Green technology automotive shape design based on neural networks and support vector regression

2014 ◽  
Vol 31 (8) ◽  
pp. 1732-1745 ◽  
Author(s):  
Kuo-Kuang Fan ◽  
Chun-Hui Chiu ◽  
Chih-Chieh Yang
Keyword(s):  
Support Vector Regression ◽  
Evaluation Method ◽  
Affective Response ◽  
Green Technology ◽  
Affective Responses ◽  
Support Vector ◽  
Shape Design ◽  
Shape Features ◽  
Systematic Analysis ◽  
Content Type

Purpose – The green technology cars have received much attention due to the air pollution and energy crisis. The purpose of this paper is to increase automotive designers’ understanding of the affective response of consumers about automotive shape design. Consumers’ preference is mainly based on a vehicle's shape features that are traditionally manipulated by designers’ intuitive experience rather than by an effective and systematic analysis. Therefore, when encountering increasing competition in today's automotive market, enhancing car designers’ understanding of consumers’ preferences on the shape features of green technology vehicles to fulfil customers’ demands, has become a common objective for automotive makers. Design/methodology/approach – In this paper, questionnaires were first used to gather consumer evaluations of certain adjectives describing automobile shape. Then, automotive styling features were systematically examined by numerical definition-based shape representations. Finally, models were individually constructed using support vector regression (SAR), which predicted consumer's affective responses, based on the adjectives selected, and which also incorporated the relationship between consumer's affective responses and automotive styling features. Findings – In order to predict and suggest the best automotive shape design, the results of this experiment of SVR can provide a basis for the future development of automobiles, particularly for green vehicle design, and support automotive makers in ensuring that automotive shape design to satisfy consumer needs. Originality/value – SVR is a valuable choice as an evaluation method to be applied in the design field of green vehicles.

Application of machine learning in predicting construction project profit in Ghana using Support Vector Regression Algorithm (SVRA)

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Emmanuel Adinyira ◽  
Emmanuel Akoi-Gyebi Adjei ◽  
Kofi Agyekum ◽  
Frank Desmond Kofi Fugar
Keyword(s):  
Machine Learning ◽  
Support Vector Regression ◽  
Cash Flow ◽  
Predictive Accuracy ◽  
Model Development ◽  
Construction Project ◽  
Support Vector ◽  
Sensitivity Index ◽  
Content Type ◽  
Hyperparameter Selection

PurposeKnowledge of the effect of various cash-flow factors on expected project profit is important to effectively manage productivity on construction projects. This study was conducted to develop and test the sensitivity of a Machine Learning Support Vector Regression Algorithm (SVRA) to predict construction project profit in Ghana.Design/methodology/approachThe study relied on data from 150 institutional projects executed within the past five years (2014–2018) in developing the model. Eighty percent (80%) of the data from the 150 projects was used at hyperparameter selection and final training phases of the model development and the remaining 20% for model testing. Using MATLAB for Support Vector Regression, the parameters available for tuning were the epsilon values, the kernel scale, the box constraint and standardisations. The sensitivity index was computed to determine the degree to which the independent variables impact the dependent variable.FindingsThe developed model's predictions perfectly fitted the data and explained all the variability of the response data around its mean. Average predictive accuracy of 73.66% was achieved with all the variables on the different projects in validation. The developed SVR model was sensitive to labour and loan.Originality/valueThe developed SVRA combines variation, defective works and labour with other financial constraints, which have been the variables used in previous studies. It will aid contractors in predicting profit on completion at commencement and also provide information on the effect of changes to cash-flow factors on profit.

Forecasting of stock price index using support vector regression with multivariate empirical mode decomposition

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yanmei Huang ◽  
Changrui Deng ◽  
Xiaoyuan Zhang ◽  
Yukun Bao
Keyword(s):  
Support Vector Regression ◽  
Empirical Mode Decomposition ◽  
Stock Price ◽  
Price Index ◽  
Support Vector ◽  
Modeling Framework ◽  
Content Type ◽  
Multivariate Empirical Mode Decomposition ◽  
Mode Decomposition ◽  
Stock Price Index

Purpose Despite the widespread use of univariate empirical mode decomposition (EMD) in financial market forecasting, the application of multivariate empirical mode decomposition (MEMD) has not been fully investigated. The purpose of this study is to forecast the stock price index more accurately, relying on the capability of MEMD in modeling the dependency between relevant variables. Design/methodology/approach Quantitative and comprehensive assessments were carried out to compare the performance of some selected models. Data for the assessments were collected from three major stock exchanges, namely, the standard and poor 500 index from the USA, the Hang Seng index from Hong Kong and the Shanghai Stock Exchange composite index from China. MEMD-based support vector regression (SVR) was used as the modeling framework, where MEMD was first introduced to simultaneously decompose the relevant covariates, including the opening price, the highest price, the lowest price, the closing price and the trading volume of a stock price index. Then, SVR was used to set up forecasting models for each component decomposed and another SVR model was used to generate the final forecast based on the forecasts of each component. This paper named this the MEMD-SVR-SVR model. Findings The results show that the MEMD-based modeling framework outperforms other selected competing models. As per the models using MEMD, the MEMD-SVR-SVR model excels in terms of prediction accuracy across the various data sets. Originality/value This research extends the literature of EMD-based univariate models by considering the scenario of multiple variables for improving forecasting accuracy and simplifying computability, which contributes to the analytics pool for the financial analysis community.

An adaptive SVR-HDMR model for approximating high dimensional problems

2015 ◽  
Vol 32 (3) ◽  
pp. 643-667 ◽  
Author(s):  
Zhiyuan Huang ◽  
Haobo Qiu ◽  
Ming Zhao ◽  
Xiwen Cai ◽  
Liang Gao
Keyword(s):  
Support Vector Regression ◽  
Direct Method ◽  
Model Representation ◽  
Computational Time ◽  
High Dimensional ◽  
Support Vector ◽  
High Dimensional Model Representation ◽  
Model Assessment ◽  
Dimensional Model ◽  
Content Type

Purpose – Popular regression methodologies are inapplicable to obtain accurate metamodels for high dimensional practical problems since the computational time increases exponentially as the number of dimensions rises. The purpose of this paper is to use support vector regression with high dimensional model representation (SVR-HDMR) model to obtain accurate metamodels for high dimensional problems with a few sampling points. Design/methodology/approach – High-dimensional model representation (HDMR) is a general set of quantitative model assessment and analysis tools for improving the efficiency of deducing high dimensional input-output system behavior. Support vector regression (SVR) method can approximate the underlying functions with a small subset of sample points. Dividing Rectangles (DIRECT) algorithm is a deterministic sampling method. Findings – This paper proposes a new form of HDMR by integrating the SVR, termed as SVR-HDMR. And an intelligent sampling strategy, namely, DIRECT method, is adopted to improve the efficiency of SVR-HDMR. Originality/value – Compared to other metamodeling techniques, the accuracy and efficiency of SVR-HDMR were significantly improved. The SVR-HDMR helped engineers understand the essence of underlying problems visually.

On Evaluation Model of Green Technology Innovation Capability of Pulp and Paper Enterprise Based on Support Vector Machines

2014 ◽  
Vol 886 ◽  
pp. 285-288 ◽  
Author(s):  
Zhi Fang Zhou
Keyword(s):  
Support Vector Machines ◽  
Evaluation Method ◽  
Technology Innovation ◽  
Evaluation Model ◽  
Green Technology ◽  
Pulp And Paper ◽  
Evaluation Index System ◽  
Support Vector ◽  
Innovation Capability ◽  
Vector Machines

Based on the analysis of the concept of green technology innovation capability, this paper not only structures the evaluation index system of green technology innovation capability in pulp and paper enterprises, builds the evaluation model of green technology innovation capability for pulp and paper enterprises based on Support Vector Machines with Radial Basis Function kernel, but also achieves the optimization of kernel function parameters, penalty factors and insensitive parameters based on a heuristic algorithm for tuning hyper-parameters. This model is more suitable for pulp and paper enterprises to evaluate green technology innovation capability, compared with the evaluation method of BP neural network.

Haptic information processing and need for touch in product evaluation

2019 ◽  
Vol 37 (1) ◽  
pp. 55-64 ◽  
Author(s):  
Subhash Jha ◽  
M.S. Balaji ◽  
Marla B. Royne Stafford ◽  
Nancy Spears
Keyword(s):  
Information Processing ◽  
Affective Response ◽  
Product Evaluation ◽  
Underlying Mechanism ◽  
Affective Responses ◽  
Haptic Information ◽  
Cognitive Response ◽  
Content Type ◽  
The Us ◽  
The Impact

Purpose This paper aims to examine the effects of purchase environment, product type and need for touch (NFT) on cognitive response, affective response and overall product evaluation in the USA and India. Design/methodology/approach Two experiments were conducted in two different consumer markets. In Study 1, participants evaluated haptic and non-haptic products and gave responses on cognitive response, affective response and overall product evaluation measures in the US market. In Study 2, the authors replicate Study 1 in a culturally different market of India and extend Study 1 by examining the moderating role of instrumental and autotelic dimensions of NFT on the effect of purchase environment on cognitive and affective responses. Findings Research findings suggest that cognitive and affective responses are the underlying mechanism between the purchase environment and overall response only for haptic product among Indian consumers. In contrast, affective response is the underlying mechanism explaining this relationship among US consumers. Furthermore, the instrumental dimension of NFT moderates the impact of purchase environment on cognitive but the autotelic NFT moderates the effect of purchase environment on affective response only for the haptic product but not for the non-haptic product. Research limitations/implications The study uses a relatively homogenous sample in the Indian market in contrast to the US market. Practical implications Results advance the understanding of the importance of haptic information processing in consumer decision-making across different purchase environments, product types and NFT using psychological distance (proximity) as a theoretical underpinning. With non-haptic shopping environments (i.e. online and mobile) growing rapidly, the results have critical implications for development of marketing strategies in Asian and US markets. Originality/value Empirical research examining the underlying mechanism by which purchase environment influences overall evaluation for haptic product is scarce. Additionally, understanding of the differential roles of instrumental and autotelic dimensions of NFT on cognitive and affective responses is very limited. This research fills this void and provides an understanding of the specific environment in evaluating haptic and non-haptic products in two distinct markets.

scholarly journals State Evaluation Method of Robot Lubricating Oil Based on Support Vector Regression

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Dongdong Guo ◽  
Xiangqun Chen ◽  
Haitao Ma ◽  
Zimei Sun ◽  
Zongrui Jiang
Keyword(s):  
Support Vector Regression ◽  
Evaluation Method ◽  
Prediction Models ◽  
Sample Volume ◽  
Spare Parts ◽  
Small Sample ◽  
Industrial Robots ◽  
Lubricating Oil ◽  
Support Vector ◽  
The Cost

Recently, the development of the Industrial Internet of Things (IIoT) has led enterprises to re-examine the research of the equipment-state-prediction models and intelligent manufacturing applications. Take industrial robots as typical example. Under the effect of scale, robot maintenance decision seriously affects the cost of spare parts and labor deployment. In this paper, an evaluation method is proposed to predict the state of robot lubricating oil based on support vector regression (SVR). It would be the proper model to avoid the structural risks and minimize the effect of small sample volume. IIoT technology is used to collect and store the valuable robot running data. The key features of the running state of the robot are extracted, and the machine learning model is applied according to the measured element contents of the lubricating oil. As a result, the cost of spare parts consumption can be saved for more than two million CNY per year.

Sign in / Sign up

Export Citation Format

Share Document