دانلود و نمایش مقالات مرتبط با Libraries::صفحه 1
بلافاصله پس از پرداخت دانلود کنید
نتیجه جستجو - Libraries

تعداد مقالات یافته شده: 39
ردیف عنوان نوع
1 Computer vision for anatomical analysis of equipment in civil infrastructure projects: Theorizing the development of regression-based deep neural networks
چشم انداز کامپیوتری برای تجزیه و تحلیل آناتومیکی تجهیزات در پروژه های زیرساختی عمرانی: نظریه پردازی توسعه شبکه های عصبی عمیق مبتنی بر رگرسیون-2022
There is high demand for heavy equipment in civil infrastructure projects and their performance is a determinant of the successful delivery of site operations. Although manufacturers provide equipment performance hand- books, additional monitoring mechanisms are required to depart from measuring performance on the sole basis of unit cost for moved materials. Vision-based tracking and pose estimation can facilitate site performance monitoring. This research develops several regression-based deep neural networks (DNNs) to monitor equipment with the aim of ensuring safety, productivity, sustainability and quality of equipment operations. Annotated image libraries are used to train and test several backbone architectures. Experimental results reveal the pre- cision of DNNs with depthwise separable convolutions and computational efficiency of DNNs with channel shuffle. This research provides scientific utility by developing a method for equipment pose estimation with the ability to detect anatomical angles and critical keypoints. The practical utility of this study is the provision of potentials to influence current practice of articulated machinery monitoring in projects.
keywords: هوش مصنوعی (AI) | سیستم های فیزیکی سایبری | معیارهای ارزیابی خطا | طراحی و آزمایش تجربی | تخمین ژست کامل بدن | صنعت و ساخت 4.0 | الگوریتم های یادگیری ماشین | معماری های ستون فقرات شبکه | Artificial intelligence (AI) | Cyber physical systems | Error evaluation metrics | Experimental design and testing | Full body pose estimation | Industry and construction 4.0 | Machine learning algorithms | Network backbone architectures
مقاله انگلیسی
2 یادگیری عمیق برای تشخیص اشیا و درک صحنه در خودروهای خودران: نظرسنجی ، چالش ها و مسائل باز
سال انتشار: 2021 - تعداد صفحات فایل pdf انگلیسی: 20 - تعداد صفحات فایل doc فارسی: 82
این مقاله یک بررسی جامع از کاربرد های یادگیری عمیق برای تشخیص اشیا و درک صحنه در وسایل نقلیه خودران ارائه میکند. برخلاف مقالات مروری موجود ، ما تئوری زیربنایی وسایل نقلیه خودران را از منظر یادگیری عمیق و پیاده سازی های فعلی بررسی میکنیم وبه دنبال آن ارزیابی های انتقادی آن ها انجام میشود. یادگیری عمیق یکی از راه حل های بالقوه برای مشکلات تشخیص اشیا و درک صحنه است که میتواند خودروهای الگوریتم محور و داده محور را فعال کند. در این مقاله قصد داریم از طریق یک نظرسنجی جامع ، شکاف بین یادگیری عمیق و خودروهای خودران را پر کنیم. ما با مقدمه ای برماشین های خودران، یادگیری عمیق و بینایی کامپیوتری و سپس مروری بر هوش عمومی مصنوعی شروع میکنیم. سپس، کتابخانه های قدرتمند یادگیری عمیق موجود و نقش و اهمیت آنها در رشد یادگیری عمیق را طبقه بندی می کنیم. در نهایت، ما چندین تکنیک را مورد بحث قرار میدهیم که به مسائل مربوط به درک تصویر در رانندگی بلادرنگ میپردازد، و پیاده سازی ها و آزمایش های اخیر انجام شده بر روی خودروهای خودران را به طور انتقادی ارزیابی میکنیم. یافته ها و اقدامات در مراحل مختلف برای ارتباط بین تکنیک های رایج و آینده نگر، و کاربرد، مقیاس پذیری و امکان پذیری یادگیری عمیق در خودروهای خودران برای دستیابی به رانندگی ایمن بدون دخالت انسان خلاصه شده اند. بر اساس نظرسنجی فعلی، چندین توصیه برای تحقیقات بیشتر درپایان این مقاله موردبحث قرار گرفته است.
کلید واژه ها: ماشین ها ی خودران | سطوح اتوماسیون | یادگیری ماشین | یادگیری عمیق | شبکه های عصبی کانولوشنال | درک صحنه | تشخیص اشیا | همجوشی حسگر چند وجهی | LiDAR | بینایی ماشین | ابتکارات رانندگی مستقل
مقاله ترجمه شده
3 Big data management capabilities and librarians innovative performance: The role of value perception using the theory of knowledge-based dynamic capability
قابلیت های مدیریت داده های بزرگ و عملکرد نوآورانه کتابداران: نقش ادراک ارزش با استفاده از تئوری قابلیت پویایی مبتنی بر دانش-2021
This study extended the concept of knowledge-based dynamic capabilities from a firm level to individual level and investigated the relationship between big data management capabilities and innovative performance of university librarians in selected Ghanaian universities. The role of big data value perception as a mediator was also assessed using the PLS-SEM. Data were validated with Cronbach’s alpha above 0.8 and with factor analysis and further convergent and discriminant validity tests. AVE values were higher than 0.5 and CR above AVE and discriminant validity test scores below 0.6. Statistical significance was at a P-value of 0.05. Knowledge-based dynamic capabilities (KDC) were found not to have a direct significant influence on innovative performance (IP) (r2 = 0.109) of librarians. However, KDC positively influenced the perceived value for big data management (BDVP) (r2 = 0.674) with the later having a significant effect on the innovative performance of librarians (r2 = 0.777). BDVP among librarians was found to significantly mediate the relationship between KDC and IP such that KDC indirectly recorded a higher path coefficient (r2 = 0.524) than its initial direct effect of 0.109. Library managers and librarians are encouraged to develop big data management capability of staff to help create positive perceptions about the relevance of the field to enhance innovation and improved performance.
keywords: توانایی پویا مبتنی بر دانش | عملکرد نوآورانه | مدیریت داده های بزرگ | کتابخانه ها | علم اطلاعات | Knowledge-based dynamic capability | Innovative performance | Big data management | Libraries | Information science
مقاله انگلیسی
4 Assessment of customer knowledge management in academic libraries: Design and validation of a checklist
ارزیابی مدیریت دانش مشتری در کتابخانه های دانشگاهی: طراحی و اعتبار سنجی چک لیست-2021
A review of the research background shows that despite the usability of customer knowledge for libraries, the concept of Customer Knowledge Management (CKM) in libraries is rarely addressed. The purpose of this study was to identify the indicators, operational instances as well as the design and validation of an all-inclusive CKM implementation instrument in academic libraries. The study was conducted in two quantitative and qualitative phases. The final instrument was a CKM strategy that consisted of various indicators preliminary designed by drawing on literature review, and operational instances identified by qualitative interviews with 12 academic library managers. A Delphi study with 20 experts was used to assess the experts’ degrees of agreement on the retrieved indicators and instances. The result was a reliable and valid checklist consisting of 67 instances under 6 major and 12 minor indicators. This instrument would allow managers to assess the state of CKM in their aca- demic libraries, improve their library performance by checking the strengths and weaknesses against the in- dicators, and also serve as a basis for training the academic library staff on how to successfully implement CKM. With objective instances, the instrument is expected to improve the quality of customer services, customer satisfaction, and customer loyalty.
keywords: مدیریت دانش | دانش مشتری | مدیریت دانش مشتری | کتابخانه های دانشگاهی | بازخورد مشتری | مطالعه دلفی | Knowledge management | Customer knowledge | Customer knowledge management | Academic libraries | Customer feedback | Delphi study
مقاله انگلیسی
5 Benchmarking vision kernels and neural network inference accelerators on embedded platforms
محک زدن هسته بینایی و شتاب دهنده های استنتاج شبکه عصبی بر روی سیستم عامل های توکار-2021
Developing efficient embedded vision applications requires exploring various algorithmic optimization trade- offs and a broad spectrum of hardware architecture choices. This makes navigating the solution space and finding the design points with optimal performance trade-offs a challenge for developers. To help provide a fair baseline comparison, we conducted comprehensive benchmarks of accuracy, run-time, and energy efficiency of a wide range of vision kernels and neural networks on multiple embedded platforms: ARM57 CPU, Nvidia Jetson TX2 GPU and Xilinx ZCU102 FPGA. Each platform utilizes their optimized libraries for vision kernels (OpenCV, Vision Works and xfOpenCV) and neural networks (OpenCV DNN, TensorRT and Xilinx DPU). Forvision kernels, our results show that the GPU achieves an energy/frame reduction ratio of 1.1–3.2× compared to the others for simple kernels. However, for more complicated kernels and complete vision pipelines, the FPGA outperforms the others with energy/frame reduction ratios of 1.2–22.3×. For neural networks [Inception-v2 and ResNet-50, ResNet-18, Mobilenet-v2 and SqueezeNet], it shows that the FPGA achieves a speed up of [2.5, 2.1, 2.6, 2.9 and 2.5]× and an EDP reduction ratio of [1.5, 1.1, 1.4, 2.4 and 1.7]× compared to the GPU FP16 implementations, respectively.
Keywords: Benchmarks | CPUs | GPUs | FPGAs | Embedded vision | Neural networks
مقاله انگلیسی
6 Deep learning-based real-world object detection and improved anomaly detection for surveillance videos
تشخیص واقعی شیء مبتنی بر یادگیری عمیق و بهبود تشخیص ناهنجاری برای فیلم های نظارتی-2021
In this fast processing world, we need fast processing programs with maximum accuracy. This can be achieved when computer vision is connected with optimized deep learning models and neural networks. The goal of this project is to build an Artificial Intelligent system that will take live CCTV camera feed as input and detect what is happening in the video and do further analysis. Concerning current technology, there are a lot many models which use computer vision, machine learning for image and video processing. All models are different from each other, use various libraries, and are difficult to integrate or need high-end systems to process. This paper aims to use a convolutional neural network model for video processing and solve most of the important video processing features like detection of the liveliness of objects, estimating counts, and anomaly detection. And also further deploy it in such a way that it’ll be easy to integrate and easy to use with API calls.© 2021 Elsevier Ltd. All rights reserved.
Keywords: Computer vision | Convolutional neural network | Deep learning | Estimating counts | Liveliness
مقاله انگلیسی
7 Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues
یادگیری عمیق برای تشخیص شی و درک صحنه در اتومبیل های خودران: بررسی ، چالش ها و مسائل باز-2021
This article presents a comprehensive survey of deep learning applications for object detection and scene perception in autonomous vehicles. Unlike existing review papers, we examine the theory underlying self-driving vehicles from deep learning perspective and current implementations, followed by their critical evaluations. Deep learning is one potential solution for object detection and scene perception problems, which can enable algorithm driven and data-driven cars. In this article, we aim to bridge the gap between deep learning and self-driving cars through a comprehensive survey. We begin with an introduction to self-driving cars, deep learning, and computer vision followed by an overview of artificial general intelligence. Then, we classify existing powerful deep learning libraries and their role and significance in the growth of deep learning. Finally, we discuss several techniques that address the image perception issues in real-time driving, and critically evaluate recent implementations and tests conducted on self-driving cars. The findings and practices at various stages are summarized to correlate prevalent and futuristic techniques, and the applicability, scalability and feasibility of deep learning to self-driving cars for achieving safe driving without human intervention. Based on the current survey, several recommendations for further research are discussed at the end of this article.
Keywords: Self-driving cars | Levels of automation | Machine learning | Deep learning | Convolutional neural networks | Scene perception | Object detection | Multimodal sensor fusion | LiDAR | Computer vision | Autonomous driving initiatives
مقاله انگلیسی
8 Collection weeding: Innovative processes and tools to ease the burden
جمع آوری علفهای هرز : فرایندها و ابزارهای نوآورانه برای کاهش بار-2020
Evaluating collections and ultimately removing content poses a variety of difficult issues, including choosing appropriate deselection criteria, communicating with stakeholders, providing accountability, and managing the overall timetable to finish projects on time. The Science and Engineering librarians at Brigham Young University evaluated their entire print collection of over 350,000 items within one year, significantly reducing the number of items kept on the open shelves and the physical collection footprint. Keys to accomplishing this project were extensive preparation, tracking progress and accountability facilitated by Google Sheets and an interactive GIS stacks map, and stakeholder feedback facilitated by a novel web-based tool. This case study discusses guidelines to follow and pitfalls to avoid for any organization that is considering a large- or small-scale collection evaluation project.
Keywords: Weeding | Academic libraries | Collection management | Deselection of library materials | Collection evaluation
مقاله انگلیسی
9 Research and application of artificial intelligence service platform for the power field
تحقیق و کاربرد بستر خدمات هوش مصنوعی برای حوزه قدرت-2020
Conventional analysis methods cannot fully meet the business needs of power grids. At present, several artificial intelligence (AI) projects in a single business field are competing with each other, and the interfaces between the systems lack unified specifications. Therefore, it is imperative to establish a comprehensive service platform. In this paper, an AI platform framework for power fields is proposed; it adopts the deep learning technology to support natural language processing and computer vision services. On one hand, it can provide an algorithm, a model, and service support for power- enterprise applications, and on the other hand, it can provide a large number of heterogeneous data processing, algorithm libraries, intelligent services, model managements, typical application scenarios, and other services for different levels of business personnel. The establishment of the platform framework could break data barrier, improve portability of technology, avoid the investment waste caused by repeated constructions, and lay the foundation for the construction of “platform + application + service” ecological chain.
Keywords: Artificial intelligence platform | Deep learning | Neural network | Model training | Application scenarios.
مقاله انگلیسی
10 Managing the “backend” of LIS research projects: A project management perspective
مدیریت "بخش انتهایی" پروژه های تحقیقاتی LIS: چشم انداز مدیریت پروژه-2020
There is very little guidance in library and information science (LIS) literature about how researchers should manage the scope, time, costs, quality, human resources, communications, and risks associated with LIS research projects. To fill this gap, researchers tested the utility of project management principles (PMP) for planning and managing a project designed to enhance the information, digital, and financial literacy of the people earning less than $2 per day in India. The customization of PMP through 29 mechanisms and 60 action items was used to conduct focus groups and in-person surveys with over 150 participants, in their native language, at 10 public libraries. PMP were most helpful for managing risks (13 solutions), communications (11 solutions), and human resources (10 solutions) of the project and treating participants ethically. PMP developed in the West were helpful before, during, and after data collection in the LIS research project in a developing country.
مقاله انگلیسی
rss مقالات ترجمه شده rss مقالات انگلیسی rss کتاب های انگلیسی rss مقالات آموزشی
logo-samandehi
بازدید امروز: 2678 :::::::: بازدید دیروز: 9616 :::::::: بازدید کل: 18962 :::::::: افراد آنلاین: 36