Proceedings of the 3rd International Conference on Applications of Intelligent Systems最新文献_第4页

Towards a Generalized System for Generative Engineering 面向生成工程的广义系统

Proceedings of the 3rd International Conference on Applications of Intelligent Systems Pub Date : 2020-01-07 DOI: 10.1145/3378184.3378227

Deepak Nagaraj, Dirk Werth

{"title":"Towards a Generalized System for Generative Engineering","authors":"Deepak Nagaraj, Dirk Werth","doi":"10.1145/3378184.3378227","DOIUrl":"https://doi.org/10.1145/3378184.3378227","url":null,"abstract":"Product design based on mechanical performance requirements and with given boundary conditions is a frequent and demanding engineering problem. In most cases, effectiveness of the design is limited to expertise of the respective designer, which also results in inefficient and incomplete exploration of the product's design space. With a large amount of data available and recent advancements in hardware technology, data-driven methods have become an increasingly common strategy for problems that are difficult to formulate or expensive to solve by creating a physical model, but such methods often lack the application perspective; they are not yet widely applied especially in engineering product development. Generative design (here, more precisely generative engineering) is one such technique which has recently gained importance. Although many preliminary studies demonstrate plausible results from data-driven generative design approaches, a closeloop-3D-generative-design-pipeline that achieves full automation and optimization of the design with respect to the product's functional requirements is still in its nascent stage. This paper proposes a generalized hybrid framework comprised of both data-based and physics-based methods to achieve this objective, as represented by the teaser figure 1. An overview of various possibilities for individual modules of the framework is also discussed.","PeriodicalId":437507,"journal":{"name":"Proceedings of the 3rd International Conference on Applications of Intelligent Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131630138","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}

引用次数: 3

Do CNN's features correlate with human fixations? CNN的特色节目与人类的关注有关联吗?

Proceedings of the 3rd International Conference on Applications of Intelligent Systems Pub Date : 2020-01-07 DOI: 10.1145/3378184.3378197

Marinella Cadoni, A. Lagorio, E. Grosso

{"title":"Do CNN's features correlate with human fixations?","authors":"Marinella Cadoni, A. Lagorio, E. Grosso","doi":"10.1145/3378184.3378197","DOIUrl":"https://doi.org/10.1145/3378184.3378197","url":null,"abstract":"In recent years, CNNs are capturing the attention of a large community of researchers, attracted by the high performance of this approach and by the surprising results obtained in many recognition/classification activities. Unfortunately, the excellent performance of CNN-based systems is accompanied by a worryingly poor understanding of why they work so well. In this document, the basic mechanisms related to the extraction of points of interest (following the first convolution phases) are considered and compared to human fixations, with the aim of better understanding analogies and differences between computational models and human recognition. Alongside, the points of interest extracted from different layers are compared in order to evaluate similarity between different networks and the how interest points evolve within the same network. Human fixations and points of interest are initially used to construct density distribution maps; a novel similarity index is then proposed in order to compare these distribution maps. Experiments on the ETD database show that human fixations, on average, tend to be contained in the density of CNN points. In other words, human fixations seem to somehow optimize the active exploration of the image by properly using the information coming from the periphery of the visual field. These first interesting results could condition emerging models for visual recognition and visual indexing, pushing towards a more attentive exploitation of coarse structural information.","PeriodicalId":437507,"journal":{"name":"Proceedings of the 3rd International Conference on Applications of Intelligent Systems","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131108116","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}

引用次数: 4

Transfer Learning based Computer Vision Technology for Assisting Visually Impaired for detection of Common Places 基于迁移学习的计算机视觉技术辅助视障人士识别公共场所

Proceedings of the 3rd International Conference on Applications of Intelligent Systems Pub Date : 2020-01-07 DOI: 10.1145/3378184.3378215

Lalita Jaiswar, Anjali Yadav, M. Dutta, C. Travieso-González, Luis Esteban-Hernández

引用次数: 2

Segmification Segmification

Proceedings of the 3rd International Conference on Applications of Intelligent Systems Pub Date : 2020-01-07 DOI: 10.1145/3378184.3378190

Vladislav Ostankovich, R. Yagfarov

引用次数: 2

The value of personal data is the Data Protection and Privacy preliminary condition: synthetic human profiles on the web and ethics 个人数据的价值是数据保护和隐私的先决条件:在网络和道德上合成人类档案

Proceedings of the 3rd International Conference on Applications of Intelligent Systems Pub Date : 2020-01-07 DOI: 10.1145/3378184.3378231

N. Fabiano

引用次数: 2