Improved Genetic Optimized Feature Selection for Online Sequential Extreme Learning Machine

Kale, Archana; Sonawane, Sumedh; Wahul, Revati M.; Dudhedia, M. A.

doi:10.18280/isi.270519

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the scientific work by Wang et al [14][15][16] regarding the study of prospects for the development of highly reliable computers using a reliable architecture of a set of instruction and emulators, the researcher draws attention to the importance of the architecture of computing machines and the speed of code assembly for the reliability and durability of functioning of modern computing technology. According to the researcher, the acceleration of code assembly can be successfully implemented through the use of various architectural solutions in computer technology when strictly following the program instructions.…”

Section: Discussionmentioning

confidence: 99%

Accelerating Code Assembly: Exploiting Heterogeneous Computing Architectures for Optimization

Karyonov

2023

ISI

View full text Add to dashboard Cite

Amid rapid technological advancements, the efficient optimization of software code assembly and compilation is paramount to the swift and reliable functioning of highperformance computing systems. This study investigates the potential for boosting code assembly speed by exploiting various computing architectures. The adopted methodology encompasses system analysis, examination of diverse computer system architectures, and the application of optimization and resource management techniques to enhance the assembly and compilation of program codes effectively. The paper delves into the evolution of computer architecture and underscores the importance of machine code, elucidating their impacts on IT development. Key areas of study include mobile object tracking, cache memory-based architectures, and GPU inference mechanisms for neural networks. The criticality of expertise, security, and contextual understanding when adopting these technologies is also emphasized. The findings from this study could catalyze the inception of novel code assembly technologies, thereby optimizing computing efficiency and expediting software development. Consequently, these advancements could diminish the time required for program creation and launch, thereby elevating industry productivity. The practical significance of this research stems from its potential application in accelerating code assembly.

show abstract

Section: Discussionmentioning

confidence: 99%

Accelerating Code Assembly: Exploiting Heterogeneous Computing Architectures for Optimization

Karyonov

2023

ISI

View full text Add to dashboard Cite

show abstract

“…With flattened inputs, a fully connected layer connects all neurons. The FC layer, if present, is usually found at the conclusion of the CNN design and can be utilized to optimize goals like class evaluation [16][17][18][19][20][21][22].…”

Section: Convolution Neural Network Modelmentioning

confidence: 99%

“…CG has no PD symptoms indicated by SL 0. Additional groups were categorized as SL: 1-3 based on the UPDRS III (20) and also the updated H and Y evaluations (21,22). (See Table 2).…”

Section: Introductionmentioning

confidence: 99%

Detection of Parkinson’s Disease Using the Spiral Diagram and Convolutional Neural Network

Singh¹,

Khare²

2022

ISI

View full text Add to dashboard Cite

This study intends to propose a PD detection using spiral sketching and CNN. The fundamental idea is to analyze a person's spiral drawings and classify them as healthy or having Parkinson's disease. Spiral sketches drawn by healthy people look almost like standard spiral shapes. However, the spirals drawn by people with Parkinson's disease look distorted because they deviate significantly from their perfect spiral shape due to slow movement, and poor hand-brain coordination. In this paper Convolution, Neural Network is used to detect Parkinson’s, and 83.6% classification accuracy is obtained.

show abstract

Parallel ensemble of a randomization-based online sequential neural network for classification problems using a frequency criterion

Gelvez-Almeida,

Barrientos,

Vilches-Ponce

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Randomization-based neural networks have gained wide acceptance in the scientific community owing to the simplicity of their algorithm and generalization capabilities. Random vector functional link (RVFL) networks and their variants are a class of randomization-based neural networks. RVFL networks have shown promising results in classification, regression, and clustering problems. For real-world applications, learning algorithms that can train with new samples over previous results are necessary because of to the constant generation of problems related to large-scale datasets. Various online sequential algorithms, commonly involving an initial learning phase followed by a sequential learning phase, have been proposed to address this issue. This paper presents a training algorithm based on multiple online sequential random vector functional link (OS-RVFL) networks for large-scale databases using a shared memory architecture. The training dataset is distributed among p OS-RVFL networks, which are trained in parallel using p threads. Subsequently, the test dataset samples are classified using each trained OS-RVFL network. Finally, a frequency criterion is applied to the results obtained from each OS-RVFL network to determine the final classification. Additionally, an equation was derived to reasonably predict the total training time of the proposed algorithm based on the learning time in the initial phase and the time scaling factor compared to the sequential learning phase. The results demonstrate a drastic reduction in training time because of data distribution and an improvement in accuracy because of the adoption of the frequency criterion.

show abstract

Improved Genetic Optimized Feature Selection for Online Sequential Extreme Learning Machine

Cited by 3 publications

References 0 publications

Accelerating Code Assembly: Exploiting Heterogeneous Computing Architectures for Optimization

Accelerating Code Assembly: Exploiting Heterogeneous Computing Architectures for Optimization

Detection of Parkinson’s Disease Using the Spiral Diagram and Convolutional Neural Network

Parallel ensemble of a randomization-based online sequential neural network for classification problems using a frequency criterion

Contact Info

Product

Resources

About