A novel encoding mechanism for particle physics

This study proposes a novel particle encoding mechanism that seamlessly incorporates the quantum properties of particles,with a specific emphasis on constituent quarks.The primary objective of this mechanism is to facilitate the digital registration and identification of a wide range of particle information.Its design ensures easy integration with different event generators and digital simulations commonly used in high-energy experiments.Moreover,this innovative framework can be easily expanded to encode complex multi-quark states comprising up to nine valence quarks and accommodating an angular momentum of up to 99/2.This versatility and scalability make it a valuable tool.

A highly reliable encoding and decoding communication framework based on semantic information

Increasing research has focused on semantic communication,the goal of which is to convey accurately the meaning instead of transmitting symbols from the sender to the receiver.In this paper,we design a novel encoding and decoding semantic communication framework,which adopts the semantic information and the contextual correlations between items to optimize the performance of a communication system over various channels.On the sender side,the average semantic loss caused by the wrong detection is defined,and a semantic source encoding strategy is developed to minimize the average semantic loss.To further improve communication reliability,a decoding strategy that utilizes the semantic and the context information to recover messages is proposed in the receiver.Extensive simulation results validate the superior performance of our strategies over state-of-the-art semantic coding and decoding policies on different communication channels.

Variational data encoding and correlations in quantum-enhanced machine learning

Leveraging the extraordinary phenomena of quantum superposition and quantum correlation,quantum computing offers unprecedented potential for addressing challenges beyond the reach of classical computers.This paper tackles two pivotal challenges in the realm of quantum computing:firstly,the development of an effective encoding protocol for translating classical data into quantum states,a critical step for any quantum computation.Different encoding strategies can significantly influence quantum computer performance.Secondly,we address the need to counteract the inevitable noise that can hinder quantum acceleration.Our primary contribution is the introduction of a novel variational data encoding method,grounded in quantum regression algorithm models.By adapting the learning concept from machine learning,we render data encoding a learnable process.This allowed us to study the role of quantum correlation in data encoding.Through numerical simulations of various regression tasks,we demonstrate the efficacy of our variational data encoding,particularly post-learning from instructional data.Moreover,we delve into the role of quantum correlation in enhancing task performance,especially in noisy environments.Our findings underscore the critical role of quantum correlation in not only bolstering performance but also in mitigating noise interference,thus advancing the frontier of quantum computing.

A Two-Layer Encoding Learning Swarm Optimizer Based on Frequent Itemsets for Sparse Large-Scale Multi-Objective Optimization

Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero.As a result,many algorithms use a two-layer encoding approach to optimize binary variable Mask and real variable Dec separately.Nevertheless,existing optimizers often focus on locating non-zero variable posi-tions to optimize the binary variables Mask.However,approxi-mating the sparse distribution of real Pareto optimal solutions does not necessarily mean that the objective function is optimized.In data mining,it is common to mine frequent itemsets appear-ing together in a dataset to reveal the correlation between data.Inspired by this,we propose a novel two-layer encoding learning swarm optimizer based on frequent itemsets(TELSO)to address these SLMOPs.TELSO mined the frequent terms of multiple particles with better target values to find mask combinations that can obtain better objective values for fast convergence.Experi-mental results on five real-world problems and eight benchmark sets demonstrate that TELSO outperforms existing state-of-the-art sparse large-scale multi-objective evolutionary algorithms(SLMOEAs)in terms of performance and convergence speed.

A Multi-Stream Scrambling and DNA Encoding Method Based Image Encryption

Information security has emerged as a key problem in encryption because of the rapid evolution of the internet and networks.Thus,the progress of image encryption techniques is becoming an increasingly serious issue and considerable problem.Small space of the key,encryption-based low confidentiality,low key sensitivity,and easily exploitable existing image encryption techniques integrating chaotic system and DNA computing are purposing the main problems to propose a new encryption technique in this study.In our proposed scheme,a three-dimensional Chen’s map and a one-dimensional Logistic map are employed to construct a double-layer image encryption scheme.In the confusion stage,different scrambling operations related to the original plain image pixels are designed using Chen’s map.A stream pixel scrambling operation related to the plain image is constructed.Then,a block scrambling-based image encryption-related stream pixel scrambled image is designed.In the diffusion stage,two rounds of pixel diffusion are generated related to the confusing image for intra-image diffusion.Chen’s map,logistic map,and DNA computing are employed to construct diffusion operations.A reverse complementary rule is applied to obtain a new form of DNA.A Chen’s map is used to produce a pseudorandom DNA sequence,and then another DNA form is constructed from a reverse pseudorandom DNA sequence.Finally,the XOR operation is performed multiple times to obtain the encrypted image.According to the simulation of experiments and security analysis,this approach extends the key space,has great sensitivity,and is able to withstand various typical attacks.An adequate encryption effect is achieved by the proposed algorithm,which can simultaneously decrease the correlation between adjacent pixels by making it near zero,also the information entropy is increased.The number of pixels changing rate(NPCR)and the unified average change intensity(UACI)both are very near to optimal values.

On the sampling strategies and models for measuring diffusion exchange with a double diffusion encoding sequence

Water exchange between the different compartments of a heterogeneous specimen can be characterized via diffusion magnetic resonance imaging(dMRI).Many analysis frameworks using dMRI data have been proposed to describe exchange,often using a double diffusion encoding(DDE)stimulated echo sequence.Techniques such as diffusion exchange weighted imaging(DEWI)and the filter exchange and rapid exchange models,use a specific subset of the full space DDE signal.In this work,a general representation of the DDE signal was employed with different sampling schemes(namely constant b1,diagonal and anti-diagonal)from the data reduction models to estimate exchange.A near-uniform sampling scheme was proposed and compared with the other sampling schemes.The filter exchange and rapid exchange models were also applied to estimate exchange with their own subsampling schemes.These subsampling schemes and models were compared on both simulated data and experimental data acquired with a benchtop MR scanner.In synthetic data,the diagonal and near-uniform sampling schemes performed the best due to the consistency of their estimates with the ground truth.In experimental data,the shifted diagonal and near-uniform sampling schemes outperformed the others,yielding the most consistent estimates with the full space estimation.The results suggest the feasibility of measuring exchange using a general representation of the DDE signal along with variable sampling schemes.In future studies,algorithms could be further developed for the optimization of sampling schemes,as well as incorporating additional properties,such as geometry and diffusion anisotropy,into exchange frameworks.

The Dissemination of Chinese Tea Culture Based on Encoding/Decoding Theory

Tea has a history of thousands of years in China and it plays an important role in the working-life and daily life of people.Tea culture rich in connotation is an important part of Chinese traditional culture,and its existence and development are also of great significance to the diversified development of world culture.Based on Stuart Hall’s encoding/decoding theory,this paper analyzes the problems in the spreading of Chinese tea in and out of the country and provides solutions from the perspective of encoding,communication,and decoding.It is expected to provide a reference for the domestic and international dissemination of Chinese tea culture.

The Dissemination of Intangible Cultural Heritage Along Beijing-Hangzhou Canal Based on Encoding/Decoding Theory

The Beijing-Hangzhou Grand Canal carries a wealth of Chinese cultural symbols,showing the lifestyle and wisdom of working people through ages.The preservation and inheritance of its intangible cultural heritage can help to evoke cultural memories and cultural identification of the Canal and build cultural confidence.This paper applies Stuart Hall’s encoding/decoding theory to analyze the dissemination of intangible heritage tourism culture.On the basis of a practical study of the villages along the Beijing-Hangzhou Grand Canal,this paper analyses the problems in the transmission of its intangible cultural heritage and proposes specific methods to solve them in four processes,encoding,decoding,communication,and secondary encoding,in order to propose references for the transmission of intangible heritage culture at home and abroad.

基于BE-MCNN模型的新闻评论情感分析方法

实时新闻评论具有文本短、信息丰富、结构复杂等特点,情感分析难以准确捕捉其真实的情感倾向。为增强语义的特征信息,减少模型过拟合问题,提高新闻评论情感分析的准确性,提出一种融合BERT模型、Transformer En⁃coder与多尺度CNN模型的新闻评论情感分析算法。首先,针对新闻评论长度较短、表达情绪观点内容较多的特点,使用BERT模型对新闻评论文本进行预训练,获得具有上下文信息的特征向量;其次,为解决模型过拟合问题,在BERT模型下游添加一层Transformer编码器;最后使用四通道双层CNN模型,通过组合不同大小尺寸的卷积核来提升模型分析新闻评论情感的性能。实验结果表明,该方法在两个新闻评论数据集上的准确率分别达到93.0%与96.4%;与不同模型的比较实验进一步证明了所提方法的有效性。

基于映射空间编码的高速运动轨道图像去模糊研究

针对轨道缺陷检测系统因镜头抖动或相机快速移动而导致所采集图像较为模糊的问题,提出一种基于最大后验概率估计思想的映射空间编码的高速运动轨道图像去模糊算法。首先,该算法使用深度编解码器和残差网络分别对数据集中清晰图像到模糊图像的映射关系和模糊核进行编码,为了保证编码时频率信息的完整性,算法在传统的残差模块上引入快速傅里叶变换通道构成双通道残差网络,以补偿多次特征提取带来的频率损失;其次,算法采用深度图像先验(Deep Image Prior,DIP)将潜在的清晰图像和模糊核进行参数化,再利用先验得到的模糊核和清晰图像来调用编码空间中的映射关系;最后,通过交替优化潜在的清晰图像和模糊核,从而去逼近一个真实未知的映射,进而实现真实场景下高速运动轨道图像的去模糊。实验结果表明,双通道残差模块提取的特征图频率信息分量强度普遍高于传统的残差模块,相较于使用传统残差模块实现该算法,采用双通道残差模块可使峰值信噪比(Peak Signal-to-Noise Ratio,PSNR)提升0.84 dB,结构相似性(Structural Similarity,SSIM)提高0.025 1。与现有的深度学习去模糊算法相比,提出的去模糊算法对高速轨道检测系统所采集图像的去模糊效果更佳,在性能方面相较于最好的去模糊算法,PSNR提高了1.84 dB,SSIM提升了0.017 3,显著提升了采集图像的质量。研究结果可为下一步识别轨道部件是否存在缺陷提供清晰图像。

新一代通用视频编码标准H.266/VVC:现状与发展

相比于上一代标准,新一代通用视频编码标准(H.266/VVC)在同等质量下能够节省大约50%的码率,且适用于多种多样的视频应用场景。论文从H.266/VVC的关键技术出发,对标准的现状、实现和应用发展进行深入探讨。H.266/VVC沿用既往标准中的双层码流体系和混合编码框架,针对帧内预测、帧间预测、变换、量化、环路滤波等所有主要编码模块进行了技术革新,并为屏幕内容视频等应用提供了高效的专用编码工具。H.266/VVC标准目前已处于实用化阶段,官方参考软件VTM和开源编解码器VVenC/VVdeC是目前最具代表性的软件编解码实现。对H.266/VVC的性能分析可以看出:H.266/VVC针对高分辨率视频取得的编码增益更为突出;主要编码工具对性能的贡献通常以复杂度为代价,但也有部分编码工具在提升编码性能的同时可降低整体编码复杂度。H.266/VVC的硬件实现面临诸多挑战,发展明显滞后于软件实现,现有研究主要集中在对具体编码模块的硬件加速方面。H.266/VVC标准发布之后,下一代视频编码标准的发展目前仍围绕混合编码框架进行探索,聚焦在两大方向:超越VVC的增强压缩关注更为先进的、非神经网络的编码工具,基于神经网络的视频编码则探索采用神经网络的编码工具。除此之外,部分或完全跳出现有混合编码框架的端到端视频编码也在飞速发展,未来视频编码标准与神经网络结合成为趋势,但面临着计算资源依赖和稳定结构两方面的考验。

MUSE DWI和常规DWI在乳腺良恶性病变中的研究

目的探讨MUSE DWI和常规DWI在乳腺良恶性疾病中的应用价值。方法对我院进行乳腺磁共振检查并有病理结果的91例患者进行研究,每位患者均进行MUSE DWI和常规DWI扫描。结果MUSE DWI图像质量高,伪影减少,对病变细节显示的更好,MUSE ADC与常规ADC,均与病理结果有一致性。结论MUSE DWI弥补DWI的缺点,对乳腺良恶性病变有较高的诊断价值。

MFFNet:多级特征融合图像语义分割网络

在图像语义分割任务中,大多数方法未将不同尺度、不同层次的特征充分利用就直接进行上采样,会造成一些有效信息被当成冗余信息而被摒弃,从而降低对某些细小类别和相似类别分割的准确性和敏感性。为此,提出一个多级特征融合网络(MFFNet)。MFFNet采用编码器-解码器结构,在编码阶段,通过上下文信息提取路径和空间信息提取路径分别获取上下文信息与空间细节信息,增强像素间关联性与边界准确性;解码阶段设计一条多级特征融合路径,利用混合双边融合模块融合上下文信息;利用高低特征融合模块融合深层信息与空间信息;利用全局通道融合模块获取不同通道之间的联系,实现不同尺度信息的全局融合。MFFNet网络在PASCAL VOC 2012和Cityscapes验证集上的平均交互比(MIoU)分别为80.70%和76.33%,取得了较好的分割结果。

基于数据驱动的配电网无功优化

传统无功电压控制由于分布式电源、储能以及柔性负荷的接入面临计算速度和精度上的挑战。该文提出了一种基于数据驱动的配电网无功电压优化方法,通过跟踪实际系统的运行参数,实现无功电压的主动控制。在极限学习机中引入自动编码器构建深度学习机制,利用自动编码器建立极限学习机输入-输出的直接耦合关系,实现无监督学习和有监督学习有机结合,缩短训练模型的迭代过程;利用蒙特卡洛法基于分布式电源、负荷预测信息构建配电网运行场景,利用深度极限学习机挖掘运行场景优化运行与无功调压设备状态间的内在联系,建立电网运行场景与系统无功调压策略的映射关系。该文提出的基于数据驱动的无功优化方法不依赖实际系统潮流计算,能够实现配电网运行状态的跟踪和无功调节设备的优化调度,为配电网无功电压的主动控制打下基础。

基于NVAE和OB-Mix的小样本数据增强方法

由于深度学习模型对海量标注数据的依赖性较高,导致目前许多前沿性目标检测理论难以适用于工业检测领域。为此,提出一种基于NVAE图像生成和OB-Mix数据增强的小样本数据扩充方法。具体方法是通过NVAE构建检测目标的数据分布模型,再通过采样潜变量的方式生成与真实目标图像属于同一分布的全新目标图像。在得到生成目标图像后,提出了OB-Mix数据增强策略,将生成目标图像与背景图像进行随机位置融合以构建出新的图像数据,从而提高网络的定位能力及泛化能力。方法在仅使用474张标注图像以及400张无检测目标的背景图像情况下,使YOLOv5的检测精确率达到95.86%,相比于不使用该方法的结果提高了17.60个百分点。

基于Transformer的多尺度遥感语义分割网络

为了提升遥感图像语义分割效果,本文针对分割目标类间方差小、类内方差大的特点,从全局上下文信息和多尺度语义特征2个关键点提出一种基于Transformer的多尺度遥感语义分割网络(muliti-scale Transformer network,MSTNet)。其由编码器和解码器2个部分组成,编码器包含基于Transformer改进的视觉注意网络(visual attention network,VAN)主干和基于空洞空间金字塔池化(atrous spatial pyramid pooling, ASPP)结构改进的多尺度语义特征提取模块(multi-scale semantic feature extraction module, MSFEM)。解码器采用轻量级多层感知器(multi-layer perception,MLP)配合编码器设计,充分分析所提取的包含全局上下文信息和多尺度表示的语义特征。MSTNet在2个高分辨率遥感语义分割数据集ISPRS Potsdam和LoveDA上进行验证,平均交并比(mIoU)分别达到79.50%和54.12%,平均F1-score(m F1)分别达到87.46%和69.34%,实验结果验证了本文所提方法有效提升了遥感图像语义分割的效果。

基于改进VGG16的自编码器视频异常检测算法

在使用自编码器结构的神经网络处理视频异常检测任务时,U-Net风格的自编码器由于编码器层数深度过浅,导致在面对复杂的数据集时,不能充分抽取更多有用的特征信息。同时,在训练模型时使用MSE(均方误差),仅考虑了预测帧与真实帧之间的像素级相似性,对于复杂场景,像素级相似性可能无法准确判断预测帧与真实帧之间的相似性。针对以上问题,对基于U-Net风格的自编码器进行改进,提出了一种使用改进的VGG16作为编码器的视频异常检测算法,同时在均方误差的基础上添加结构相似性(SSIM)损失函数。改进的VGG16去掉了全连接层,并加入了残差连接防止特征退化,添加SSIM在计算像素级相似性的同时计算图像的亮度、对比度和结构等方面的相似性来优化网络。实验结果表明,改进后的算法,在Ped2数据集上检测效果达到95.91%,在Avenue数据集上检测效果达到84.89%,与改进前的方法相比分别提高了0.80%和0.19%,验证了所提方法的有效性。

融合改进自编码器和残差网络的入侵检测模型

互联网中存在大量隐私数据,因此防止网络入侵成为保护网络安全的关键问题。为提高网络入侵检测的准确率并解决其收敛慢问题,设计一种改进的堆叠自动编码器和残差网络(ISAE-ResNet)入侵检测模型。融合栈式自编码器和残差网络,首先将预处理后的数据输入到改进的栈式自编码器中,该栈式自编码器由2个副编码器和1个主编码器组成,数据经过副编码器和主编码器训练后重构出新的特征来防止过拟合问题;然后将解码层的权重捆绑到编码层进行优化,使模型参数减半来进行降维,提高模型的收敛速度;最后将处理过的数据输入到改进的残差网络中,并基于改进的ResNet网络设计一种加入软阈值函数的残差模块,通过降低数据中的噪声来提高模型准确率。在CIC-IDS-2017数据集上的实验结果表明,该模型准确率为98.67%,真正例率为95.93%,误报率为0.37%,损失函数值快速收敛至0.042,在准确率、真正例率、误报率和收敛速度方面均超过对比入侵检测模型,具有较高的有效性和可行性。

面向风格多样化的多对多语音情感转换

针对现有基于生成对抗网络的语音情感转换仍然存在情感分离不明显,且转换后的语音情感缺乏多样性问题,提出了一种面向风格多样化的多对多语音情感转换方法。该方法基于一个双生成器结构的生成对抗网络模型,通过对不同生成器的中间编码进行一致性损失约束确保语音内容和说话人特征具有一致性,以提升转换后语音情感与目标情感的相似性。此外,该方法通过情感映射网络和情感特征编码器为生成器提供同类情感的多样化情感表征。实验结果表明,所提情感语音转换方法得到的语音情感更接近目标情感,且情感样式更加丰富。

FMA-DETR:一种无编码器的Transformer目标检测方法

DETR是第一个将Transformer应用于目标检测的视觉模型。在DETR结构中,Transformer编码器对已高度编码的图像特征进行再编码,这在一定程度上导致了网络功能的重复。此外,由于Transformer编码器具有多层深度堆叠的结构和巨大的参数量,导致网络优化变得困难,模型收敛速度缓慢。本文设计了一种无编码器的Transformer目标检测网络模型。由于不需要引入Transformer编码器,本文的模型比DETR参数量更小、计算量更低、模型收敛速度更快。但是,直接去除Transformer编码器将降低网络的表达能力,导致Transformer解码器无法从数量庞大的图像特征中关注到包含目标的图像特征,从而使检测性能大幅降低。为了缓解这个问题,本文提出了一种混合特征注意力(fusion-feature mixing attention,FMA)机制,它通过自适应特征混合和通道交叉注意力弥补检测网络特征表达能力的下降,将其应用于Transformer解码器可以减轻由于去除Transformer编码器带来的性能降低。在MS-COCO数据集上,本文网络模型(称为FMA-DETR)实现了与DETR相近的性能表现,同时本文的模型拥有更快的收敛速度、更小的参数量以及更低的计算量。本文还进行了大量消融实验来验证所提出方法的有效性。