WATER RESOURCES TRANSFORMATION AND WATER QUALITY VARIATION IN THE URUMQI RIVER BASIN

Like other inland basins in arid regions, the natural vertical zones create special conditions for water resources transformation in the Urumqi River Basin. In the course of water resources transformation and utilization, the chemical composition and degree of mineralization are influenced by both geographic conditions and human activities. Although the Urumqi River is rather small in runoff and rather short in flow distance, the water quality changes substantially along the river. However, ion concentrations of surface and ground water in the whole basin are relatively low, generally less than 1 g/L. Therefore, the basin is good at providing low-mineralized water. The pollution is not so serious and the water impurity does not surpass the national standard for drinking. As long as people are conscious with protecting water quality and reducing the further water pollution, it is possible for harm of the slight pollution to be eliminated.

基于卷积神经网络与Transformer的电能质量扰动分类方法

复杂电能质量扰动(power quality disturbances, PQD)的智能分类对于智能电网发展具有重要意义。扰动特征的提取与定位、模式识别与分类是电能质量扰动分类方法研究的难点。采用深度学习算法,将具有关注全局信息的Transformer与善于提取局部特征的卷积神经网络相融合,提出一种基于卷积神经网络(convolutional neural network, CNN)与Transformer的电能质量扰动分类方法,即CTranCBA。这种双深度学习模型分类方法主要是通过一维卷积神经网络提取电能质量扰动信号特征,利用Transformer自注意力机制引导模型关注序列中不同位置间的依赖关系,实现对扰动信号局部特征与全局特征的互补,克服了因感受野的限制而带来的识别不清、分类不准等问题。使用23种不同电能质量扰动信号,将CTranCBA与Deep-CNN、CNN-LSTM、CNN-CBAM方法进行比较。结果表明:该方法在分类准确率和抗噪性方面表现优异,可为电能质量扰动智能分类提供一种新的方法。

基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估

与从现实场景中拍摄的自然图像不同,屏幕内容图像是一种合成图像,通常由计算机生成的文本、图形和动画等各种多媒体形式组合而成.现有评估方法通常未能充分考虑图像边缘结构信息和全局上下文信息对屏幕内容图像质量感知的影响.为解决上述问题,本文提出一种基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估模型.首先,使用高斯拉普拉斯算子构造由失真屏幕内容图像高频信息组成的边缘结构图,然后通过卷积神经网络(Convolutional Neural Network,CNN)对输入的失真屏幕内容图像和相应的边缘结构图进行多尺度的特征提取与融合,以图像的边缘结构信息为模型训练提供额外的信息增益.此外,本文进一步构建了基于Transformer的多尺度特征编码模块,从而在CNN获得的局部特征基础上更好地建模不同尺度图像和边缘特征的全局上下文信息.实验结果表明,本文提出的方法在指标上优于其他现有的无参考和全参考屏幕内容图像质量评估方法,能够取得更高的主客观视觉感知一致性.

Power Quality Disturbance Classification Method Based on Wavelet Transform and SVM Multi-class Algorithms

The accurate identification and classification of various power quality disturbances are keys to ensuring high-quality electrical energy. In this study, the statistical characteristics of the disturbance signal of wavelet transform coefficients and wavelet transform energy distribution constitute feature vectors. These vectors are then trained and tested using SVM multi-class algorithms. Experimental results demonstrate that the SVM multi-class algorithms, which use the Gaussian radial basis function, exponential radial basis function, and hyperbolic tangent function as basis functions, are suitable methods for power quality disturbance classification.

Application of Slantlet Transform Based Support Vector Machine for Power Quality Detection and Classification

Concern towards power quality (PQ) has increased immensely due to the growing usage of high technology devices which are very sensitive towards voltage and current variations and the de-regulation of the electricity market. The impact of these voltage and current variations can lead to devices malfunction and production stoppages which lead to huge financial loss for the production company. The deregulation of electricity markets has made the industry become more competitive and distributed. Thus, a higher demand on reliability and quality of services will be required by the end customers. To ensure the power supply is at the highest quality, an automatic system for detection and localization of PQ activities in power system network is required. This paper proposed to use Slantlet Transform (SLT) with Support Vector Machine (SVM) to detect and localize several PQ disturbance, i.e. voltage sag, voltage swell, oscillatory-transient, odd-harmonics, interruption, voltage sag plus odd-harmonics, voltage swell plus odd-harmonics, voltage sag plus transient and pure sinewave signal were studied. The analysis on PQ disturbances signals was performed in two steps, which are extraction of feature disturbance and classification of the dis- turbance based on its type. To take on the characteristics of PQ signals, feature vector was constructed from the statistical value of the SLT signal coefficient and wavelets entropy at different nodes. The feature vectors of the PQ disturbances are then applied to SVM for the classification process. The result shows that the proposed method can detect and localize different type of single and multiple power quality signals. Finally, sensitivity of the proposed algorithm under noisy condition is investigated in this paper.

Comparison of GPR Random Noise Attenuation Using Autoregressive-FX Method and Tunable Quality Factor Wavelet Transform TQWT with Soft and Hard Thresholding

Ground Penetration Radar is a controlled source geophysical method which uses high frequency electromagnetic waves to study shallow layers. Resolution of this method depends on difference of electrical properties between target and surrounding electrical medium, target geometry and used bandwidth. The wavelet transform is used extensively in signal analysis and noise attenuation. In addition, wavelet domain allows local precise descriptions of signal behavior. The Fourier coefficient represents a component for all time and therefore local events must be described by the phase characteristic which can be abolished or strengthened over a large period of time. Finally basis of Auto Regression (AR) is the fitting of an appropriate model on data, which in practice results in more information from data process. Estimation of the parameters of the regression model (AR) is very important. In order to obtain a higher-resolution spectral estimation than other models, recursive operator is a suitable tool. Generally, it is much easier to work with an Auto Regression model. Results shows that the TQWT in soft thresholding mode can attenuate random noise far better than TQWT in hard thresholding mode and Autoregressive-FX method.

Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network

Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.

Population Quality-based Demographic Dividend,Industrial Transformation and Sustainable Development of the Chinese Economy and Society

China is faced with a decreasing labor supply and therefore is losing its cost advantage.However,benefiting from continuous improvement of population quality,China's population quality-based demographic dividend begins to replace the quantity-based dividend to play a dominant role in economic development.Thus,in supply-side structure,rather than essential factors,it paves the way for the sustainable development of the Chinese economy.With the addition of the successful industrial transformation and upgrading,China still has the advantage to overcome the middle income trap and maintain the momentum of economic growth.

Research Status of Water Quality Criteria and Standards and Analysis on the Transformation Methods

Under the vision of development for the new era,China has entered a stage of high-quality economic development and an important window period in which we have the conditions and ability to address the prominent issue of economic development and ecological protection in a coordinated way.However,all kinds of environmental benchmark values in China are lacking and need to be constantly supplemented and improved.Therefore,exploring and putting forward a simple and efficient method for the transformation of environmental criteria into environmental standards is an important basis for the rapid establishment of relevant environmental criteria system and the effective promotion of the development of environmental standards system towards a scientific and reasonable direction.In this paper,the water environment is taken as the research object.By analyzing the research progress of environmental criteria and standards at home and abroad,and the foreign method of transforming environmental criteria into environmental standards,combined with the problems faced in the process of transforming environmental criteria into environmental standards in China,an effective method to transform China's environmental criteria into environmental standards is analyzed.After analysis and comparison,it is found that the pollution reduction accounting method could achieve their simple and efficient conversion.Under the premise of obtaining environmental criteria for certain pollutants,environmental criteria for certain pollutants could be obtained by distributing pollutants reduction costs,and accounting economic benefits after reaching standard,thus obtaining the environmental standard of this type of pollutant,which provides reference to determine the environmental standard limits of such pollutants.

Transient Power and Quality Events Analysed Using Hilbert Transforms

This work presents an advanced mathematical tool applicable to the recognition and classification of power system transients and disturbances. Disturbances without a periodic pattern or with a non-linear pattern require a more suitable tool than the Fourier series （Fast Fourier or Windowed Fourier Transforms）. To overcome these drawbacks, other tools have been broadly used, such as the wavelet transform. However, the wavelet transform also has some drawbacks such as the lack of adaptivity or interpretation of nonlinear phenomena that the Hilbert and Hilbert Huang Transform techniques could mitigate. The Hilbert techniques transform a time domain function into a space representation both in time and frequency. In the paper, the technique is applied to analyse several short-term and steady events, like a short circuit, a capacitor-switching transient, or a line energisation, showing the abilities of the Hilbert-based transforms.

Does Green Food Certification promote agri-food export quality?Evidence from China

The construction of a food certification system plays a vital role in upgrading export quality, which previous studies have largely overlooked. We match China's industry-level data of Green Food Certification with its HS6-digit export data of agri-food products to quantify the impact of Green Food Certification on export quality. We identify the significant and positive effect of Green Food Certification on export quality. The 2SLS estimation based on instrumental variables and a range of robustness checks confirm the validity and robustness of the benchmark conclusions. Further analysis discloses that Green Food Certification improves export quality by raising agricultural production efficiency and brand premiums. Heterogeneity analysis shows that the effect of Green Food Certification varies across regions, notably improving the quality of agri-food products exported to developed regions and regions with high levels of import supervision. Furthermore, among various product types, Green Food Certification significantly improves the export quality of primary products and products vulnerable to non-tariff measures. The above findings could guide the future development of agri-food quality certification systems, potentially leading to a transformation and promotion of the agri-food trade.

基于自监督视觉Transformer的图像美学质量评价方法

现有的图像美学质量评价方法普遍使用卷积神经网络(CNN)提取图像特征,但受局部感受野机制的限制,CNN较难提取图像的全局特征,导致全局构图关系、全局色彩搭配等美学属性缺失。为解决该问题,提出基于自监督视觉Transformer(SSViT)模型的图像美学质量评价方法。利用自注意力机制建立图像局部块之间的长距离依赖关系,自适应地学习图像不同局部块之间的相关性,提取图像的全局特征,从而刻画图像的美学属性;同时,设计图像降质分类、图像美学质量排序和图像语义重构这3项美学质量感知任务,利用无标注的图像数据对视觉Transformer(ViT)进行自监督预训练,增强全局特征的表达能力。在AVA(Aesthetic Visual Assessment)数据集上的实验结果显示,SSViT模型在美学质量分类准确率、皮尔森线性相关系数(PLCC)和斯皮尔曼等级相关系数(SRCC)指标上分别达到83.28%、0.7634和0.7462。以上实验结果表明,SSViT模型具有较高的图像美学质量评价准确性。

基于双模态Transformer模型的话务量预测

为降低客户服务中心电话的等待率,提升服务质量。针对现有算法不能实现中长期话务量预测的问题,提出了一种基于双模态Transformer模型的话务量预测方法。首先采集并预处理某运营商真实的话务量数据,通过双模态特征融合构造出有益特征,最后采用多种模型进行话务量预测以及多种衡量指标对预测结果进行分析。结果表明:与其他算法比较,Transformer模型性能较好,对运营商资源的合理配置具有较高的指导意义,同时更易获得客户较高的满意度和忠诚度。

Power Supply Quality Analysis Using S-Transform and SVM Classifier

In this paper, a SVM classifier based on S-Transform is presented for power quality disturbances classification. Firstly, seven types of PQ events are created using Matlab simulation. These signals are analyzed to detect and localize PQ events via S-Transform by visual inspection. Then five significant features of the PQ disturbances are extracted from the S-Transform output. Afterwards, PQ disturbance samples with the five features are fed to SVM for training and automatic classification. Besides, particle swarm optimization is implemented to improve the performance of SVM. The results of the classification indicate that SVM classifier is an effective mechanism to detect and classify power quality disturbances.

基于Transformer的空调能耗预测模型构建与参数优化

针对空调系统能耗预测建模过程中的数据质量、模型输入参数筛选等问题,研究基于Transformer神经网络的空调系统能耗预测模型构建和参数优化方法,结果表明:可以通过广义极端学生化偏差方法对数据中的离群值进行检测修正,从而提升数据质量;通过余弦相似度对输入参数进行两两相关性检验来消除各参数间的多重共线性,实现对输入参数的初步筛选;采用随机森林算法计算初选参数对空调能耗预测结果的影响来判断冗余参数,进而完成对输入特征参数的最终筛选;建立的空调能耗预测模型对数据测试集的预测结果均方根误差RMSE为38.831 kW,相关系数R^(2)为0.952,表现出了良好的预测性能。

The Digitization of Public Services and Its Contribution to the Quality of Service in Relation to User Satisfaction

In recent years, some governments have been working on solutions to transform public administrations and provide high-quality services to users. The United Nations has recommended integrating digital technology into various aspects of life, including public services. The objective is to offer real-time, high-quality digital services, improve the delivery of public services, enhance their effectiveness and efficiency, while achieving objectives such as transparency, interoperability and citizen satisfaction. However, most governments in developing countries are unable to keep up with this trend. As a result, they often create digital public services that fall short of users’ expectations. This study aims to identify the fundamental factors influencing the quality of service in relation to user satisfaction and to explore the relevance of digital technology in implementing this quality within Cameroon public administrations. To achieve this, we used a qualimetric research method, which included non-directive interviews, questionnaires, and structured observations. The results showed that the public services offered in our study environment did not meet users’ expectations. However, the study identified the fundamental aspects to be considered in providing quality public services connected to user satisfaction, as well as the strengths of digitization in achieving this quality.

Construction and Practice of Education and Teaching Quality Assurance Systems in Applied Colleges and Universities under the Background of Digital Intelligence

This paper discusses the optimization strategy of education and teaching quality assurance systems in applied colleges and universities under the background of digital intelligence.It first summarizes the relevant theories of digital intelligence transformation and analyzes the impact of digital intelligence transformation on higher education.Secondly,this paper puts forward the principles of constructing the quality assurance system of applied colleges,including strengthening the quality assurance consciousness,improving teachers’digital literacy,and implementing digital intelligence governance.From the practical perspective,this paper expounds on strategies such as optimizing educational teaching resource allocation,constructing a diversified evaluation system of teaching quality,strengthening the construction and training of teaching staff,and innovating teaching management methods.Specific optimization measures are put forward,such as improving policies,regulations,and system guarantees,strengthening cooperation between schools and enterprises,integrating industry,school,and research,building an educational information platform,and improving the monitoring and feedback mechanism of educational quality.

USformer-Net:基于U-Net和Swin Transformer的脑部MRI图像质量评价方法

针对现有的脑部MRI图像质量评价方法准确率低、难以应用于实际临床环境中的问题,提出一种基于提取感兴趣区域的脑部MRI图像质量自动评价模型USformer-Net,并创建了带有主观质量评价标签的脑部MRI图像数据集。USformer-Net模型基于U-Net和Swin Transformer模型构建并针对脑部MRI图像的特殊性进行了改进。首先,利用轻量化的U-Net网络对具有临床诊断价值的大脑主要区域进行分割,提取出感兴趣区域;其次,利用Swin Transformer的串联窗口自注意力运算(W-MSA)、滑动窗口自注意力运算(SW-MSA)以及其特征融合方式,将特征金字塔(FPN)、兴趣区域匹配(ROI Align)及全连接网络(FC)结合在Swin Transformer骨干特征提取网络中进行图像质量评价。USformer-Net模型能够忽略无关噪声,准确提取出影响诊断的主要区域并进行图像质量评价。实验结果表明,在MRI图像质量评价任务中该模型准确率为87.84%,精度为91.84%,召回率为92.05%,F1-score为91.99%,相较于其他评价方法各项指标均有不同程度提升。最终结果显示该模型能够有效保证脑部MRI图像质量评价的准确性,创建的带有主观质量评价标签的数据集也为该领域的研究提供了更好的数据支持。

数字化转型、新质生产力与企业创新绩效

在大数据与互联网时代,企业数字化转型是企业发展的必然趋势,转型过程也将对企业创新绩效产生影响。利用2015—2021年中国上市公司企业微观数据,实证分析发现:企业数字化转型将显著提升企业创新绩效水平,并通过企业科技研发投入和企业创新专利产出来体现。采用一系列稳健性检验和内生性方法分析后,模型结论依旧成立。异质性分析发现,国有企业、非重污染企业以及处在东南部区域企业数字化转型对企业创新绩效的影响效应更强。机制分析发现,企业数字化转型可通过提升企业新质生产力来提高企业的创新绩效水平。最后,从企业本身、监管机构以及政府三个角度对数字化转型和企业创新发展提出展望。

基于Transformer模型的干辣椒等级分类方法研究

针对生产出的干辣椒品相不一的问题,提出基于Transformer模型的干辣椒等级分类识别方法。根据干辣椒特征,确定干辣椒等级标准,包括优质干辣椒、合格干辣椒和不合格干辣椒3个等级。制备干辣椒数据集并划分为训练集和测试集。首先结合Visual Transformer(ViT)网络和分类网络,引入并改进Shifted windows Transformer(Swin Transformer)网络,使用高斯误差线性单元(GELU)做激活函数,使用自适应矩估计(Adam)做优化函数。通过加载在ImageNet数据集训练的权重进行模型初始化,表明迁移学习方式可有效提高模型特征提取能力。通过对比ViT模型和Swin Transformer模型两种模型来训练干辣椒数据集,表明Swin Transformer模型测试准确率较高。实验表明,利用迁移学习的Swin Transformer模型准确率最高,达到95.26%,这为干辣椒等级分拣问题提供了新的解决办法,同时可作为其他果蔬品相识别的参考。