基于Blending-Clustering集成学习的大坝变形预测模型

【目的】变形是反映大坝结构性态最直观的效应量,构建科学合理的变形预测模型是保障大坝安全健康运行的重要手段。针对传统大坝变形预测模型预测精度低、误报率高等问题导致的错误报警现象,【方法】选取不同预测模型和聚类算法集成,构建了一种Blending-Clustering集成学习的大坝变形预测模型,该模型以Blending对单一预测模型集成提升预测精度为核心,并通过Clustering聚类优选预测值改善模型稳定性。以新疆某面板堆石坝变形监测数据为实例分析,通过多模型预测性能比较,对所提出模型的预测精度和稳定性进行全面评估。【结果】结果显示:Blending-Clustering模型将预测模型和聚类算法集成,均方根误差(RMSE)和归一化平均百分比误差(nMAPE)明显降低,模型的预测精度得到显著提高;回归相关系数(R~2)得到提升,模型具备更强的拟合能力;在面板堆石坝上22个测点变形数据集上的预测评价指标波动范围更小,模型的泛化性和稳定性得到有效增强。【结论】结果表明:Blending-Clustering集成预测模型对于预测精度、泛化性和稳定性均有明显提升,在实际工程具有一定的应用价值。

基于Prophet算法和Blending集成学习的实时负荷中期预测

目前的中期负荷预测一般未考虑负荷实时状态,而负荷数据的非线性、季节性、随机性、时序性特征将影响实时负荷的中期预测。构建一个实时负荷中期预测的框架,采用Prophet算法提取负荷数据的季节性部分,采用Blending集成学习对负荷数据的非季节部分进行滚动预测,将季节性部分和非季节性部分合成中期负荷实时数据。爱尔兰电力系统的算例结果验证了模型的有效性和稳定性。

Umami taste components in chicken-spices blends and potential effect of aroma on umami taste intensity

In this study,umami taste intensity(UTI)and umami taste components in chicken breast(CB)and chickenspices blends were characterized using sensory and instrumental analysis.Our main objective was to assess the aroma-umami taste interactions in different food matrices and reconcile the aroma-taste perception to assist future product development.The impact of key aroma,including vegetable-note"2-pentylfuran",meaty"methional",green"hexanal",and spicy-note-estragole and caryophyllene"on UTI was evaluated in monosodium glutamate and chicken extract.We found that spices significantly decreased UTI and umami taste components in CB.Interestingly,the perceptually similar odorants and tastants exhibited the potential to enhance UTI in food matrices.Methional was able to increase the UTI,whereas spicy and green-note components could reduce the UTI significantly.This information would be valuable to food engineers and formulators in aroma selection to control the UTI perceived by consumers,thus,improving the quality and acceptability of the chicken products.

A review:Health benefits and physicochemical characteristics of blended vegetable oils

Oil blending is the method of choice used worldwide to improve oxidative stability and nutritional value.There is no such edible oil/fat that meets all the recommendations from the health point of view.The fatty acid composition of vegetable oils decides the fate of the oil.Pure single oil is unable to provide a balanced amount of fatty acids(FAs)required/recommended on a daily intake basis.Blending oils/fats is an appropriate procedure of physically mixing multiple oils in suitable proportions which may provide functional lipids with improved antioxidant potential and desirable physical and chemical properties.This review piled up the accessible data on the blending of diverse oils/fats in the combination of binary,ternary,quaternary,or other types of oils into a single blended oil.Blending can be found very convincing towards appropriate FA profile,enhancement in physicochemical characteristics,and augmented stability for the period of storage or when used as cooking/frying processes which could ultimately serve as an effectual dietary intervention towards the health protectiveness.

Research on Blended Teaching Mode:A Case Study of Floristry

In order to better carry out research on education and teaching,the author consulted relevant literature on blended teaching mode from 2011-2021 through CNKI,Web of Science and other websites,summarized and analyzed the research status of blended teaching mode,in order to lay a good foundation for studying blended teaching mode in course teaching.

An Analysis on the Blended Teaching Mode of College English

This paper explores blended teaching in college English from five aspects:the connotation,theoretical basis,design principles,advantages,and challenges of blended teaching and blended teaching models.The purpose is to attract more foreign language practitioners and learners to pay attention to this model and put it into practice.

基于Blending集成学习的多源信息液压系统多类故障诊断研究

针对传统故障诊断方法准确性不高、耗时长问题,研究通过多个EfficientNet模型对传感器数据进行预训练,并使用XGBoost作为元学习器,提出了一种基于Blending集成学习的多源信息液压系统多类故障诊断方法。实验结果表明,各个子分类器在训练次数达到300次后趋于收敛,准确率均达到95%左右。该方法具有较高的准确性和鲁棒性,为液压系统故障诊断提供了一种有效的解决方案。

Effects of Perceived Teacher Support on Student Behavioral Engagement in the Blended Learning Environment:Learning Experience as a Mediator

Blended learning(BL)has been widely adopted to improve students’academic achievements in higher education.However,its success relies mainly on student engagement,which plays an essential role in active learning and provides a rich understanding of students’experiences.The study utilized three self-designed scales-the Teacher Support Scale,Student Engagement Scale,and Student Learning Experience Scale-to gauge and examine the impact and relationship between perceived teacher support,student behavioral engagement,and the intermediary role of learning experiences.A cohort of 899 college students undertaking the obligatory College English course through BL modes across five Chinese universities actively participated by completing a comprehensive questionnaire.The results showed significant correlations between perceived teacher support,learning experience,and behavioral engagement.Perceived teacher support significantly predicted students’behavioral engagement,with socio-affective support exerting the most substantial predictive effects.All predictive effects were partially mediated by learning experience(learning mode,online resources,overall LMS-based learning,interaction with their instructor and peers,and learning outcome).The influence of perceived teacher support on behavioral engagement differed between students who reported the most positive(vs.negative)learning experiences.Suggestions for further research are offered for consideration.

Application Effect of Blended Education Strategy Based on the Learning Pass Platform in Phase III Cardiac Rehabilitation of Patients with Coronary Artery Disease

Objective:To explore the application effect of the blended education strategy based on the Learning Pass platform in the phase III cardiac rehabilitation of patients with coronary artery disease.Methods:90 patients diagnosed with coronary artery disease in the Department of Cardiology of our hospital from January 2019 to January 2021 were selected and divided into the control group and the experimental group according to the method of randomized numerical table,with 45 cases in each group.Both the experimental group and the control group received pre-discharge cardiac rehabilitation education by conventional means.The control group received education and supervision information via WeChat after discharge,while the experimental group joined the Learning Pass platform to receive online and offline hybrid education and supervision,with online as the mainstay and offline as a supplement.The disease cognitive level,self-management skills,quality of life,medication adherence,and emotional status of the two groups were compared.Results:The disease cognitive levels in the experimental group were significantly higher than those of the control group(P<0.05);the scores of the experimental group in terms of quality of life,self-management skills,and medication adherence were significantly higher than those of the control group(P<0.05);and the scores of anxiety and depression in the experimental group were significantly lower than those of the control group(P<0.05).Conclusion:The blended education strategy based on the Learning Pass platform has a significant application effect in phase III cardiac rehabilitation of patients with coronary artery disease.It can improve patients’disease cognitive level,self-management skills,and quality of life,and provide a basis for improving patients’prognosis.

Secure e-Prescription Management System:Mitigating Blended Threat in IoBE

New information and communication technologies(ICT)are being applied in various industries to upgrade the value of the major service items.Moreover,data collection,storage,processing,and security applications have led to the creation of an interrelated ICT environment in which one industry can directly influence the other.This is called the“internet of blended environ-ments”(IoBE),as it is an interrelated data environment based on internet-of-things collection activities.In this environment,security incidents may increase as size and interconnectivity of attackable operations grow.Consequently,pre-emptive responses to combined security threats are needed to securely utilize IoBE across industries.For example,the medical industry has more stringent information protection measures than other industries.Consequently,it has become a major target of attackers,as more clinician–patient interactions occur over the internet owing to COVID-19.Therefore,this study aims to acquire security for IoBE while focusing on the medical industry.Among the various types of medical ICT services,this study analyzes dataflow and potential security threats from the e-prescription lifecycle perspective,which is highly utilized,strongly data-centric,and has numerous security issues.Based on our analysis,we propose a secure authentication and data-sharing scheme.

Use of Plant-Based Accelerator to Enhance Rate of Gain of Strength of Kenyan Blended Cement

Concrete is the most widely used construction material in the world. The situation in the country is not an exception as most of the infrastructures in Kenya such as buildings, bridges, concrete drainage among others, are constructed using concrete. Sadly, the failure of buildings and other concrete structures is very common in Kenya. Blended Portland cement type 32.5 N/mm2 is the most widely used concrete binder material and is found in all parts of the country. Despite blended cement CEM 32.5 being the most commonly used cement type in construction industry in Kenya and most developing countries as a result of its low price and availability locally, its strength gain has been proven to be lower compared to when other types of cement are used due to quantity of pozzolanic material added to the blend. This paper outlines findings of an experimental investigation on the use of cypress tree extract as an accelerator to enhance rate of gain of strength on Kenyan blended cements. Six different blended cement brands locally available were used during the study. Cement chemical analysis was done using X-ray diffraction method while for the cypress extract, Atomic Absorption Spectrometer machine was used. Physical and mechanical properties were checked based on the British standards. The generation of the concrete mix design was done using the British DOE method and concrete was tested for the compressive strength at 7, 14, 21, 28, 56 and 90 days. It was observed that 15% dosage of the extract expressed as a mass percentage of the cement content gives the most improved compressive strength of concrete, 10.4% at 7 days and 9.5% at 28 days hence the optimum. It was further noted that when Cypress tree extract is used as an accelerator in the mix, the blended cement concrete achieves the design strength at 27 days saving 10 days of the project duration compared to when no accelerator is used while the ultimate strength is achieved at 67 days. The study therefore recommends the use of the cypress tree bark extract at a dosage of 15%, by mass, of the cement content as an accelerator when the structure is to be loaded at 28 days and waiting up to 39 days before loading the structure if no accelerator is used for blended cement concrete.

Terminal Blend橡胶泡沫沥青制备及性能评价

为弥补传统泡沫沥青高温稳定性和黏附性的不足,解决传统橡胶沥青发泡效果不理想的缺陷,对terminal blend(TB)橡胶泡沫沥青进行了研究,探究了TB橡胶泡沫沥青发泡效果的影响规律,对其微观形貌与特征进行了表征,同时评估了TB橡胶泡沫沥青的高温性能、温度敏感性和黏度.结果表明:采用TB橡胶沥青制备泡沫沥青具备可行性;相比传统泡沫沥青,TB橡胶泡沫沥青在温度敏感性降低的同时,还显著提升了高温性能和黏度;微观结果显示TB橡胶泡沫沥青的发泡过程仅为物理过程,而且受发泡温度和发泡用水量的影响,其中后者对整体发泡效果的影响更加明显;TB橡胶泡沫沥青的最佳发泡温度为160°C、发泡用水量为2.7%.

Separation of a C_(3)H_(6)/C_(2)H_(4) mixture using Pebax^(■) 2533/PEG600 blend membranes

In industry, ethylene(C_(2)H_(4))/propylene(C_(3)H_(6)) separations are usually performed by a cryogenic process,which is energy intensive. Membrane separation technology is an alternative separation process that saves energy and is efficient. In this study, blend membranes were prepared by doping polyethylene glycol(PEG600) into a poly(ether-block-amide)(Pebax^(■) 2533) matrix and were used to separate the C_(2)H_(4)/C_(3)H_(6) mixture. The PEG 600 and Pebax^(■) 2533 polymers have good compatibility because they share hydrogen bonds. The addition of PEG600 is conducive to the hydrophilicity and the free volume of blend membranes, and it is also conducive to the solubility of C_(2)H_(4) and C_(3)H_(6) in the membranes, which improves the ability of the membranes to separate this gas pair. The Pebax^(■) 2533/PEG600 blend membrane with 15%(mass) PEG600 showed the highest separation performance in our investigated membranes, with a C_(3)H_(6)/C_(2)H_(4) selectivity of 8.9 and a C_(3)H_(6) permeability of 196 barrer(1 barrer = 1.33×10^(14)m^(3)(STP)·m·m^(-2)·s^(-1)·kPa^(-1)) at 238 K and 0.2 MPa, which is higher than that of the Pebax^(■) 2533/NaY-6%(mass) membrane(α_(C_(3)H_(6)/C_(2)H_(4)) =6.5, P_(C_(3)H_(6))=211 barrer) reported in our previous work. It is confirmed that incorporating PEG600 into the Pebax^(■) 2533 matrix to fabricate blend membranes is an efficient strategy for separating light olefins.

Volatile profile and multivariant analysis of Sanhuang chicken breast in combination with Chinese 5-spice blend and garam masala

Sanhuang chicken is a popular native breed in China and well-known for delicious flavour.Spices could enhance the chicken meat flavour and work well in preservation.Chinese 5-spice blend(CS)and garam masala(GM)are routinely using spices in China and Pakistan,respectively.The flavour profiles of Sanhuang chicken breast(CB)and its blends with CS and GM were obtained by electronic nose(E-nose),solid-phase microextraction gas chromatography-mass spectrometry(SPME GC-MS)and GC-ion mobility spectrometry(GC-IMS).Principal component analysis(PCA)efficiently discriminated the aroma profiles of three chicken formulations.The GC-chromatographs revealed the significant aroma alterations of chicken breast meat after marination with spices.Aldehydes were the major contributors of chicken aroma,while most of the aromatic hydrocarbons were generated by spices.Almost all chicken key-compounds produced by oxidation reaction were either reduced or eliminated by marination,showing the antioxidation capacity of spices leading to meat preservation.GC-IMS is not only a rapid and comprehensive detection method,but also proved to be more sensitive than GC-MS.The substantial role of both traditional spices in enhancing flavour quality of chicken meat,and their exposure as functional ingredients in Chinese and Pakistan cuisines could lead to the cross-cultural meat trade opportunities.

基于Blending集成学习模型的电力市场日前出清电价预测

精准的掌握未来电价信息对把握市场的运行状态、支撑市场参与各方进行有效决策、推动市场主体合理优化资源配置具有重要意义。因此基于Blending集成学习机制构建了一种面向于日前电价预测的综合模型。该模型充分考虑电价的高波动性特点,采用Ashin变换,减小了输入数据波动性对预测模型的影响;选取SVM、LightGBM、EWNN、SARIMAX 4种较为成熟的单一电价预测模型作为初级学习器,进而保证了基于Blending集成学习模型的预测精度。选用美国PJM电力市场实际运行数据对上述构建的电价预测模型进行验证,通过对预测结果的对比分析,表明构建的基于Blending集成学习机制的电价综合预测模型集成了多种传统预测模型的优点,具有较好的准确性与稳定性。

基于FPFF-Blending模型融合的个体工商户信用评价研究

个体工商户信用评价研究往往通过单一机器学习模型建立,其预测精确率较低,抗干扰能力较弱。基于特征金字塔的FPFF特征融合算法,应用于Blending模型融合框架,建立个体工商户信用评价异质融合模型,并赋予模型可解释性,综合解决单一模型稳定性较差、原有Blending框架融合模型过拟合、融合模型缺乏可解释性的问题。通过对个体工商户数据集进行实证实验,结果表明:融合模型较单一机器学习模型在个体工商户信用评价场景下具有更优的预测性能和泛化能力。

Research on blended teaching Mode of Cultivating problem-solving ability--Take the course"Curriculum Design and Evaluation"as an example

Based on the literature analysis,this paper identifies the five factors of problem-solving skills:cognitive ability,knowledge,meta-cognitive ability,motivation,and emotion;teaching intervention strategies;and teaching sessions that affect the development of problem-solving ability.On this basis,a blended teaching mode for cultivating problem-solving ability is designed.The article uses the problem-solving ability evaluation questionnaire to test the effect of pre-test and post-test after teaching intervention on 25 college students.The results verify that the blended teaching model designed in this paper is effective in promoting the cultivation of problem-solving ability,and provide a reference for promoting the cultivation of students'problem-solving ability in the context of the normalization of blended teaching.

Closed-loop scheduling optimization strategy based on particle swarm optimization with niche technology and soft sensor method of attributes-applied to gasoline blending process

Gasoline blending scheduling optimization can bring significant economic and efficient benefits to refineries.However,the optimization model is complex and difficult to build,which is a typical mixed integer nonlinear programming(MINLP)problem.Considering the large scale of the MINLP model,in order to improve the efficiency of the solution,the mixed integer linear programming-nonlinear programming(MILP-NLP)strategy is used to solve the problem.This paper uses the linear blending rules plus the blending effect correction to build the gasoline blending model,and a relaxed MILP model is constructed on this basis.The particle swarm optimization algorithm with niche technology(NPSO)is proposed to optimize the solution,and the high-precision soft-sensor method is used to calculate the deviation of gasoline attributes,the blending effect is dynamically corrected to ensure the accuracy of the blending effect and optimization results,thus forming a prediction-verification-reprediction closed-loop scheduling optimization strategy suitable for engineering applications.The optimization result of the MILP model provides a good initial point.By fixing the integer variables to the MILPoptimal value,the approximate MINLP optimal solution can be obtained through a NLP solution.The above solution strategy has been successfully applied to the actual gasoline production case of a refinery(3.5 million tons per year),and the results show that the strategy is effective and feasible.The optimization results based on the closed-loop scheduling optimization strategy have higher reliability.Compared with the standard particle swarm optimization algorithm,NPSO algorithm improves the optimization ability and efficiency to a certain extent,effectively reduces the blending cost while ensuring the convergence speed.

Blend with the Sea Surface Temperature from Different Satellites and Their Comparison in the Southeast Pacific Ocean

The daily sea surface temperature(SST)data from three kinds of different satellites of GMI,GOES and MODIS were applied to do the blend in the Southeast Pacific Ocean throughout the whole year of 2020.The coverage rates of the SST of the blend result were improved highly and more stable throughout the whole year,compared with the result of the single satellite of GMI,GOES,and MODIS.The yearly average coverage rates of GMI,GOES,MODIS,and blend were 43%,48%,30%,and 76%,and their corresponding yearly average standard deviation(SD)were 4%,6%,7%,and 4%,respectively.All the coverage rates of these three satellites were low from April to September.The valid observation days calculated in the whole year over every grid were used to represent the spatial distribution patterns of the coverage rates.The spatial distribution patterns of coverage rates from GOES and MODIS were similar that their valid observation days were higher in the northwest area and lower in the south area,and those of GMI was contrary to the former two.The ranges of valid observation day was from GOES,GMI,and MODIS were 0-364,6-254,and 9-231 d,respectively.After the blend,all the observation day of every grid in the research region was enhanced(103-366 d).Especially the near shore and south area,and the minimum valid observation day increased largely from the single digits to hundreds digit.

To Blend or Not to Blend? Anxiety Buffering Effects of Essential Oil Aromas

Essential oils of pure lavender and lavender blends have been employed as potential anxiolytic aromas in aromatherapy, but a direct comparison of their effectiveness is lacking. The current study investigated the effects of aroma on induced anxiety in non-clinical adults, comparing pure lavender, a commercially available blend and a no aroma control. An experimental, quantitative, mixed factorial design with an opportunity sample of 60 participants was employed. Participants were randomly allocated to three equal groups, one tested in a room infused with lavender aroma, the second with the doTerra Peace® blend, and the third free from any aroma. Participants’ state anxiety scores were measured before and after a novel video-based anxiety induction procedure. Data analysis revealed that the anxiety induction was successful and that both aromas delivered small to medium-sized buffering effects compared to no aroma. The findings add to a small body of research in an area where the practice is global yet has limited scientific evaluation. Future studies utilising brain imaging and blood serum analysis to investigate the anxiolytic mechanism of aromas would be beneficial to further our understanding.