statistics

摘要： What is the role and place of statistics in modern artificial intelligence and machine learning?This paper surveys some currently fashionable topics in Artificial Intelligence(AI)and related fields,namely Machine Learning(ML).Moreover,it tries to outline how statisticians can contribute to AI.The paper reflects personal opinions and perspectives I gained working as a Chief Data Scientist in an international consulting firm that focuses on data analytics.

摘要： Some games may have a Nash equilibrium if the parameters (e.g. probabilities for success) take certain values but no equilibrium for other values. So there is a transition from Nash equilibrium to no Nash equilibrium in parameter space. However, in real games in business and economics, the input parameters are not given. They are typically observed in several similar occasions of the past. Therefore they have a distribution and the average is used. Even if the averages are in an area of Nash equilibrium, some values may be outside making the entire result meaningless. As the averages are sometimes just guessed, the distribution cannot be known. The main focus of this article is to show this effect in an example, and to explain the surprising result by topological explanations. We give an example of two players having three strategies each (e.g. player and keeper in penalty shooting) where we demonstrate the effect explicitly. As the transition of Nash equilibrium to no equilibrium is sharp, there may be a special form of chaos which we suggest to call topological chaos.

摘要： Oceanic noise is the background interference in sonar performance prediction and evaluation at high sea states.Statistics of underwater ambient noise during Typhoons Soulik and Nida were analyzed on the basis of experimental measurements conducted in a deep area of the Philippine Sea and the South China Sea.Generated linear regression,frequency correlation matrix(FCM),Burr distribution and Gumbel distribution were described for the analysis of correlation with environmental parameters including wind speed(WS),significant wave height(SWH),and the inter-frequency relationship and probability density function of noise levels(NLs).When the typhoons were quite close to the receivers,the increment of NLs exceeded 10 dB.Whilst ambient noise was completely dominated by wind agitation,NLs were proportional to the cubic and quintic functions of WS and SWH,respectively.The fitted results between NLs and oceanic parameters were different for“before typhoon”and“after typhoon”.The fitted slopes of linear regression showed a linear relationship with the logarithm of frequency.The average observed typhoon-generated NLs were 5 dB lower than the Wenz curve at the same wind force due to the insufficiently developed sea state or the delay between NLs and WS.The cross-correlation coefficient of FCM,which can be utilized in the identification of noise sources in different bands,exceeded 0.8 at frequencies higher than 250 Hz.Furthermore,standard deviation increased with frequency.The kurtosis was equal to 3 at>400 Hz approximately.The characteristics of NLs showed good agreement with the results of FCM.

摘要： An experimental investigation on rice husk ash(RHA)and Conplast SP 430(CP-admixture)was carried out to evaluate their effects on the paste characteristics(soundness,consistency,initial and final setting times).The cement content used was 300g and the brand was‘Ashaka’Portland cement conforming to BS EN 121973.Various combinations of the mixtures OPC-RHA-CP-admixture were used to establish performance characteristics of the pastes.Statistical characteristics,and linear regression models(no-transformation,λ=0.5,and Box-Cox transformation)were developed on the experimental data for decisions on their performances。

摘要： This paper investigates the social networks usage by students in Abidjan city, Côte d’Ivoire. We focus on a descriptive or quantitative analysis to understand the motivations and how students make use of internet and social networks. More than six hundred forms were distributed to persons we have deemed as students. In return, we received more than 93% of the forms that have been processed. The study highlights the materials and the digital platforms that students used the most. The majority of the respondents reported to have access to the social networks in their mobile phones, with WhatsApp leading this application ranking, followed by Instagram, Facebook, YouTube, and Tik Tok. The survey shows that two third of our respondents are aged from 19 to 25 years old and almost half of the respondents spend daily 2 to 5 hours on digital platforms. The investigation also reveals that the main online activities are the e-commerce, chatting, information, and entertainment. The paper addresses also the online harassment of the students and it shows that more than one tenth of them have been victims of cyber-bullying. This study might be useful for governments, institutions, academia, individuals and professionals in order to communicate efficiently with a given population for a better use of social networks and to prevent students from harassment.

摘要： The abundance patterns of r-process-enhanced stars contain key information required to constrain the astrophysical site(s)of r-process nucleosynthesis,and to deepen our understanding of the chemical evolution of our Galaxy.To expand the sample of known r-process-enhanced stars,we have developed a method to search for candidates in the LAMOST medium-resolution(R7500)spectroscopic survey by matching the observed spectra to synthetic templates around the EuⅡline at 6645.1 A.We obtain a sample of 13 metal-poor(-2.35<[Fe/H]<-0.91)candidates from 12209 unique stars with 32774 mediumresolution spectra.These candidates will be further studied by high-resolution follow-up observations in the near future.We describe some extensions of this effort to include larger samples of stars,in particular at lower metallicity,using the strength of the BaⅡline at 6496.9 A.

摘要： Braiding Majorana zero modes(MZMs)is the key procedure toward topological quantum computation.However,the complexity of the braiding manipulation hinders its experimental realization.Here we propose an experimental setup consisting of MZMs and a quantum dot state which can substantially simplify the braiding protocol of MZMs.Such braiding scheme,corresponding to a specific closed loop in the parameter space,is quite universal and can be realized in various platforms.Moreover,the braiding results can be measured and manifested through electric current,providing a simple and novel way to detect the non-Abelian statistics of MZMs.

摘要： An evaluation of the effects of additives and firing temperatures on clay bricks characteristics was studied.The two(2)additives used were sawdust ash(SDA)and iron ore tailing wastes(IOTW),and the five(5)firing temperatures of 400o C to 1200o C at intervals of 200o C were applied.The fired bricks were tested for linear shrinkage,water absorption,density,and compressive strength.The results of the investigations showed that firing temperature improved the clay brick characteristics across all replacement levels.However,the SDA additions increased the linear shrinkage and the water absorption but decreased the density and compressive strength.On the other hand,the addition of IOTW to the clay-SDA mixture,reduced both the linear shrinkage and water absorption of the clay bricks,and increased the density and compressive strength.The statistical values and the regression models derived on the experimental data using Minitab 18 Software were significant.

摘要： BACKGROUND Of 25%of randomised controlled trials(RCTs)on interventions for inflammatory bowel disease(IBD)have no power calculation.AIM To systematically review RCTs reporting interventions for the management of IBD and to produce data for minimum sample sizes that would achieve appropriate power using the actual clinical data.METHODS We included RCTs retrieved from Cochrane IBD specialised Trial register and CENTRAL investigating any form of therapy for either induction or maintenance of remission against control,placebo,or no intervention of IBD in patients of any age.The relevant data was extracted,and the studies were grouped according to the intervention used.We recalculated sample size and the achieved difference,as well as minimum sample sizes needed in the future.RESULTS A total of 105 trials were included.There was a large discrepancy between the estimated figure for the minimal clinically important difference used for the calculations(15%group differences observed vs 30%used for calculation)explaining substantial actual sample size deficits.The minimum sample sizes indicated for future trials based on the 25 years of trial data were calculated and grouped by the intervention.CONCLUSION A third of intervention studies in IBD within the last 25 years are underpowered,with large variations in the calculation of sample sizes.The authors present a sample size estimate resource constructed on the published evidence base for future researchers and key stakeholders within the IBD trial field.

摘要： A“simplified”figure was proposed in 2011 to summarize the results of controlled trials that evaluate different treatments aimed at the same disease condition.The original criteria for classifying individual binary comparisons included superiority,inferiority and no significance difference;hence,they did not differentiate between no proof of difference vs proof of no difference.We updated the criteria employed in the original“simplified”figure in order to include this differentiation.A revised version of the simplified figure is proposed and described herein.An example of application is also presented.The example is focused on first-line treatments for paroxysmal atrial fibrillation.Three treatments(medical therapy,cryoballoon ablation,radiofrequency ablation)are compared with one another through direct and indirect comparisons.

摘要： 本发明公开了一种基于Statistic‑TDMA与LoRa的数据传输方法，其特点是综合使用了Statistic‑TDMA(统计时分复用)、FDMA(频分复用)和TDMA(时分复用)技术。每个集中器与其对应的终端之间采用TDMA进行数据传输，网关与集中器之间采用FDMA和跳频技术进行数据传输，最后LoRa网关采用Statistic‑TDMA技术将各个集中器收集到的节点数据进行统计处理。本发明能够有效提高LoRa网络容量、信道利用率、传输距离性能，可以利用普通的单通道射频芯片实现多通道数据传输，系统成本低，开发难度低，实用性强。

摘要： 本发明公开了涉及风力发电领域的一种基于Gap Statistic的风电场机群划分方法。该方法根据风电场内所有风电机组的在一段时间内有功功率数据，作为风电机群的分群指标，通过K‑means聚类算法实现对风电场机群进行不同聚类数目的划分,应用Gap Statistic算法首先确定聚类问题所判定类的最优数目，确定最优聚类结果。本方法考虑了常规风电场等值所忽略的最优聚类数，提高了聚类效果。

摘要： 本发明公开了一种基于Statistic‑TDMA与LoRa的数据传输方法，其特点是综合使用了Statistic‑TDMA(统计时分复用)、FDMA(频分复用)和TDMA(时分复用)技术。每个集中器与其对应的终端之间采用TDMA进行数据传输，网关与集中器之间采用FDMA和跳频技术进行数据传输，最后LoRa网关采用Statistic‑TDMA技术将各个集中器收集到的节点数据进行统计处理。本发明能够有效提高LoRa网络容量、信道利用率、传输距离性能，可以利用普通的单通道射频芯片实现多通道数据传输，系统成本低，开发难度低，实用性强。

摘要： 一种SDN数据流flow‑statistics低开销采集方法，其步骤为：S1：定义SDN数据流flow‑statistics采集的相关参数；S2：依次初始化各参数；S3：控制器下发数据流条目；当接收到PacketIn数据包时，下发对应的数据流条目至相关的交换机；同时将该数据流加入集合；S4：控制器持续监听flow‑statistics报文；S5：判断监控周期是否结束；如果结束，跳转步骤S6；如果没有结束，跳转步骤S4；S6：调整相应数据流的门限值；S7：控制器分析接收到的flow‑statistics相关报文；S8：进入数据流下一周期的监控。本发明具有准确度高、实时性好、开销较小等优点。

摘要： 一种SDN数据流flow‑statistics低开销采集方法，其步骤为：S1：定义SDN数据流flow‑statistics采集的相关参数；S2：依次初始化各参数；S3：控制器下发数据流条目；当接收到PacketIn数据包时，下发对应的数据流条目至相关的交换机；同时将该数据流加入集合；S4：控制器持续监听flow‑statistics报文；S5：判断监控周期是否结束；如果结束，跳转步骤S6；如果没有结束，跳转步骤S4；S6：调整相应数据流的门限值；S7：控制器分析接收到的flow‑statistics相关报文；S8：进入数据流下一周期的监控。本发明具有准确度高、实时性好、开销较小等优点。