با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
ردیف | عنوان | نوع |
---|---|---|
1 |
MagLoc : A magnetic induction based localization scheme for fresh food logistics
MagLoc: یک طرح محلی سازی مبتنی بر القای مغناطیسی برای تدارکات مواد غذایی تازه-2022 An IoT infrastructure to continuously monitor the fresh food supply chain can quickly detect
food quality and contamination issues and thereby reduce costs and food wastage. This, in turn,
involves several challenges including the development of inexpensive quality/contamination
sensors to be deployed in a fine grain manner in the food boxes, technologies for sensor
level communications, online data management and analytics, and logistics driven by such
analytics. In this paper, we study the issues related to the communication among sensing
modules deployed in the fresh food boxes and thereby an automated localization of the boxes
that may have quality/contamination issues. In this context we study the near-field magnetic
induction (NFMI) based communication and localization, as the ubiquitous RF communications
suffer high attenuation through the water/mineral rich tissue media. An accurate localization
of the sensors inside boxes within the food pallets is very challenging in this environment. In
this paper we propose a novel magnetic induction based localization scheme, and show that
with a small number of anchor nodes, the localization can be done without any errors for boxes
as small as 0.5 meter on the side, and with small errors even for boxes half as big.
Keywords: Smart sensing | Industrial sensors | Food supply chain | Physical Internet | Magnetic communication | Localization |
مقاله انگلیسی |
2 |
Digital interoperability in logistics and supply chain management: state-of-the-art and research avenues towards Physical Internet
قابلیت همکاری دیجیتال در تدارکات و مدیریت زنجیره تأمین: پیشرفته ترین و روشهای تحقیقاتی به سمت اینترنت فیزیکی-2021 Interoperability is playing an increasing role for today’s logistics and supply chain management (LSCM)
because of the trends of cooperation or coopetition. Especially, digital interoperability concerning data
or information exchange becomes a key enabler for the next evolutions that will massively rely upon
digitalization, artificial intelligence, and autonomous systems. The notion of Physical Internet (PI) is one
such evolution, an innovative worldwide logistic paradigm aimed at interconnecting and coordinating
logistics networks for efficiency and sustainability. This paper investigates how digital interoperability
can help interconnect logistics and supply networks as well as the operational solutions for sustainable
development, and examines the new challenges and research opportunities for digital interoperability
under the PI paradigm. To this end, we study the most relevant technologies for digital interoperability in LSCM, via a bibliometric analysis based on 208 papers published during 2010−2020. The results
reveal that the present state-of-the-art solutions of digital interoperability are not fully aligned with PI
requirements and show new challenges, research gaps and opportunities that need further discussion.
Accordingly, several research avenues are suggested to advance research and applications in this area,
and to achieve interconnection in logistics and supply networks for sustainability. Keywords: Interoperability | Interconnection | Physical internet | Digitalization | Logistics | Supply Chain management | Bibliometric review | State-of-the-art | Research avenues |
مقاله انگلیسی |
3 |
هوش مصنوعی برای پیش بینی در مدیریت زنجیره تامین: مطالعه موردی میزان مصرف قند سفید در تایلند
سال انتشار: 2019 - تعداد صفحات فایل pdf انگلیسی: 6 - تعداد صفحات فایل doc فارسی: 22 این مقاله یک مدل مناسب برای پیش بینی روند میزان مصرف شکر سفید در تایلند با توجه به نوسانات نرخ مصرف امروزه ارائه می دهد. در این مقاله روی دو نوع مدل اصلی پیش بینی که مدل های رگرسیون و شبکه های عصبی هستند ، تمرکز خواهد شد. علاوه بر این ، عملکرد با استفاده از Root Mean Square Error (RMSE) و مقدار آماری TheilU ارزیابی می شود. پس از پردازش آزمایشات ، نتایج نشان می دهد که شبکه عصبی راجعه با حافظه کوتاه مدت (LSTM) با شرایط ترکیبی بین میزان مصرف موجود و سایر عوامل مرتبط مانند تأمین تولید ، میزان واردات ، صادرات و موجودی کالا بهترین عملکرد را برای پیش بینی فراهم می کند. همچنین تنظیم پارامترهای مدل مسئله مهمی است.
کلمات کلیدی: یادگیری ماشین | اینترنت فیزیکی | پیش بینی تقاضا | شبکه عصبی | رگرسیون |
مقاله ترجمه شده |