Image super‐resolution via dynamic network

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.

Intelligent Recognition Using Ultralight Multifunctional Nano‑Layered Carbon Aerogel Sensors with Human‑Like Tactile Perception

Humans can perceive our complex world through multi-sensory fusion.Under limited visual conditions,people can sense a variety of tactile signals to identify objects accurately and rapidly.However,replicating this unique capability in robots remains a significant challenge.Here,we present a new form of ultralight multifunctional tactile nano-layered carbon aerogel sensor that provides pressure,temperature,material recognition and 3D location capabilities,which is combined with multimodal supervised learning algorithms for object recognition.The sensor exhibits human-like pressure(0.04–100 kPa)and temperature(21.5–66.2℃)detection,millisecond response times(11 ms),a pressure sensitivity of 92.22 kPa^(−1)and triboelectric durability of over 6000 cycles.The devised algorithm has universality and can accommodate a range of application scenarios.The tactile system can identify common foods in a kitchen scene with 94.63%accuracy and explore the topographic and geomorphic features of a Mars scene with 100%accuracy.This sensing approach empowers robots with versatile tactile perception to advance future society toward heightened sensing,recognition and intelligence.

Electromagnetic scattering and imaging simulation of extremely large-scale sea-ship scene based on GPU parallel technology

Aiming to solve the bottleneck problem of electromagnetic scattering simulation in the scenes of extremely large-scale seas and ships,a high-frequency method by using graphics processing unit(GPU)parallel acceleration technique is proposed.For the implementation of different electromagnetic methods of physical optics(PO),shooting and bouncing ray(SBR),and physical theory of diffraction(PTD),a parallel computing scheme based on the CPU-GPU parallel computing scheme is realized to balance computing tasks.Finally,a multi-GPU framework is further proposed to solve the computational difficulty caused by the massive number of ray tubes in the ray tracing process.By using the established simulation platform,signals of ships at different seas are simulated and their images are achieved as well.It is shown that the higher sea states degrade the averaged peak signal-to-noise ratio(PSNR)of radar image.

联邦学习系统攻击与防御技术研究综述

联邦学习作为一种使用分布式训练数据集构建机器学习模型的新兴技术,可有效解决不同数据用户之间因联合建模而导致的本地数据隐私泄露问题,从而被广泛应用于多个领域并得到迅速发展.然而,现有的联邦学习系统已被证实在数据收集阶段、训练阶段和推理阶段都存在潜在威胁,危及数据的隐私性和系统的鲁棒性.本文从安全威胁和隐私威胁两类潜在威胁入手,围绕机密性、完整性和可用性(CIA三元组)给出了联邦学习场景中安全属性的详细定义,并对联邦学习中各类攻击方式和防御手段进行了系统全面综述.首先,本文对横向、纵向联邦学习过程,以及潜在威胁分别进行了概述,并从对抗性攻击和非对抗性攻击两个角度,分析了投毒攻击、对抗样本攻击和推理攻击等常见攻击的基本概念、实施阶段和现有方案.进一步地,依据不同的攻击方式,将防御手段划分为鲁棒性提升方法和隐私性增强技术两类:鲁棒性提升方法主要防御系统遭受的对抗性攻击,包括数据消毒、鲁棒性聚合、异常检测、对抗训练、知识蒸馏和剪枝等,隐私性增强技术主要防御系统遭受的非对抗性攻击,包括同态加密、安全多方计算、差分隐私和区块链等.最后,本文给出了联邦学习中鲁棒性和隐私性方面的未来研究方向.

Accelerated prediction of Cu-based single-atom alloy catalysts for CO_(2) reduction by machine learning

Various strategies,including controls of morphology,oxidation state,defect,and doping,have been developed to improve the performance of Cu-based catalysts for CO_(2) reduction reaction(CO_(2)RR),generating a large amount of data.However,a unified understanding of underlying mechanism for further optimization is still lacking.In this work,combining first-principles calculations and machine learning(ML)techniques,we elucidate critical factors influencing the catalytic properties,taking Cu-based single atom alloys(SAAs)as examples.Our method relies on high-throughput calculations of 2669 CO adsorption configurations on 43 types of Cu-based SAAs with various surfaces.Extensive ML analyses reveal that low generalized coordination numbers and valence electron number are key features to determine catalytic performance.Applying our ML model with cross-group learning scheme,we demonstrate the model generalizes well between Cu-based SAAs with different alloying elements.Further,electronic structure calculations suggest surface negative center could enhance CO adsorption by back donating electrons to antibonding orbitals of CO.Finally,several SAAs,including PCu,AgCu,GaCu,ZnCu,SnCu,GeCu,InCu,and SiCu,are identified as promising CO_(2)RR catalysts.Our work provides a paradigm for the rational design and fast screening of SAAs for various electrocatalytic reactions.

SW-Net: A novel few-shot learning approach for disease subtype prediction

Few-shot learning is becoming more and more popular in many fields,especially in the computer vision field.This inspires us to introduce few-shot learning to the genomic field,which faces a typical few-shot problem because some tasks only have a limited number of samples with high-dimensions.The goal of this study was to investigate the few-shot disease sub-type prediction problem and identify patient subgroups through training on small data.Accurate disease subtype classification allows clinicians to efficiently deliver investigations and interventions in clinical practice.We propose the SW-Net,which simulates the clinical process of extracting the shared knowledge from a range of interrelated tasks and generalizes it to unseen data.Our model is built upon a simple baseline,and we modified it for genomic data.Supportbased initialization for the classifier and transductive fine-tuning techniques were applied in our model to improve prediction accuracy,and an Entropy regularization term on the query set was appended to reduce over-fitting.Moreover,to address the high dimension and high noise issue,we future extended a feature selection module to adaptively select important features and a sample weighting module to prioritize high-confidence samples.Experiments on simulated data and The Cancer Genome Atlas meta-dataset show that our new baseline model gets higher prediction accuracy compared to other competing algorithms.

Effects of curcumin on uterine leiomyoma in a rat model by inhibiting β-catenin/Wnt signaling pathway

Background:Women with uterine leiomyomas may suffer severe symptoms.To avoid risks of side effects,it is necessary to develop an optimal agent to shrink leiomyomas with fewer side effects and a lower recurrence rate.Curcumin may have a lower side effect in uterine leiomyoma treatment.Methods:We established the estrogen-and-progesterone-induced murine model of uterine leiomyoma.Next,we determined the expression of related genes of the β-catenin/Wnt signaling pathway by western blot,reverse transcription-polymerase chain reaction,and immunohistochemistry.We also noticed the morphological changes in uterine tissues by hematoxylin-eosin staining.Results:Curcumin plays an important role in Wnt/β-catenin signaling pathway-related expression including β-catenin,adenomatous polyposis coli,glycogen synthase kinase-3β,Wnt-11,and serum hormone concentrations.Conclusions:Curcumin could the down-regulation of serum hormone concentrations and inhibition of the β-catenin/Wnt signaling pathway in the treatment of uterine leiomyoma.

Timing and Single-pulse Study of Pulsar J1909+0122 Discovered by CRAFTS

We report the discovery of PSR J1909+0122 by the Five-hundred-meter Aperture Spherical Radio Telescope(FAST)as part of the Commensal Radio Astronomy FAST Survey.PSR J1909+0122 has a spin period of 1.257 s and a dispersion measure of 186.2 pc cm^(-3).The averaged pulse profile shows two distinct components.We performed a single-pulse study based on a one-hour observation at 1.25 GHz on 2021 August 23.We used a threshold of 5σ_(ep) to measure the nulling fraction(NF)as 63%±1.5%.The longitude-resolved fluctuation spectra and fast Fourier transform spectra of the binary sequences revealed the quasi-periodicity of nulling with a period of 30 rotation periods.We examined the reliability of the periodicity by comparing it to random noise injection.The NF,E,and modulation periodicity P_(M) of PSR J1909+0122 were compared with other periodic nulling pulsars,showing that the source of J1909+0122 has the second largest NF in the population.Long-term timing observations over six months were used to derive the phase-connected ephemeris of this pulsar.The measured P and P values disfavor dipolar geometry for polar gap models,and the prediction for a space-charge-limited flow model in the case of inverse Compton scattering is only just above the death line.In this work,PSR J1909+0122 has revealed possible correlations between nulling behavior and pulsar properties,which will help to shed light on the pulsar emission mechanism and its temporal evolution in future observations.

Reciprocating Magnetic Fields in the Pulsar Wind Observed from the Black Widow Pulsar J1720-0534

We report the radio observations of the eclipsing black widow pulsar J1720-0534, a 3.26 ms pulsar in orbit with a low mass companion of mass 0.029 to 0.034 M⊙. We obtain the phase-connected timing ephemeris and polarization profile of this millisecond pulsar(MSP) using the Five-hundred-meter Aperture Spherical radio Telescope(FAST), the Green Bank Telescope(GBT), and the Parkes Telescope. For the first time from such a system, an oscillatory polarization angle change was observed from a particular eclipse egress with partial depolarization, indicating 10-milliGauss-level reciprocating magnetic fields oscillating in a length scale of 5 ×10^(3)km(assuming an orbital inclination angle of 90°) outside the companion's magnetosphere. The dispersion measure variation observed during the ingresses and egresses shows the rapid raising of the electron density in the shock boundary between the companion's magnetosphere and the surrounding pulsar wind. We suggest that the observed oscillatory magnetic fields originate from the pulsar wind outside the companion's magnetosphere.

基于层级注意力机制的互联网用户信用评估框架

随着互联网的发展,基于用户信用的在线服务产品也越来越多地应用到各个领域.在这些信用数据中,除了传统的信贷数据,还包含用户网上消费数据等,因此如何利用这些数据来评估用户的信用等级是一个亟待解决的重要问题.之前的方法主要是基于信贷领域属性的研究,缺乏在互联网领域的研究,并且这些方法很少考虑用户的不同属性对其信用的不同的重要程度.因此,为了解决这些问题,提出一个基于层级注意力机制用户信用评估模型框架(HAM-UCE),模型首先构建用户信用画像,然后利用层级注意力机制在多个注意力层逐步获取更重要的用户属性特征,实现对用户信用等级的评估.实验结果表明该方法能够有效地实现对用户信用进行等级评估,能够比基准算法取得更好的性能.

Recent Progresses in Deep Learning Based Acoustic Models

In this paper,we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques.We first discuss models such as recurrent neural networks(RNNs) and convolutional neural networks(CNNs) that can effectively exploit variablelength contextual information,and their various combination with other models.We then describe models that are optimized end-to-end and emphasize on feature representations learned jointly with the rest of the system,the connectionist temporal classification(CTC) criterion,and the attention-based sequenceto-sequence translation model.We further illustrate robustness issues in speech recognition systems,and discuss acoustic model adaptation,speech enhancement and separation,and robust training strategies.We also cover modeling techniques that lead to more efficient decoding and discuss possible future directions in acoustic model research.

Highly sensitive and fast response strain sensor based on evanescently coupled micro/nanofibers

Flexible strain sensors play an important role in electronic skins,wearable medical devices,and advanced robots.Herein,a highly sensitive and fast response optical strain sensor with two evanescently coupled optical micro/nanofibers(MNFs)embedded in a polydimethylsiloxane(PDMS)film is proposed.The strain sensor exhibits a gauge factor as high as 64.5 for strain≤0.5%and a strain resolution of 0.0012%which corresponds to elongation of 120 nm on a 1 cm long device.As a proof-of-concept,highly sensitive fingertip pulse measurement is realized.The properties of fast temporal frequency response up to 30 kHz and a pressure sensitivity of 102 kPa^(−1) enable the sensor for sound detection.Such versatile sensor could be of great use in physiological signal monitoring,voice recognition and micro-displacement detection.

一种基于用户反馈检测大型在线系统前台故障的方法

大型在线系统在不同终端中的客户端由于兼容问题和频繁迭代容易出现前台显示故障,如控件覆盖、乱码等。由于传统系统后台的指标监控方法无法应对症状繁杂的前台故障,提出利用用户反馈动态检测前台故障的方案,通过对用户反馈的实时分析,挖掘其中关键信息动态构建监控指标,来表征并覆盖各种类型的前台故障。进一步设计快速在海量指标中进行异常检测的两阶段算法,实时地检测出指标中的异常并反映故障。该方法在多个真实大型在线系统中均获得了良好的检测效果,准确率达70%,召回率超过90%。

基于语义相似性的跨模态图文内容筛选存储机制研究

随着多媒体数据的爆发式增长,云端数据呈现出大规模多模态混合并存的特性.服务于数据分析的传统存储系统因为缺乏数据的语义管理而面临读取延时超长的挑战.针对图像和文本2种模态数据,在传统存储系统之上提出一种跨模态图文数据内容筛选存储机制(cross-modal image and text content sifting storage,CITCSS),用于提供大规模在线相似性内容筛选服务,从存储系统层面缓解数据分析时必须从存储中读出所有数据的读带宽压力.机制分为离线与在线2个阶段.离线阶段中,引入基于自监督的生成对抗式Hash方法,系统利用这种方法生成语义元数据.然后,将元数据注入独立的元数据空间.最后,根据相似性Hash码间汉明距离能够度量语义距离的特点,利用Neo4j图数据库构建Hash元数据图谱,并在语义图谱中建立Hash码与存储路径之间的映射.在线阶段中,用户发送与分析相关的图像或文本,存储系统首先转化数据为Hash码.然后,在筛选半径内通过Hash元数据图谱寻找相似节点,进而找到相似文件的底层存储路径返回筛选数据.实验结果表明,与传统语义存储系统相比,CITCSS在召回率超过98%的性能下,读取延迟相对降低了99.07%~99.77%.

Kinematic,Workspace and Force Analysis of A Five-DOF Hybrid Manipulator R(2RPR)R/SP+RR

In the present study,the over-constrained hybrid manipulator R(2RPR)R/SP+RR is considered as the research objective.In this paper,kinematics of the hybrid manipulator,including the forward and inverse position,are analyzed.Then,the workspace is checked based on the inverse position solution to evaluate whether the workspace of the hybrid manipulator meets the requirements,and the actual workspace of the hybrid robot is analyzed.After that,the force analysis of the over-constrained parallel mechanism is carried out,and an ADAMS-ANSYS rigid-flexible hybrid body model is established to verify the simulation.Based on the obtained results from the force analysis,the manipulator structure is designed.Then,the structure optimization is carried out to improve the robot stiffness.Finally,calibration and workspace verification experiments are performed on the prototype,cutting experiment of an S-shaped aluminum alloy workpiece is completed,and the experiment verifies the machining ability of the prototype.This work conducts kinematics,workspace,force analyses,structural optimization design and experiments on the over-constrained hybrid manipulator R(2RPR)R/SP+RR,providing design basis and technical support for the development of the novel hybrid manipulator in practical engineering.

A Novel Robust Zero-Watermarking Algorithm for Audio Based on Sparse Representation

Behind the prevalence of multimedia technology,digital copyright disputes are becoming increasingly serious.The digital watermarking prevention technique against the copyright infringement needs to be improved urgently.Among the proposed technologies,zero-watermarking has been favored recently.In order to improve the robustness of the zero-watermarking,a novel robust audio zerowatermarking method based on sparse representation is proposed.The proposed scheme is mainly based on the K-singular value decomposition(K-SVD)algorithm to construct an optimal over complete dictionary from the background audio signal.After that,the orthogonal matching pursuit(OMP)algorithm is used to calculate the sparse coefficient of the segmented test audio and generate the corresponding sparse coefficient matrix.Then,the mean value of absolute sparse coefficients in the sparse matrix of segmented speech is calculated and selected,and then comparing the mean absolute coefficient of segmented speech with the average value of the selected coefficients to realize the embedding of zero-watermarking.Experimental results show that the proposed audio zerowatermarking algorithm based on sparse representation performs effectively in resisting various common attacks.Compared with the baseline works,the proposed method has better robustness.

Establishment and validation of a computer-assisted colonic polyp localization system based on deep learning

BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-based computer-assisted detection(CADe)techniques were established from small single-center datasets,and unrepresentative learning materials might confine their application and generalization in wide practice.Although CADes have been reported to identify polyps in colonoscopic images and videos in real time,their diagnostic performance deserves to be further validated in clinical practice.AIM To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.METHODS With high-quality screening and labeling from 55 qualified colonoscopists,a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe.In addition,the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps.Finally,we conducted a selfcontrolled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.RESULTS The CADe was able to identify polyps in the test dataset with 95.0%sensitivity and 99.1%specificity.For colonoscopy videos,all 86 polyps were detected with 92.2%sensitivity and 93.6%specificity in frame-by-frame analysis.In the prospective validation,the sensitivity of CAD in identifying polyps was 98.4%(185/188).Folds,reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies.Colonoscopists can detect more polyps(0.90 vs 0.82,P<0.001)and adenomas(0.32 vs 0.30,P=0.045)with the aid of CADe,particularly polyps<5 mm and flat polyps(0.65 vs 0.57,P<0.001;0.74 vs 0.67,P=0.001,respectively).However,high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time(P=0.32;P=0.16,respectively).CONCLUSION CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas,and further confirmation is warranted.

隐私计算关键技术与创新

数据已经成为数字经济中重要的生产要素和战略资源。在实际应用中,数据分散在各个机构,由于隐私保护等原因,这些数据很难整合到一起,形成数据孤岛,从而阻碍大数据与人工智能产业的发展。隐私计算可以破解数据孤岛难题,在保障用户隐私的同时赋能多方数据协同应用,助力释放数据融合价值。对隐私计算的关键技术与创新成果,包括隐私集合求交技术、斜向联邦学习、异步并行计算、消息压缩机制、单向通信连接方案、可信执行环境、联合数据分析等进行了研究和分析,并对这些技术与创新在Angel PowerFL通用隐私计算平台中的应用进行了介绍。

Neural saliency algorithm guide bi-directional visual perception style transfer

The artistic style transfer of images aims to synthesise novel images by combining the content of one image with the style of another,which is a long-standing research topic and already has been widely applied in real world.However,defining the aesthetic perception from the human visual system is a challenging problem.In this study,the authors propose a novel method for automatic visual perception style transfer.First,they render a novel saliency detection algorithm to automatically perceive the visual attention of an image.Then,different from conventional style transfer algorithm in which style transferring is applied uniformly across all image regions,the authors apply a saliency algorithm to guide the style transferring process,enabling different types of style transferring to occur in different regions.Extensive experiments show that the proposed saliency detection algorithm and the style transfer algorithm are superior in performance and efficiency。

基于同态加密和秘密分享的纵向联邦LR协议研究

提出了一种新颖的两方纵向联邦逻辑回归协议,并在半诚实安全模型下证明了该协议的安全性,包括模型训练流程和模型推理流程的安全性,且无需对非线性函数使用多项式近似计算,从而保证了联邦逻辑回归协议模型无损。