As a significant component of the cislunar space infrastructure (CSI), lunar surface communication and navigation infrastructure (LSCNI) provides more convenient communication networking services for the surface local users within hotspot areas, and also provides reference of surface local positioning and navigation as well as certain positioning, navigation and timing (PNT) capacities. On the basis of trend analysis, overall architectures of lunar surface communication and navigation infrastructure arc proposed focusing on the medium and long-term strategic development of current major projects as well as future large-scale lunar activities. The architectures contain the network architecture and the lunar surface-space interfaces. Then, the solutions to some core issues such as lunar frequency planning, radio wave channel modeling, network access, high-speed transmissions, positioning and navigation methods arc analyzed. Finally, suggestions for phased construction and technological development roadmap arc proposed, providing reference for the planning and construction of communication and navigation systems for future lunar exploration missions.

Developing upon open system architecture, Software-Defined Spacecraft, as a new generation of spacecraft, can support payload plug-and-play, application software loading as needed, and system function reconfiguration on demand. Therefore, the Software-Defined Spacecraft is able to solve the design and application limitations of traditional specific-designed spacecraft, making it become a significant developing trend of future spacecraft. Regarding to the software defined spacecraft bus, this paper analyzes the requirements for avionics system on the aspects of space field development, technology development and corresponding applications. Then, combining with the development status, the avionics system architecture of software defined spacecraft is proposed, along with the related key technologies.

Mars is the next milestone in our exploration of solar system. As the result of the very long distance between earth and Mars, it takes a long time for the microwave signal to travel between them. Therefore, the ground station cannot control the deep space probe on and around the Martian surface in real time, which puts forward higher requirements for fully autonomous and high reliable communication between deep space detectors. The forward link is usually defined as the link from the orbiter to the rover, which includes the telecommand from the earth station. The return link is usually defined as the link from the rover to the orbiter, which contains the key telemetry of the rover and the information which are collected by the payload of the rover. Due to the limited time of visible communication arc, the forward link telecommand and the return link information are both very important, frame loss is not allowed in them. Thus, the ARQ (Automatic Repeat-reQuest) mechanism is introduced in CCSDS proximity-1 protocol to ensure the reliability of the data transmission. However, the efficiency of ARQ will be greatly affected when the forward and return rates do not match, which will cause a sharp decrease of the communication throughput in the arc section. In this paper, the self-adaptive bidirectional ARQ transmission window regulation method based on CCSDS proximity-1 for Mars exploration is presented, which could adaptively estimate the time delay and change the window parameter to ensure the high efficiency of both links. Compared with the traditional method, higher throughput could be achieved during the precious visible arc. The hardware implementation shows that only limited logic resource are needed which is suitable for the Mars exploration mission.

Reading irregular scene text is a challenging problem in scene text recognition. Rectification is a popular measure to reduce irregularities of text in images. Existing rectification methods seek to rectify text images into a strictly regular form via free parametric transformation functions. However, they always suffer from information loss or severe deformation due to their poor constraints to the transformation functions. In our investigation, we found that CNN and attention are robust to many slight irregularities. What inspires us to propose a novel and effective rectification method that mainly rectifies the principle regularities, and leaves the slight irregularities to the CNN-LSTM-attention recognizer. Our rectification method first estimates the character densities and directions of the input image in a down-sampled map then finds a best fitting curve from a small predefined Bézier curve set, and finally rectifies the input image with a transformation function corresponding to the selected curve. Transformation functions are carefully designed so that they neither lose important visual information nor cause severe deformation. Extensive experiments on seven benchmark datasets show that our method achieves the state of the art performance in most cases, especially in curved text recognition.

Tianwen-1 Mars exploration mission is a mission for China to “Orbit, Fall and Patrol” Mars though a launch. Entry, Descent and Landing (EDL) of Mars exploration mission is a key part in the whole mission process. Based on the characteristics of relay communication task in this process, this paper introduces the relay communication system scheme and key technology of Tianwen-1 Mars probe adapted to the characteristics of complex timing，high autonomy, black barrier phenomenon and high dynamics of EDL segment communication task. At the same time, combined with the landing mission of Tianwen-1, the in orbit verification of relay communication in EDL is summarized and analyzed. The relay communication scheme proposed in this paper successfully supports the relay communication mission of the EDL section of the Mars Exploration of Tianwen-1.

针对深空探测任务对高速数据传输能力的需求,文章在调研国内外深空测控通信系统现有支持能力与空间激光通信技术最新发展成果的基础上,对我国深空探测任务对空间光通信技术高效化、网络化的发展需求进行了梳理;对深空光信号捕获瞄准跟踪技术、高光子效率信号调制与编码技术、地面高效信号接收技术和深空光通信中继与组网技术的实现途径进行了分析.结合我国未来深空探测任务规划与实际需求,借鉴国外相关领域的技术发展路线,提出了适用于我国国情的深空探测光通信发展设想,旨在构建高效、高速的中国深空测控通信网.

Scene text image super-resolution (STISR) has been regarded as an important pre-processing task for text recognition from low-resolution scene text images. Most recent approaches use the recognizer's feedback as clues to guide super-resolution. However, directly using recognition clue has two problems: 1) Compatibility. It is in the form of probability distribution, has an obvious modal gap with STISR - a pixel-level task; 2) Inaccuracy. it usually contains wrong information, thus will mislead the main task and degrade super-resolution performance. In this paper, we present a novel method C3-STISR that jointly exploits the recognizer's feedback, visual and linguistical information as clues to guide super-resolution. Here, visual clue is from the images of texts predicted by the recognizer, which is informative and more compatible with the STISR task; while linguistical clue is generated by a pre-trained character-level language model, which is able to correct the predicted texts. We design effective extraction and fusion mechanisms for the triple cross-modal clues to generate a comprehensive and unified guidance for super-resolution. Extensive experiments on TextZoom show that C3-STISR outperforms the SOTA methods in fidelity and recognition performance. Code is available in https://github.com/zhaominyiz/C3-STISR.

"天问一号"火星探测器超高频(Ultra high frequency,UHF)频段中继通信系统作为中国首次火星探测任务实现的重要组成部分,负责为着陆巡视器与环绕器之间在火星进入、下降、着陆阶段(Entry,descent and landing,EDL)与火面巡视阶段提供高效可靠的通信服务.本文对中国火星探测器UHF频段中继通信方案进行了介绍,给出中继通信系统的组成、技术指标及链路设计方法,并对在轨飞行试验数据进行了分析.结果表明,全新研制的"天问一号"探测器UHF频段中继通信系统圆满完成了任务目标,其设计、实现和应用为后续中国深空中继通信系统研制提供了技术参考.

We address a challenging problem: recognizing multiple text sequences from an image by pure end-to-end learning. It is twofold: 1) Multiple text sequences recognition. Each image may contain multiple text sequences of different content, location and orientation, we try to recognize all these texts in the image. 2) Pure end-to-end (PEE) learning. We solve the problem in a pure end-to-end learning way where each training image is labeled by only text transcripts of the contained sequences, without any geometric annotations. Most existing works recognize multiple text sequences from an image in a non-end-to-end (NEE) or quasi-end-to-end (QEE) way, in which each image is trained with both text transcripts and text locations. Only recently, a PEE method was proposed to recognize text sequences from an image where the text sequence was split to several lines in the image. However, it cannot be directly applied to recognizing multiple text sequences from an image. So in this paper, we propose a pure end-to-end learning method to recognize multiple text sequences from an image. Our method directly learns the probability distribution of multiple sequences conditioned on each input image, and outputs multiple text transcripts with a well-designed decoding strategy. To evaluate the proposed method, we construct several datasets mainly based on an existing public dataset and two real application scenarios. Experimental results show that the proposed method can effectively recognize multiple text sequences from images, and outperforms CTC-based and attention-based baseline methods.

The current security method of Internet-of-Vehicles (IoV) systems is rare, which makes it vulnerable to various attacks. The malicious and unauthorized nodes can easily invade the IoV systems to destroy the integrity, availability, and confidentiality of information resources shared among vehicles. Indeed, access control mechanism can remedy this. However, as a static method, it cannot timely response to these attacks. To solve this problem, we propose an intelligent edge-chain-enabled access control framework with vehicle nodes and roadside units (RSUs) in this study. In our scenario, vehicle nodes act as lightweight nodes, whereas RUSs serve as full and edge nodes to provide access control services. Considering the low accuracy of risk prediction due to limited training sets, we leverage a generative adversarial networks (GANs) to convert the risk prediction to a sequence generation. Moreover, aiming at the problems of gradient disappearance and mode collapse existed in the original GANs, we devise a Wasserstein combined GANs (WCGANs). Simulation results demonstrate that WCGAN has higher prediction accuracy than the original GANs. Additionally, it can also improve the accuracy of access control of risk prediction-based access control (RPBAC) model.

Eosinophilic granulomatosis with polyangiitis (EGPA), formerly called Churg-Strauss syndrome, is a rare chronic necrotizing eosinophilic granulomatous inflammatory disease characterized by eosinophil-rich granulomatous inflammation and small- to medium-size vessel vasculitis associated with bronchial asthma and eosinophilia, which is positive for anti-neutrophil cytoplasmic antibody (ANCA) in approximately 50-70% of cases. We report a case of a 23-year-old woman was admitted to our hospital because of a of small vesicles on both lower limbs and a 4-month history of small scattered skin rash with pruritus V6 on both lower limbs four-month history of scattered skin rash with pruritus. Laboratory data from peripheral blood revealed leukocytosis, eosinophilia, thrombocytosis, hyperfibrinolysis, and mild renal injury. Her ANCA was negative, and the skin pathological examination showed granuloma lesions with eosinophils, while elevated eosinophils were also found in the bone marrow. EGPA was diagnosed. On the other hand, the patient had 2-year-long rhinosinusitis, 9-month-long nephrotic syndrome, and 1-month-long dry cough, which might be a type of asthma. With steroid therapy followed by systemic immunomodulatory therapy, the patient's symptoms were relieved. Our case report and literature review highlight the importance of recognizing cough variant asthma as an initial presenting symptom of EGPA, providing an opportunity for early diagnosis and treatment to reduce the risk of further disease progression and morbidity.

With the rapid increase of mobile devices and online media, more and more people prefer posting/viewing videos online. Generally, these videos are presented on video streaming sites with image thumbnails and text titles. While facing huge amounts of videos, a viewer clicks through a certain video with high probability because of its eye-catching thumbnail. However, current video thumbnails are created manually, which is time-consuming and quality-unguaranteed. And static image thumbnails contain very limited information of the corresponding videos, which prevents users from successfully clicking what they really want to view. In this paper, we address a novel problem, namely GIF thumbnail generation, which aims to automatically generate GIF thumbnails for videos and consequently boost their Click-Through-Rate (CTR). Here, a GIF thumbnail is an animated GIF file consisting of multiple segments from the video, containing more information of the target video than a static image thumbnail. To support this study, we build the first GIF thumbnails benchmark dataset that consists of 1070 videos covering a total duration of 69.1 hours, and 5394 corresponding manually-annotated GIFs. To solve this problem, we propose a learning-based automatic GIF thumbnail generation model, which is called Generative Variational Dual-Encoder (GEVADEN). As not relying on any user interaction information (e.g. time-sync comments and real-time view counts), this model is applicable to newly-uploaded/rarely-viewed videos. Experiments on our built dataset show that GEVADEN significantly outperforms several baselines, including video-summarization and highlight-detection based ones. Furthermore, we develop a pilot application of the proposed model on an online video platform with 9814 videos covering 1231 hours, which shows that our model achieves a 37.5% CTR improvement over traditional image thumbnails. This further validates the effectiveness of the proposed model and the promising application prospect of GIF thumbnails.

Face recognition has been extensively studied in computer vision and artificial intelligence communities in recent years. An important issue of face recognition is data privacy, which receives more and more public concerns. As a common privacy-preserving technique, Federated Learning is proposed to train a model cooperatively without sharing data between parties. However, as far as we know, it has not been successfully applied in face recognition. This paper proposes a framework named FedFace to innovate federated learning for face recognition. Specifically, FedFace relies on two major innovative algorithms, Partially Federated Momentum (PFM) and Federated Validation (FV). PFM locally applies an estimated equivalent global momentum to approximating the centralized momentum-SGD efficiently. FV repeatedly searches for better federated aggregating weightings via testing the aggregated models on some private validation datasets, which can improve the model's generalization ability. The ablation study and extensive experiments validate the effectiveness of the FedFace method and show that it is comparable to or even better than the centralized baseline in performance.

In this paper, for the first time, we study label propagation in heterogeneous graphs under heterophily assumption. Homophily label propagation (i.e., two connected nodes share similar labels) in homogeneous graph (with same types of vertices and relations) has been extensively studied before. Unfortunately, real-life networks (e.g., social networks) are heterogeneous, they contain different types of vertices (e.g., users, images, and texts) and relations (e.g., friendships and co-tagging) and allow for each node to propagate both the same and opposite copy of labels to its neighbors. We propose a IC-partite label propagation model to handle the mystifying combination of heterogeneous nodes/relations and heterophily propagation. With this model, we develop a novel label inference algorithm framework with update rules in near-linear time complexity. Since real networks change overtime, we devise an incremental approach, which supports fast updates for both new data and evidence (e.g., ground truth labels) with guaranteed efficiency. We further provide a utility function to automatically determine whether an incremental or a re-modeling approach is favored. Extensive experiments on real datasets have verified the effectiveness and efficiency of our approach, and its superiority over the state-of-the-art label propagation methods.

As fixed compression ratio is used in traditional deep space exploration image transmission application, the same compression code rate is allocated to each image. However, since the information of each image in a space observation mission is nonuniform, the image with more information will inevitably lead to more compression distortion than the image with less information. Obviously, it's not an efficient way to transmit information in terms of data importance or overall distortion. Therefore, we proposed a combinatorial optimal bit rate allocation algorithm to improve the efficiency of image transmission in space application. Different from traditional method, the rate-distortion model of wavelet coefficients for each image in a transmission task was built, and under the overall maximum transmission rate constraint, an bit-rate optimal allocation was applied for each image to minimize the overall distortion of a batch of images. The proposed algorithm can be widely used in image compression algorithm with embedded code stream characteristics, such as JPEG2000 and SPIHT. Experimental results shows that in the range of 2.6 to 10 compression ratio, the algorithm can reduce image distortion MSB by 40%∼64% at the same overall transmission code rate, which equivalent to improvement of PSNR 3 dB to 5.4 dB.

患者男性,64岁,诊断为阵发性心房颤动(简称房颤),行冷冻球囊肺静脉电隔离,术中房颤发作,当4个肺静脉完全隔离后,房颤不能终止,给予电复律,房颤短暂转复后不能维持窦性心律.将球囊和Archieve电极回撤至右房并送至上腔静脉(SVC)入口,记录到SVC内高频紊乱电位,遂采用冷冻球囊行SVC电隔离(-41℃ 和-40℃两次,时间40 s)房颤终止,但SVC内仍有高频电位,再行第3次冷冻(-40℃,60 s),SVC内电位消失.继续冷冻至-41℃,76 s时,X线下见右侧膈肌运动幅度减弱,术后第2天出现气促,X线胸片示右侧膈肌明显抬高.术后6个月时,右侧膈肌位置恢复正常.

The AIS communication system is a global positioning aided navigation system, which can improve the safety of ship operation and the reliability of navigation. A spaceborne AIS system can dynamically monitoring ships in the global area. But It has many challenges such as message collision and signal transmission loss. This paper first designed a LEO AIS constellation, analyzed the coverage of this constellation, and then carried out the design of the on board AIS receiving system, including an array antenna and a receiver. Finally, the method of multi-user signal separation and detection was expounded.

In this paper, adaptive subcarrier-bandwidth multiple access (ABMA) is proposed as a novel downlink multi-user access scheme to support robust wireless communications in the high-mobility environments with different kinds of high-speed receivers. The proposed ABMA allows flexible spectrum resource allocation and subcarrier bandwidth adaptation according to mobile receivers' velocities. Resource band is used as the unit for spectrum resource allocation. Well-localized band-pass filters are applied on each resource band, in order to control the multiple access interference and achieve coexistence of different subcarrier bandwidth. Universal receiver structure with low implementation complexity is described as part of the scheme. Theoretical and numerical results show that the ABMA scheme is effective in repelling the impact of high-range Doppler effects and performs high robustness in the high-mobility environments.

We study the minimum mean-squared error (MMSE) precoding for multiuser visible light communication downlink systems. Different from radio frequency systems, this problem does not admit a closed-form solution due to the light-emitting diode optical power constraints. To handle the difficult non-convex problem, we transform it into an equivalent convex form via the Charnes-Cooper transformation. In this way, we are able to achieve the globally optimal MMSE precoder by solving only one convex problem, thus requiring much lower complexity than the existing alternating algorithm. The proposed non-alternating method is also extended to robust the MMSE precoder optimization in the presence of statistical channel-state information errors.

目的:探索aVL/aVR导联S波振幅比鉴别左冠窦（leftcoronarycusp,LCC）起源室性期前收缩（prematureventricularcontraction,PVC）的实用性。方法:回顾性分析2013年1月至2017年8月于中南大学湘雅二医院心血管内科住院治疗,并经体表心电图初步判断及导管射频消融术中腔内电生理图证实的特发性流出道PVC患者372例。比较起源于不同部位的PVC,其12导联体表心电图QRS波振幅之间的差异。结果:45例PVC起源于LCC,58例起源于右冠窦（right coronary cusp,RCC）,269例起源于右室流出道（rightventricularoutflowtract,RVOT）。心电图QRS波相关参数中受试者工作特征曲线下面积（AUC）最大的指标为a VL/aVR导联S波振幅比,其在LCC组（1.69±0.74）高于RCC组（1.29±0.63,P＜0.001）和RVOT组（0.84±0.48,P＜0.001）;其AUC值及95%CI为0.894（0.824～0.964）,界值为1.50。a VL/aVR导联S波振幅比＞1.50鉴别LCC起源PVC的敏感度、特异度及准确度分别为88.9%,91.4%和91.1%。结论:a VL/aVR导联S波振幅比在LCC起源PVC的鉴别中有一定价值。