Genetically optimized extreme learning machine

Matias, Tiago; Araújo, Rui; Antunes, Carlos Henggeler; Gabriel, Dulce

doi:10.1109/etfa.2013.6647975

Cited by 8 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early stages of neural network development, evolutionary algorithms were commonly employed to find optimal architectures and weights [44]. Matias et al [45] utilized the genetically optimized extreme learning machine (GO-ELM) to optimize the network architecture. Some researchers [46,47] have employed an adaptive strategy to progressively expand the network structure layer by layer from a small network guided by specific principles.…”

Section: Optimized Network Structure Designmentioning

confidence: 99%

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

Lian,

Li,

Dong

et al. 2024

Electronics

View full text Add to dashboard Cite

Automatic detection of safety helmet wearing is significant in ensuring safe production. However, the accuracy of safety helmet detection can be challenged by various factors, such as complex environments, poor lighting conditions and small-sized targets. This paper presents a novel and efficient deep learning framework named High-Resolution You Only Look Once (HR-YOLO) for safety helmet wearing detection. The proposed framework synthesizes safety helmet wearing information from the features of helmet objects and human pose. HR-YOLO can use features from two branches to make the bounding box of suppression predictions more accurate for small targets. Then, to further improve the iterative efficiency and accuracy of the model, we design an optimized residual network structure by using Optimized Powered Stochastic Gradient Descent (OP-SGD). Moreover, a Laplace-Aware Attention Model (LAAM) is designed to make the YOLOv5 decoder pay more attention to the feature information from human pose and suppress interference from irrelevant features, which enhances network representation. Finally, non-maximum suppression voting (PA-NMS voting) is proposed to improve detection accuracy for occluded targets, using pose information to constrain the confidence of bounding boxes and select optimal bounding boxes through a modified voting process. Experimental results demonstrate that the presented safety helmet detection network outperforms other approaches and has practical value in application scenarios. Compared with the other algorithms, the proposed algorithm improves the precision, recall and mAP by 7.27%, 5.46% and 7.3%, on average, respectively.

show abstract

Section: Optimized Network Structure Designmentioning

confidence: 99%

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

Lian,

Li,

Dong

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In the ELM, several hidden node parameters such as input weights, bias, and impact factors are created randomly. In Figure 6 , x j represents the input parameter, and L is the number of parameter vectors in the extreme learning machine feature space acquired by parameter mapping [ 63 ] and linear variable solving [ 64 ]. ELM has three properties [ 65 ] compared with conventional ANN: The linking weights and thresholds are artificially set, which can be adjusted after setting.…”

Section: Machine Learning Techniquementioning

confidence: 99%

Prediction of Chloride Diffusion Coefficient in Concrete Modified with Supplementary Cementitious Materials Using Machine Learning Algorithms

Fuhaid

Alanazi

2023

Materials

View full text Add to dashboard Cite

The chloride diffusion coefficient (Dcl) is one of the most important characteristics of concrete durability. This study aimed to develop a prediction model for the Dcl of concrete incorporating supplemental cementitious material. The datasets of concrete containing supplemental cementitious materials (SCMs) such as tricalcium aluminate (C3A), ground granulated blast furnace slag (GGBFS), and fly ash were used in developing the model. Five machine learning (ML) algorithms including adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), support vector machine (SVM), and extreme learning machine (ELM) were used in the model development. The performance of the developed models was tested using five evaluation metrics, namely, normalized reference index (RI), coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE). The SVM models demonstrated the highest prediction accuracy with R2 values of 0.955 and 0.951 at the training and testing stage, respectively. The prediction accuracy of the machine learning (ML) algorithm was checked using the Taylor diagram and Boxplot, which confirmed that SVM is the best ML algorithm for estimating Dcl, thus, helpful in establishing reliable tools in concrete durability design.

show abstract

Analysis of Metaheuristic Algorithms for Optimized Extreme Learning Machines in Various Sectors

Devikanniga

Alex

2023

EAI/Springer Innovations in Communication and Computing

View full text Add to dashboard Cite

Genetically optimized extreme learning machine

Cited by 8 publications

References 23 publications

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

HR-YOLO: A Multi-Branch Network Model for Helmet Detection Combined with High-Resolution Network and YOLOv5

Prediction of Chloride Diffusion Coefficient in Concrete Modified with Supplementary Cementitious Materials Using Machine Learning Algorithms

Analysis of Metaheuristic Algorithms for Optimized Extreme Learning Machines in Various Sectors

Contact Info

Product

Resources

About