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 |
Explainability and Dependability Analysis of Learning Automata based AI Hardware
تحلیل توضیح و قابلیت اطمینان یادگیری سخت افزار هوش مصنوعی مبتنی بر Automata-2020 Explainability remains the holy grail in designing
the next-generation pervasive artificial intelligence (AI) systems.
Current neural network based AI design methods do not
naturally lend themselves to reasoning for a decision making
process from the input data. A primary reason for this is the
overwhelming arithmetic complexity.
Built on the foundations of propositional logic and game
theory, the principles of learning automata are increasingly
gaining momentum for AI hardware design. The lean logic based
processing has been demonstrated with significant advantages
of energy efficiency and performance. The hierarchical logic
underpinning can also potentially provide opportunities for bydesign
explainable and dependable AI hardware. In this paper,
we study explainability and dependability using reachability
analysis in two simulation environments. Firstly, we use a behavioral
SystemC model to analyze the different state transitions.
Secondly, we carry out illustrative fault injection campaigns in
a low-level SystemC environment to study how reachability is
affected in the presence of hardware stuck-at 1 faults. Our
analysis provides the first insights into explainable decision
models and demonstrates dependability advantages of learning
automata driven AI hardware design. Keywords: Rainfall | Artificial | Computing | Simulation | Architecture |
مقاله انگلیسی |
2 |
A novel dynamics model of ball-screw feed drives based on theoretical derivations and deep learning
دل دینامیکی جدید درایوهای خورشیدی پیچ بر اساس مشتقات نظری و یادگیری عمیق-2019 High fidelity models of feed drive are critical factors to increase positioning accuracy and decrease contour error. To predict feed drives dynamics, this paper reports a novel method for modeling dynamics of feed drive by combining advantages of theoretical derivations and deep learning. First, the paper derives a rigid-flexible-combined dynamics model (RFCDM) for feed drive from classical dynamics theory. Then parameters identification of RFCDM is accomplished by referring product manuals and conducting constant velocity experiment with different feed rates. Continuous action reinforcement learning automata (CARLA) is adopted to tune all parameters of RFCDM simultaneously. A simulation error estimation model (SEEM) is applied to approximate simulation error between models sim- ulation position and worktables actual position. The hybrid dynamics model (HDM) of feed drives which integrates RFCDM with SEEM is validated by experiments with various tra- jectories. Experimental results show that the gap between HDMs prediction position and worktables actual position is on the order of magnitude of 0.01 mm which is about 1/10 of the tracking error, indicating the HDM can predict the dynamics of feed drives with safe accuracy. Keywords: Feed drive | Dynamics model | CARLA | Deep learning |
مقاله انگلیسی |
3 |
An on-demand coverage based self-deployment algorithm for big data perception in mobile sensing networks
الگوریتم خودمراقبتی مبتنی بر پوشش تحت تقاضا برای درک داده های بزرگ در شبکه های حسگر سیار-2018 Mobile Sensing Networks have been widely applied to many fields for big data perception such as
intelligent transportation, medical health and environment sensing. However, in some complex envi
ronments and unreachable regions of inconvenience for human, the establishment of the mobile sensing
networks, the layout of the nodes and the control of the network topology to achieve high performance
sensing of big data are increasingly becoming a main issue in the applications of the mobile sensing
networks. To deal with this problem, we propose a novel on-demand coverage based self-deployment
algorithm for big data perception based on mobile sensing networks in this paper. Firstly, by considering
characteristics of mobile sensing nodes, we extend the cellular automata model and propose a new mobile
cellular automata model for effectively characterizing the spatial–temporal evolutionary process of nodes.
Secondly, based on the learning automata theory and the historical information of node movement, we
further explore a new mobile cellular learning automata model, in which nodes can self-adaptively and
intelligently decide the best direction of movement with low energy consumption. Finally, we propose a
new optimization algorithm which can quickly solve the node self-adaptive deployment problem, thus,
we derive the best deployment scheme of nodes in a short time. The extensive simulation results show
that the proposed algorithm in this paper outperforms the existing algorithms by as much as 40% in
terms of the degree of satisfaction of network coverage, the iterations of the algorithm, the average
moving steps of nodes and the energy consumption of nodes. Hence, we believe that our work will make
contributions to large-scale adaptive deployment and high performance sensing scenarios of the mobile
sensing networks.
Keywords: Mobile sensing network ، High performance sensing ، Big data perception ، Node self-deployment ، On-demand coverage ، Mobile cellular learning automata |
مقاله انگلیسی |
4 |
روش جدید پیش بینی پیوند سری های زمانی: روش اتوماتای یادگیر
سال انتشار: 2017 - تعداد صفحات فایل pdf انگلیسی: 16 - تعداد صفحات فایل doc فارسی: 27 پیش بینی پیوند یک چالش بزرگ در شبکه های اجتماعی است که از ساختار شبکه ای برای پیش بینی پیوندهای آتی استفاده می کند. روش های رایج پیش بینی پیوند برای پیش بینی پیوندهای مخفی از نمایش گراف ایستا استفاده می کنند که در آن تصویری از شبکه برای یافتن پیوندهای آتی یا مخفی مورد استفاده قرار می گیرد. برای مثال، پیش بینی پیوند مبتنی بر معیار تشابه، روش سنتی رایجی است که معیار تشابه را برای تمامی پیوندهای غیرمتصل محاسبه نموده، پیوندها را براساس معیارهای تشابه آنها مرتب نموده و پیوندهای با امتیاز تشابه بالاتر را به عنوان پیوندهای آتی برچسب گذاری می کند. از آنجاکه فعالیت های افراد در شبکه های اجتماعی، پویا و غیرقطعی است، و ساختار شبکه ها با گذشت زمان تغییر می کند، استفاده از گراف های قطعی برای مدلسازی و تحلیل شبکه ی اجتماعی نمی تواند روش مناسبی باشد. در مسأله ی پیش-بینی پیوند سری های زمانی، احتمال وقوع پیوند سری های زمانی برای پیش بینی پیوندهای آتی مورد استفاده قرار می گیرد. ما در این مقاله یک روش پیش بینی پیوند سری های زمانی مبتنی بر اتوماتای یادگیر را پیشنهاد می کنیم. در الگوریتم پیشنهادی برای هر پیوندی که قرار است پیش بینی شود، یک اتوماسیون یادگیری داریم و هر اتوماسیون یادگیری در تلاش است وجود یا عدم وجود پیوند متناظر را پیش بینی کند. برای پیش بینی احتمال وقوع پیوند در زمان T، یک دنباله ی متشکل از مراحل 1 تا T-1 داریم و اتوماسیون یادگیری این مراحل را می پیماید تا وجود یا عدم وجود پیوند مربوطه را بیاموزد. زمانیکه احتمال وقوع پیوند سری های زمانی را در نظر بگیریم، آزمایشات اولیه ی پیش بینی پیوند با شبکه های ایمیل و نویسندگی مشترک، نتایج رضایت بخشی را فراهم می آورد.
کلیدواژه ها: شبکه ی اجتماعی | پیش بینی پیوند | سری های زمانی | اتوماتای یادگیر |
مقاله ترجمه شده |
5 |
Irregular cellular learning automata-based algorithm for sampling social networks
الگوریتم مبتنی بر اتوماتای یادگیری سلولی نامنظم برای نمونه برداری شبکه های اجتماعی-2017 Since online social networks usually have quite huge size and limited access, smaller subgraphs of them are
often produced and analysed as the representative samples of original graphs. Sampling algorithms proposed so
far are categorized into three main classes: node sampling, edge sampling, and topology-based sampling. Classic
node sampling algorithm, despite its simplicity, performs surprisingly well in many situations. But the problem
with node sampling is that the connectivity in sampled subgraph is less likely to be preserved. This paper
proposes a topology–based node sampling algorithm using irregular cellular learning automata (ICLA), called
ICLA-NS. In this algorithm, at first an initial sample subgraph of the input graph is generated using the node
sampling method and then an ICLA isomorphic to the input graph is utilized to improve the sample in such a
way that the connectivity of the sample is ensured and at the same time the high degree nodes are also included
in the sample. Experimental results on real–world social networks indicate that the proposed sampling
algorithm ICLA-NS preserves more accurately the underlying properties of the original graph compared to
existing sampling methods in terms of Kolmogorov-Smirnov (KS) test.
Keywords: Complex networks | Social networks | Network sampling | Graph mining | Cellular learning automata |
مقاله انگلیسی |
6 |
An adaptive trust-Stackelberg game model for security and energy efficiency in dynamic cognitive radio networks
یک مدل بازی اعتماد استاکلبرگ تطبیقی برای امنیت و بهره وری انرژی در شبکه های رادیویی شناختی پویا-2017 Due to the potential of cooperative cognitive radio networks (CCRNs) in addressing the spectrum scarcity
problem in wireless communication networks, CCRN has become a subject of active research. For exam
ple, security and energy efficiency are two salient areas of research in CCRNs. In this paper, we propose
a novel adaptive trust-Stackelberg game model designed to (a) improve the energy efficiency and (b) de
fend against insider attacks in CCRNs. More specifically, the distributed learning algorithm (DLA) for the
relays in our model, inspired by the stochastic learning automata, allows the system to achieve Stack
elberg equilibrium in the proposed game; and the trust evolution based on evolutionary stable strategy
algorithm (TEEA) allows the primary user to defend against insider attacks efficiently and adaptively ad
just the trust evolution in dynamic CCRNs. We demonstrate the utility of the proposed model comparing
with other models using a numerical investigation. The numerical results show that the proposed model
can improve the performance in energy efficiency and defending against insider attacks with an appro
priate cooperation between primary users and relays.
Keywords: Dynamic cooperative cognitive radio | networks | Secure Relay Selection | Power control | Stackelberg game | Reinforce learning |
مقاله انگلیسی |
7 |
A new reasoning and learning model for Cognitive Wireless Sensor Networks based on Bayesian networks and learning automata cooperation
یک مدل استدلال و یادگیری جدید برای شبکه های حسگر بی سیم شناختی مبتنی بر شبکه های بیزی و همکاری اتوماسیون یادگیری-2017 Adding cognition to existing Wireless Sensor Networks (WSNs) with a cognitive networking approach,
which deals with using cognition to the entire network protocol stack to achieve end-to-end goals, brings
about many benefits. However cognitive networking may be confused with cognitive radio or cross-layer
design, it is a different concept; cognitive radios applies cognition only at the physical layer to overcome
the problem of spectrum scarcity, and cross layer design usually focuses on linking at least two non
consecutive specific layers, to achieve a particular goal. Indeed, it can be said that the cognitive radio and
the cross layer design are two effective methods in cognitive networking. To the best of our knowledge,
almost all of the existing researches on the Cognitive Wireless Sensor Networks (CWSNs) have focused
on spectrum allocation and interference reduction in the physical layer. In this paper, we propose a new
reasoning and learning model for CWSNs, in which firstly, a team of learning automata is employed to
construct a Bayesian Network (BN) model of the parameters of the network protocol stack, and then the
constructed BN is used to tune the controllable parameters. The BN represents the dependency relation
ships between the parameters of the network protocol stack, and the BN-based reasoning is an efficient
tool for cross-layer optimization, in order to maximize the perceived network performance. Simulations
have been done to evaluate the performance of the proposed model. The results of the simulations show
that the proposed model successively adds cognition to a WSN and improves the performance of the
communication network.
Keywords: Bayesian Networks | Cognitive networks | Learning automata | Reasoning | Wireless Sensor Network |
مقاله انگلیسی |