Research progress on water resources management theory of “basing four aspects on water resources”EI北大核心CSCD

In order to implement the rigid constraint system for water resources and promote refined management of water resources, based on the analysis of the concept and notion of “basing four aspects on water resources” and the summary of the experience of water resources management, the basic theory and management guidelines for water resources control of “basing four aspects on water resources” are proposed. The latest progress of “ basing four aspects on water resources” is systematically sorted out, and it is pointed out that further research on the water resources control of “basing four aspects on water resources” should be deepened from the aspects of macro-system evaluation system construction, water resources optimization allocation model reconstruction, and refinement of water resources control system. © 2023, Editorial Board of Water Resources Protection. All rights reserved.     

融合画像和文本信息的轻量级关系图注意推荐模型

针对当前基于图神经网络的推荐系统受数据稀疏影响推荐效率不高的问题,提出融合画像和文本信息的轻量级关系图注意推荐模型(LightRGAN)。首先,利用用户画像和项目画像初始化用户和项目的嵌入表示。其次,引入评论、项目描述和项目类型作为辅助信息,并通过基于多头注意力机制的文本嵌入网络挖掘同一用户评论集和描述集中文本之间的潜在联系。然后,通过融合注意力机制的轻量级关系图卷积网络学习用户和项目的嵌入表示。最后,对各层嵌入表示加权求和并通过预测网络计算匹配分数。在三个公开数据集上的实验结果表明LightRGAN的效果优于多个现有的基线模型,评估指标HR@20、NDCG@20较最优基线模型最少提升了2.58%、2.37%。     

信息化时代Java SE课程网络资源建设与应用研究

运用超星泛雅平台创建了Java SE课程的教学PPT、教学视频、课后作业等网络资源,学生利用所创建Java SE课程的网络资源进行课前预习、课中学习、练习及完成教师发布课后作业等环节的训练.在超星泛雅平台上积累了学生学习Java SE课程网络资源丰富的过程性学习数据,通过分析所积累的学习数据,能有效地评价每一位学生的学习效果和老师应用Java SE课程网络资源的教学效果.     

"互联网+"时代个性化试题推荐方法

"互联网+"环境下,网上自主学习已成常态.文章提出一种个性化试题推荐方法,先通过认知诊断模型诊断出学生的认知状态,再采用协同过滤方法推荐试题,能给学生推荐准确且可解释性的试题.     

教育信息化背景下劳动教育的新要求和新问题

劳动教育是教育体系的重要组成部分,国家对高校劳动教育提出加强价值观的引导、提升劳动综合技能等新要求.调查发现,高校劳动教育存在边缘化、教育方法简单、考评机制不健全等问题.基于教育信息化2.0的时代背景,从加强校园文化建设、拓展劳动教育平台、健全劳动教育考核机制三方面,对高校的劳动教育提出建议,希望能为高校更好地开展劳动教育提供有价值的参考.     

光纤网络在线监测管理系统优化设计

针对光纤网络在线监测系统在使用过程中存在诸如创建光路等操作繁琐、告警数据展现不实时、监测设备可扩展性差以及测试数据分析不够准确的问题,采用WebGIS、HTML5和WebSocket等技术对其进行优化改造.系统中增加了通信机,并采用一种基于小波变换动态降噪的方法进行OTDR曲线数据分析,实现了操作可视化、告警数据实时展现、兼容不同协议的监测设备,大幅提升OTDR曲线数据分析的快速性和准确性.     

基于深度学习的机器人复杂动作控制技术研究

本文提出了一种基于深度学习的手势识别来控制机器人做复杂动作的解决方案.本文提出的方案展现出有效的开放性和可扩展性,无论是手势识别还是在机器人复杂动作方面,都可以根据需求做相应调整.同时,本研究工作创建了一个有效的基于人工智能网络的机器人控制实用实验平台.实验设计分别以运用6个基础手势控制机器人在危险环境中清除可疑物品为例,验证了开发的平台可以让机器人实时、远程地完成预设复杂动作,满足现实中自然人机交互的功能.     

Image compression and encryption algorithm based on compressive sensing and nonlinear diffusion

Multimedia Tools and Applications - Compressive sensing is widely used to image compression and encryption algorithms due to its high efficiency, but the existing algorithms have some flaws and...     

Design of a broadband dielectric resonator antenna and its application in low sensitivity frequency beam‐scanning array with wide scanning angle and suppressed sidelobes

In this paper, a broadband dielectric resonator antenna (DRA) with a simple H‐slot feeding structure is proposed. The broad bandwidth (~45%) and uni‐directional radiation enable this DRA suitable to work as a radiation element in the construction of a beam‐scanning array with not only low frequency sensitivity which is important for accurate angle estimation of in‐coming targets, but also a wide scanning range. Moreover, stable coupling coefficients are established around all the above three resonances with respect to its corresponding feeding line, ensuring a low sidelobe level (SLL) across the whole operating frequency range. In order to realize such a DRA, a latticed rectangular structure is utilized to generate the lower two resonances, while the upper resonance is generated by its H‐shaped feeding slot. The shape of the latticed dielectric resonator is also modified according to a 3‐D printed fixing structure for an accurate installation. A 20‐element beam‐scanning prototype is demonstrated and manufactured. The range of scanning angle is from ?36° to +13° within the bandwidth of 10 to 16 GHz, corresponding to a frequency sensitivity of only 122.5 MHz/^o. The achieved SLL are smaller than 19 dB for all scanning beams. The above performance indicates that, this array is very suitable for near‐range radar systems requiring an accurate angle estimation.     

Delay‐dependent stability of nonlinear hybrid neutral stochastic differential equations with multiple delays

In this article, we study the delay‐dependent stability of a class of hybrid neutral stochastic differential equations (NSDEs) with multiple delays which is highly nonlinear. Some novel stability criteria are investigated according to Lyapunov functions and generalized Itô's formula. In particular, we generalize and improve the results in Shen et al, Systems & Control Letters (2018) from a single delay to multiple delays.