ML

摘要： 基于iOS[1]移动操作系统中的增强现实(Augmented Reality)[2]和机器学习(Machine Learning)[3]技术,与中华传统文化古诗将结合,设计了一款集听说读画考为一体的应用程序—画中诗App。该App充满趣味性和创作性,既能陶冶用户的文学素养,又可以培养想象力和创造力。

摘要： The 21st Century era and new modern technologies surrounding us day-in and day-out have opened a new door to“Pandora Box”,that we do know it as AI(artificial intelligence)and its two essential integrated components namely ML(machine learning)and DL(deep learning).However,the strive and progress in AI,ML,and DL pretty much has taken over any industry that we can think of,when it comes to dealing with cloud of structured data in form of BD(big data).A NPP(nuclear power plant)has multiple complicated dynamic system-of-components that have nonlinear behaviors.For controlling the plant operation under both normal and abnormal conditions,the different systems in NPPs(e.g.,the reactor core components,primary and secondary coolant systems)are usually monitored continuously,which leads to very huge amounts of data.Of course Nuclear Power Industry in form of GEN-IV(Generation IV)has not been left behind in this 21st century era by moving out of GEN-III(Generation III)to more modulars form of GEN-IV,known as SMRs(small modular reactors),with a lot of electronic gadgets and electronics that read data and information from it to support safety of these reactor,while in operation with a built in PRA(probabilistic risk assessment),which requires augmentation of AI in them to enhance performance of human operators that are engaged with day-to-day smooth operation of these reactors to make them safe and safer as well as resilience against any natural or man-made disasters by obtaining information through ML from DL that is collecting massive stream of data coming via omni-direction.Integration of AI with HI(human intelligence)is not separable,when it comes to operation of these smart SMRs with state of the art and smart control rooms with human in them as actors.This TM(technical memorandum)is describing the necessity of AI playing with nuclear reactor power plant of GEN-IV being in operation within near term sooner than later,when specially we are facing today’s cyber-attacks with their smart malware agents at work.

摘要： Hyperuricemia is an alarming issue that contributes to cardiovascular disease.Uric acid(UA)level was proven to be related to pulse wave velocity,a marker of arterial stiffness.A hyperuricemia prediction method utilizing photoplethysmogram(PPG)and arteriograph by using machine learning(ML)is proposed.From the literature search,there is no available papers found that relates PPG with UA level even though PPG is highly associated with vessel condition.The five phases in this research are data collection,signal preprocessing including denoising and signal quality indexes,features extraction for PPG and SDPPG waveform,statistical analysis for feature selection and classification of UA levels using ML.Adding PPG to the current arteriograph able to reduce cost and increase the prediction performance.PPG and arteriograph data were measured from 113 subjects,and 226 sets of data were collected from the left and right hands of the subjects.The performance of four types of ML,namely,artificial neural network(ANN),linear discriminant analysis(LDA),k-nearest neighbor(kNN),and support vector machine(SVM)in predicting hyperuricemia was compared.From the total of 98 features extracted,16 features of which showed statistical significance for hyper and normouricemia.ANN gives the best performance compared to the other three ML techniques with 91.67%,95.45%,and 94.12%for sensitivity,specificity,and accuracy,respectively.Features from PPG and arteriograph able to be used to predict hyperuricemia accurately and noninvasively.This study is the first to find the relationship of PPG with hyperuricemia.It shows a significant relation between PPG signals and arteriograph data toward the UA level.The proposed method of UA prediction shows its potential for noninvasive preliminary assessment.

摘要： The scope of the 5G network is not only limited to the enhancements in the form of the quality of service(QoS),but it also includes a wide range of services with various requirements.Besides this,many approaches and platforms are under the umbrella of 5G to achieve the goals of endto-end service provisioning.However,the management of multiple services over heterogeneous platforms is a complex task.Each platform and service have various requirements to be handled by domain experts.Still,if the next-generation network management is dependent on manual updates,it will become impossible to provide seamless service provisioning in runtime.Since the traffic for a particular type of service varies significantly over time,automatic provisioning of resources and orchestration in runtime need to be integrated.Besides,with the increase in the number of devices,amount,and variety of traffic,the management of resources with optimization becomes a challenging task.To this end,this manuscript provides a solution that automates the management and service provisioning through multiple platforms while assuring various aspects,including automation,resource management and service assurance.The solution consists of an intent-based system that automaticallymanages different orchestrators,and eliminates manual control by abstracting the complex configuration requirements into simple and generic contracts.The proposed systemconsiders handling the scalability of resources in runtime by usingMachine Learning(ML)to automate and optimize service resource utilization.

摘要： Brain tumors are considered as most fatal cancers.To reduce the risk of death,early identification of the disease is required.One of the best available methods to evaluate brain tumors is Magnetic resonance Images(MRI).Brain tumor detection and segmentation are tough as brain tumors may vary in size,shape,and location.That makes manual detection of brain tumors by exploring MRI a tedious job for radiologists and doctors’.So an automated brain tumor detection and segmentation is required.This work suggests a Region-based Convolution Neural Network(RCNN)approach for automated brain tumor identification and segmentation using MR images,which helps solve the difficulties of brain tumor identification efficiently and accurately.Our methodology is based on the accurate and efficient selection of tumorous areas.That reduces computational complexity and time.We have validated the designed experimental setup on a standard dataset,BraTS 2020.We used binary evaluation matrices based on Dice Similarity Coefficient(DSC)and Mean Average Precision(mAP).The segmentation results are compared with state-of-the-art methodologies to demonstrate the effectiveness of the proposed method.The suggested approach attained an averageDSC of 0.92 andmAP 0.92 for 10 patients,while on the whole dataset,the scores are DSC 0.89 and mAP 0.90.The following results clearly show the performance efficiency of the proposed methodology.

摘要： This paper proposes the multiple-input multiple-output(MIMO)detection scheme by using the deep neural network(DNN)based ensemble machine learning for higher error performance in wireless communication systems.For the MIMO detection based on the ensemble machine learning,all learning models for the DNN are generated in offline and the detection is performed in online by using already learned models.In the offline learning,the received signals and channel coefficients are set to input data,and the labels which correspond to transmit symbols are set to output data.In the online learning,the perfectly learned models are used for signal detection where the models have fixed bias and weights.For performance improvement,the proposed scheme uses the majority vote and the maximum probability as the methods of the model combinations for obtaining diversity gains at the MIMO receiver.The simulation results show that the proposed scheme has improved symbol error rate(SER)performance without additional receive antennas.

摘要： Bat algorithm(BA)is an eminent meta-heuristic algorithm that has been widely used to solve diverse kinds of optimization problems.BA leverages the echolocation feature of bats produced by imitating the bats’searching behavior.BA faces premature convergence due to its local search capability.Instead of using the standard uniform walk,the Torus walk is viewed as a promising alternative to improve the local search capability.In this work,we proposed an improved variation of BA by applying torus walk to improve diversity and convergence.The proposed.Modern Computerized Bat Algorithm(MCBA)approach has been examined for fifteen well-known benchmark test problems.The finding of our technique shows promising performance as compared to the standard PSO and standard BA.The proposed MCBA,BPA,Standard PSO,and Standard BA have been examined for well-known benchmark test problems and training of the artificial neural network(ANN).We have performed experiments using eight benchmark datasets applied from the worldwide famous machine-learning(ML)repository of UCI.Simulation results have shown that the training of an ANN with MCBA-NN algorithm tops the list considering exactness,with more superiority compared to the traditional methodologies.The MCBA-NN algorithm may be used effectively for data classification and statistical problems in the future.

摘要： 快速、准确地从卫星影像中提取水体信息一直是遥感应用的热点问题,在水资源管理、水环境监测和灾害应急管理等领域极具应用价值。虽然目前已有多种针对Landsat系列影像的水体提取方法,但由于地理位置、地形和水体形态等环境背景因素的影响,导致同种方法在不同的环境背景中呈现出不同的提取效果。本文针对人为影响严重、影像明暗对比强烈的城区(北京怀柔县城周边)以及地形起伏明显、水体细小的非城区(北京密云水库周边)2种典型背景环境,选择波段设置略有差异的Landsat 5(2009年)和Landsat 8(2019年)卫星影像,对比了常用的指数法(NDWI和MNDWI)和分类法(最大似然法和支持向量机)在水体信息提取方面的优势和不足。结果表明:在城区背景中,SVM的准确性最高(总体精度>97%);在非城区背景中,MNDWI与SVM的精度相当(总体精度>95%),前者更适用于水体的快速提取,而后者提取的山间细碎河流更完整,且在Landsat 8中应用的效果更好。该研究为不同环境背景下水体提取方法的选择提供了参考。

摘要： 目前,基于机器学习的情感分类研究虽然在高资源语言的研究中取得了不错的发展,但是对于一些小语种(例如孟加拉语)这样的语言仍然处于起步阶段.研究小语种的情感分类关键在于语言处理模型和语料库的选取.本项研究提出了一种基于Transformer的情感分类技术,可以将小语种文本分为6种基本情感:愤怒、恐惧、厌恶、悲伤、快乐和惊讶.为了完成本项分类任务,准备了6000个小语种文本组成的语料库,然后利用各种机器学习模型(例如SVM、MNB、LR、RF)、深度神经网络模型(例如CNN,BiLSTM,CNN+BiLSTM)和基于Transformer模型(例如Bangla-BERT,m-BERT,XLM-R)的方法进行训练,结果证明基于Transformer的方法要优于其他模型.

摘要： In the past decade or so,AI(artificial intelligence)technology has been growing with such a mesmerizing speed that today its presence in almost any industry that deals with any huge sheer volume of data is taking advantage of AI by integrating it into their day-to-day operation.Meanwhile,seven billion people worldwide shape the world’s energy system and directly impact the fundamental drivers of energy,both renewable and non-renewable sources,to meet the demand for electricity from them.These energy sources can be reached from nature such as solar,wind,etc.,and human-made such as NPPs(nuclear power plants)in the form of either fission as an old technology since the Manhattan project and in the near future as fusion in the form of magnetic or inertial confinements.Meanwhile,AI controlling nuclear reactors are about to happen.The basic idea is to apply AI with its two subset components as ML(machine learning),and DL(deep learning)techniques to go through the mountains of data that come from a reactor,spot patterns in it,and calling them to the unit’s human attention operators is not invadable either.Designers of such nuclear reactors will combine simulation and real-world data,comparing scenarios from each to develop“confidence[in]what they can predict and what is the range of uncertainty of their prediction”.Adding that,in the end,the operator will make the final decisions in order to keep these power plants safe while they are in operation and how to secure them against cyber-attack natural or human-made disasters.In this short communication article,we would like to see how we can prove some of these concepts;then a NPP manufacturer can pick it up and use it in their designs of a new generation of these reactors.

摘要： 介绍了改制的用于常量分析的小型滴定管，提出了与之适应的小型滴定分析法。采用该管实验，仅消耗5mL的滴定济。滴定操作技术规范、简便。与常规滴定比较，小型滴定分析可节约试剂经费的80℅，准确度与精密度无显著性差异。

摘要： 介绍了改制的用于常量分析的小型滴定管，提出了与之适应的小型滴定分析法。采用该管实验，仅消耗5mL的滴定济。滴定操作技术规范、简便。与常规滴定比较，小型滴定分析可节约试剂经费的80℅，准确度与精密度无显著性差异。

摘要： 介绍了改制的用于常量分析的小型滴定管，提出了与之适应的小型滴定分析法。采用该管实验，仅消耗5mL的滴定济。滴定操作技术规范、简便。与常规滴定比较，小型滴定分析可节约试剂经费的80℅，准确度与精密度无显著性差异。

摘要： 介绍了改制的用于常量分析的小型滴定管，提出了与之适应的小型滴定分析法。采用该管实验，仅消耗5mL的滴定济。滴定操作技术规范、简便。与常规滴定比较，小型滴定分析可节约试剂经费的80℅，准确度与精密度无显著性差异。

摘要： 本发明涉及气垫船运动控制领域，具体涉及的是一种基于纵向速度规划的气垫船高速回转控制方法。本发明采用基于侧滑角约束的航速规划方法解决了气垫船采用传统非线性反馈控制在高速回转时的失速问题，能够保证气垫船在回转的同时实现精确的航速跟踪，提高了气垫船的机动性和作业能力，本发明在保证气垫船在高速回转过程中准确跟踪期望艏向的同时避免回转率过大导致的甩尾现象，提高了气垫船在高速回转时的可靠性和安全性。

摘要： 本发明适用于材料技术领域，提供了一种低光泽度聚氯乙烯材料及其制备方法、应用，其中，所述低光泽度聚氯乙烯材料包括以下重量份数的原料：聚氯乙烯树脂80～100份、稳定剂1～10份、增塑剂4～15份、加工助剂0.8～5份、改质剂4～15份、消光剂0～5.5份以及润滑剂0.5～5份。本发明通过稳定剂、增塑剂、加工助剂、改质剂、消光剂以及润滑剂各原料的合理配比，配合特定种类的聚氯乙烯树脂，所得到的低光泽度聚氯乙烯材料，不仅易于加工成型、且具有较为优异力学性能，且低光泽度，耐温以及成本低；另外，通过消光剂的加入可进一步降低材料光泽度的同时，进一步提高本发明聚氯乙烯材料机械力学性能，具有很好的经济效益。

摘要： 本发明涉及光纤耦合技术领域，尤其涉及一种高效率的叠阵型半导体激光器，包括激光源、光束整形组件、会聚透镜、鲍威尔棱镜组件和光纤；所述激光源发出的光束经过光束整形组件进行整形；整形后的光束经会聚透镜会聚，会聚后光束经过鲍威尔棱镜组件进行光束整形可以耦合进光纤的光束。本发明系统结构简单,便于操作,减少了操作步骤,光纤耦合效率达到84.3％。

摘要： 本申请公开了一种变频空调控制方法、装置、电子设备和介质。其中方法包括：获取空调的设置温度值，获取当前室内温度值；根据所述设置温度值、所述当前室内温度值和预设偏差阈值，确定所述变频空调的系统负荷率；获取当前室外温度值，获取所述变频空调的目标器件的信息；依据所述当前室外温度值、所述目标器件的信息以及所述系统负荷率，确认总传热温差；以达到所述总传热温差为目标，对所述变频空调的制冷系统进行控制，可以控制空调系统在不同负荷率下、不同室外温度值下运行在比较高的能效，实现空调系统节能运行。

摘要： 本发明涉及兽医生物技术领域，尤其涉及一种猪轮状病毒重组蛋白以及表达该蛋白的重组腺病毒和应用。所述所述重组蛋白由猪轮状病毒5型VP7蛋白和猪轮状病毒9型VP8蛋白连接组成，具体包括如SEQ ID NO:1所示的氨基酸序列。本发明将猪轮状病毒5型VP7蛋白和猪轮状病毒9型VP8蛋白的编码基因的基因序列构建至腺病毒表达载体中，并进行密码子优化，制备得到针对猪轮状病毒的重组腺病毒，该重组腺病毒表达的目的蛋白的结构和功能与天然状态完全一致，具有较高的安全性和免疫原性。

摘要： 本发明公开了一种改性TPEE电缆料及其制备方法，所述改性TPEE电缆料，按重量份数计，其组分包含改性TPEE100份，阻燃剂50‑100份，阻燃协效剂2‑10份，润滑剂1‑5份，抗氧剂1‑5份，助剂5‑10份。本发明提供的改性TPEE电缆料通过对TPEE接枝功能化石墨烯，以及对阻燃剂氢氧化镁进行改性，使其兼具优异的阻燃性能，力学性能，热老化性能以及加工性能，并且可回收利用，环境友好。

摘要： 本发明公开了一种路线规划方法，包括：获取N个订单的物流信息，所述物流信息包括订单地址，所述订单地址包括第一地址以及第二地址，其中，所述第一地址为目的地在直送范围内的地址，所述第二地址为目的地在直送范围外的地址，N为正整数；筛选出所述订单地址为所述第一地址的M个订单，确定配送M个订单的第一初始路线，对所述第一初始路线进行优化，得到第一优化路线，M为小于等于N的正整数；筛选出所述订单地址为所述第二地址的N‑M个订单，确定配送所述N‑M个订单的第二初始路线，对所述第二初始路线进行优化，得到第二优化路线。

摘要： 本发明公开了一种芳砜纶/四氧化三铁磁性长丝的制备方法，包括如下步骤：四氧化三铁磁性纳米颗粒制备、芳砜纶/四氧化三铁共混纺丝液制备、湿法纺丝，得到具有不同截面形状的磁性长丝。本发明可以实现芳砜纶的连续化湿法纺丝，制备过程温和可控；本发明将四氧化三铁磁性颗粒结合到芳砜纶纤维中，可以实现芳砜纶纤维的功能化，使得芳砜纶纤维具备磁性；本发明采用蛋白模板调控法制备四氧化三铁磁性颗粒，实现四氧化三铁磁性颗粒形貌及尺寸调控，同时使得纳米颗粒在纺丝液中分散均匀性；本发明制备的芳砜纶/四氧化三铁磁性长丝可用于保健、过滤、智能纺织品等领域。

摘要： 本发明属于污水处理技术领域，尤其是涉及一种污水水质预处理快速检测装置，包括检测水箱，检测水箱内壁上固定连接有第一竖板和第二竖板，第一竖板和第二竖板将检测水箱分隔成处理腔室、检测腔室和储存腔室，处理腔室内底壁上固定连接有向下延伸的梯形凸起，且梯形凸起内形成沉淀腔室，梯形凸起的下端固定连接有两根竖直的排污管，检测水箱的侧壁上固定连接有与处理腔室连通的污水进水管。优点在于：本发明可以对不同分层的污水进行水质检测，且多层之间的检测过程均为独立过程，不会出现相互之间的影响，能够对污水进行实时的检测，有助于后续的数据统计，另外采用分级式的检测方式，能够有效的对污水进行全面的检测，提高检测的质量。

摘要： 本发明公开了一种软硬件联合验证系统及方法。该系统包括：驱动软件、基于systemc模拟的存储器和异构集群；驱动软件嵌入在systemc框架中；驱动软件根据预设验证需求向异构集群发送驱动指令；存储器加载并保存待验证数据；异构集群根据驱动指令从存储器中提取待验证数据，计算得到输出数据，发送至驱动软件；驱动软件根据输出数据进行软硬件的联合验证。通过systemc模拟异构集群，驱动软件嵌入systemc框架，为驱动软件提供与硬件功能相等的模型，实现驱动软件对硬件的控制流程，协助软件前期的开发与调试，为硬件提供标准数据。解决了现有技术中软件与硬件在大多数的系统开发中分开进行，导致开发周期长的技术问题。