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 |
---|---|---|
61 |
An automatic algorithm of identifying vulnerable spots of internet data center power systems based on reinforcement learning
یک الگوریتم خودکار برای شناسایی نقاط آسیب پذیر سیستم های قدرت مرکز داده اینترنتی بر اساس یادگیری تقویتی-2020 The internet data center (IDC) power system provides power guarantee for cloud computing and other information
services, so its importance is self-evident. However, the occurrence time of malignant destructive
events such as lightning strikes, errors in operation and cyber-attacks is unpredictable. But the loss can be
minimized by formulating coping strategies in advance. So, identifying the vulnerable spots of the IDC power
system come to be the key to guarantee the normal operation of information systems. Generally, the IDC power
network can be modelled as a graph G, and then, the methods of finding nodes’ centrality can be applied to
analyse the vulnerability. By our experience, it is not the best approach.
Unlike the previous approaches, we do not solve the issue as the traditional graph problem. Instead, we fully
utilize the characteristics of the IDC power network and apply reinforcement learning techniques to identify the
vulnerability of the IDC power network. To our best knowledge, it is the first applying of artificial intelligence in
traditional IDC power network.
In this article, we propose PFEM, a parallel fault evolution model for the IDC power network, which can
accelerate the process of electrical fault evolution. Moreover, we designed an algorithm which can automatically
find the vulnerable spots of the IDC power network.
The experiment on a real IDC power network demonstrate that the impact of vulnerable devices derived from
our proposed algorithm after failure is about 5% higher than that of other algorithms, and tripping single-digit
electrical devices of the IDC power system with our proposed algorithm will lead to loss of all loads. Keywords: Internet data center | Power system | Vulnerability | Reinforcement learning | Maintenance |
مقاله انگلیسی |
62 |
Adaptive real-time optimal energy management strategy for extender range electric vehicle
مدیریت انرژی بهینه زمان واقعی تطبیقی برای وسایل نقلیه برقی دامنه توسعه دهنده-2020 The extender range electric vehicle (EREV) is an effective way to solve the “mileage anxiety” of pure
electric vehicles, and the fuel economy of EREV is the key point of energy optimization. This paper
designed an adaptive real-time optimal energy management strategy for EREV. Firstly, an improved
shooting algorithm is proposed, which can determine the range of the equivalent factor (EF) according to
the power configuration parameters of the vehicle, and then the secant method is used to quickly
calculate the initial value of the EF. Secondly, from the perspective of energy flow, the intrinsic operation
mechanism of equivalent consumption minimization strategy (ECMS) control strategy is revealed, and
the working relationship between the five working modes of EREV is clarified. Thirdly, based on the car
navigation and geographic location information system, the EF is periodically updated to achieve
effective maintenance of the battery state of charge (SOC), so as to obtain the optimal power allocation.
Finally, The fuel economy and real-time performance of the proposed energy management strategy are
simulated and compared. To verify fuel economy, the rule-based control strategy and the power
following control strategy were used as comparison. The results show that the proposed control strategy
has better fuel economy and adaptability. To verify real-time performance, the proportional integral
derivative ECMS (PID-ECMS) and shooting method ECMS (S-ECMS) were used as comparison. The results
show that the proposed strategy is better in both fuel economy and real-time performance. Keywords: Extended range electric vehicle | Real-time optimization | Adaptive energy management | Improved shooting method | Equivalent consumption minimization | strategy |
مقاله انگلیسی |
63 |
Online RBM: Growing Restricted Boltzmann Machine on the fly for unsupervised representation
آنلاین RBM: در حال رشد محدودیت ماشین بولتزمن در پرواز برای نمایندگی بدون نظارت-2020 In this work, we endeavor to investigate and propose a novel unsupervised online learning algorithm,
namely the Online Restricted Boltzmann Machine (O-RBM). The O-RBM is able to construct and adapt
the architecture of a Restricted Boltzmann Machine (RBM) artificial neural network, according to the
statistics of the streaming input data. Specifically, for a training data that is not fully available at the
onset of training, the proposed O-RBM begins with a single neuron in the hidden layer of the RBM,
progressively adds and suitably adapts the network to account for the variations in streaming data
distributions. Such an unsupervised learning helps to effectively model the probability distribution of
the entire data stream, and generates robust features. We will demonstrate that such unsupervised
representations can be used for discriminative classifications on a set of multi-category and binary
classification problems for unstructured image and structured signal data sets, having varying degrees
of class-imbalance. We first demonstrate the O-RBM algorithm and characterize the network evolution
using the simple and conventional multi-class MNIST image dataset, aimed at recognizing hand-written
digit. We then benchmark O-RBM performance to other machine learning, neural network and Class
RBM techniques using a number of public non-stationary datasets. Finally, we study the performance
of the O-RBM on a real-world problem involving predictive maintenance of an aircraft component
using time series data. In all these studies, it is observed that the O-RBM converges to a stable,
concise network architecture, wherein individual neurons are inherently discriminative to the class
labels despite unsupervised training. It can be observed from the performance results that on an
average O-RBM improves accuracy by 2.5%–3% over conventional offline batch learning techniques
while requiring at least 24%–70% fewer neurons. Keywords: Restricted Boltzmann Machine | Online learning | Unsupervised representation |
مقاله انگلیسی |
64 |
Scaling up and scaling out: Consilience and the evolution of more nurturing societies
مقیاس گذاری و عدم مقیاس گذاری: تساهل و تکامل جوامع پرورشی بیشتر-2020 This paper argues that diverse disciplines within the human sciences have converged in
identifying the conditions that human beings need to thrive and the programs, policies, and
practices that are needed to foster well-being. In the interest of promoting this view, we suggest
that this convergence might usefully be labeled “The Nurture Consilience.” We review evidence
from evolutionary biology, developmental, clinical, and social psychology, as well as public
health and prevention science indicating that, for evolutionary reasons, coercive environments
promote a “fast” life strategy that favors limited self-regulation, immediate gratification, and
early childbearing. However, this trajectory can be prevented through programs, practices, and
policies that (a) minimize toxic social and biological conditions, (b) limit opportunities and
influences for problem behavior, (c) richly reinforce prosocial behavior, and (d) promote
psychological flexibility. The recognition of these facts has prompted research on the adoption,
implementation, and maintenance of evidence-based interventions. To fully realize the fruits of
this consilience, it is necessary to reform every sector of society. We review evidence that free- market advocacy has promoted the view that if individuals simply pursue their own economic well-being it will benefit everyone, and trace how that view led business, health care, education,
criminal justice, and government to adopt practices that have benefited a small segment of the
population but harmed the majority. We argue that the first step in reforming each sector of
society would be to promote the value of ensuring everyone’s well-being. The second step will
be to create contingencies that select beneficial practices and minimizes harmful ones. Keywords: prevention | nurturing environments | consilience | public health |
مقاله انگلیسی |
65 |
Optimal policy for structure maintenance: A deep reinforcement learning framework
سیاست مطلوب برای نگهداری ساختار: یک چارچوب یادگیری تقویتی عمیق-2020 The cost-effective management of aged infrastructure is an issue of worldwide concern. Markov decision process
(MDP) models have been used in developing structural maintenance policies. Recent advances in the artificial
intelligence (AI) community have shown that deep reinforcement learning (DRL) has the potential to solve large
MDP optimization tasks. This paper proposes a novel automated DRL framework to obtain an optimized
structural maintenance policy. The DRL framework contains a decision maker (AI agent) and the structure that
needs to be maintained (AI task environment). The agent outputs maintenance policies and chooses maintenance
actions, and the task environment determines the state transition of the structure and returns rewards to the
agent under given maintenance actions. The advantages of the DRL framework include: (1) a deep neural network
(DNN) is employed to learn the state-action Q value (defined as the predicted discounted expectation of the
return for consequences under a given state-action pair), either based on simulations or historical data, and the
policy is then obtained from the Q value; (2) optimization of the learning process is sample-based so that it can
learn directly from real historical data collected from multiple bridges (i.e., big data from a large number of
bridges); and (3) a general framework is used for different structure maintenance tasks with minimal changes to
the neural network architecture. Case studies for a simple bridge deck with seven components and a long-span
cable-stayed bridge with 263 components are performed to demonstrate the proposed procedure. The results
show that the DRL is efficient at finding the optimal policy for maintenance tasks for both simple and complex
structures. Keywords: Bridge maintenance policy | Deep reinforcement learning (DRL) | Markov decision process (MDP) | Deep Q-network (DQN) | Convolutional neural network (CNN) |
مقاله انگلیسی |
66 |
A survey on clone refactoring and tracking
مروری بر فاکتورگیری مجدد و ردیابی کلون-2020 Code clones, identical or nearly similar code fragments in a software system’s code-base, have mixed impacts on software evolution and maintenance. Focusing on the issues of clones researchers suggest managing them through refactoring, and tracking. In this paper we present a survey on the state-of-the-art of clone refactoring and tracking techniques, and identify future research possibilities in these areas. We define the quality assessment features for the clone refactoring and tracking tools, and make a comparison among these tools considering these features. To the best of our knowledge, our survey is the first comprehensive study on clone refactoring and tracking. According to our survey on clone refactoring we realize that automatic refactoring cannot eradicate the necessity of manual effort regarding finding refactoring opportunities, and post refactoring testing of system behaviour. Post refactoring testing can require a significant amount of time and effort from the quality assurance engineers. There is a marked lack of research on the effect of clone refactoring on system performance. Future investigations in this direction will add much value to clone refactoring research. We also feel the necessity of future research towards real-time detection, and tracking of code clones in a big-data environment. Keywords: Code clones |Clone-types |Clone refactoring |Clone tracking |
مقاله انگلیسی |
67 |
Model-based vehicular prognostics framework using Big Data architecture
چارچوب پیش آگهی های وسایل نقلیه مبتنی بر مدل با استفاده از معماری داده های بزرگ-2020 Nowadays, the continuous technological advances allow designing novel Integrated Vehicle Health Man-agement (IVHM) systems to deal with strict safety regulations in the automotive field with the aim atimproving efficiency and reliability of automotive components. However, challenging issue, which arisesin this domain, is handling a huge amount of data that are useful for prognostic. To this aim, in thispaper we propose a cloud-based infrastructure, namely Automotive predicTOr Maintenance In Cloud(ATOMIC), for prognostic analysis that leverages Big Data technologies and mathematical models of bothnominal and faulty behaviour of the automotive components to estimate on-line the End-Of-Life (EOL)and Remaining Useful Life (EUL) indicators for the automotive systems under investigation. A case studybased on the Delphi DFG1596 fuel pump has been presented to evaluate the proposed prognostic method.Finally, we perform a benchmark analysis of the deployment configurations of ATOMIC architecture interms of scalability and cost. Keywords:Model-based prognostic analysis | Big Data analysis | Cloud computing servicesa |
مقاله انگلیسی |
68 |
Optimal policy for structure maintenance: A deep reinforcement learning framework
سیاست بهینه برای نگهداری ساختار: یک چارچوب یادگیری تقویت عمیق-2020 The cost-effective management of aged infrastructure is an issue of worldwide concern. Markov decision process
(MDP) models have been used in developing structural maintenance policies. Recent advances in the artificial
intelligence (AI) community have shown that deep reinforcement learning (DRL) has the potential to solve large
MDP optimization tasks. This paper proposes a novel automated DRL framework to obtain an optimized
structural maintenance policy. The DRL framework contains a decision maker (AI agent) and the structure that
needs to be maintained (AI task environment). The agent outputs maintenance policies and chooses maintenance
actions, and the task environment determines the state transition of the structure and returns rewards to the
agent under given maintenance actions. The advantages of the DRL framework include: (1) a deep neural network
(DNN) is employed to learn the state-action Q value (defined as the predicted discounted expectation of the
return for consequences under a given state-action pair), either based on simulations or historical data, and the
policy is then obtained from the Q value; (2) optimization of the learning process is sample-based so that it can
learn directly from real historical data collected from multiple bridges (i.e., big data from a large number of
bridges); and (3) a general framework is used for different structure maintenance tasks with minimal changes to
the neural network architecture. Case studies for a simple bridge deck with seven components and a long-span
cable-stayed bridge with 263 components are performed to demonstrate the proposed procedure. The results
show that the DRL is efficient at finding the optimal policy for maintenance tasks for both simple and complex
structures. Keywords: Bridge maintenance policy | Deep reinforcement learning (DRL) | Markov decision process (MDP) | Deep Q-network (DQN) | Convolutional neural network (CNN) |
مقاله انگلیسی |
69 |
An Overview of AI-Enabled Remote Smart-Home Monitoring System Using LoRa
مروری بر سیستم مانیتورینگ از راه دور هوشمند در خانه با هوش مصنوعی با استفاده از LoRa-2020 With the advancement of communication
technology, Internet of Things (IoT) enabled smart
home (SH) applications have engrossed substantial
attention nowadays. However, a few meter range
coverage and higher implementation cost are the main
limitations of existing SH systems based on other
cellular networks or short distance technologies. In this
paper, a long range (LoRa) based SH system is
proposed for remote monitoring and maintenance of
IoT sensors and devices using artificial intelligence (AI)
concept. A brief overview of what tasks LoRa can
perform in SH networking are conferred. An AI-based
data flow system for IoT server and cloud is also
presented in this paper. Keywords: Low-power | wide area network (LPWAN) | internet of things (IoT) | long range (LoRa) | smart home (SH) | artificial intelligence (AI) |
مقاله انگلیسی |
70 |
Hybrid infrastructures, hybrid governance: New evidence from Nairobi (Kenya) on green-blue-grey infrastructure in informal settlements
زیرساخت های ترکیبی ، حاکمیت ترکیبی: شواهد جدید نایروبی (کنیا) در مورد زیرساخت های سبز-آبی خاکستری در شهرک های غیر رسمی-2020 In expanding informal neighborhoods of cities in sub-Saharan Africa, sustainable management of storm
and wastewater drainage is fundamental to improving living conditions. Planners debate the optimal
combination between "green" or natural infrastructure, traditional "grey" infrastructure, and "blue"
infrastructure, which mimics natural solutions using artificial materials. Many advocate for small-scale,
niche experiments with these approaches in informal settings, in order to learn how to navigate the
intrinsic constraints of space, contested land tenure, participation, and local maintenance. This paper
reports the benefits and limitations of implementing and managing local green, blue and grey
infrastructure solutions in an urban informal setting. We studied ten completed public space projects
that featured urban drainage infrastructure in the informal neighborhood of Kibera, Nairobi. The analysis
drew from ten surveys with project designers and seven semi-structured interviews with site managers.
The studied spaces featured different combinations of green, grey, and blue drainage infrastructure that
have evolved over years of operation, maintenance, and change in the settlement. All projects featured
participation in design, mixed design methods, hybrid infrastructure, and community governance
models with potential to interact successfully with municipal actors. Results show that involvement in
the co-development of small-scale green infrastructure changed peoples valuation, perception, and
stewardship of nature-based systems and ecosystem services. These results have implications for the
larger scale adoption, integration, and management of urban drainage infrastructure. They also suggest
that hybrid systems of infrastructure and governance constitute a resilient approach to incremental and
inclusive upgrading. Keywords: Green infrastructure | Urban drainage | Hybrid infrastructure | Governance | Participation | Climate vulnerability | Informal settlements | Community leadership |
مقاله انگلیسی |