Customer satisfaction and loyalty analysis with classification algorithms and Structural Equation Modeling

Businesses can maintain their effectiveness as long as they have satisfied and loyal customers. Customer relationship management provides significant advantages for companies especially in gaining competitiveness. In order to reach these objectives primarily companies need to identify and analyze their customers. In this respect, effective communication and commitment to customers and changing market conditions is of great importance to increase the level of satisfaction and loyalty. To evaluate this situation, level of customer satisfaction and loyalty should be measured correctly with a comprehensive approach. In this study, customers are investigated in 4 main groups according to their level of satisfaction and loyalty with a criteria and group based analysis with a new method. We use classification algorithms in WEKA programming software and Structural Equation Modeling (SEM) with LISREL tools together to analyze the effect of each satisfaction and loyalty criteria in a satisfaction–loyalty matrix and extend the customer satisfaction and loyalty post-analysis research bridging the gap in this field of research. To convert developed conceptual thought to experimental study, white goods industry is exemplified. 15 criteria are used for evaluation in 4 customer groups and a satisfaction–loyalty survey developed by experts is applied to 200 customers with face-to-face interviews. As a result of the study, a customer and criteria grouping method is created with high performance classification methods and good fit structural models. In addition, results are evaluated for developing a customer strategy improvement tool considering method outcomes.     

Thermodynamic analysis of natural gas reciprocating compressors based on real and ideal gas models

The accurate modelling and investigating effects of various parameters of the reciprocating compressors are important subjects. In this work, based on first law of thermodynamics, conversation of mass and real and ideal gas assumptions, a theoretical analysis has been constructed to simulate natural gas reciprocating compressors. For computing the thermodynamic properties of natural gas based on real gas model, the AGA8 equation of state has been used. Numerical results validated with previous measured values and showed a good agreement. The effects of important parameters such as: angular speed, clearance and pressure ratio have been studied on the performance of the compressors. The results reveal the in-control volume temperature for ideal gas is more than real gas model but the mass flow rate and work for real gas is higher than ideal gas model. On the other hand, the indicated work that required for compression is greater for ideal gas model.     

Modeling and simulation of biphasic catalytic hydrogenation of a hydroformylated fuel

A model was developed based upon PR78 CEOS, Twu's alpha function and vdW mixing rules for simulating a pioneering chemical process of fuel upgrading. The chemical process of aqueous biphasic hydrogenation of a real hydroformylated fuel was experimentally conducted and simulated. The hydrogenation of the fuel occurred in aqueous media with in situ produced Ru-catalyst converting containing aldehydes to the corresponding alcohols. The above heterogenization of the homogeneous catalyst offered to the process an efficient and convenient way of catalyst recovery. The reaction temperature effect and the influence of hydrogen pressure in aqueous biphasic catalytic hydrogenation were examined. RuCl₃/TPPTS catalytic system proved to be an effective catalyst for fuel upgrading process, with the highest conversion of the aldehydes present in a hydroformylated fuel to reach 98.9% at 120 °C, 75 bar and at a short reaction time (2 h). A complete phase behavior of the fuel as well as a validation test of the simulation model were accomplished.     

Application of robust machine learning methods to modeling hydrogen solubility in hydrocarbon fuels

Having accurate information about the hydrogen solubility in hydrocarbon fuels and feedstocks is very important in petroleum refineries and coal processing plants. In the present work, extreme gradient boosting (XGBoost), multi-layer perceptron (MLP) trained with Levenberg–Marquardt (LM) algorithm, adaptive boosting support vector regression (AdaBoost?SVR), and a memory-efficient gradient boosting tree system on adaptive compact distributions (LiteMORT) as four novel machine learning methods were used for estimating the hydrogen solubility in hydrocarbon fuels. To achieve this goal, a database containing 445 experimental data of hydrogen solubilities in 17 various hydrocarbon fuels/feedstocks was collected in wide-spread ranges of operating pressures and temperatures. These hydrocarbon fuels include petroleum fractions, refinery products, coal liquids, bitumen, and shale oil. Input parameters of the models are temperature and pressure along with density at 20 °C, molecular weight, and weight percentage of carbon (C) and hydrogen (H) of hydrocarbon fuels. XGBoost showed the highest accuracy compared to the other models with an overall mean absolute percent relative error of 1.41% and coefficient of determination (R²) of 0.9998. Also, seven equations of state (EOSs) were used to predict hydrogen solubilities in hydrocarbon fuels. The 2- and 3-parameter Soave-Redlich-Kwong EOS rendered the best estimates for hydrogen solubilities among the EOSs. Moreover, sensitivity analysis indicated that pressure owns the highest influence on hydrogen solubilities in hydrocarbon fuels and then temperature and hydrogen weight percent of the hydrocarbon fuels are ranked, respectively. Finally, Leverage approach results exhibited that the XGBoost model could be well trusted to estimate the hydrogen solubility in hydrocarbon fuels.     

Thermodynamic models for H2O–CO2–H2 mixtures in near-critical and supercritical regions of water

The PVTx properties of the H₂O–CO₂–H₂ mixtures have significant applications in the technology of supercritical water gasification of coal. Here, we first carry out the molecular dynamics simulations of the PVTx properties of the H₂O–CO₂–H₂ mixtures in the near-critical and supercritical regions of water to generate 600 datasets at 750–1150 K and 4.0–443.5 MPa. The molar fraction of each composition in the ternary mixtures ranges from 10% to 80%. Later we investigate the applicability of a well-known thermodynamic model for the ternary mixtures, namely the Duan-Møller-Weare equation of state (DMW EOS). It is observed that the DMW EOS shows great potential in the prediction of the PVTx properties of the ternary mixtures. However, it is noted that the mixing parameters describing the binary interactions of H₂O–H₂ and CO₂–H₂ are still unknown in the DMW EOS. By determining the missing mixing parameters using the Levenberg-Marquardt algorithm, the accuracy of the original DMW EOS is improved for the ternary mixtures. Moreover, optimizing the coefficients in the DMW EOS further promotes the accuracy of the model for the H₂O–CO₂–H₂ mixtures. The results from this work may facilitate the development of supercritical water gasification of coal.     

Factors that determine residents’ acceptance of smart city technologies

ABSTRACT

While some cities attempt to determine their residents’ demand for smart-city technologies, others simply move forward with smart-related strategies and projects. This study is among the first to empirically determine which factors most affect residents’ and public servants’ intention to use smart-city services. A Smart Cities Stakeholders Adoption Model (SSA), based on Unified Theory of Acceptance and Use of Technology (UTAUT2), is developed and tested on a mid-size U.S. city as a case study. A questionnaire was administered in order to determine the influence of seven factors – effort expectancy, self-efficacy, perceived privacy, perceived security, trust in technology, price value and trust in government – on behaviour intention, specifically the decision to adopt smart-city technologies. Results show that each of these factors significantly influenced citizen intention to use smart-city services. They also reveal perceived security and perceived privacy to be strong determinants of trust in technology, and price value a determinant of trust in government. In turn, both types of trust are shown to increase user intention to both adopt and use smart-city services. These findings offer city officials an approach to gauging residential intention to use smart-city services, as well as identify those factors critical to developing a successful smart-city strategy.     

Morison方程中动水阻力项对桥梁桩柱地震反应的影响

在深水桥梁地震反应分析中,当采用Morison方程来考虑桩等水中横向小尺寸结构上水的作用时,等效为增加了一个附加惯性力项和一个附加阻力项,其中,附加阻力项是非线性的。由于非线性附加阻力项的存在,给采用反应谱方法求解桥梁的地震反应带来不便。本文讨论了非线性阻力项对一般桥梁桩柱结构地震反应的贡献,得到的结论是阻力项的贡献很小,可以忽略。这样,水中桥梁地震反应的计算就得到了很大的简化。     

Close-range blast loading on empty recyclable metal beverage cans for use in sacrificial cladding structure

This article deals with the experimental and numerical blast study on a single empty recyclable metal beverage can. The idea is to make a macro-foam (sacrificial cladding structure) out of these cans to protect the main load bearing members of civil engineering structures from the air blast load. Close-range free air blast tests have been conducted to understand the crushing behaviour and the energy absorption of a single empty beverage can in detail. To conduct such an air blast test a special small-scale test set-up was designed and manufactured. The effect of skin plate surface area and its nature on the blast parameters is studied. Furthermore, the effect of inertia of the skin plate on the crushing performance of the beverage can is evaluated. Tests have been conducted with different plates (made of aluminium and sandwich composite materials) with different masses which represent the skin plate of the proposed sacrificial structure. The measured blast parameters from the experimental tests were compared with ConWep predicted data. Furthermore, the influence of the finite surface area of the skin plate on the clearing of the reflected pressure waves was also studied. The deformation behaviour and the corresponding energy absorption of empty beverage cans were captured. During the experimental blast tests it was observed that a part of the total reflected impulse (∼30%) was lost before it transfers to the non-sacrificial structure. Hence, in order to investigate this phenomenon Eulerian-Lagrangian coupled analyses were conducted using Hydrocodes. The results from these analyses showed that the diffraction and ground reflected pressure wave caused the loss in impulse. The results from the numerical studies have been compared and validated with the experimental results.     

基于协方差分析描述函数技术的弹道导弹落点预报

针对采用Monte-Carlo方法对非线性系统进行统计分析效率低下的问题,将协方差分析描述函数法(CADET)应用于弹道导弹落点预报与精度分析.介绍CADET方法的统计线性化思想,提出一种针对一阶可微随机变量函数的统计线性化方法,建立弹道导弹被动段的均值和方差计算的CADET模型.该方法通过一次计算就可得到随机变量数字...     

Removal of Lissamine Red From Wastewater Using Waste Materials

Feasibility of a waste material, flyash, as a material for purification of wastewater containing Lissamine Red has been studied. Effects of time and concentration, temperature and pH on the removal of the dye have been studied. Lower concentrations favour the uptake of dye from water and the maximum removal was observed at a dye concentration of 20 mgL m 1 , 30°C, pH of 7 and adsorbent particle size of 53 µm. Dynamics of the uptake was studied using Lagergren's equation. The mass transfer coefficient was found to be 0.05 cmmin m 1 at a concentration of 20 mgL m 1 , 30°C and 53 µm particle size.