Table of Contents

31 December 2019, Volume 40 Issue 6 Previous Issue    Next Issue

---

For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Select

Matrix Factorization Recommendation Based on  Collaborative Regression Model LI Zhen-bo1,2,3, YANG Jin-qi1, YUE Jun4 2019, 40(6): 983-990.  DOI: 10.11996/JG.j.2095-302X.2019060983 Abstract ( 84 )   PDF (531KB) ( 128 )   Recommendation system is an effective way to solve the problem of information overload. It is difficult for the traditional recommendation system to select items that meet the user’s personalized preferences from mass data, and the recommendation quality is disappointing. By optimizing the traditional collaborative filtering recommendation algorithm, this paper proposes a matrix factorization algorithm (CLMF) for collaborative regression model in view of data sparsity and other problems. The method uses machine learning algorithm to identify the in-depth characteristics of content information, which increases the information capacity of original data. Constructs auxiliary feature matrix, maximizes the role of feature labels through feature matrix fusion, and combines data labels, semantic information and scoring matrix to get the algorithm framework. The experimental results on the real dataset show that the new recommendation algorithm can effectively solve the problem of missing eigenvalues, improve the data sparsity, significantly enhance the scalability of the algorithm and the coverage. Related Articles | Metrics

Select

Artistic Paintings Classification Based on Information Entropy QIAN Wen-hua1, XU Dan1, XU Jin2, HE Lei2, HAN Zhen-yang1 2019, 40(6): 991-999.  DOI: 10.11996/JG.j.2095-302X.2019060991 Abstract ( 122 )   PDF (913KB) ( 158 )   Aiming at the improvement of the accuracy and efficiency of artistic paintings classification algorithm, this paper puts forward a style painting classification algorithm based on information entropy. Firstly, seven representative painting styles, including cartoons, sketches, oil paintings, watercolor paintings, and art painting styles of Chinese pyrography, ink painting and murals, were selected as the research objectives, and the images are pre-processed by denoising and normalization. Secondly, we extracted the style features of painting images and obtain the color entropy, block entropy and contour entropy respectively. Then, the algorithm combined the information entropy of different input painting styles. During the calculation of the information entropy, the color space was transformed from RGB to LAB, and the image color entropy was obtained from a and b channel values and weighting functions. By dividing the artistic images into blocks, we calculated the average entropy of all the blocks to obtain block entropy. Contourlet transform was used to obtain the contour information of artistic images, and we obtained contour entropy. After that, color entropy, block entropy and contour entropy were merged and extracted, and support vector machine (SVM) was applied to train the artistic style image to obtain the classification model of artistic paintings. Finally, we extracted the entropy characteristics of the samples to be identified, and obtained the final classification results by SVM. The method proposed has the advantages of less feature dimension, fast operation and scale invariance. The experimental results show that the proposed method can improve the classification accuracy and efficiency of different painting styles. Related Articles | Metrics

Select

A Clothing Saliency Prediction Method Based on Video Data SHI Min1, HOU Ming1, LIU Ya-ning1,2, MAO Tian-lu2, WANG Zhao-qi2 2019, 40(6): 1000-1007.  DOI: 10.11996/JG.j.2095-302X.2019061000 Abstract ( 119 )   PDF (2631KB) ( 109 )   The human visual attention mechanism shows that when the human eyes look at the target, the attention will only be focused on few areas of interest, while most of the other areas out of interest in the field of vision will be automatically ignored. The study of human visual attention mechanism and the construction of an effective clothing saliency prediction model can be used to guide more realistic and effective clothing motion modeling and improve the efficiency of simulation. In this paper, we analyzed the video data of the dressed human movement, constructed a variety of video samples, and adopted eye movement technology to collect the gaze data of real human eyes. Gauss convolution was used to generate the salient image of video frame as the Ground-truth required for training model. In the video feature extraction, the underlying image features, high-level semantic features and motion features were combined to construct feature vectors and tags, and the significance prediction model based on clothing video was obtained by support vector machine (SVM) training. The experimental results show that the proposed method outperforms the traditional significance prediction algorithm and hassome robustness in clothing saliency prediction. Related Articles | Metrics

Select

Hierarchical Joint Image Completion Method Based on  Generative Adversarial Network JI Jian-jian, YANG Gang 2019, 40(6): 1008-1016.  DOI: 10.11996/JG.j.2095-302X.2019061008 Abstract ( 80 )   PDF (1762KB) ( 118 )    Existing image completion work is mostly based on missing regions with regular, small area or sufficient context information. When the area of the region to be completed is relatively large, the completion work tends to be blurred or distorted due to the lack of context information and the instability of the generative adversarial network (GAN) training. Especially, if the missing area is located at the edge of the image, the final completion result will have large blank area or pseudo color. To solve the above two problems, the method of hierarchical joint image completion on the basis of GAN is proposed, and the network structure is improved to address the problem of unstable GAN training. On the one hand, it overcomes the problem of the generation of blank area in completion results due to the large missing area, thereby producing more realistic and clear texture details. On the other hand, it makes the adversarial network training more stable and suppresses the generation of pseudo-color. The experimental results demonstrate that the proposed method achieves better completion results. Related Articles | Metrics

Select

Holographic Visualization and Interactive System Realization of  Digital Flower Plants LI Zhi, CAI Dong-na 2019, 40(6): 1017-1023.  DOI: 10.11996/JG.j.2095-302X.2019061017 Abstract ( 159 )   PDF (763KB) ( 141 )   The digitization and visualization of flower plants’ morphology, structure and growth process are important research contents of modern forestry research. Digital flower plants have a wide range of applications and demands in science, education and display. Holographic, the cutting-edge technology, whose principle is derived from ‘Pepper’s ghost’ phenomenon. It is usually used to display fabricated images, enabling the integration of digital visions and the real world. It has of fairly appreciable visual effect and high user acceptance. The combination of holographic technology and digital flower plants can enhance the visualization of digital flower plants, thus achieving better effects in display, education and exhibition occasions. Based on what has been achieved, the holographic visualization of digital flower plants is the focus of study in this paper, which, in combination with an interactive system facilitates the design of a set of processes that is characteristic of visuality and interactiveness. Thus it is a feasible scheme capable of carrying out in-depth research on digital flower plants, providing implications for further study on digital plants and related applications. Related Articles | Metrics

Select

Review on Feature Extraction of Traffic Sign Recognition XUE Bo, LI Wei, SONG Hai-yu, FANG An-qi, PENG Jing-tao, WANG Peng-jie, GUO Hong-ye 2019, 40(6): 1024-1031.  DOI: 10.11996/JG.j.2095-302X.2019061024 Abstract ( 128 )   PDF (544KB) ( 176 )   Traffic sign recognition (TSR) is an important research direction of intelligent transportation system (ITS). Feature extraction is the key point of traffic sign recognition research. This paper focuses on feature extraction of traffic sign recognition and summarizes common manual features and depth features. Manual features include color histogram, scale invariant feature transformation feature, local binary pattern feature, directional gradient histogram feature, Haar-like feature, Gabor wavelet feature, Canny feature, etc. Depth features are extracted from AlexNet, VGG16, Inception, etc. Various features are extracted from the same data set (GTSRB). Various features are compared and analyzed quantitatively by using the same classifier and the same evaluation index system. This paper makes an intuitive comparative research of performance for different features and different types of traffic signs by means of charts and graphs, aiming at providing a reference for the selection of feature vectors and for the further research of traffic sign recognition. Related Articles | Metrics

Select

Research on Path Planning Method of Ancient Architectural Scene Based on Depth Map and Aesthetic Evaluation HU Peng, LI Lin, YANG Jing, LIU Xiao-ping 2019, 40(6): 1032-1037.  DOI: 10.11996/JG.j.2095-302X.2019061032 Abstract ( 105 )   PDF (1950KB) ( 60 )   With the development of virtual reality technology, virtual scenic spots are more and more widely used in promotion and introduction of tourist attractions. Roaming function is one of the important functions in virtual scenic spots. In order to make visitors understand the real scenic environment, it is necessary to plan the path according to the needs of visitors and the real environment, find a short enough path between two points without obstacles on the premise that visitors can browse enough pleasing scenery on the path. Firstly, through the analysis of image aesthetic rules, we obtain the factors that affect the aesthetic quality. Then we improve the ant colony algorithm, add image quality constraints, and avoid deadlock problem. We plan a path for an unknown scene, and get a path that conforms to image aesthetics. Experimental results show that the average landscape quality obtained by this method is higher than that of ant colony algorithm, and this method is more suitable for ancient architectural scenes. References | Related Articles | Metrics

Select

The Research about RJMCMC+SA Image Segmentation Algorithm to Automatically Determine the Number of Categories ZHANG Wen-kun1, WANG Xi-yuan1,2, HAN Jia-xue1 2019, 40(6): 1038-1047.  DOI: 10.11996/JG.j.2095-302X.2019061038 Abstract ( 69 )   PDF (2532KB) ( 84 )    Based upon the premise of ensuring the complexity and accuracy of remote sensing image segmentation model, it is crucial to automatically determine the number of segmentation categories. An image segmentation algorithm is constructed in this paper by combining reversible jump Markov Chain Monte Carlo and simulated annealing (RJMCMC+SA). The image is smoothed geometrically by Gauss curvature filtering (GC), and the posterior probability distribution is established by formalizing the parameters in the nonlinear regression model based on Bayesian theory. And then RJMCMC algorithm is used to accomplish the posterior probability distribution and construct the probability transfer core. After that SA algorithm is used to accelerate the convergence of the probability transfer kernel to determine the number and parameters of the radial basis function in the segmentation algorithm and complete the automatic determination of the number of categories and image global segmentation. Finally, the segmentation algorithm is compared with four RBF segmentation models in panchromatic remote sensing images and Berkeley University experimental database images. The data analysis shows that the algorithm not only strikes a good balance in complexity and accuracy, but also automatically determines the number of image categories. Related Articles | Metrics

Select

Feature Set Selection of Pattern Design Source Code Based on  Perceptual Semantic Fuzzy Factor Evaluation WANG Mei-chao1, LIN Li1, WAN Lu1, GAO Yun-kun2 2019, 40(6): 1048-1056.  DOI: 10.11996/JG.j.2095-302X.2019061048 Abstract ( 62 )   PDF (1629KB) ( 85 )   At present, most perceptual research approaches the design issue directly from imagery to design features, while we are lack of such perceptual research characteristic of backward induction based on the design source code ofimage inducement. For the sake of the user and through combining perceptual fuzzy factor evaluation and cluster analysis, this paper puts forward a method of screening the design source code of backward image inducement, extracting the feature of pattern design source code which triggers the user’s perceptual image. Firstly, the data samples are screened to establish a sample perceptual semantic space, and the basic factors are selected by the fit evaluation method. Secondly, the fuzzy factor evaluation is used to determine the evaluation and reliability of the factor weight acquisition pattern set, and the pattern design source code feature set is screened with the factor taken as the evaluation criterion in combination with the cluster analysis. Finally, the validity and feasibility of the method are verified by T-test, taking the Miao costume pattern as a case study. The results show that the method can effectively guide the establishment of the source code feature set based on the perceptual cognitive theory. Related Articles | Metrics

Select

Blind Motion Image Deblurring Using Two-Frame Generative  Adversarial Network LUO Qi-bin1,2, CAI Qiang1,2 2019, 40(6): 1056-1063.  DOI: 10.11996/JG.j.2095-302X.2019061056 Abstract ( 95 )   PDF (4000KB) ( 232 )   Traditional methods of motion blur blind removal are required to predict the fuzzy kernel of the blurred images and then restore the clear images. However, the fuzzy kernel in the real environment is complex, causing such method to fail to reduce the difference between the actual image and the restored one. Moreover, the application of the popular generative adversarial model directly to image blurring blind removal will cause serious pattern collapse. Therefore, based on the characteristics of deblurring tasks, we proposed an end-to-end generative adversarial network model—two-frame generative adversarial network. The scheme does not need to predict the fuzzy kernel, and it can directly realize the blind removal of the motion blur of images. Based on the original CycleGan, the two-frame generative adversarial network improved its network structure and loss function to improve the accuracy of blind removal of moving images and greatly improve the stability of the network in the case of limited samples. The minimum mean square error was used to optimize the network training. Finally, a clear image was obtained by the adversarial training between generative network and discriminant network. Experimental results on the ILSVRC2015 VID dataset show that the method has a higher quality of restoration. And the restored results appear to be better in subsequent target detection tasks. Related Articles | Metrics

Select

Local Human Mesh Deformation Method Based on  Bounded Biharmonic Weights TONG Li-jing, LI Jin, LAI Yu-ping, FU Xiao-qin 2019, 40(6): 1064-1071.  DOI: 10.11996/JG.j.2095-302X.2019061064 Abstract ( 127 )   PDF (3330KB) ( 210 )   In order to improve local deformation quality of 3D human body model in motion, a local human body mesh deformation method combining bounded biharmonic weights with dual quaternion blending skinning is proposed. Firstly, the 3D human body model is tetrahedralized. Then the bone control unit of the model is set up. Next, the bounded biharmonic weights of each bone control unit for the movement deformation of each vertex in the human body local model is calculated by minimizing the sum of Laplacian energy and the boundary constraints of the weight setting. After that, the mesh vertexes of the 3D human body model are bound to the bone control unit, and the motion parameters of each bone control unit are converted to double quaternions. Finally, in the double quaternion operation space, the motion deformation of the 3D local model driven by bone control units is calculated with the bounded biharmonic weights, in order to achieve the blending skinning combining the dual quaternion with the bounded biharmonic weights in motion state. The experimental results show that this method enables the local model of 3D human body to be more smoothly and more naturally deformed in motion. Related Articles | Metrics

Select

Weighted Optimization Integrated Convolutional Neural Network and  Its Application in 3D Model Recognition WANG Xin-ying, WANG Ya 2019, 40(6): 1072-1078.  DOI: 10.11996/JG.j.2095-302X.2019061072 Abstract ( 57 )   PDF (1013KB) ( 84 )   3D models enjoy a popularity. It has always been our concern as to how to effectively manage and classify the 3D models in these databases. However, due to the similarity between different 3D models is difficult to calculate, it is difficult to obtain a robust and widely applicable 3D model classification algorithm. Thus a weighted optimization integrated convolutional neural network model is proposed and applied to the classification and recognition of 3D models. Firstly, the depth projection view of the 3D model is obtained to maximize the reserve of spatial information of the 3D model. Then, the adjusted VGG network is used to train the depth projection images from different angles and extract the predictive probability values. Finally, the final classification results of the complete 3D model are obtained by weighted ensemble algorithm. The experiments on ModelNet10 and ModelNet40 databases show that the average classification accuracy of the 3D model is 92.84% and 86.51% respectively. In terms of performance prediction, the network is superior to the ordinary single convolution neural network, and its classification accuracy can be significantly improved in 3D model recognition. Related Articles | Metrics

Select

UVA Visual Tracking Via Multi-Cue Fusion Correlation Filter with Re-Detection DONG Mei-bao1, YANG Han-wen1,2, GUO Wen1, MA Si-yuan1, ZHENG Chuang1 2019, 40(6): 1079-1086.  DOI: 10.11996/JG.j.2095-302X.2019061079 Abstract ( 97 )   PDF (1041KB) ( 233 )    UAV (unmanned aerial vehicle) visual tracking is the core area of the future visual tracking applications, but the research is just emerging. It is difficult to track the target robustly in UAV visual tracking, due to the small and unclear appearanceof the target, the change of the flight attitude of the drone and its poor flight stability. Especially if tracking occlusion occurs, the algorithm cannot update the model after tracking drift. To alleviate these problems, we propose a multi-cue fusion tracking method with re-detection based on correlation filter. Firstly, multi-feature fusion is used to improve the discriminability of target appearance representation in UAV tracking. Secondly, when the occlusion occurs, the search area is expanded, and the sliding window sampling is used to find the target area with the highest confidence and the model update is realized. Tracking experiments on a series of challenging drone videos show that the proposed tracking algorithm has better robustness when encountering occlusion problems, which improves the accuracy of the drone in the target tracking. Related Articles | Metrics

Select

Improved VGG Neural Network Applied to Defect Detection of   Diode Glass Bulb Image DU Chao, LIU Gui-hua 2019, 40(6): 1087-1092.  DOI: 10.11996/JG.j.2095-302X.2019061087 Abstract ( 81 )   PDF (1665KB) ( 188 )   In response to the solution of the problem that the image defects of diode glass bulb are mostly detected by manual feature extraction and the recognition is of low accuracy, an improved VGG network for diode glass bulb image defect detection is proposed. Firstly, the glass bulb image is preprocessed. At the same time, the VGG-19 model of convolution neural network structure is pre-trained by the original large sample data set to obtain the pre-training model. Then, part of the weight parameters of the pre-training model, such as convolution and pooling, are transferred to the fixed layer of the improved network model by the method of transfer learning. In this model, the non-fixed layer is used for improvement and the full-connection layer structure of the network is re-set and optimized. Finally, the improved model is trained with the preprocessed image data set of the glass bulb, and the parameters and weights of the non-fixed convolution layer and the new full-connection layer are obtained. The results of the experiment on the data set of the diode glass bulb show that the method can effectively improve the accuracy of the classification and recognition of the diode glass bulb defect detection and the accuracy rate can reach 98.3%. Related Articles | Metrics

Select

Demand Analysis and System Function Design of Smart Venue Based on “Technology Winter Olympics” LIU Zhan-sheng1, SUN Jia-jia1, LI Jiu-lin2, LIU Xi-mei1 2019, 40(6): 1093-1098.  DOI: 10.11996/JG.j.2095-302X.2019061093 Abstract ( 194 )   PDF (618KB) ( 180 )   With the implementation of the national key R&D plan of “Technologically-oriented Winter Olympics” and the rapid development of emerging technologies such as BIM, internet of things, mobile internet, big data, artificial intelligence, etc., information technology is gradually infiltrating into the construction of the green and energy-saving sports stadiums with best operational benefits for “smart venues” to emerge. However, the intelligent construction and sustainable operation of China’s sports stadiums still face serious problems. The stadiums are mostly for a small number of single-point intelligent applications, and the post-game operating conditions are not good, lacking the demand analysis and functional design for contemporary smart venues. By analyzing the high-tech application of the smart venues in the previous sports events and summarizing the application characteristics and trends, the needs of the contemporary smart venues were analyzed comprehensively, and the corresponding viewing service system in the stadiums was designed according to the demand for the viewing service. Finally, suggestions for the development of smart venues were given as reference for the construction and operation of smart venues in the future. Related Articles | Metrics

Select

Research on IFC Model Checking Method Based on Knowledge Base GAO Ge1,2, ZHANG Yue-mei1,2, LIU Han1,2, LI Zhi3, GU Ming1,2 2019, 40(6): 1099-1108.  DOI: 2095-302X(2019)06-1099-10 Abstract ( 168 )   PDF (900KB) ( 167 )   With the development of building information modeling (BIM) technology in AEC field at home and abroad, industry foundation classes (IFC) has been widely used as a BIM open data standard nowadays. The geometric and semantic information representations of IFC are very complex, and the scale of the model is increasing. The existing automatic model checking methods based on memory or fixed path queries are faced with challenges of time, space efficiency and query complexity. To solve these problems, an IFC model checking method based on knowledge base is proposed. By parsing and modeling the IFC model into the labeled property graph (LPG) and storing it in the graph database, the reasonable and query-flexible structured knowledge is formed. Based on the establishment of knowledge base, we designed a property link reasoning and pruning based IFC semantic checking algorithms and the related geometric checking algorithms. The IfcGraph automatic checking system is developed, which realizes efficient storage and flexible checking of models and improves the efficiency and usability of the automatic checking process. Finally, the feasibility of the proposed method and system is verified by a practical engineering project. Related Articles | Metrics

Select

Design Research on Neo-Chinese Style Range Hoods Based on  Evaluation Grid Method LU Yi-zhou, PEI Jun 2019, 40(6): 1109-1115.  DOI: 10.11996/JG.j.2095-302X.2019061109 Abstract ( 155 )   PDF (1921KB) ( 162 )   In order to accurately design range hoods for Neo-Chinese style home environment, it is necessary to analyze the user’s preference for that style and transform it into a specific design strategy. Firstly, with evaluation gird method in miryoku engineering in in-depth interview, attractive factors from Neo-Chinese home style were extracted and evaluation grid figures were built. Secondly, the compatibility between the existing range hoods and the attraction factors of Neo-Chinese style was analyzed through questionnaires to make a design strategy. Finally, the effectiveness of the design strategy was tested on the improved design of the range hoods. It was found that the most attraction factors of Neo-Chinese home style include overall harmony, elegance and retaining, composedness and tranquility, as well as its simplicity and plainness. However, the existing range hoods perform poorly in elegance and retraining and environmental adaptability. The refined design based on the evaluation grid figures can better adapt to the Neo-Chinese style home environment. The results show that the evaluation grid method can effectively establish the connection between the subjective preference of the home style and the specific design features, providing implications for the design of household products. Related Articles | Metrics

Select

Automatic Generation Method of Dimension Annotating for  Floor Plane Based on IFC Standard HOU Wen-long, DENG Xue-yuan 2019, 40(6): 1116-1122.  DOI: 10.11996/JG.j.2095-302X.2019061116 Abstract ( 107 )   PDF (596KB) ( 109 )   In the collaborative application of building information modeling (BIM) technology, 2D drawing information plays a significant role in establishing the spatial layout of the modeling and representing the size information of components. In addition the representation of 2D dimension information based on IFC standard overcomes the difficulty that the dimension annotation for 3D models of different industries cannot be conducted using an integrated BIM software tool. In order to examine the space layout and size information of BIM components in a more efficient way, this paper proposes a method to automatically generate 2D dimension annotations for 3D models based on IFC standard. Firstly, the extraction, classification, transformation and storage mechanism of geometric and spatial position information for building components on the same floor is developed. Secondly, the dimension information of all annotated components in the floor is obtained. Then, combined with the space orientation and shape representation of annotated entities based on IFC standard, 2D dimension annotated entities are established and linked with the annotated components. Finally, the proposed method is verified with a two-story building case. Related Articles | Metrics

Select

Multi-LoD Expression and Automatic Information Integration of  Cracks in Ancient Wooden Buildings LIU Ying-hua1,2,3, XIE Lin-lin1,4, LI Ai-qun1,4, HOU Miao-le1,2,3, LIU Hao-yu1,2,3 2019, 40(6): 1123-1129.  DOI: 10.11996/JG.j.2095-302X.2019061123 Abstract ( 118 )   PDF (1187KB) ( 115 )   The ancient wooden building is fairly valuable. Scientific understanding, intuitive expression and automatic information integration of the damage are conducive to better cultural inheritance. Although historic building information modeling (HBIM) technology has the characteristics of high correlation between model and information, and it can integrate information into the model, which is highly compatible with the requirements of the information expression integration of ancient buildings, there are still some problems in application, such as the fine division of damage model expression and the difficulty of the quick integration of a large amount of damage information. This paper takes the crack damage of ancient wooden buildings as an example. Firstly, the multi-Level of Detail (LoD) expression standard of crack model was proposed. Then, the information integration method of HBIM was analyzed in detail, that is, the component information is managed by electronic list in Revit. In order to solve the problem of the large amount of information, the secondary development of Revit was carried out by writing external commands and the software was loaded as an external application to automatically integrate and update information. Finally, the method was verified by an HBIM model of an ancient wooden building, and the automatic information integration of 64 pillars was completed within 4 seconds. It shows the efficiency and reliability of the multi-LoD expression method and information automatic integration algorithm, which can provide reference for the expression, integration and management of the information of historical buildings. Related Articles | Metrics

Select

Research on Automatic Labeling Method of Architectural Aluminum Formwork Installation Drawing WANG Xue-wei, SHENG Bu-yun, ZHANG Yun, LIU Yuan-zhi 2019, 40(6): 1130-1136.  DOI: 10.11996/JG.j.2095-302X.2019061130 Abstract ( 123 )   PDF (574KB) ( 130 )   Currently, the construction workers in the aluminum formwork industry mainly assemble aluminum formwork according to the two-dimensional installation and construction drawings. In view of the large number and numerous types of aluminum templates, the large workload of marking the template parts and the chaotic layout, the present study focused on the automatic labeling method of aluminum formwork construction drawing. Firstly, the aluminum template and the annotation information model are established. The part matching information search method is proposed to find the parts that match the fittings. The method of dividing the parts space level is proposed to determine the position of the parts in the space. The parallel display method of the label information is presented to calculate the offset angle of the annotation. Finally the automatic text labeling and layout method is proposed to achieve automatic labeling of aluminum template installation and construction drawings. The example analysis shows that the method greatly reduces the workload of the aluminum formwork construction drawing, improves the design efficiency and the drawing quality, and has been put to production practice. Related Articles | Metrics

Select

Comprehensive Importance of Integrating User Satisfaction with User Demand LIU Da-shuai1, YANG Qin2, LV Jian1, WANG Wei-xing2 2019, 40(6): 1137-1142.  DOI: 10.11996/JG.j.2095-302X.2019061137 Abstract ( 90 )   PDF (376KB) ( 109 )    In consideration of the subjectivity and fuzziness involved in the process of determining the importance of user demand and the problem of the neglect of the effect of the degree of user demand preference on the importance of user demand, a method of determining the comprehensive importance of user demands is proposed based on fuzzy theory, Kano model, approximate ideal solution ranking method and entropy weight method. First of all, market research and design research were made to obtain the original user demand information, and then fuzzy clustering was applied to obtain the new information. Secondly, we used fuzzy Kano model to investigate the new user requirements, acquiring the attribute classification of them as well as their Si and DSi coefficients. Thirdly, TOPSIS (technique for order preference by similarity to ideal solution) method was used to determine the matching degree of user demand factors and user satisfaction, and the quantitative value of user demand satisfaction was obtained. Finally, the entropy weight method was used to calculate the primary importance of user demand, and the user demand satisfaction value was multiplied by the primary importance weight to get the comprehensive importance function of user demand. Taking the design and development of a new type of civil friction welding machine as an example, we verified the feasibility and effectiveness of this method, providing implications for the design and development of high-end CNC machine tools. Related Articles | Metrics