ردیف | عنوان | نوع |
---|---|---|
1 |
DEGAN : شبکه های مولد متخاصم غیر متمرکز
سال انتشار: 2021 - تعداد صفحات فایل pdf انگلیسی: 9 - تعداد صفحات فایل doc فارسی: 23 در این مطالعه، یک چارچوب توزیع شده و غیرمتمرکز از شبکه های مولد متخاصم (GAN) بدون تبادل داده های آموزشی پیشنهاد شد. هر گره شامل مجموعه ی از داده محلی ، یک تفکیک کننده کننده و یک مولد است که فقط گرادیان ژنراتور آن با سایر گره ها به اشتراک گذاشته می شوند. در این مقاله ، تکنیک توزیع جدید معرفی می شود که در آن کارکنان مستقیماً با یکدیگر ارتباط برقرار می کنند و هیچ گره مرکزی وجود ندارد. نتایج تجربی ما در مجموعه داده های معیار ، عملکرد و دقت تقریباً یکسانی را در مقایسه با چارچوب های GAN متمرکز موجود نشان می دهد. چارچوب پیشنهادی به عدم یادگیری غیرمتمرکز برای GAN ها می پردازد.
کلمات کلیدی: یادگیری عمیق | شبکه های مولد متخاصم | یادگیری ماشین توزیع شده | معماری غیرمتمرکز |
مقاله ترجمه شده |
2 |
سرمایه گذاری مالی بلاکچین برمبنای الگوریتم شبکه یادگیری عمیق
سال انتشار: 2020 - تعداد صفحات فایل pdf انگلیسی: 11 - تعداد صفحات فایل doc فارسی: 30 به منظور مطالعه استفاده از یادگیری عمیق برای پردازش داده های مالی، پیشنهاد می شود که می توان از فناوری مرتبط با شبکه عصبی و یادگیری عمیق برای داده های مالی استفاده کرد و از شاخص واقعی سهام و داده های آتی برای بررسی تاثیر کاربرد شبکه عصبی و یادگیری عمیق استفاده کرد. درابتدا نظریه و مدل یادگیری عمیق و شبکه عصبی با جزئیات معرفی می شوند. سپس از یک شبکه عصبی ساده و مدل یادگیری عمیق در شاخص سهام و پیش بینی قیمت آتی استفاده می شود. داده های استفاده شده در داده های ورودی به مدل شامل قیمت یک سهام در معامله جاری و برخی شاخص های داده ای و قیمت بسته شدن یک سهام در زمان بعدی می شود. کاهش قیمت در خروجی منعکس خواهد شد. اگر خروجی برای 1 بالا و برای صفر پایین باشد، داده های جدید پس از راه اندازی مدل وارد خواهند شد. نهایتا" جهت قضاوت روی تاثیر کاربرد مدل، می توان پس از مقایسه e و تحلیل تاثیر کاربرد مدل، داده های خروجی را با داده های واقعی مقایسه کرد. نتایج نشان می دهند که تحقیق انجام شده در این مطالعه می تواند به سرمایه گذاران کمک کند تا یک مدل سرمایه گذاری خودکار و راهبرد سرمایه گذاری در بازار سهام بسازند. از این سازه می توان برای ارجاع جهت بهبود راهبرد سرمایه گذاری سرمایه گذاران و نرخ بازگشت استفاده کرد.
کلیدواژه ها: یادگیری عمیق | سرمایه گذاری در بازار بورس | شبکه عصبی | سرمایه گذاری مالی |
مقاله ترجمه شده |
3 |
Modified deep learning and reinforcement learning for an incentive-based demand response model
یادگیری عمیق اصلاح شده و یادگیری تقویتی برای یک مدل پاسخ تقاضای مبتنی بر انگیزه-2020 Incentive-based demand response (DR) program can induce end users (EUs) to reduce electricity demand
during peak period through rewards. In this study, an incentive-based DR program with modified deep
learning and reinforcement learning is proposed. A modified deep learning model based on recurrent
neural network (MDL-RNN) was first proposed to identify the future uncertainties of environment by
forecasting day-ahead wholesale electricity price, photovoltaic (PV) power output, and power load. Then,
reinforcement learning (RL) was utilized to explore the optimal incentive rates at each hour which can
maximize the profits of both energy service providers (ESPs) and EUs. The results showed that the
proposed modified deep learning model can achieve more accurate forecasting results compared with
some other methods. It can support the development of incentive-based DR programs under uncertain
environment. Meanwhile, the optimized incentive rate can increase the total profits of ESPs and EUs
while reducing the peak electricity demand. A short-term DR program was developed for peak electricity
demand period, and the experimental results show that peak electricity demand can be reduced by 17%.
This contributes to mitigating the supply-demand imbalance and enhancing power system security. Keywords: Demand response | Modified deep learning | Reinforcement learning | Smart grid |
مقاله انگلیسی |
4 |
Recent advances in digital image manipulation detection techniques: A brief review
پیشرفت های اخیر در تکنیک های تشخیص دستکاری تصویر دیجیتال: مروری کوتاه-2020 A large number of digital photos are being generated and with the help of advanced image editing
software and image altering tools, it is very easy to manipulate a digital image nowadays. These
manipulated or tampered images can be used to delude the public, defame a persons personality and
business as well, change political views or affect the criminal investigation. The raw image can be
mutilated in parts or as a whole image so there is a need for detection of what type of image tampering is
performed and then localize the tampered region. Initially, single handcrafted manipulated images were
used to detect the only image tampering present in the image but in a real-world scenario, a single image
can be mutilated by numerous image manipulation techniques. Nowadays, multiple tampering
operations are performed on the image and post-processing is done to erase the traces left behind by the
tampering operation, making it more difficult for the detector to detect the tampering. It is seen that the
recent techniques that are used to detect image manipulation are based on deep learning methods. In this
paper, more focus is on the study of various recent image manipulation detection techniques. We have
examined various image forgeries that can be performed on the image and various image manipulation
detection and localization methods. Keywords: Image manipulation | Image tampering | Convolutional neural network | Deep learning |
مقاله انگلیسی |
5 |
A Novel Multi-Modal Framework for Migrants Integration Based on AI Tools and Digital Companion
یک چارچوب چند حالته جدید برای ادغام مهاجران بر اساس ابزارهای هوش مصنوعی و همراه دیجیتال-2020 ICT have proven to provide significant aid for appropriate integration
of migrants. These tools can support the inclusion
by providing guidance, education opportunities, job seeking,
culture immersion and facilitating access to primary services.
In this paper, a complete framework for migrants (with special
focus on refugees) guidance and inclusion is presented.
This framework comprises a set of novel AI tools aimed at
enabling mentioned services from diverse perspectives: a)
users’ profiling; b) skills matching c) recommendations; d)
user profiling and e) digital companion. Consideration about
data collection, data flow, architecture and interactions are
provided. Index Terms: AI users’ profiling | Deep Learning |
مقاله انگلیسی |
6 |
Automatic human identification from panoramic dental radiographs using the convolutional neural network
شناسایی خودکار انسان از رادیوگرافی دندانپزشکی پانوراما با استفاده از شبکه عصبی کانولوشن-2020 Human identification is an important task in mass disaster and criminal investigations. Although several
automatic dental identification systems have been proposed, accurate and fast identification from
panoramic dental radiographs (PDRs) remains a challenging issue. In this study, an automatic human
identification system (DENT-net) was developed using the customized convolutional neural network
(CNN). The DENT-net was trained on 15,369 PDRs from 6300 individuals. The PDRs were preprocessed by
affine transformation and histogram equalization. The DENT-net took 128 128 7 square patches as
input, including the whole PDR and six details extracted from the PDR. Using the DENT-net, the feature
extraction took around 10 milliseconds per image and the running time for retrieval was 33.03
milliseconds in a 2000-individual database, promising an application on larger databases. The
visualization of CNN showed that the teeth, maxilla, and mandible all contributed to human
identification. The DENT-net achieved Rank-1 accuracy of 85.16% and Rank-5 accuracy of 97.74% for
human identification. The present results demonstrated that human identification can be achieved from
PDRs by CNN with high accuracy and speed. The present system can be used without any special
equipment or knowledge to generate the candidate images. While the final decision should be made by
human specialists in practice. It is expected to aid human identification in mass disaster and criminal
investigation Keywords: Forensic odontology | Human identification | Panoramic dental radiographs | Deep learning | Convolutional neural network |
مقاله انگلیسی |
7 |
AI-based Framework for Deep Learning Applications in Grinding
چارچوبی مبتنی بر هوش مصنوعی برای کاربردهای یادگیری عمیق در شبکه سازی-2020 Rejection costs for a finish-machined
gearwheel with grinding burn can rise to the order of 10,000 euros
each. A reduction in costs by reducing rejection rate by only 5-10
pieces per year already amortizes costs for data-acquisition
hardware for online process monitoring. The grinding wheel wear,
one of the major influencing factors responsible for the grinding
burn, depends on a large number of influencing variables like
cooling lubricant, feed rate, circumferential wheel speed and wheel
topography. In the past, machine learning algorithms such as
Support Vector Machines (SVM), Hidden Markov Models (HMM)
and Artificial Neural Networks (ANN) have proven effective for the
predictive analysis of process quality. In addition to predictive
analysis, AI-based applications for process control may raise the
resilience of machining processes. Using machine learning methods
may also lead to a heavy reduction of cost amassed due to a physical
inspection of each workpiece. With this contribution, information
from previous works is leveraged and an AI-based framework for
adaptive process control of a cylindrical grinding process is
introduced. For the development of such a framework, three
research objectives have been derived: First, the dynamic wheel
wear needs to be modelled and measured, because of its strong
impact on the resulting workpiece quality. Second, models to predict
the quality features of the produced workpieces depending on
process setup parameters and materials used have to be established.
Here, special focus is set on deriving models that are independent
of a specific wheel-workpiece-pair. The opportunity to use such a
model in a variety of grinding configurations gives the production
line consistent process support. Third, the resilience of analytical
models regarding graceful degradation of sensors needs to be
tackled, since the stability of such systems has to be guaranteed to
be used in productive environments. Process resilience against
human errors and sensor failures leads to a minimization of
rejection costs in production. To do so, a framework is presented,
where virtual sensors, upon the failure or detection of an erroneous
signal from physical sensors, will be activated and provide signals
to the downstream smart systems until the process is completed or
the physical sensor is changed. Keywords: Cylindrical Grinding | Wheel Wear | Virtual Sensors | Process Resilience | Artificial Intelligence |
مقاله انگلیسی |
8 |
Reinforcement learning based on movement primitives for contact tasks
یادگیری تقویتی بر اساس ابتدای حرکت برای وظایف تماس-2020 Recently, robot learning through deep reinforcement learning has incorporated various robot tasks through deep
neural networks, without using specific control or recognition algorithms. However, this learning method is
difficult to apply to the contact tasks of a robot, due to the exertion of excessive force from the random search
process of reinforcement learning. Therefore, when applying reinforcement learning to contact tasks, solving the
contact problem using an existing force controller is necessary. A neural-network-based movement primitive
(NNMP) that generates a continuous trajectory which can be transmitted to the force controller and learned
through a deep deterministic policy gradient (DDPG) algorithm is proposed for this study. In addition, an
imitation learning algorithm suitable for NNMP is proposed such that the trajectories similar to the demonstration
trajectory are stably generated. The performance of the proposed algorithms was verified using a square
peg-in-hole assembly task with a tolerance of 0.1 mm. The results confirm that the complicated assembly trajectory
can be learned stably through NNMP by the proposed imitation learning algorithm, and that the assembly
trajectory is improved by learning the proposed NNMP through the DDPG algorithm. Keywords: AI-based methods | Force control | Deep Learning in robotics and automation |
مقاله انگلیسی |
9 |
Accelerated Computer Vision Inference with AI on the Edge
استنتاج چشم انداز رایانه ای سریع با هوش مصنوعی در لبه-2020 Computer vision is not just about breaking down
images or videos into constituent pixels, but also about making
sense of those pixels and comprehending what they represent.
Researchers have developed some brilliant neural networks and
algorithms for modern computer vision. Tremendous developments
have been observed in deep learning as computational
power is getting cheaper. But data-driven deep learning and cloud
computing based systems face some serious limitations at edge devices
in real-world scenarios. Since we cannot bring edge devices
to the data-centers, so we bring AI to the edge devices with AI
on the Edge. OpenVINO toolkit is a powerful tool that facilitates
deployment of high-performance computer vision applications to
the edge devices. It converts existing applications into hardwarefriendly
and inference-optimized deployable runtime packages
that operate seamlessly at the edge. The goals of this paper are
to describe an in-depth survey of problems faced in existing
computer vision applications and to present AI on the Edge along
with OpenVINO toolkit as the solution to those problems. We
redefine the workflow for deploying computer vision systems and
provide an efficient approach for development and deployment
of edge applications. Furthermore, we summarize the possible
works and applications of AI on the Edge in future in regard to
security and privacy. Index Terms: Artificial Intelligence | Deep Learning | Neural Networks | Computer Vision | AI on the Edge | OpenVINO |
مقاله انگلیسی |
10 |
Interactive Transport Enquiry with AI Chatbot
استعلام حمل و نقل تعاملی با هوش مصنوعی Chatbot-2020 Public transportation is used efficiently by millions
of people all over the world. People tend to travel to different
places and at certain times they may feel completely lost in a new
place. Our chatbot comes to rescue at this time. A Chatbot is
often described as one of the most promising tools for
communication between humans and machines using artificial
intelligence. It is a software application that is used to conduct an
online chat conversation via text by using natural language
processing (NLP) and deep learning techniques. It provides
direct contact with a live human agent in the form of GUI. This
AI chatbot confirms the current location and the final destination
of the user by asking a few questions. It examines the user’s
query and extracts the appropriate entries from the database.
The deep learning techniques that are used in this chatbot are
responsible for understanding the user intents accurately to avoid
any misconceptions. Once the user’s intention has been
recognized, the chatbot provides the most relevant response for
the user’s query request. Then the user gets all the information
about the bus names along with their numbers so that the person
can travel safely to the desired location. Our chatbot is
implemented in pythons Keras library and used Tkinter for
GUI. Keywords: artificial intelligence | chatbot | natural language processing | deep learning | Keras | GUI | Tkinter |
مقاله انگلیسی |