Improved Neural Network using Integral-RELU based Prevention Activation for Face Detection

Kirana, Kartika Candra; Wibawanto, Slamet; Hidayah, Nur; Cahyono, Gigih Prasetyo; Asfani, Khoirudin

doi:10.1109/iceeie47180.2019.8981443

Cited by 17 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The jump connection of residual data through the convolution layer and ADR block follows the principle of 'first in first out'; that is, the input image is a jump connected to the corresponding last deconvolution layer, and the second convolution layer is a jump connected to the corresponding penultimate ADR block. The attention decoder is composed of an ADR block, deconvolution layer and ReLU unit [21].…”

Section: Residual Stack Denoise Autoencoder (Rsdae)mentioning

confidence: 99%

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Guo,

Song,

Zeng

et al. 2023

Eng. Res. Express

View full text Add to dashboard Cite

To improve pipeline transportation efficiency, long-distance pipelines need to be cleaned regularly. Pipeline inspection gauges (PIGs) are widely used in pigging operations. The traditional PIG localization method generally has a large error and cannot achieve continuous tracking. To solve the problem of PIG real-time tracking and localization, this paper proposes a method of PIG localization for oil pipelines based on a denoising autoencoder(DAE). The attention deconvolution residual block (ADR) is introduced in the decoder part of the DAE, so that this model can learn and use global information to selectively emphasize key features, suppress useless features, and improve the noise removal performance of the model. After denoising, the negative pressure wave(NPW) signal is normalized, the time delay is extracted, and the PIG is located using the NPW localization formula. Experiments show that this method can effectively achieve real-time PIG localization. Compared with the EMD and DAE positioning methods, the relative positioning accuracy is increased by 3.5 times and 8.4 times, respectively.

show abstract

Section: Residual Stack Denoise Autoencoder (Rsdae)mentioning

confidence: 99%

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Guo,

Song,

Zeng

et al. 2023

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…The further research is combining attendance of teleconference-oriented LMS will be conducted using the approaches of previous study [26]- [28]. In addition to improving the sound noise, the noise signal needs to be eliminated.…”

Section: Conclussionsmentioning

confidence: 99%

Design of Teleconference-based Learning Management System for a Learning Tool in the Co-19 Pandemic

Kirana

Wibawanto

Cahyono³

2020

2020 4th International Conference on Vocational Education and Training (ICOVET)

Self Cite

View full text Add to dashboard Cite

The Co-19 pandemic affects worldwide classical education. It has led to the optimization of E-Learning. Learning Management Systems integrate the learning materials and human resources systems, but cannot provide human interaction in real-time. Teleconferencing platforms allowed communication in real-time, but cannot integrate the learning materials and human resources systems. In order to optimize real-time interaction in the learning management system, a teleconference-oriented learning management system is proposed. The configuration of database and user interface are required to combine the two systems. The Teleconference Platform was also hired as LMS course. In order to determine the experience of the teleconference-oriented LMS, the User Experience Questionnaire (UEQ) of the proposed LMS and the original LMS is tested using T-Test. UEQ is filled out by 85 students. The result show that attractiveness, perspicacity, performance, dependability, and stimulation reached respectively 0

show abstract

“…[4]. In another case study the activation model also improves the classification results [10]. They was inspiring to scrutinize the CNN settings to produce more optimal values.…”

Section: Introductionmentioning

confidence: 97%

“…Based on all those studies, CNN was successful in classification [4], [10], [11]. However, there are several 2DCNN settings that need to be set at the architectural design stage, such as the use of dropouts, output shapes, activation models, and early stopping.…”

Section: Introductionmentioning

confidence: 99%

Optimization of 2D-CNN Setting for the classification of covid disease using Lung CT Scan

Kirana

Wibawanto²,

Hidayat³

2022

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

RT-PCR is considered the best diagnostic tool. Previous studies have demonstrated the reliability of CNN in classifying classifications, but CNN requires a lot of training data. Meanwhile, at the CT Scan clinic, patients are limited. Therefore, exploration of 2D-CNN settings is proposed to optimize CNN performance on limited data. We compare: (1) activation models, (2) output shapes per layer, (3) dropout layers, and (4) early stopping values. The test results show that RELU activation is better than Sigmoid. Rescaling (128x128) is better for scala (64x64) and (256x256) which affects the output shape model of each layer. In this learning stage, the use of dropouts in the CNN architecture achieves robust accuracy than the architecture that ignores dropouts. The use of 15 early stoppings is better than other values compared. 20 images of pneumonia and 20 images of covid have been tested using the proposed method and achieved 87.50% accuracy, 80.00% precision, 100% recall, and 99.89% F1-Score. Our method is superior to the the comparison method in terms of accuracy, precision, recall, and f1-score, which achieves 85%, 70%, 100%, and 82.35%, respectively.

show abstract

Improved Neural Network using Integral-RELU based Prevention Activation for Face Detection

Cited by 17 publications

References 17 publications

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Research on pipeline inspection gauges localization based on residual denoising autoencoder

Design of Teleconference-based Learning Management System for a Learning Tool in the Co-19 Pandemic

Optimization of 2D-CNN Setting for the classification of covid disease using Lung CT Scan

Contact Info

Product

Resources

About