Validating neural network-based online adaptive systems: a case study

Liu, Yan; Čukić, Bojan; Gururajan, Srikanth

doi:10.1007/s11219-007-9017-4

Cited by 14 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the analysis of the rate of convergence may inspire confidence that system state will predictably quickly reach a desirable state. Here we intentionally use term "desirable" rather than "correct" state because we may not know what a correct adaptation is in an unforeseen context [52]. This problem necessitates investigation of scientific principles needed to move software assurance beyond current conceptions and calculations of correctness.…”

Section: Adaptation-specific Model-driven Environmentsmentioning

confidence: 99%

Software Engineering for Self-Adaptive Systems: A Research Roadmap

Cheng¹,

Lemos²,

Giese³

et al. 2009

Lecture Notes in Computer Science

Self Cite

797

535

View full text Add to dashboard Cite

Abstract. The goal of this roadmap paper is to summarize the state-ofthe-art and to identify critical challenges for the systematic software engineering of self-adaptive systems. The paper is partitioned into four parts, one for each of the identified essential views of self-adaptation: modelling dimensions, requirements, engineering, and assurances. For each view, we present the state-of-the-art and the challenges that our community must address. This roadmap paper is a result of the Dagstuhl Seminar 08031 on "Software Engineering for Self-Adaptive Systems, " which took place in January 2008.

show abstract

Section: Adaptation-specific Model-driven Environmentsmentioning

confidence: 99%

Software Engineering for Self-Adaptive Systems: A Research Roadmap

Cheng¹,

Lemos²,

Giese³

et al. 2009

Lecture Notes in Computer Science

Self Cite

797

535

View full text Add to dashboard Cite

show abstract

“…Botnets are developed in different ways. Botnets can be categorized into three major categories like P2P, Web and IRC depends on how bots are restricted by the masters [34], [35].…”

Section: Botnet-based Ddos Attacksmentioning

confidence: 99%

A Review on Detection, Defensive and Mitigation of DDoS Attacks with Traceback Methods

Alluraiah¹

2021

TURCOMAT

View full text Add to dashboard Cite

The most tremendous attacks in the globeis Distributed Denial of Service (DDoS) attacks, which is the very powerful and typical external attempts to weak bandwidth of the victims or interrupt legitimate users to access the services. The traditional Internet services of architecture is unsafe to DDoS attacks and the collection of internet connected devices affected by the malwares, then it allows the intruders to control all the internet connected devices is a Botnet or attacked networks.In Botnet, one disadvantage is that if the Botnet is set up then the intruder creates the large-scale networks to attack on more number of victims.As anoutcome of the permanentgrowth of latest attacks and constantly growingcollection of weak sources on the internet, the Detection, Prevention of DDoS attack and Trace back methods have been proposed.In this paper, we have reviewed various types of classification methods for DDoS attacks and its countermeasures. Finally,this survey paper assesses and illustrates the efficiency of variousDDoS attacks including detection, defense and mitigation, trace back methods. These methods rely on better router functionality or changes to existing protocols. The advantages and disadvantages of existing research methods in this problem are also described..

show abstract

“…Artificial Neural Networks are famous learning models for their ability to cope with the demands of a changing environment (Liu et al, 2007). In this study, we analyze the application of Artificial Neural Network (ANN) controller in process industry as a replacement of PID control (or other similar controls) to control the angular position of a DC motor.…”

Section: Applying Artificial Neural Network (Ann) Controllermentioning

confidence: 99%

On replacing PID controller with ANN controller for DC motor position control

Aamir¹

2013

IJRSC

View full text Add to dashboard Cite

The process industry implements many techniques with certain parameters in its operations to control the working of several actuators on field. Amongst these actuators, DC motor is a very common machine. The angular position of DC motor can be controlled to drive many processes such as the arm of a robot. The most famous and well known controller for such applications is PID controller. It uses proportional, integral and derivative functions to control the input signal before sending it to the plant unit. In this paper, another controller based on Artificial Neural Network (ANN) control is examined to replace the PID controller for controlling the angular position of a DC motor to drive a robot arm. Simulation is performed in MATLAB after training the neural network (supervised learning) and it is shown that results are acceptable and applicable in process industry for reference control applications. The paper also indicates that the ANN controller can be less complicated and less costly to implement in industrial control applications as compared to some other proposed schemes.

show abstract

Validating neural network-based online adaptive systems: a case study

Cited by 14 publications

References 12 publications

Software Engineering for Self-Adaptive Systems: A Research Roadmap

Software Engineering for Self-Adaptive Systems: A Research Roadmap

A Review on Detection, Defensive and Mitigation of DDoS Attacks with Traceback Methods

On replacing PID controller with ANN controller for DC motor position control

Contact Info

Product

Resources

About