approach.

Rate-compatible modulation (RCM) achieves seamless rate adaptation under time-varying channels by varying the number of transmitted symbols at a small granularity. The implementation of effective decoders based on the belief propagation (BP) algorithm suffers from the varying number of symbols and highly complex symbol nodes. Considering these RCM-specific characteristics, we present a top–down design methodology, including decoding algorithm, mapping matrix construction, and hardware implementation. The layered BP algorithm provides the potential to implement the decoders that fine-tune the decoding throughput according to the number of symbols. To mitigate the impact of inter-layer data dependency on decoding throughput and facilitate the implementation of low parallelism decoders, a construction and optimization algorithm is proposed to obtain the two-level quasi-cyclic matrices with small sub-matrix size. The proposed algorithm and matrix are applied to a partially parallel RCM decoder for a ${5544 \times 5544}$ matrix on a field-programmable gate-array (FPGA) device. A memory access structure that requires only one barrel shifter is used to improve area efficiency. The post-route results show that the decoder achieves a throughput of 377 M ~ 1100 Mbit/s at six iterations with a clock frequency of 218 MHz.

Privacy-aware location-based service (PA-LBS) preserves LBS users’ privacy but undesirably sacrifices service quality. In order to balance the two factors with satisfactory user experience, existing frameworks are faced with two barriers, that is, scalability and social-friendliness. First, existing schemes do not enable LBS users to flexibly scale their privacy level on service provision. Such a lack of scalability easily results in either unacceptable service-quality degradation or insufficient privacy protection and fails to meet dynamic user requirements. Second, existing schemes handle privacy protection by merely considering the trust relationship between users and servers but ignore the complex trust relationships among users. As a result, users cannot preserve privacy in location-based social services that involve user-to-user interactions. In this paper, we present the first scalable and social-friendly PA-LBS system. In particular, we propose a novel camouflage algorithm with a formal privacy guarantee that enables LBS users to expose their location information by scaling two privacy related factors, that is, camouflage range and place type. Furthermore, we apply the scalable ciphertext policy attribute-based encryption algorithm to enable LBS users to effectively control the access from other users to their location information. Moreover, we also demonstrated the operational efficiency of the proposed system through successful implementations on Android devices.

Video delivery has been playing an essential role in video services over edge networks. Although HTTP segment-based streaming, e.g., Dynamic Adaptive Streaming over HTTP (DASH), has become the prevailing technique, it cannot provide guaranteed video playback in terms of bitrate to mobile users. In essence, HTTP streaming downloads the video segments in a best effort fashion, i.e., passively responding to the channel dynamics. This can cause unstable playback with frequent rebuffer and multi-client competition that degrades a network-wide performance. In this paper, we present a network-assisted streaming framework for Guaranteed Playback-Experience Streaming over HTTP (GESH) that leverages the proactive control of network resources and joint coordination among multiple clients for service-aware network resource allocation. Specifically, GESH is empowered by a new weighted proportional fair scheduling without modifying existing cellular infrastructure, a per-segment channel variation model, and a suite of algorithms to seek the optimal weights for the scheduling. Extensive evaluations show that GESH can maximally guarantee the video playback of multiple users, as well as significantly outperforming conventional HTTP streaming and current DASH systems.

With rapid development of space platforms such as small satellites and UAVs for public services, remote sensing services have been considered as one of the most promising services in space information networks. Small satellites and UAVs equipped with sensors such as cameras capture on-demand images and videos. Various remote sensing services using these images and videos can be enabled for public users, including geographical photography, navigation, live broadcast, surveillance and monitoring, road traffic analysis, and so on. In these remote sensing services, images and videos must be transmitted to individual users in a real-time manner. Therefore, the transmission techniques adopted will have direct impact on the received quality of users. As a newly emerged robust wireless transmission scheme, Soft- Cast is able to accommodate multiple receivers of different channel conditions by directly transmitting power scaled samples. In this article, CS and robust transmission-based SoftCast are investigated for downlink image/video-based remote sensing services under resource-limited, time-varying, and heterogeneous space environments, which are developed in order to improve bandwidth utilization efficiency and to achieve graceful performance, respectively. The proposed ComCast scheme is implemented by integrating CS and robust transmission into one framework to exploit benefits from both techniques. Furthermore, resource allocation in ComCast is also addressed to minimize system distortion caused by both CS and transmission. Simulation results demonstrate that ComCast outperforms the existing CS-based scheme as well as the robust transmission scheme in terms of peak signal-to-noise ratio and visual quality.

The task of classifying mammograms is very challenging because the lesion is usually small in the high resolution image. The current state-of-the-art approaches for medical image classification rely on using the de-facto method for ConvNets - fine-tuning. However, there are fundamental differences between natural images and medical images, which based on existing evidence from the literature, limits the overall performance gain when designed with algorithmic approaches. In this paper, we propose to go beyond fine-tuning by introducing a novel framework called MorphHR, in which we highlight a new transfer learning scheme. The idea behind the proposed framework is to integrate function-preserving transformations, for any continuous non-linear activation neurons, to internally regularise the network for improving mammograms classification. The proposed solution offers two major advantages over the existing techniques. Firstly and unlike fine-tuning, the proposed approach allows for modifying not only the last few layers but also several of the first ones on a deep ConvNet. By doing this, we can design the network front to be suitable for learning domain specific features. Secondly, the proposed scheme is scalable to hardware. Therefore, one can fit high resolution images on standard GPU memory. We show that by using high resolution images, one prevents losing relevant information. We demonstrate, through numerical and visual experiments, that the proposed approach yields to a significant improvement in the classification performance over state-of-the-art techniques, and is indeed on a par with radiology experts. Moreover and for generalisation purposes, we show the effectiveness of the proposed learning scheme on another large dataset, the ChestX-ray14, surpassing current state-of-the-art techniques., 10 pages, 5 figures

Spectral clustering has been an attractive topic in the field of computer vision due to the extensive growth of applications, such as image segmentation, clustering and representation. In this problem, the construction of the similarity matrix is a vital element affecting clustering performance. In this paper, we propose a multi-view joint learning (MVJL) framework to achieve both a reliable similarity matrix and a latent low-dimensional embedding. Specifically, the similarity matrix to be learned is represented as a convex hull of similarity matrices from different views, where the nuclear norm is imposed to capture the principal information of multiple views and improve robustness against noise/outliers. Moreover, an effective low-dimensional representation is obtained by applying local embedding on the similarity matrix, which preserves the local intrinsic structure of data through dimensionality reduction. With these techniques, we formulate the MVJL as a joint optimization problem and derive its mathematical solution with the alternating direction method of multipliers strategy and the proximal gradient descent method. The solution, which consists of a similarity matrix and a low-dimensional representation, is ultimately integrated with spectral clustering or K-means for multi-view clustering. Extensive experimental results on real-world datasets demonstrate that MVJL achieves superior clustering performance over other state-of-the-art methods.