Table of Contents

30 June 2020, Volume 41 Issue 3 Previous Issue    Next Issue

---

For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Select

Using problem-solving theories to investigate user behaviors in interactive visual analytics of complex information ZHANG Hui-jun, CHEN Jun-jie 2020, 41(3): 325-334.  DOI: 10.11996/JG.j.2095-302X.2020030325 Abstract ( 67 )   PDF (521KB) ( 81 )   Recently, to address the challenges imposed by big data, research on interactive visualization and visual analytics, which is aimed at combining human intelligence and machine computational powers in data analysis, has become increasingly important. However, the design of complex-information-oriented interactive visualization and visual analytics systems still lacks effective cognitive foundations as a guidance. Existing frameworks or design guidelines, such as sense-making, focus largely on the external characteristics of analytical activities and offer little insight into fundamental cognition that underpins analytical behaviors. In this paper, we proposed a theoretical framework based on problem-solving theories to help explain the essential cognitive activities in interactive visual analytics, advocated an approach to understanding the visual analytics process as a process to solve ill-defined problems, and explored the impacts of problem representations and problem-solving strategies on visual analytics behaviors. We see our contribution as two-folded. Theoretically, we borrowed problem-solving theories from cognitive science to study complex interactive activities in visual analytics, and this approach may offer insight into the design of interactive systems involving complex information-analytical behaviors. Practically, we discussed the design and evaluation of visual analytics tools from the perspective of supporting problem-solving. Related Articles | Metrics

Select

Research on human-machine interface design of exterior screen of driverless delivery car WANG Wen-juan, ZHANG Bi-han, FU Meng-ting, LIN Zheng-he, PEI Jing-yi, WANG Jian-min 2020, 41(3): 335-341.  DOI: 10.11996/JG.j.2095-302X.2020030335 Abstract ( 141 )   PDF (743KB) ( 125 )   With the rapid development of intelligent vehicles and logistics, and the combination of these two industries has promoted the emergence of driverless delivery cars. In order to improve the safety, efficiency and user experience of the driverless delivery car, the design of the human-machine interface (HMI) of the car’s exterior screen was studied. We first put forward the theory of human-vehicle-environment relationship based on driverless delivery cars, and studied the design requirements of vehicle exterior interface in view of the running scenario flow of delivery cars. On this basis, the information architecture, multi-channel interaction mode and interface design of the exterior interface of the driverless delivery car were discussed and practiced, and the usability test was conducted regarding the preliminary prototype design of recycling function. The test results show that the preliminary interactive prototype of the driverless delivery car’s exterior screen runs logically smoothly and has high usability. The survey results show the users’ hope for the driverless delivery car to be accurately located and the use of the points system for exchanging material rewards. This research indicates that HMI design can improve the safety, efficiency and user experience of the driverless delivery car. Through modifying and perfecting the design of the exterior screen with test and iteration, the design of the exterior screen will be continuously improved. Related Articles | Metrics

Select

Immersion evaluation of virtual roaming with proprioceptive interaction ZHOU Qiang1, ZHANG Min-xiong1, WU Xin-li1, LI Xin1,HUANG Jin-peng1, YANG Wen-zhen1, PAN Zhi-geng2,3 2020, 41(3): 342-349.  DOI: 10.11996/JG.j.2095-302X.2020030342 Abstract ( 87 )   PDF (2195KB) ( 77 )   Immersion is significantly characteristic of virtual roaming. Currently perceptual distortion is a serious problem in virtual roaming with proprioceptive interaction. Thus, the visual perception of virtual scene motion cannot match the somatosensory perception, which undermines the immersion of virtual roaming. The curve non-equidistant interpolation algorithm, isometric interpolation algorithm and the real-time interpolation algorithm were established based on Catmull-Rom curve, so as to carry out the immersion evaluation of virtual roaming with proprioceptive interaction. The results of subjective evaluation experiments and simulation experiments show that the non-equidistant interpolated roaming paths of Catmull-Rom curves had obvious somatosensory distortions both in uniform roaming and in variable-speed roaming. The equidistant interpolation roaming path based on Catmull-Rom curve was suitable for uniform roaming, but unsuitable for variable-speed roaming. The real-time interpolated roaming path based on Catmull-Rom curve can match the real-motion speed with the scene-motion speed, thus solving the inconsistency between the visual perception and body motion perception in virtual roaming. Therefore, the proposed algorithms can improve the immersion of virtual roaming. Related Articles | Metrics

Select

Research on user experience quality about the time delay of videos on mobile internet TAN Hao1, SUN Jia-hao2 2020, 41(3): 350-355.  DOI: 10.11996/JG.j.2095-302X.2020030350 Abstract ( 72 )   PDF (590KB) ( 56 )   With the development of mobile Internet and the rapid growth of mobile video services, satisfactory quality of experience (QoE) has become a key factor for operators to retain users. Quantitative evaluation criteria was established for mobile video services with different kinds of time delay from the perspective of user experience. According to the method of scenario simulation, a real mapping relationship of the user experience quality was proposed in the subjective scale form of the mean opinion score (MOS). Then a hierarchical study was taken on users’ effective response to delayed videos. The effect of single and multiple initial buffer time and stalling time on user experience quality was obtained. Besides, the evaluation level system of user experience quality was created. In a short video, negative user experience occurs when there is a single delay longer than four seconds. Under the circumstance of the same delay duration, the user experience quality of the initial buffer time is slightly better than that of the stalling time. If many delays occur in a certain mobile video service, compared with a lower frequency of long delays, the short but frequent delays will bring more negative experience to users. Related Articles | Metrics

Select

Research on aided design platform based on 3D headform and acupoint distribution SHAO Yu-guang1, LI Zhe-lin1, YU Guang-zheng2, LI Yu-qi1, DENG Xiang-hong1, JIANG Li-jun1 2020, 41(3): 356-361.  DOI: 10.11996/JG.j.2095-302X.2020030356 Abstract ( 61 )   PDF (3649KB) ( 61 )   In order to design headwear products suitable for the headform of Chinese people and improve the suitability and comfort when the product is used, a research on the graphic platform for assisting the design of headwear products was carried out. Firstly, the three-dimensional digital models of five types of standard heads were reconstructed based on the National Standards. A total of 15 three-dimensional digital head models were constructed according to headform scaling factors at the 5th, 50th, and 95th percentile of different headforms. According to the acupoint distribution and positioning method of traditional Chinese medicine, a three-dimensional distribution model of 7 meridians and 78 acupoints was built on the constructed headform. The WebGL development kit Three.js was used to develop an aided design platform of headwear products, realizing such functions of continuous deformation of the multi-percentile headforms, dynamic positioning of the head acupoints and datum-planes cutting. The platform can provide a suitability analysis of acupoint matching, gap of the fit area and interference. A headwear massager was tried on for adaptability analysis, and the problems of the product structure had been effectively found. The method proposed in this research may provide implications for the compatibility analysis of related headwear products. Related Articles | Metrics

Select

Joint enhanced local maximal occurrence representation and k-KISSME metric learning for person re-identification SUN Rui1,2, XIA Miao-miao1,2, LU Wei-ming1,2, ZHANG Xu-dong1,2 2020, 41(3): 362-371.  DOI: 10.11996/JG.j.2095-302X.2020030362 Abstract ( 56 )   PDF (2364KB) ( 116 )   Person re-identification is an important technique for automatically searching for pedestrians in surveillance videos. This technology consists of two key parts, feature representation and metric learning. Effective feature representations should be robust to changes in illumination and viewpoint, and the discriminative metric learning can improve the matching accuracy of person images. However, most of the existing features were based on local or global feature representation and failed to efficiently use the fine details and profile information of the appearance of pedestrians. More importantly, metric learning was usually conducted in a linear feature space, and nonlinear structures in the feature space couldn’t be efficiently utilized. To solve these problems, we first designed an effective feature representation called enhanced local maximal occurrence representation (eLOMO), which could realize the fusion of fine details and profile information of the appearance of the person image and satisfy the human visual recognition mechanism. Furthermore, we proposed a kernelized KISSME metric learning (k-KISSME) method, simple and efficient, only requiring two inverse covariance matrices to be estimated. In addition, to handle changes in light and viewing angle, we applied Retinex transforms and scale-invariant texture descriptors. Experiments show that the proposed method possesses the ability regarding abundant and integral person feature representation and improves the recognition rate of person re-identification in comparison with the existing mainstream methods. Related Articles | Metrics

Select

Visual gesture recognition technology based on long short term memory and deep neural network HE Jian1,2, LIAO Jun-jie2, ZHANG Cheng2, WEI Xin2, BAI Jia-hao2, WANG Wei-dong1,2 2020, 41(3): 372-381.  DOI: 10.11996/JG.j.2095-302X.2020030372 Abstract ( 78 )   PDF (2808KB) ( 220 )   Aiming at the problem that visual gesture recognition is susceptible to light conditions, background information and changes in gesture shape, this paper analyzed the spatial context features of human gestures. First, this paper established a dynamic gesture model based on the contour features of human skeleton and body parts. The convolutional pose machine (CPM) and the single shot multibox detector (SSD) technology were utilized to build deep neural network, so as to extract the contour features of human gesture skeleton and body parts. Next, the long short term memory (LSTM) network was introduced to extract the temporal features of skeleton, left and right hand, and head contour in dynamic human gestures, so as to further classify and recognize gestures. On this basis, this paper designed a dynamic gesture recognizer based on spatial context and temporal feature fusion (GRSCTFF), and conducted network training and experimental analysis on GRSCTFF through the video sample database of traffic police command gestures. The experimental results show that GRSCTFF can quickly and accurately recognize the dynamic traffic police command gestures with an accuracy of 94.12%, and it has strong anti-interference ability to light, background and gesture shape changes. Related Articles | Metrics

Select

Classification of engine main bearing cap parts using SIFT-SVM method SHI Zhi-liang, ZHANG Peng-fei, LI Xiao-yao 2020, 41(3): 390-398.  DOI: 10.11996/JG.j.2095-302X.2020030382 Abstract ( 66 )   PDF (5193KB) ( 155 )   The recognition and classification of mechanical components is a key process on the manufacturing automation line. In terms of the classification of the mixed and cleaned engine main bearing cap, through the analysis of the actual characteristics of the main bearing cap parts, the classification and recognition method for the main bearing cap based on SIFT-SVM was proposed. The method first extracted all scale-invariant feature transform (SIFT) feature vectors of the training dataset image, then employed the K-means clustering method to cluster all feature vectors into K classifications, and substituted the obtained K clustering results into the bag of word model (BoW). “Vocabulary” was utilized to describe each training image, thereby obtaining a BoW description of the image. The BoW description of each image served as a training input, and the classification model for the main bearing cap was trained using a support vector machine (SVM). The experimental results show that under the calibrated lighting conditions, the recognition rate of the main bearing cap parts can reach 100%, and the recognition time for a single part was 0.6 seconds, which verified the effectiveness and efficiency of the algorithm. Related Articles | Metrics

Select

Fusion of geometric and orientation information for 3D palmprint recognition WANG Xi1,2, GAI Shao-yan1,2, DA Fei-peng1,2 2020, 41(3): 390-398.  DOI: 10.11996/JG.j.2095-302X.2020030390 Abstract ( 41 )   PDF (1212KB) ( 108 )   In order to improve the robustness and accuracy of the feature representation of 3D palmprint, a method integrating the geometric and directional features of curved surfaces was proposed. Based on the existing method using the surface type (ST)-based coding to extract geometric features of a 3D palm, we proposed to use the shape index (SI)-based coding to jointly characterize the geometric features of 3D palmprints. This operation can effectively reduce the impact on accuracy brought by the error encoding caused by the threshold. Moreover, we proposed a multi-scale modified competitive coding (MSMCC) to characterize the orientation features. The multi-dictionary collaborative-representation (CR)-based framework was employed to merge the geometric and orientation features into the decision level to perform identification. Extensive experiments on the public 3D palmprint database prove that the proposed method can achieve an optimal rank-1 recognition accuracy while maintaining a relatively low computational complexity. Related Articles | Metrics

Select

Hyperbola extraction method based on multi-label hierarchical clustering algorithm of GPR images LI Wen-sheng, YUAN Da, MIAO Cui, WANG Dong-yu 2020, 41(3): 399-408.  DOI: 10.11996/JG.j.2095-302X.2020030399 Abstract ( 47 )   PDF (1282KB) ( 111 )   Hyperbola extraction in ground penetrating radar (GPR) images is an important feature to analyze the location and structure of underground objects. However, there are often some problems with the extracted hyperbola, such as incomplete structure, fragmentation, and shape anomalies, caused by the interference of noise and clutter that are typical of real environments. These issues are not conducive to the subsequent quantitative operations, such as data analysis and 3D modeling. In this context, this paper proposed a multi-label hierarchical clustering-based hyperbola extraction method (MHCE) for the hyperbola extraction of GPR images. Firstly, through evaluating the stability between pixel neighborhoods by the means of information entropy, an information entropy-based distance method was constructed to conduct the hierarchical clustering algorithm. Next, a multi-label clustering method was proposed based on the adjacency space of the clustering results, so as to reduce the influence of clutter and noise on hyperbola extraction. Finally, the hyperbola was extracted combined with the fitting shape and texture orientation of the multi-label clustering results. The experimental results show that this method is robust for GPR images and can be used to obtain the shape and position parameters of a normalized hyperbola. Related Articles | Metrics

Select

ForegroundNet: a semantic and motional feature based foreground detection algorithm LAI Shao-chuan1, WANG Jia-xin2,3, MA Cui-xia2 2020, 41(3): 409-416.  DOI: 10.11996/JG.j.2095-302X.2020030409 Abstract ( 54 )   PDF (687KB) ( 51 )   Aiming at the problem that the previous foreground detection methods depend more heavily on scene information, a real-time foreground detection deep learning model ForegroundNet without iteratively updating the background model is proposed. ForegroundNet extracts semantic features from current and auxiliary images with backbone networks firstly, the auxiliary images which can be either an adjacent image frame or an automatically generated background image. These features are further fed into deconvolution network with short connections, which make the final feature maps have the same size as input images and contain semantic and motional features in different scales, finally we use softmax layer to perform a binary classification. The results on CDNet dataset show that ForegroundNet achieves better F-Measure of 0.94 compare to the 0.82 of suboptimal method. More over ForegroundNet has good real-time performance that its speed reaches 123 fps. Related Articles | Metrics

Select

Study on the extraction and classification of EEG characteristics in ADHD patients based on Pearson’s optimal electrode selection ZOU Ling1,2, WU Fan1,2, BI Hui1,2, TIAN Bo-fan1,2, SONG Zhi-wei1,2, WANG Su-hong3 2020, 41(3): 417-423.  DOI: 10.11996/JG.j.2095-302X.2020030417 Abstract ( 264 )   PDF (671KB) ( 53 )   Event-related potential (ERP) can be used for EEG feature extraction and classification for children with attention deficit hyperactivity disorder (ADHD) and normal children. Firstly, the EEG signals of two kinds of children were collected by the gambling task paradigm. Secondly, the optimal electrode was selected based on the Pearson correlation coefficient algorithm, and the optimal electrode EEG signal was preprocessed. Then, time domain features (mean, variance, peak) and frequency domain features (Theta band power, Alpha band power) of pre-processed EEG signals were extracted. Finally, traditional classification methods (Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), Bootstrap Aggregating (Bagging), Linear Discriminant Analysis (LDA), Back Propagation (BP) and combined classifier classification methods (LDA-SVM, BP-SVM) were used to complete the classification of two kinds of EEG signals. The results demonstrate that the classification accuracy of traditional BP classifier was up to 80.52% and that of the combined classifier was up to 88.88%. The combined classification method can improve the classification accuracy for ADHD children and provide technical support for ADHD neurofeedback rehabilitation treatment based on the BCI technology. Related Articles | Metrics

Select

Extraction of spatial features of emotional EEG signals based on common spatial pattern YAN Meng-meng1, LV Zhao1,2, SUN Wen-hui1 2020, 41(3): 424-429.  DOI: 10.11996/JG.j.2095-302X.2020030424 Abstract ( 86 )   PDF (2208KB) ( 55 )   In order to enhance the performance of electroencephalogram (EEG)-based emotion recognition and improve the accuracy of multi-classification, a spatial filtering algorithm using the common spatial pattern (CSP) was proposed. Firstly, the traditional CSP method was used to design the spatial domain filter. On this basis, three types of emotion recognition EEG signals (i.e., positive, neutral, and negative) were linearly projected by this filter, so as to extract spatial features. Furthermore, considering that the traditional joint approximation diagonalization (JAD) algorithm using the “highest score eigenvalue” criterion may result in the failure to distinguish the multi-classification emotional states, different eigenvalue selection methods were designed in terms of the position of the eigenvalues with the highest scores. Under our lab environment, the comparative experiments using the support vector model (SVM) as a classifier have been carried out. The results show that the CSP-based spatial feature extraction method has an impressive accuracy of 87.54% on average in three-class emotion state recognition, proving the feasibility of the method in  the application of emotion recognition. Related Articles | Metrics

Select

Research on hull welding techniques based on knowledge engineering MA Guo-hui, TIAN Ling, LIU Si-chao, CHEN Jun-yu 2020, 41(3): 430-437.  DOI: 10.11996/JG.j.2095-302X.2020030430 Abstract ( 51 )   PDF (586KB) ( 58 )   In the process of shipbuilding, the knowledge in the field of hull welding is lack of effective induction, which results in poor reusability and sharing. To solve these problems, based on knowledge engineering technologies, this paper studies the methods of knowledge acquisition, classification, representation and reasoning application in hull welding and develops a knowledge base of techniques, which effectively realizes the sharing and reuse of knowledge. Firstly, a classification mode and access to acquire the knowledge of hull welding were put forward. Secondly, on this basis, the results of the research on knowledge representation method based on ontology was applied to the hull welding process and a domain ontology was established. Thirdly, a reasoning mode of welding process was put forward, and a rule base of process was established based on normative documents such as national standards and industry standards and instructive documents such as professional books and expert opinions, then a fuzzy rule reasoning system was designed. Finally a knowledge base system for hull welding process was designed and developed, and such functions were standardized as knowledge acquisition, knowledge representation, knowledge reasoning and knowledge management, providing support platform of knowledge sharing and reuse for related personnel in the field of hull welding, and providing implications for the use of knowledge engineering technologies in other fields of shipbuilding. Related Articles | Metrics

Select

Application research on the KJ/FA/TRIZ integration method in anterior maxillary traction appliance design ZHANG Fang-lan, YAO Wan-tong, LIU Long-ji 2020, 41(3): 438-445.  DOI: 10.11996/JG.j.2095-302X.2020030438 Abstract ( 56 )   PDF (1019KB) ( 49 )   Aimed at solving such problems as discomfort and inconvenience of the maxillary anterior traction appliance, an innovative design method based on FA and TRIZ was proposed. The relationship and the component interaction matrix between the functions and structures were established based on the FA. The TRIZ was adopted to analyze the connections between the interacted components and sub-functions, thus forming the function-field model. Its categories were divided based on the actual utility. Then 76 standard solutions were employed to address problems, thereby obtaining an improved design of appliance. Finite element analysis was made to evaluate the redesign scheme by giving the materials and forces. A comparative experiment was undertaken to evaluate the redesign scheme. Finally, the feasibility of the FA/TRIZ integration method and evaluation method was verified through the implementation of the innovative design of the maxillary anterior traction appliance. Related Articles | Metrics

Select

Research on product design scheme evaluation based on TOPSIS method of structure entropy weight CHEN Xiang, WEI Hua 2020, 41(3): 446-452.  DOI: 10.11996/JG.j.2095-302X.2020030446 Abstract ( 91 )   PDF (744KB) ( 63 )   In order to improve the efficiency of rational decision-making in the process of product design scheme evaluation, this paper proposed a method of product design scheme evaluation based on TOPSIS (technique for order preference by similarity to ideal solution) and the method of structure entropy weight. In the evaluation process, the evaluation indexes of product design scheme were determined first, and then the experts ranked each evaluation index based on its priority. After obtaining the “typical ranking”, the weight of each evaluation index was calculated through structural entropy calculation and “cognition blindness”, thus enabling itself to replace the weight coefficient set by experts in TOPSIS method. Next, the matrix of weighted standard decision-making for each index of design scheme was constructed, and then the ideal solution of each index was obtained. Based on the above procedures, the relative closeness degree of each design scheme to its ideal solution can be obtained, and the corresponding ranking of design schemes can be determined after comparison. Finally, the evaluation process was applied to the decision-making of the design scheme evaluation of recording pens, which verified the feasibility and effectiveness of this method. Related Articles | Metrics

Select

Evaluation method and application of rehabilitation training products  for autistic children based on AHP and TOPSIS WANG Mei-xue, ZHAI Hong-lei 2020, 41(3): 453-460.  DOI: 10.11996/JG.j.2095-302X.2020030453 Abstract ( 104 )   PDF (873KB) ( 62 )   In order to study the methods and processes for evaluating the design of rehabilitation training products for autistic children and to reduce the subjectivity and one-sidedness in selecting a scheme, AHP and TOPSIS methods were used to comprehensively evaluate the rehabilitation training products for autistic children. Firstly, the evaluation system for rehabilitation training products was constructed through literature research and interviews with experts. Secondly, the AHP method was employed to determine the weight of the evaluation elements, then the experts’ scoring method was utilized to establish an initial evaluation matrix. After standardizing the processing of matrix, we obtained weighted normalization matrix, which led to the positive ideal solution and negative ideal solution. Then the final ranking was in the manner of calculating the distance between each solution to be evaluated and the ideal solution. Finally, this method was verified. Based on the AHP and TOPSIS methods, the evaluation method for autistic children's rehabilitation training products realized the prioritization of 3 rehabilitation training products, which can reduce the subjectivity and one-sidedness in the evaluation of the design plan and will be conducive to the future rehabilitation training products for autistic children. The method provides experience for design evaluation and program optimization of rehabilitation products for autistic children in the future. Related Articles | Metrics

Select

Research on role modeling design of intervention card for autistic children based on visual cognition ZHAO Yu-wan1, ZHANG Bing-chen1, WANG Yan-qun2, SONG Li-shu3 2020, 41(3): 461-468.  DOI: 10.11996/JG.j.2095-302X.2020030461 Abstract ( 134 )   PDF (1878KB) ( 65 )   Based on the visual cognitive characteristics of autistic children, explorations were made on the visual image preference of autistic children, and analyses were conducted concerning the design elements of role modeling of intervention cards, thus giving full play to the effectiveness of intervention cards. First, through such channels as rehabilitation institutions, teaching aids, and special education websites, the intervention cards for autistic children currently circulated in the market were sorted out, a representative role model of the cards was selected, and the image analysis was made regarding the characteristics of the role model and the visual image vocabulary was sorted out based on the visual cognitive characteristics of autistic children. Then the semantic difference method was adopted to combine the visual image vocabulary with the map. The main factors of visual image were extracted by the factor analysis. Finally, the mapping relationship between visual cognitive preference and mental image factors of autistic children was constructed. Through the investigation and experiment, the representative role modeling of intervention cards was sorted out. If we combine the visual preference and image vocabulary of autistic children and adjust the modeling characteristics, the appeal of role modeling of intervention cards can be enhanced, the effectiveness of intervention training improved, and experience for teaching aids provided. Related Articles | Metrics

Select

Comprehensive evaluation and optimization method of products for the elderly based on FAHP and TOPSIS——a case study on the smart bracelet for the elderly YANG Mei, CONG Yang-fan, LI Xue-rui 2020, 41(3): 469-479.  DOI: 10.11996/JG.j.2095-302X.2020030469 Abstract ( 102 )   PDF (909KB) ( 86 )   In order to comprehensively evaluate the smart bracelet for the elderly more thoroughly, an evaluation model was established, so as to facilitate the evaluation and optimization of the final scheme. The model was established from such 4 dimensions as product design, user experience, human-computer interaction and practical production. Firstly, the fuzzy analytic hierarchy process (FAHP) method was employed based on the triangular fuzzy number to acquire weight values of every index. Then, the technique for order preference by similarity to ideal solution (TOPSIS) method was utilized to evaluate and order every scheme. An example could be found in 16 schemes of the smart bracelet for the elderly of a certain brand and prove the feasibility and practical significance of this FAHP-TOPSIS method. Such an evaluation and optimization method can help solve problems in consideration of the fuzzy thinking to systematize, hierarchize and quantify the thinking process. It can thus ultimately propose a clear evaluation scheme and optimized method for the smart bracelet for the elderly. Related Articles | Metrics

Select

Comparison method of BIM models based on component shape distribution and registration position WANG Jia1,2, WU Lei1, ZHOU Xiao-ping1,2, SONG Bing-yu3, LI Liang-hui4 2020, 41(3): 480-489.  DOI: 10.11996/JG.j.2095-302X.2020030480 Abstract ( 109 )   PDF (1920KB) ( 68 )   Various versions of BIM models will appear in different stages of the entire life cycle of a building, and the differences among these models can provide support for the decision-making in the construction and operation of the building. Most BIM model comparisons are based on visual inspection, manual counting, and selective inspection of attributes. Although some scholars and relevant institutions have studied some methods of automatic comparison of BIM models, most of them rely on the ID of components in the model, and the results of comparison cannot be directly reflected in specific components and attributes. Aimed at these problems, a comparison method of BIM models was proposed based on shape distribution and registration position, extracting features from components for component matching and compareing BIM models on the component level. Firstly, shape distribution of the components was constructed based on their geometric information to calculate the similarity between the shape distribution of components of similar types. Secondly, the positions of the components were matched and the similarity between the positions was calculated. Then two similarity degrees were combined to match components and the differences between matched components were compared. Finally, the difference between models was obtained, and WebGL was used for visual presentation. This method disregards the influence of the changes of component ID on model comparison, capable of working out the differences among models on the component level. Related Articles | Metrics

Select

Research on knowledge-based BIM for automated compliance checking system in architectural design CHEN Yuan, ZHANG Yu, KANG Hong 2020, 41(3): 490-499.  DOI: 10.11996/JG.j.2095-302X.2020030490 Abstract ( 200 )   PDF (958KB) ( 110 )   It is of great significance to conduct the research on automated compliance checking system of architectural design, in terms of ensuring that the building information model (BIM) meets the design rules requirements and increasing the degree of automated compliance checking. Combined with the theory of compliance checking and the expert system method, this research proposed the framework of the automatic compliance checking system with BIM as the test target, and realized the compliance checking process by separating rule knowledge from reasoning mechanism. Taking the Design code for residential buildings as an example, this paper conducted the knowledge analysis on the provisions in the specification, summarized the expression of code knowledge, as well as built the rule base and the access mechanism to the rule base. Next, the reasoning mechanism under logical strategy was established. Through reasoning the rule information and BIM information in the rule base, checking results were output. Finally, this paper constructed a verification platform of compliance checking system, completed the process of model data extraction and rule reasoning through BIM examples, realized the function of compliance checking, and verified the framework of compliance checking method. The structure of the compliance checking method proposed in this research is more comprehensive and can therefore guide the follow-up research. This automated compliance checking system can effectively improve the efficiency of BIM compliance checking, ensure the quality of checking, and promote the development of informatization in the field of construction engineering. Related Articles | Metrics