{"title":"Comparing Performance and Efficiency of Designers and Design Intelligence","authors":"Zhenlin Song, Linyun Sun","doi":"10.1109/ISCID52796.2021.00022","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00022","url":null,"abstract":"Intelligent design has been an emerging important area in the design. Existing works related to intelligent design use objective indicators to measure the quality of AI design by comparing the differences between AI-generated data and real data. However, the level of quality and efficiency of intelligent design compared to human designers remains unclear. We conducted user experiments to compare the design quality and efficiency of advanced design methods with that of junior designers. The conclusion is advanced intelligent design methods are comparable with junior designers on painting. Besides, intelligent design uses only 10% of the time spent by the junior designer in the tasks of layout design, color matching, and video editing.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130917630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Customer Preference-centered Method of Exhibition Design Trend Forecasting","authors":"Ruiyi Cai, Chunlei Chai, Xingxing Yi","doi":"10.1109/ISCID52796.2021.00059","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00059","url":null,"abstract":"In exhibition design, there is usually a difference between the design intention and the customer's actual experience. Therefore, it is necessary to incorporate customer preferences into the design strategy generation system. This article proposes a customer preference-centered trend forecasting method for exhibition design, and verifies its feasibility through a case study. This method is based on a set of standardized procedures, including fitting the relationship between customer preferences and design features, and trend prediction based on historical data. The article aims to support the proposal of user preference-centered design strategies, eliminate the perception difference between designers and customers, and provide guidance for practical applications.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129728281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yujia Lu, W. You, Chang-yuan Yang, Shi Chen, Yuxi Wang, Lingyun Sun
{"title":"An Explainable XGBoost-based Approach for Assessing Product Presentation Video","authors":"Yujia Lu, W. You, Chang-yuan Yang, Shi Chen, Yuxi Wang, Lingyun Sun","doi":"10.1109/ISCID52796.2021.00034","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00034","url":null,"abstract":"Product presentation video, an essential medium for online product presentation, mainly conveys product information to consumers. The quality of product information expression will affect consumer's purchase experience, even purchase decisions. But many video production novices often have difficulty assessing the effectiveness of their videos and doing optimization. Thus, we adopt information mediums' perceived usefulness and perceived ease of use as assessment indicators, and propose an automatic explainable assessment method. The method is based on the combined use of the extreme gradient boosting algorithm and SHapley Additive exPlanations method, which is implemented to assess video samples and generate explanations on the assessment results. We create a product presentation video dataset for development and evaluation. The results show that our method can assess video effectively, and provide insights into the shortcomings of videos' production like experts.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129853540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on crew-level maintenance strategy for ship equipment based on risk-based decision","authors":"R. Zhang, Jinlin Liu, Zheng Gu","doi":"10.1109/ISCID52796.2021.00029","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00029","url":null,"abstract":"Aiming at the problems of “excessive maintenance” in the current maintenance strategy for ship equipment and crew level, which leads to insufficient effective use period of equipment, waste of maintenance resources, and difficulty in identifying potential equipment failures, based on the risk decision theory, the ship equipment maintenance strategy model is established, and the analytic hierarchy process and the Delphi method are applied to obtain the dangerous impact value of each fault. On this basis, a reasonable maintenance support strategy is formulated according to the evaluation result to solve the existing maintenance strategy. The existing problems provide theoretical support. Based on the research results of this paper, the risk evaluation model of a shaft system intermediate bearing is established, and the risk maintenance strategy of this bearing is formulated. In order to improve the scientific nature of the maintenance strategy of this bearing, the validity of the research results of this paper is verified at the same time.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128554813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Mining Resident Activity Pattern Based on Spatio-temporal Trajectory Data","authors":"Jiangyue Sun, Zhentao Zhang, Haibo Chen, Daolei Liang","doi":"10.1109/ISCID52796.2021.00075","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00075","url":null,"abstract":"The research on residents' activity pattern based on spatio-temporal trajectory data is helpful to the optimization of urban operation. At present, one of the difficulties in the research is how to determine the regularity of residents' activities when the labeled samples are sparse. We propose an improved periodic decision algorithm of sliding window, combined with feedforward neural network to search outlier activity patterns. Experimental results show that our method can effectively classify the overall travel features and quantify individual activity abnormalities.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130661628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Locally Linear Embedding Based on t-Distribution Grasshopper Optimization Algorithm","authors":"Ming Li, Zan Yang, Dan Li, Wei Nai, Y. Xing","doi":"10.1109/ISCID52796.2021.00078","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00078","url":null,"abstract":"Locally linear embedding (LLE) is a classical nonlinear dimensionality reduction algorithm for manifold learning in the field of machine learning (ML). The main idea of LLE is to pursue the linear isomorphism in the algebraic relationship between high-dimensional spatial data and low-dimensional spatial data after dimensionality reduction, and obtain the projection points of low-dimensional space by solving two optimization sub-problems. The optimization part of LLE is usually solved by gradient descent (GD) method. however, GD method has many disadvantages, such as easy to fall into the trap of local minimum, the closer to the optimal solution, the easier it is to show sawtooth effect. In order to overcome the above difficulties, in this paper, an LLE based on t-distribution grasshopper optimization algorithm has been proposed, it uses t-distribution grasshopper optimization algorithm which is a gradient independent swarm intelligence algorithm to replace GD for parameter optimization. Via numerical experiment, the effectiveness of the proposed algorithm has been proved.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126829518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design Semantic Typicality Calculation in Conceptual Spaces","authors":"Linna Zhu, Chengyu Lin, Jiangjie Huang","doi":"10.1109/ISCID52796.2021.00008","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00008","url":null,"abstract":"The assessment of typicality is a vital aspect of design evaluations. Based on the theories of fuzzy semantic cell and feature prototype model (FPM), we proposed an objective method to measure design semantic typicality. Design semantic typicality was assessed based on the Euclidian distances between a design case and its prototype. It could be calculated by the mean distance between the prototypes of design features and the prototype of the benchmark category in conceptual spaces. We validate this method in two experiments. Based on the analysis of empirical and experimental results, we confirmed that the proposed method is a promising approach to quantify design semantic typicality, which is able to largely reflect the human perception of design typicality.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126568413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Method for improving Data Quality of Large-scale Simulation","authors":"Zhijun Han, Wei Li","doi":"10.1109/ISCID52796.2021.00046","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00046","url":null,"abstract":"Data quality has always been a concern for both system developers and users, especially in recent years, the accuracy and reliability of data in the application of some large simulation systems are becoming more and more imporant. Based on the six-grade scale model, firstly this paper sets on an index hierarchy of data quality evaluation and its weights, in order to understand the comprehensive status of large-scale simulation system data quality, then based on pearl curve function establishes data fitting model, and from the curve which we got can be directly seen the relationship between funding strength and data quality. At last based on the fund allocation model of genetic algorithm, we can promot the continuous improvement of the data quality, and further improve credibility of the large-scale large simulation system.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121222245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Study on wearability of light-weight and broken weft denim","authors":"Xiaoying Zhu, Min Huang, Si Chen, Zimin Jin","doi":"10.1109/ISCID52796.2021.00048","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00048","url":null,"abstract":"In this paper, we designed a kind of weft backed weave denim fabric. Two experimental factors were designed:structure and weft density. Six denim samples were prepared according to the whole scheme sample design, and tested crease recovery, moisture permeability, air permeability, drapability of the sample. Using a fuzzy comprehensive evaluation method studied on the relationship between wearability, fabric structure and weft density. The results show that the crease recovery, moisture permeability, air permeability, drapability of the sample is better. When the face weave is 1/7 right twill and the weft density is 20 yarn/cm, the crease recovery, moisture permeability and air permeability of the sample was better. when the face weave is 1/5 right twill and the weft density is 25 yarn/cm.the drapability of the sample was better. When the face weave is 1/5 right twill, the back weave is plain weave and the weft density is 20 yarn/cm.the wearability of light-weight and broken weft denim is better. The purpose of this study is to explore a better wearability scheme of light-weight and broken weft denim, and provide some reference for the development of new denim.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133492002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development Study on CBTC Related Techniques Based on Systematically Analyzing Granted Invention Patents of Past 20 Years","authors":"Yuchao Hu, Tianlun Zhong, Qi Wang, Wei Nai","doi":"10.1109/ISCID52796.2021.00077","DOIUrl":"https://doi.org/10.1109/ISCID52796.2021.00077","url":null,"abstract":"In the past 20 years or more, a new type of train operation and control system (OCS) - communication based train control (CBTC) has been widely concerned and studied by rail transit signal industry. CBTC is characterized by two-way communication between the train and ground through wireless communication, which is used to replace the track circuit to realize train operation control. Discussing the development of CBTC related technologies in the past 20 years is of certain significance to understand the development of urban rail transit. Till now, scholars have studied a variety of technologies involved in CBTC and multiple stages of system development, but the relevant research is mostly limited to the function and performance of CBTC in one aspect. As the invention patents applied in this field can be regarded as the best material for analyzing the development of CBTC related technologies, in this paper, through the search and analysis of CBTC related patents in the past 20 years, the development direction of CBTC related technologies has been clarified, and the development trend of CBTC and its related technologies has also been pointed out.","PeriodicalId":332239,"journal":{"name":"2021 14th International Symposium on Computational Intelligence and Design (ISCID)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133963708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}