An Overview of Extreme Learning Machine

Bohua, Deng; Zhang, Xinman; Gong, Weiyong; Shang, Dongpeng

doi:10.1109/crc.2019.00046

Cited by 18 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, to evaluate the correctness of the algorithm results, we will observe these three outputs for each scenario. In addition, we will assess the time performance of the algorithm depending on the increase in the number of visitors and the change of the merging parameter b in the machine learning model [ 40 – 42 ].…”

Section: Resultsmentioning

confidence: 99%

Cyber Risk Recommendation System for Digital Education Management Platforms

Yin¹,

Chen²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Covid-19 pandemic has ushered in a new school and academic year for students in a distance learning regime. This new daily routine was unprecedented and undoubtedly unusual, especially for the younger ones. At this point and at these ages, the risk of cyber fraud is even greater. The transition from the physical environment to the Internet took place quickly without the appropriate time to control potential risks and the proper information and training of teachers and students. Some common threats that need to be addressed to protect learners and their data when using e-learning methods are malicious remote access, malware, phishing, cyber fraud, etc. Considering the above situation, this work presents an innovative cyber risk recommendation system for digital education management platforms. The system in question is a distributed two-stage algorithm based on game theory and machine learning, which is trained by the constant change in the choice of recommendations by users to maximize security. We examine the algorithm’s ability to simulate a user system in which everyone independently selects a user recommendation, assesses the environment and the implications of this choice, and then concludes whether it will continue to have that recommendation fixed. The methodology with which we have represented the digital e-learning system has been done with an approach that directly corresponds with their general view as a cyber-physical-social system. We consider the digital school as an environment that brings limitations, leading us to a pretty demanding personalization problem. Users coexist in this environment, in which everyone acts voluntarily but influences and is influenced by the surrounding environment. Our results lead us to conclude that this algorithm responds in a fully effective, flexible, and efficient way to the needs of protection and risk assessment of e-learning education systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Cyber Risk Recommendation System for Digital Education Management Platforms

Yin¹,

Chen²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…For a given SLFN, there are N such equations (as many nodes of the hidden layer) that can be written as follows [ 26 ]:

where the array H is the output of the hidden layer.

…”

Section: Methodsmentioning

confidence: 99%

“…In the minimization process, the vector W , which is the sum of the weights ( w i , b i ) and the biases ( β i ), is adjusted iteratively according to the following relation [ 26 ]:

where n is the learning rate of the neural network. We used an easy-to-use, simple, and fast ELM as an algorithm for retrieving hidden variables in problem-solving.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Methods to Detect Voltage Glitch Attacks on IoT/IIoT Infrastructures

Jiang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A majority of modern IoT/IIoT digital systems rely on cryptographic implementations to provide satisfactory levels of security. Hardware attacks such as side-channel analysis attacks or fault injection attacks can significantly degrade and even eliminate the desired level of security of the infrastructure in question. One of the most dangerous attacks of this type is voltage glitch attacks (VGAs), which can change the intended behavior of a system. By effectively manipulating the voltage at a specific time, an error can be injected that can change the intentional conduct and bypass system security features or even extract confidential information such as encryption keys by analyzing incorrect outputs of the firmware. This study proposes an innovative VGAs detection system based on advanced machine learning. Specifically, an innovative semisupervised learning methodology is used that utilizes a hybrid combination of algorithms. Specifically, a heuristic clustering method is used based on a linear fragmentation of group classes. In contrast, the ELM methodology is used as an algorithm for retrieving hidden variables through convex optimization.

show abstract

“…The performance weights were then measured analytically, rather than iterated. [19,20] This paper is described in section 1 st Introduction of IDS, DL, EML. In section 2 nd we overview IDS and its various functions and numerous types of datasets used in IDS.…”

Section: Elmmentioning

confidence: 99%

A Review on Intrusion Detection System Based on Various Learning Techniques

Raj¹,

Jain²,

Kamble³

2021

IJAINN

View full text Add to dashboard Cite

In this world of the Internet, security plays an important role as Internet users grow rapidly. Security in the network is one of the modern periods' main issues. In the last decade, the exponential growth and massive use of the Internet have enabled system security vulnerabilities a critical aspect. Intrusion detection system to track unauthorized access as well as exceptional attacks through secured networks. Several experiments on the IDS have been carried out in recent years. And to know the current state of machine learning approaches to address the issue of intrusion detection. IDS is commonly used for the detection and recognition of cyberattacks at the network and host stage, in a timely and automatic manner. This research assesses the creation of a deep neural network (DNN), a form of deep learning model as well as ELM to detect unpredictable and unpredictable cyber-attacks

show abstract

An Overview of Extreme Learning Machine

Cited by 18 publications

References 34 publications

Cyber Risk Recommendation System for Digital Education Management Platforms

Cyber Risk Recommendation System for Digital Education Management Platforms

Machine Learning Methods to Detect Voltage Glitch Attacks on IoT/IIoT Infrastructures

A Review on Intrusion Detection System Based on Various Learning Techniques

Contact Info

Product

Resources

About