Abstract depiction of human figures in impressionist art and children’s picture books
چکیده ای از چهره های انسان در هنرهای تجسمی و کتاب های تصویری کودکان-2019
The human figure is important in art. I discuss examples of the abstract depiction of the human figure, from both impressionist painting and children’s book illustration, and the challenge faced in algorithmically mimicking what human artists can achieve. I demonstrate that there are excellent examples in both genres that provide insight into what a human artist sees as important in providing abstraction at different levels of detail. The challenge lies in the human brain having enormous knowledge about the world and an ability to make fine distinctions about other humans from posture, clothing and expression. This allows a human to make assumptions about human figures from a tiny amount of data, and allows a human artist to take advantage of this when creating art. The question for the computer graphics community is whether and how we could algorithmically mimic what a human artist can do. I provide evidence from both genres to suggest possible ways forward.
Keywords: Impressionism | Abstraction | Representation | Perception
Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding
تشخیص نقص تصویر جوش تشخیص عمیق مبتنی بر یادگیری عمیق برخط با استفاده از شبکه های عصبی همگرا برای آلیاژ آل در جوش قوس رباتیک-2019
Accurate on-line weld defects detection is still challenging for robotic welding manufacturing due to the complexity of weld defects. This paper studied deep learning–based on-line defects detection for aluminum alloy in robotic arc welding using Convolutional Neural Networks (CNN) and weld images. Firstly, an image acquisition system was developed to simultaneously collect weld images, which can provide more information of the real-time weld images from different angles including top front, top back and back seam. Then, a new CNN classification model with 11 layers based on weld image was designed to identify weld penetration defects. In order to improve the robustness and generalization ability of the CNN model, weld images from different welding current and feeding speed were captured for the CNN model. Based on the actual industry challenges such as the instability of welding arc, the complexity of the welding environment and the random changing of plate gap condition, two kinds of data augmentation including noise adding and image rotation were used to boost the CNN dataset while parameters optimization was carried out. Finally, non-zero pixel method was proposed to quantitatively evaluate and visualize the deep learning features. Furthermore, their physical meaning were clearly explained. Instead of decreasing the interference from arc light as in traditional way, the CNN model has taken full use of those arc lights by combining them in a various way to form the complementary features. Test results shows that the CNN model has better performance than our previous work with the mean classification accuracy of 99.38%. This paper can provide some guidance for on-line detection of manufacturing quality in metal additive manufacturing (AM) and laser welding.
Keywords: Deep learning | Defects detection | Al alloy | Robotic arc welding | Convolutional neural networks | Weld images | Feature visualization
Key Time Steps Selection for CFD Data based on Deep Metric Learning
انتخاب مراحل زمانی کلیدی برای داده های CFD بر اساس یادگیری عمیق متریک-2019
As one of the main technologies of flow visualization, key time steps selection plays a key role in solving storage limit and has been intensively studied. In this paper, we introduce Deep Metric Learning (DML) into key time steps selection for Computational Fluid Dynamics (CFD) data and propose a local selection method based on DML. In specific, the proposed method samples small patches from CFD data, trains a Siamese deep neural network which has a symmetry structure with two Convolutional Neural Networks (CNN), and then selects the key time steps according to the similarities between consecutive time steps which are assessed by the networks. Compared with one of the existing local selection methods, the Myers’s method, our method has advantages in accuracy, precision and recall, and the selection results are better. Experimental results also demonstrate the good generalization of the proposed method on CFD datasets.
Keywords: flow visualization | key time steps selection | CFD flow field | deep metric learning
Marketing analytics: Methods, practice, implementation, and links to other fields
تجزیه و تحلیل بازاریابی: روش ها ، تمرین ، اجرا و پیوند به زمینه های دیگر-2019
Marketing analytics is a diverse field, with both academic researchers and practitioners coming from a range of backgrounds including marketing, expert systems, statistics, and operations research. This paper provides an integrative review at the boundary of these areas. The aim is to give researchers in the in- telligent and expert systems community the opportunity to gain a broad view of the marketing analytics area and provide a starting point for future interdisciplinary collaboration. The topics of visualization, segmentation, and class prediction are featured. Links between the disciplines are emphasized. For each of these topics, a historical overview is given, starting with initial work in the 1960s and carrying through to the present day. Recent innovations for modern, large, and complex “big data”sets are described. Prac- tical implementation advice is given, along with a directory of open source R routines for implementing marketing analytics techniques.
Keywords: Analytics | Prediction | Marketing | Visualization | Segmentation | Data mining
Toward a taxonomy of entrepreneurship education research literature: A bibliometric mapping and visualization
به سمت طبقه بندی ادبیات تحقیق در زمینه آموزش کارآفرینی: یک نقشه برداری و تجسم کتابشناختی-2019
The retrospective amount of research literature dedicated to entrepreneurship education (EE) is overwhelming, which makes producing an overview difficult. However, advanced bibliometric mapping and clustering techniques can help visualize and structure complex research literature. Thus, the objective of this mapping study is to systematically explore and cluster the EE research literature to deliver a taxonomic scheme that can serve as a basis for future research. The analyzed data, which were drawn from the Web of Science and Scopus, consist of 1773 peer-reviewed documents published between 1975 and 2014. On the one hand, this taxonomy should create stronger ties to educational research; on the other, it can foster international research collaboration to boost both interdisciplinary EE and its impact on a global basis. This work reinforces our understanding of current EE research by identifying and distilling the most powerful intellectual relationships among its contributions and contributors. Consequently, this study addresses not only the academic community but also entrepreneurship educators and policymakers in an effort to boost entrepreneurial spirit, design effective policy instruments, and, ultimately, improve societal welfare.
Keywords: Entrepreneurship education | Bibliometric mapping | Bibliometric visualization | Systematic mapping study | TaxonomyJEL classification:L26 | Entrepreneurship
Interactive visualization and analysis of antihypertensive prescriptions using National Health Insurance claims data
بصری سازی تعاملی و تحلیل نسخه های ضد فشار خون با استفاده از ادعاهای بیمه ملی بهداشت و درمان-2018
Interactive visualization is an important approach to help to understand and to explain large amounts of data, particularly in light of decision support. Although data visualization have been introduced in healthcare and clinical fields, analytics has often been performed by data experts, focused on specific subjects, or insufficient statistical evidence. Therefore, this study suggests the procedures of effective and efficient visualization of big data for general healthcare researchers. Specifically, the procedure includes conventional regression analyses followed by interactive data visualization for prescription patterns of antihypertensive drugs. Methods: As a large-scale nationally representative prescription data, the Korean National Health Insurance claims data were collected. Conventional descriptive and regression analyses were conducted for therapy decision and prescription patterns using the software R. Then, based on the statistically significant findings, dashboards were developed to visualize interactively the patterns of prescriptions using the software Tableau. Results: Major characteristics (genders, age groups, healthcare institutions, and comorbidities) explained the differences in therapy and the average number of drugs prescribed as well as differences among most commonly prescribed drug classes. Two interactive dashboards were created for visualizing prescription patterns with incorporation of horizontal bar charts, packed bubble charts, treemaps, filled maps, radar charts, box and whisker plots, and filters. Conclusion: In the current big data era, interactive data visualization offers substantial opportunities to have comprehensive view, extract insights and evidence from the flood of vast amounts of data. This study’s interactive visualizations can provide healthcare professionals insight into prescription patterns and demonstrate the value of creating interactive dashboards to support informed and timely decision-making. Exploring big data using interactive visualization is expected to deliver many future benefits in healthcare fields.
Keywords: Prescriptions; National Health Insurance Claims database; Hypertension; Interactive Visualization
A survey towards an integration of big data analytics to big insights for value-creation
مروری به سوی تجمیع تحلیل داده های بزرگ به بینشی بزرگ برای ایجاد ارزش-2018
Big Data Analytics (BDA) is increasingly becoming a trending practice that generates an en ormous amount of data and provides a new opportunity that is helpful in relevant decision making. The developments in Big Data Analytics provide a new paradigm and solutions for big data sources, storage, and advanced analytics. The BDA provide a nuanced view of big data development, and insights on how it can truly create value for firm and customer. This article presents a comprehensive, well-informed examination, and realistic analysis of deploying big data analytics successfully in companies. It provides an overview of the architecture of BDA including six components, namely: (i) data generation, (ii) data acquisition, (iii) data storage, (iv) advanced data analytics, (v) data visualization, and (vi) decision-making for value-creation. In this paper, seven Vs characteristics of BDA namely Volume, Velocity, Variety, Valence, Veracity, Variability, and Value are explored. The various big data analytics tools, techniques and tech nologies have been described. Furthermore, it presents a methodical analysis for the usage of Big Data Analytics in various applications such as agriculture, healthcare, cyber security, and smart city. This paper also highlights the previous research, challenges, current status, and future di rections of big data analytics for various application platforms. This overview highlights three issues, namely (i) concepts, characteristics and processing paradigms of Big Data Analytics; (ii) the state-of-the-art framework for decision-making in BDA for companies to insight value-crea tion; and (iii) the current challenges of Big Data Analytics as well as possible future directions.
Keywords: Big data ، Data analytics ، Machine learning ، Big data visualization ، Decision-making ، Smart agriculture ، Smart city application ، Value- reation ، Value-discover ، Value-realization
سرمایه اجتماعی، سرمایه انسانی، و پایداری: یک تحلیل کتاب شناسی و تصویری
سال انتشار: 2018 - تعداد صفحات فایل pdf انگلیسی: 19 - تعداد صفحات فایل doc فارسی: 39
توجه آکادمیک به سرمایه اجتماعی و انسانی، رشد فزاینده ای را شاهد است. به همین صورت، رابطه این دو با پایداری نیز گسترش یافته، به خصوص در مقایسه با رابطه پایداری با سرمایه طبیعی و سرمایه مالی و اقتصادی. با این وجود، تحقیقات کتاب شناسی و تصویری روی این روابط هنوز کافی نیست. این مطالعه اقدام به تحلیل روند تکامل تحقیقات در مورد سرمایه طبیعی، سرمایه مالی و اقتصادی، و سرمایه اجتماعی و انسانی مرتبط با پایداری می کند. از سوی دیگر، این مطالعه یک تحلیل کتاب شناسی در مورد سرمایه اجتماعی و سرمایه انسانی (SHC) مرتبط با پایداری ارائه می کند. این مطالعه، 635 منبع گردآوری شده از «وبِ علم» (WoS) در بخش دیتابیس مجموعه اصلی را بررسی کرده و از برنامه مشاهده کننده تسجم مشابهت ها (VOS) برای نقشه بندی گرافیکی مطالب استفاده می کند. این تحلیل شامل بررسی وجود همزمان کلیدواژه ها، استناد همزمان و تألیف همزمان می باشد. نتایج نه تنها جدیدترین و کامل ترین روندها را نشان می دهند، بلکه روند تکامل مربوط به انتشارات، ژورنال های مهم، اسناد، موضوعات، نویسندگان، نهادها و کشورها را تحلیل می نمایند. این مطالعه یک چارچوب بصری و ساختاری از تحقیقات مربوط به این حوزه برای محققین و کارشناسان ارائه می کند.
واژگان کلیدی: سرمایه اجتماعی | سرمایه انسانی | کتاب شناسی | تجسم
|مقاله ترجمه شده|
Initiating a system for visualizing and measuring dynamic knowledge
آغاز یک سیستم برای تجسم و اندازه گیری دانش پویا-2018
Knowledge is key to sustainable competitive advantage, but different kinds of knowledge affect competitive advantage differently, and they exhibit qualitatively different dynamic properties and behaviors. This places particular importance on understanding the dynamics of knowledge as it flows, and organization managers seek to visualize and measure such flows for efficacy and efficiency alike. Unfortunately, knowledge is inherently intangible, invisible and resistant to quantification, particularly when in dynamic motion. Moreover, managing key organization knowledge is left often to haphazard, trial and error processes, rendering pursuits of sustainable competitive advantage daunting at best and infeasible in many cases. Even when guided by well-accepted models in extant theory, managers may not be selecting the best knowledge flow processes for their purposes. The research described in this article builds upon Knowledge Flow Theory and application to initiate a system for visualizing and measuring dynamic knowledge. We leverage a multidimensional model to delineate and analyze a diversity of knowledge as it flows through the organization, and we draw analogically to develop a system of dynamic knowledge equations that enable measurement. We then illustrate its practical use and utility through a representative organization example, which we supplement with decision guidance pertaining to some funda mental knowledge flow tradeoffs facing decision makers. This article closes with a summary of key results and implications, which give us cause to rethink some concepts, assumptions and implications in the literature.
Keywords: Knowledge ، Knowledge flow ، Knowledge management ، Knowledge flow theory ، Dynamics ، Measurement
A soft computing approach to big data summarization
رویکرد محاسباتی نرم برای خلاصه سازی داده های بزرگ-2018
The added value of a dataset lies in the knowledge a domain expert can extract from it. Considering the continuously increasing volume and velocity of these datasets, efficient tools have to be defined to generate meaningful, condensed and human-interpretable representations of big datasets. In the proposed approach, soft computing techniques are used to define an interface between the numerical and categorical space of data definition and the linguistic space of human reasoning. Based on the expert’s own vocabu lary about the data, a personal summary composed of linguistic terms is efficiently generated and graphically displayed as a term cloud offering a synthetic view of the data properties. Using dedicated indexing strategies linking data and their subjective linguis tic rewritings, exploration functionalities are provided on top of the summary to let the user browse the data. Experimentations confirm that the space change operates in linear time wrt. the size of the dataset making the approach tractable on large scale data.
Keywords: Data personalisation; Linguistic summaries; Soft computing; Knowledge extraction; Visualization; Specificity measure