Risk-based water quality decision-making under small data using Bayesian network

A knowledge-based network for Section Yidong Bridge,Dongyang River,one tributary of Qiantang River,Zhejiang Province,China,is established in order to model water quality in areas under small data.Then,based on normal transformation of variables with routine monitoring data and normal assumption of variables without routine monitoring data,a conditional linear Gaussian Bayesian network is constructed.A "two-constraint selection" procedure is proposed to estimate potential parameter values under small data.Among all potential parameter values,the ones that are most probable are selected as the "representatives".Finally,the risks of pollutant concentration exceeding national water quality standards are calculated and pollution reduction decisions for decision-making reference are proposed.The final results show that conditional linear Gaussian Bayesian network and "two-constraint selection" procedure are very useful in evaluating risks when there is limited data and can help managers to make sound decisions under small data.

Failure rate analysis and maintenance plan optimization method for civil aircraft parts based on data fusion

In the face of data scarcity in the optimization of maintenance strategies for civil aircraft,traditional failure data-driven methods are encountering challenges owing to the increasing reliability of aircraft design.This study addresses this issue by presenting a novel combined data fusion algorithm,which serves to enhance the accuracy and reliability of failure rate analysis for a specific aircraft model by integrating historical failure data from similar models as supplementary information.Through a comprehensive analysis of two different maintenance projects,this study illustrates the application process of the algorithm.Building upon the analysis results,this paper introduces the innovative equal integral value method as a replacement for the conventional equal interval method in the context of maintenance schedule optimization.The Monte Carlo simulation example validates that the equivalent essential value method surpasses the traditional method by over 20%in terms of inspection efficiency ratio.This discovery indicates that the equal critical value method not only upholds maintenance efficiency but also substantially decreases workload and maintenance costs.The findings of this study open up novel perspectives for airlines grappling with data scarcity,offer fresh strategies for the optimization of aviation maintenance practices,and chart a new course toward achieving more efficient and cost-effective maintenance schedule optimization through refined data analysis.

A LoRa-based protocol for connecting IoT edge computing nodes to provide small-data-based services

Data is becoming increasingly personal.Individuals regularly interact with a variety of structured data,ranging from SQLite databases on the phone to personal sensors and open government data.The“digital traces left by individuals through these interactions”are sometimes referred to as“small data”.Examples of“small data”include driving records,biometric measurements,search histories,weather forecasts and usage alerts.In this paper,we present a flexible protocol called LoRaCTP,which is based on LoRa technology that allows data“chunks”to be transferred over large distances with very low energy expenditure.LoRaCTP provides all the mechanisms necessary to make LoRa transfer reliable by introducing a lightweight connection setup and allowing the ideal sending of an as-long-as necessary data message.We designed this protocol as communication support for small-data edge-based IoT solutions,given its stability,low power usage,and the possibility to cover long distances.We evaluated our protocol using various data content sizes and communication distances to demonstrate its performance and reliability.

Data science for oceanography:from small data to big data

The rapid development of ocean observation technology has resulted in the accumulation of a large amount of data and this is pushing ocean science towards being data-driven.Based on the types and distribution of oceanographic data,this paper analyzes the present and makes predictions for the future regarding the use of big and small data in ocean science.The ocean science has not fully entered the era of big data.There are two ways to expand the amount of oceanographic data to better understanding and man-agement of the ocean.On the data level,fully exploit the potential value of big and small ocean data,and transform the limited,small data into rich,big data,will help to achieve this.On the application level,oceanographic data are of great value if realize the federation of the core data owners and the consumers.The oceanographic data will provide not only a reliable scientific basis for climate,ecological,disaster and other scientific research,but also provide an unprecedented rich source of information that can be used to make predictions of the future.

An analytical model for estimating rock strength parameters from small-scale drilling data

The small-scale drilling technique can be a fast and reliable method to estimate rock strength parameters. It needs to link the operational drilling parameters and strength properties of rock. The parameters such as bit geometry, bit movement, contact frictions and crushed zone affect the estimated parameters.An analytical model considering operational drilling data and effective parameters can be used for these purposes. In this research, an analytical model was developed based on limit equilibrium of forces in a Tshaped drag bit considering the effective parameters such as bit geometry, crushed zone and contact frictions in drilling process. Based on the model, a method was used to estimate rock strength parameters such as cohesion, internal friction angle and uniaxial compressive strength of different rock types from operational drilling data. Some drilling tests were conducted by a portable and powerful drilling machine which was developed for this work. The obtained results for strength properties of different rock types from the drilling experiments based on the proposed model are in good agreement with the results of standard tests. Experimental results show that the contact friction between the cutting face and rock is close to that between bit end wearing face and rock due to the same bit material. In this case,the strength parameters, especially internal friction angle and cohesion, are estimated only by using a blunt bit drilling data and the bit bluntness does not affect the estimated results.

A new package:MySAS for small angle scattering data analysis

In this paper,A MySAS package,which is verified on Windows XP,can easily convert two-dimensional data in small angle neutron and X-ray scattering analysis,operate individually and execute one particular operation as numerical data reduction or analysis,and graphical visualization.This MySAS package can implement the input and output routines via scanning certain properties,thus recalling completely sets of repetition input and selecting the input files.On starting from the two-dimensional files,the MySAS package can correct the anisotropic or isotropic data for physical interpretation and select the relevant pixels.Over 50 model functions are fitted by the POWELL code using x^2 as the figure of merit function.

Model-data-driven seismic inversion method based on small sample data

As sandstone layers in thin interbedded section are difficult to identify,conventional model-driven seismic inversion and data-driven seismic prediction methods have low precision in predicting them.To solve this problem,a model-data-driven seismic AVO(amplitude variation with offset)inversion method based on a space-variant objective function has been worked out.In this method,zero delay cross-correlation function and F norm are used to establish objective function.Based on inverse distance weighting theory,change of the objective function is controlled according to the location of the target CDP(common depth point),to change the constraint weights of training samples,initial low-frequency models,and seismic data on the inversion.Hence,the proposed method can get high resolution and high-accuracy velocity and density from inversion of small sample data,and is suitable for identifying thin interbedded sand bodies.Tests with thin interbedded geological models show that the proposed method has high inversion accuracy and resolution for small sample data,and can identify sandstone and mudstone layers of about one-30th of the dominant wavelength thick.Tests on the field data of Lishui sag show that the inversion results of the proposed method have small relative error with well-log data,and can identify thin interbedded sandstone layers of about one-15th of the dominant wavelength thick with small sample data.

Consensus of heterogeneous multi-agent systems based on sampled data with a small sampling delay

In this paper, consensus problems of heterogeneous multi-agent systems based on sampled data with a small sampling delay are considered. First, a consensus protocol based on sampled data with a small sampling delay for heterogeneous multi-agent systems is proposed. Then, the algebra graph theory, the matrix method, the stability theory of linear systems, and some other techniques are employed to derive the necessary and sufficient conditions guaranteeing heterogeneous multi-agent systems to asymptotically achieve the stationary consensus. Finally, simulations are performed to demonstrate the correctness of the theoretical results.

Data processing of small samples based on grey distance information approach

Data processing of small samples is an important and valuable research problem in the electronic equipment test. Because it is difficult and complex to determine the probability distribution of small samples, it is difficult to use the traditional probability theory to process the samples and assess the degree of uncertainty. Using the grey relational theory and the norm theory, the grey distance information approach, which is based on the grey distance information quantity of a sample and the average grey distance information quantity of the samples, is proposed in this article. The definitions of the grey distance information quantity of a sample and the average grey distance information quantity of the samples, with their characteristics and algorithms, are introduced. The correlative problems, including the algorithm of estimated value, the standard deviation, and the acceptance and rejection criteria of the samples and estimated results, are also proposed. Moreover, the information whitening ratio is introduced to select the weight algorithm and to compare the different samples. Several examples are given to demonstrate the application of the proposed approach. The examples show that the proposed approach, which has no demand for the probability distribution of small samples, is feasible and effective.

基于多核数据合成的离线小数据驱动的进化算法

为了增强离线数据驱动的进化算法在小数据情景中的表现,削弱代理模型对数据集规模的依赖,提出基于多核数据合成的离线小数据驱动的进化算法(DDEA-MKDS).考虑到代理模型易因小数据陷入过拟合,通过经验公式与遍历法找出针对离线数据集的最优隐含层节点数,以简化模型结构.为了弥补数据量的不足,训练了3个不同核函数的径向基网络生成合成数据,通过轮盘赌法选择其中的部分数据与原数据集合并,使用新数据集训练代理模型.将DDEA-MKDS与其他5种流行的离线数据驱动的进化算法在6个单目标基准测试问题上进行对比,实验结果表明,所提算法在数据量极小的条件下能够取得良好的效果,寻优效率显著优于其他算法.

A Review of Cybersecurity Challenges in Small Business: The Imperative for a Future Governance Framework

Technological shifts—coupled with infrastructure, techniques, and applications for big data—have created many new opportunities, business models, and industry expansion that benefit entrepreneurs. At the same time, however, entrepreneurs are often unprepared for cybersecurity needs—and the policymakers, industry, and nonprofit groups that support them also face technological and knowledge constraints in keeping up with their needs. To improve the ability of entrepreneurship research to understand, identify, and ultimately help address cybersecurity challenges, we conduct a literature review on the state of cybersecurity. The research highlights the necessity for additional investigation to aid small businesses in securing their confidential data and client information from cyber threats, thereby preventing the potential shutdown of the business.

Data Mining for Small and Medium Enterprises: A Conceptual Model for Adaptation

The following paper explored data mining issues in Small and Medium Enterprises’ (SMEs), firstly exploring the relationship between data mining and economic development. With SME’s contributing most employment prospects and output within any emerging economy such as the Kingdom of Saudi Arabia. Adopting technology will improve SME’s potential for effective decision making and efficient operations. Hence, it is important that SMEs have access to data mining techniques and implement the most suited into their business to improve their business intelligence (BI). The paper is aimed to critically review the existing literature on data mining in the field of SME to provide a theoretical underpinning for any future work. It has been found data mining to be complicated and fragmented with a multitude of options available for businesses from quite basic systems implemented within Excel or Access to more sophisticated cloud-based systems. For any business, data mining is trade-off between the need for data analysis, and intelligence against the cost and resource-use of the system put in place. Multiple challenges have been identified to data mining, most notably the resource-intensive nature of systems (both in terms of labor and capital) and the security issues of data collection, analysis and storage;with General Data Protection Regulation (GDPR) a key focus for Kingdom of Saudi Arabia businesses. With these challenges the paper suggests that any SME starts small with an internal data mining exercise to digitalize and analyze their customer data, scaling up over time as the business grows and acquires the resources needed to properly manage any system.

基于改进ACGAN算法的带钢小样本数据增强方法

为了解决带钢小样本数据集在深度学习中出现的模式崩溃、图像模糊和错判等问题,提出一种改进的ACGAN数据增强方法。首先,模型中引入带梯度惩罚项的Wasserstein距离作为损失函数,解决了模式崩溃和训练不稳定问题;其次,生成器网络中改进标签反卷积网络,使标签信息更好地贯穿整个生成网络,并在其末端设计了去噪结构,提高了生成图像质量;接着,判别器网络中引入级联融合思想,增强了网络判别能力;最后,将改进前后的模型在NEU带钢表面缺陷数据集和MNIST数据集上进行对比实验,结果表明:所提模型生成各类样本图像的清晰度、准确性明显提高,并且客观指标FID的平均值在NEU带钢表面缺陷数据集上下降了15.8%,在MNIST数据集下降了73%,为带钢小样本数据集的扩充提供了一种新方法。

基于特征融合的GA-SVM配电网单相接地故障选线方法

针对配电网单相接地故障数据量较少时,选线方法精度不高,提出一种基于特征融合的遗传算法优化支持向量机(genetic algorithm-support vector machine,GA-SVM)配电网单相接地故障选线方法,采用傅里叶变换、有功功率法以及小波包变换对不同故障工况下每一条线路的暂态零序电流进行分解,提取基波幅值、五次谐波幅值、平均有功功率分量及小波能量值四种特征,经主成分分析法对这四种特征进行融合,提取主成分分量,建立特征数据库,将特征数据库的80%作为训练集,20%作为测试集,通过GA-SVM对特征数据库中的样本进行训练,实现故障选线。通过MATLAB/Simulink搭建包含5条馈线的配电网仿真模型进行验证,结果表明,提出的算法可以通过小样本数据实现故障选线,选线精度较高,适用性强。

面向中医药高维小样本的多组学数据融合方法初探

随着大数据和人工智能技术的发展,组学技术在中医药研究中的广泛应用生成了大型实验数据集,跨尺度寻找海量数据之间的关联成为可能,由此也逐步进入数据密集型研究范式。重视技术及算力工具的多组学数据融合分析模式作为新兴方法之一,或许是该领域的突破点。中医学的整体观念与多组学数据融合的理念呈现相似之处,但其数据类型呈现高维小样本特征,因此需要通过降维等的方式对数据进行处理。目前的挑战是如何选择适合数据的分析方法,增加对生理功能和疾病诊疗过程的系统理解。因此该文通过对多组学数据融合的理论和框架进行探索,分析中医药高维小样本多组学数据融合的方法,拟为中医药的发展提供思路。

基于对偶贝叶斯U-Net的波阻抗不确定性反演方法研究

传统的深度神经网络通常只能实现确定性的预测,无法对反演结果进行不确定性分析,即无法对反演结果的可靠性进行评价。为实现标签数据不足条件下精确的波阻抗反演和对反演结果的不确定性分析,提出了一种基于对偶贝叶斯U-Net的波阻抗不确定性反演方法。首先,开展基于对偶贝叶斯U-Net、前沿深度学习反演方法和传统不确定性反演方法的模拟数据实验,对比分析3种方法的反演精度。然后,将对偶贝叶斯U-Net和传统不确定性反演方法的反演可靠性和对于含噪数据反演的鲁棒性进行对比分析。最后,将对偶贝叶斯U-Net应用于实际地震资料波阻抗反演中。模拟数据实验结果表明,该方法的对偶贝叶斯U-Net在少量标签数据条件下具有较高反演精度并对含噪数据反演有较强鲁棒性。此外,不确定性分析表明,该方法的反演结果可靠性强。实际数据测试结果表明,对偶贝叶斯U-Net能在实际工区数据反演中获得合理并可靠的反演结果。

基于自适应反馈机制的小差异化图像纹理特征信息数据检索

针对小差异化图像纹理相似度和噪声等因素导致纹理特征挖掘效果较差的问题,设计一种自适应反馈结合局部二值机制的小差异化图像纹理特征挖掘方法.使用规范割策略将图像数据各点拟作节点,使用节点间的连接线权重计算2点的相似度,采用支持向量机训练图像属性参数分类图像属性,进一步归纳图像类别.运用跳跃连接方法传输图像数据,将数据引入卷积神经网络剔除图像噪声.将中心点像素值当作反馈因子,创建自适应反馈判定条件,利用局部二值模式实现小差异化图像纹理特征挖掘.在MATLAB平台进行试验,从卷积神经网络收敛性、图像频谱纹理单元数、平均准确率、图像数据匹配度等方面进行了分析,分析结果表明:随着迭代次数不断增加,精度损失逐渐降低,基本收敛到稳定值,达到了预期训练效果;所提出方法挖掘的图像频谱纹理单元数3800个以上,更贴合人眼视觉信息;平均准确率为0.87,准确率@1、准确率@5和准确率@10的平均值分别为0.90、0.84和0.85;挖掘耗时低于5 s,图像数据匹配度高于90.3%,验证了所提出方法可在图像纹理特征识别操作中发挥应有作用.

大数据背景下中小型企业财务风险管控的探究

国务院在《促进大数据发展行动纲要》中指出建立“用数据说话、用数据决策、用数据管理、用数据创新”的新的管理机制,肯定了数据对企业的重要意义。伴随着云计算等大数据技术的高速发展,企业对大数据的应用越来越广泛,进入了大数据时代。这些企业能够更快、更多、更早地发现财务信息与非财务信息;也能更快地发现并应对财务风险;能够帮助管理者提早掌握公司运营状况,应对财务危机,及时采取应对措施,降低损失。

Small Cell成为移动网络市场新宠儿的重要启示

在全球LTE和智能终端发展,未来移动数据业务流量数百倍增长背景下,Small Cell从数据卸载将走上提升网络容量的主要地位,预计其市场规模将明显超过宏蜂窝基站;中国虽然LTE频率资源相对多,但仍需结合BBU-RRU基站,适度发展Small Cell。行业应抓住市场机遇,争取足够的话语权。

一种小体积MEMS传感器数据记录仪

对飞行器发射航行阶段的数据测试是目前研究的重要方向。数据记录仪作为一种可装载的数据采集装置,具有重要的研究价值。针对小型飞行器的数据采集工作,提出了一种具有小体积、低功耗、高性能以及高抗过载能力的微电子机械系统(MEMS)传感器数据记录仪。它能够对三轴角速度、加速度以及磁场数据进行同步测量。数据计算和实验测试结果表明,记录仪总体积为22.4 cm^(3),工作状态下的功耗仅为0.68 W。通过抗过载工艺使系统抗过载能力达到了18000g,实现了对于小体积、低功耗和高抗过载能力的特性要求。通过Labview软件对磁场数据进行测量及误差分析,得到线性度误差最大值仅为-1.14%,满足HMC1053三轴磁传感器线性度误差优于±1.8%的指标要求,能够实现对于小型飞行器发射航行过程中的数据采集,具有很高的可行性。