Channel Correlation Based User Grouping Algorithm for Nonlinear Precoding Satellite Communication System

Low Earth Orbit(LEO)multibeam satellites will be widely used in the next generation of satellite communication systems,whose inter-beam interference will inevitably limit the performance of the whole system.Nonlinear precoding such as Tomlinson-Harashima precoding(THP)algorithm has been proved to be a promising technology to solve this problem,which has smaller noise amplification effect compared with linear precoding.However,the similarity of different user channels(defined as channel correlation)will degrade the performance of THP algorithm.In this paper,we qualitatively analyze the inter-beam interference in the whole process of LEO satellite over a specific coverage area,and the impact of channel correlation on Signal-to-Noise Ratio(SNR)of receivers when THP is applied.One user grouping algorithm is proposed based on the analysis of channel correlation,which could decrease the number of users with high channel correlation in each precoding group,thus improve the performance of THP.Furthermore,our algorithm is designed under the premise of co-frequency deployment and orthogonal frequency division multiplexing(OFDM),which leads to more users under severe inter-beam interference compared to the existing research on geostationary orbit satellites broadcasting systems.Simulation results show that the proposed user grouping algorithm possesses higher channel capacity and better bit error rate(BER)performance in high SNR conditions relative to existing works.

A novel similarity measurement approach considering intrinsic user groups in collaborative filtering

To improve the similarity measurement between users, a similarity measurement approach incorporating clusters of intrinsic user groups（ SMCUG） is proposed considering the social information of users. The approach constructs the taxonomy trees for each categorical attribute of users. Based on the taxonomy trees, the distance between numerical and categorical attributes is computed in a unified framework via a proper weight. Then, using the proposed distance method, the nave k-means cluster method is modified to compute the intrinsic user groups. Finally, the user group information is incorporated to improve the performance of traditional similarity measurement. A series of experiments are performed on a real world dataset, M ovie Lens. Results demonstrate that the proposed approach considerably outperforms the traditional approaches in the prediction accuracy in collaborative filtering.

Deep Learning Based User Grouping for FD-MIMO Systems Exploiting Statistical Channel State Information

The joint spatial division and multiplexing(JSDM)is a two-phase precoding scheme for massive multiple-input-multiple-output(MIMO)system under frequency division duplex(FDD)mode to reduce the amount of channel state information(CSI)feedback.To apply this scheme,users need to be partitioned into groups so that users in the same group have similar channel covariance eigenvectors while users in different groups have almost orthogonal eigenvectors.In this paper,taking the clustered user model into account,we consider the user grouping of JSDM for the downlink massive MIMO system with uniform planar antenna array(UPA)at base station(BS).A deep learning based user grouping algorithm is proposed to improve the efficiency of the user grouping process.The proposed grouping algorithm transfers the statistical CSI of all users into a picture,and utilizes the deep learning enabled objective detection model you look only once(YOLO)to divide the users into different groups rapidly.Simulation results show that the proposed user grouping scheme can achieve higher sum rate with less time delay.

Enhancing Next-Item Recommendation Through Adaptive User Group Modeling

Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship between users.This work is based on the intuition that dynamic groups of like-minded users exist over time.By considering the impact of latent user groups,we can learn a user’s preference in a better way.To this end,we propose a recommendation model based on learning user embeddings by modeling long and short-term dynamic latent user groups.Specifically,we utilize two network units to learn users’long and short-term sessions,respectively.Meanwhile,we employ two additional units to determine the affiliation of users with specific latent groups,followed by an aggregation of these latent group representations.Finally,user preference representations are shaped comprehensively by considering all these four aspects,based on an attention mechanism.Moreover,to avoid setting the number of groups manually,we further incorporate an adaptive learning unit to assess the necessity for creating a new group and learn the representation of emerging groups automatically.Extensive experiments prove our model outperforms multiple state-of-the-art methods in terms of Recall,mean average precision(mAP),and area under curve(AUC)metrics.

User grouping and optimization-based pilot scheduling for mitigating the pilot contamination in massive multi cell MIMO systems

Massive multiple-input multiple-output(massive MIMO)is a promising approach in wireless communication systems for providing improved link reliability and spectral effi-ciency and it helps several users.The main aim is to solve pilot contamination issue in massive MIMO systems;this research paper utilizes two approaches for reducing the contamination.This paper presents the user grouping approach based on sparse fuzzy C-means clustering(sparse FCM),which groups user parameters based on parameters such as large-scale fading factor,SINR,and user distance.Here,same pilot sequences are assigned to center users in which the impact of pilot contamination is limited,while the algorithm assigns orthogonal pilot sequences to the edge users that suffer severely from pilot contamination.Therefore,the proposed user grouping keeps away from the inappropriate grouping of users,enabling effective grouping even under the worst situations of the channel.Secondly,pilot scheduling is done based on elephant spider monkey optimization(ESMO),which is designed by integrating elephant herding optimization(EHO)into spider monkey optimization(SMO).The performance of pilot scheduling based on grouping-based ESMO is evaluated based on achievable rate and SINR.The proposed method achieves maximal achievable rate of 41.29 bps/Hz and maximal SINR of 124.31 dB.

Research on User Pairing Techniques Based on NOMA in Cognitive Radio Networks

This paper outlined a Non-Orthogonal Multiple Access (NOMA) grouping transmission scheme for cognitive radio networks. To address the problems of small channel gain difference of the middle part users caused by the traditional far-near pairing algorithm, and the low transmission rate of the traditional Orthogonal Multiple Access (OMA) transmission, a joint pairing algorithm was proposed, which provided multiple pairing schemes according to the actual scene. Firstly, the secondary users were sorted according to their channel gain, and then different secondary user groups were divided, and the far-near pairing combined with (Uniform Channel Gain Difference (UCGD) algorithm was used to group the secondary users. After completing the user pairing, the power allocation problem was solved. Finally, the simulation data results showed that the proposed algorithm can effectively improve the system transmission rate.

多无人机辅助NOMA网络的联合无线资源分配算法

为了满足高容量需求和通信质量,提出了一种多无人机(Unmanned Aerial Vehicle, UAV)辅助下行非正交多址(Non-Orthogonal Multiple Access, NOMA)网络的联合定位、用户调度、用户配对和功率分配优化算法。在基站位置固定的网络场景下,推导出通用最优用户配对和功率分配策略闭式解。针对多小区场景,将无人机的位置优化问题转化为一个局部合作博弈问题,并证明所提博弈是一个精确的潜在博弈,它至少有一个纯策略纳什均衡(Pure Strategy Nash Equilibrium, PNE),且最优的纳什均衡(Nash Equilibrium, NE)能够最大化网络和速率。设计了一种集中分布式学习算法寻找最优PNE。仿真结果表明,该算法优于现有方案,显著提高了网络效用。

面向用户多样化业务需求的多波束卫星系统动态资源分配算法

多波束卫星通信系统由于其高吞吐量和高资源利用率而受到广泛关注.已有研究主要考虑多波束卫星通信系统的信道或功率分配问题,但较少考虑用户分组和动态资源分配策略的联合优化设计,导致系统性能受限.此外,现有研究往往假设固定的波束覆盖半径,忽略了波束覆盖半径可变性对波束覆盖性能提升的影响.本文研究了多波束卫星通信系统中的用户分组和资源分配问题,提出了一种两阶段资源管理方案.针对动态和多样化的用户服务需求,首先设计一种基于Voronoi图的迭代用户分组算法以实现分组之间的负载均衡,然后将子信道和功率分配问题建模为系统平均效用函数最大化问题.为解决该问题,将每个波束视为一个智能体,采用一种基于多智能体深度Q网络(Deep Q Network,DQN)的算法来确定子信道和功率分配策略.仿真结果表明,与K-均值用户分组方案相比,本文所提出的基于Voronoi图的迭代用户分组算法对应的用户组负载差异值可降低49.2%,体现了本文所提算法在实现用户组间负载均衡方面的优势.此外,本文所提两阶段资源管理方案与现有文献中所提算法相比,系统所提供容量与用户需求差值可降低83.43%,体现了本文所提算法在实现系统资源高效利用及用户服务需求保障方面的性能优势.

移动场景下反向散射混合多址算法研究

随着移动物联网的发展,在移动场景下实现高速、低功耗的信息传递具有重要研究价值。反向散射通信作为一种低功耗的通信技术可以解决功耗与能量供应问题。NOMA(非正交多址接入)是实现高频谱效率的技术,基于用户之间信道增益差进行配对通信,但是当用户信道增益差过小时,会产生强干扰进而严重影响性能,而采用OMA(正交多址接入)可以降低干扰。针对移动场景中因信道增益频繁变化而导致的性能降低以及能量供应问题,构建了移动场景下反向散射混合多址系统模型,提出反向散射设备在移动场景中使用NOMA或OMA的动态阈值,以最大化复用NOMA提升速率,剩余设备则采用OMA,并在此基础上提出最佳信道增益差配对算法。仿真结果表明,在移动场景中相较于传统方法,和速率、中断概率、复用用户数都有显著提高,在小型无人机、无人船等方面具有应用价值。

具有无线携能技术的MIMO-NOMA系统

用户干扰降低了毫米波大规模多输入多输出(MIMO)非正交多址接入(NOMA)系统的频谱效率和能量效率,针对这一问题,提出将无线携能技术(SWIPT)引入基于混合预编码(HP)的MIMO-NOMA系统,并设计了用户分组、混合预编码以及功率分配方案。首先,提出了簇头选择算法,以设计模拟预编码,基于等效信道相关性进行用户分组,并最大化等效信道增益设计数字预编码;其次,为追求用户间的公平性,提出一种基于二分的功率分配方案,以实现最小可达速率最大化。理论分析和仿真结果表明,信噪比(SNR)为5dB时,相较于现有的具有无限携能的正交多址方案,所提方案在全连接架构下频谱效率提升约24.8%,在子连接架构下能量效率提升约24.6%。

结合用户共同意图及社交关系的群组推荐方法

已有的群组推荐模型,在求解用户表示时大多比较单调且仅简单利用用户间的社交关系,使得用户表示不够准确,并且大都未考虑用户共同意图以及社交关系对群组偏好的影响,导致推荐的项目很难符合用户的需求。基于此,提出一种结合用户共同意图及社交关系的群组推荐模型(GR-UCISI)。首先构造用户-项目交互历史与社交关系相结合的用户意图分离模型,利用图神经网络采集每个用户的用户-项目交互以及社交关系信息,求解用户意图和项目表示;其次利用网络游走算法与K-means聚类算法将用户分组,结合用户群组、用户意图以及群组意图聚合过程获取群组共同意图表示;最后根据群组共同意图表示与项目表示得出群组推荐项目列表。该方法充分考虑到用户的个性以及群组成员间的共性对群组偏好的影响,同时结合社交关系缓解数据稀疏性问题,提升模型性能。实验结果表明,与9个对比模型中推荐效果最好的模型相比,在Gowalla数据集上,GR-UCISI的Precision和NDCG指标值分别提高3.01%和5.26%;在Yelp-2018数据集上,GR-UCISI的Precision和NDCG指标值分别提高2.96%和1.12%。

交互式包装赋能乡村产业振兴路径研究

本文探讨了交互式包装在乡村产业振兴中提升农产品附加值、产品销售、品牌推广、文化传承的作用及潜在影响,它以独特的互动性和数字化展示方式为乡村产业提供了全新的展示平台和市场营销机会。但交互式包装的娱乐性、游戏性、体验性等诸多优势也是需要反思的,设计不能只站在市场和商业营销的层面考虑,还肩负着价值引导、文化传承和审美取向的责任,故针对不同用户群特点,农产品交互包装也应该有所侧重地将中国传统农业文化、农耕文明、民俗风情等融入其中,以凸显民族和地域特征,提升交互体验的隐性价值,在助力乡村产业振兴的同时带动文化振兴,推动城乡一体化创新发展。

融合群体兴趣和核心用户影响的群组推荐方法研究

[目的/意义]为提高群组推荐准确率和可解释性,针对现有的群组推荐方法较少关注群组内核心用户对群体兴趣的影响,综合考虑群组整体兴趣和群组内核心用户对其他用户的影响,提出融合群体兴趣和核心用户影响的群组推荐方法。[方法/过程]首先,借鉴h指数思想计算群组内每个用户的影响力,识别群组内核心用户;其次,利用LDA主题模型进行群体兴趣建模和核心用户兴趣建模;最后,综合考虑群组中用户自身兴趣和其受核心用户影响而产生的兴趣进行资源推荐服务。[结果/结论]利用微博数据进行实证,验证了此方法的有效性。

基于用户需求和Cite Space视角的方言交互设计研究

目的 在“Z时代”群体中普及方言相关文化,提升目标群体对方言的兴趣。方法 首先从用户需求的视角出发,通过Kano模型分析“Z时代”群体对方言交互产品的相关用户需求、归纳出功能、界面、主题三个层面的需求并进行排序;其次以湘语区方言为例,运用Cite Space软件对方言相关文献进行分析生成知识图谱,以此为基础优化得到方言知识图谱地图;最后构建出以知识图谱为核心、以用户需求为导向的设计框架并进行交互产品设计。结果 在用户需求指引下,结合知识图谱构建了产品设计框架,并完成方言APP的设计。结论 将用户需求和Cite Space软件引入方言APP的设计中,有助于提升目标用户群体对于方言的兴趣,对方言年轻化、数字化提供了新思路,同时也为相关文化类APP提供了设计流程的借鉴与参考。

多波束低轨卫星用户分组与资源分配算法

与地面网络设施相比,卫星的机载资源十分有限,面对用户地理位置及流量需求分布的不均匀,传统的固定分组和固定资源分配方式缺乏灵活性,限制了系统容量。基于地理位置的用户分组,利用相控阵天线产生的具有灵活方向和波束宽度的动态波束和跳波的时间分片技术,可以实现对卫星资源的合理分配和高效利用。在低轨多波束卫星场景下,利用P中心问题模拟用户分组问题算法对卫星用户进行分组,实现用户平均信息速率的最大化。基于分组结果提出一套适用于用户分组方案的灵活资源分配算法,并在最后加入一个组间资源调配的过程,以避免空闲资源的浪费。经过实验数据模拟和性能评估,所提算法比传统的用户分组和资源分配算法更能够有效提升系统吞吐量,降低用户平均排队时延。

基于用户群体体验研究的人体工学椅优化设计

目的为提升人体工学椅的群体用户体验水平,从用户需求出发,研究产品的群体用户体验设计策略。方法首先,从白领人群对产品的行为特征、操作习惯和情感变化出发,结合唐·诺曼(Don Norman)提出的三层次理论,从欲望层次、行为层次和反应层次确定群体用户体验的关键评价指标,其次,应用提出的“概率密度有序加权”(Probability Density Ordered Weighting,PDOW)方法构建产品用户群体体验综合评价模型,克服用户体验测试的不确定性,并探寻用户群体评价结果与评价指标的联系。最后,设计白领人群人体工学椅产品用户体验实验,确定人体工学椅最佳方案。结果建模结果表明,应用综合评价模型,能够很好地反映出白领人群对人体工学椅外观、交互和情感的偏好,设计出用户体验更好的产品。结论“概率密度有序加权”方法可有效消除测试的不确定性,准确得出用户群体对产品的综合评价结果,其低成本、便捷高效的特性有助于产品设计过程中更好地了解用户群体的偏好,给产品设计中用户群体体验优化提供了新的解决思路。

毫米波大规模MIMO-NOMA系统用户分簇和功率分配设计

针对多用户毫米波大规模多输入多输出-非正交多址接入(MIMO-NOMA)系统功率分配计算复杂的问题,提出新用户分簇和功率分配方案,提高系统的频谱效率。首先改进基于簇头选择的用户分簇方案,根据真实信道动态选择阈值并确定分簇数目,使分簇结果更适合实际情况,用户从波束中获得更大增益。然后以最大化系统频谱效率和能量效率的加权和为目标设计功率分配,使用改进的元启发算法求解。通过对粒子群(PSO)算法引入新的矢量成分和添加余弦扰动使算法更快收敛到全局最优值,并融合沙猫优化(SCSO)算法使算法结果更加精确。仿真结果表明,与现有算法相比,本文提出方案的频谱效率和能量效率优于传统方案,且更适合多用户情况。

基于老年用户群体的APP界面设计研究

对老年生活服务类APP的界面设计进行研究,了解老年用户群体的需求,并为其提供更优质、便捷、安全、满足老年人多元化需求的APP界面设计体验。

面向用户侧不同用电群体的低碳运行用电策略

“双碳”目标的持续推进对用户侧能源消费提出了新的要求,传统用电方式将逐渐向低碳化、清洁化发展。为了应对用户的低碳用电需求,提出一种面向用户侧不同用电群体的低碳运行用电策略。首先,分析用户用电行为特征,结合有损网络的碳排放流理论,构建低碳运行用电策略模型,并制定经济性评价指标。其次,依据节点碳势变化特性,采用蚁狮优化算法对模型进行求解,准确获取不同用户的低碳用电策略。最后,采用IEEE14节点系统对所提模型及方法进行仿真分析,进一步验证所提低碳运行用电策略的有效性。

基于用户画像的大学生群体综合特征分析方法

精准化育人是当前“以人为本”教育理念下高校育人管理工作的应然取向。用户画像技术作为一种能够精准分析用户特征、描绘用户行为的技术手段,可以很好地应用于大学生群体特征分析,推动教育个性化和信息化。针对目前大学生群体综合特征分析方法效率低下、结果真实性差的问题,提出一种基于用户画像技术的大学生群体综合特征画像标签体系与构建框架,旨在准确分析大学生群体的综合特征。通过爬取相关信息平台、发放问卷调查、联系高校相关部门等方式获取可公开数据展开实验分析,采用K-means算法聚类分析得到5类大学生群体,分别为全面型、学霸型、大众型、兴趣型和低迷型。实验结果表明,该画像标签体系与构建框架能有效反映大学生群体的综合特征,为高校个性化和精准化教育管理提供支持,同时也有助于促进大学生的自我认知与管理。