Deep learning's fitness for purpose: A transformation problem frame's perspective

Gudaparthi, Hemanth; Niu, Nan; Yang, Yu-Bin; Doren, Matthew Van; Johnson, Reese

doi:10.1049/cit2.12237

Cited by 3 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas many related research studies have been conducted earlier, most of these are based on equal-core piles, and simplified analysis of short-core composite piles is still rare. Today, deep learning [18][19][20] and artificial intelligence [21,22] provide a unique opportunity for predicting the axial force field of piles. Consequently, structural engineering is predictable due to deep learning's specific ability to handle complex nonlinear structural systems under various conditions.…”

Section: Calculation Of Composite Modulus Of Elasticity Of Sdcm Pilementioning

confidence: 99%

Nonlinear Analysis of Bearing Characteristics of Stiffened Deep Cement Mixing Piles under Vertical Loading

Jiu,

Gao,

Lei

et al. 2024

Buildings

View full text Add to dashboard Cite

Stiffened deep cement mixing (SDCM) piles are composite piles that combine the advantages of single large-diameter deep cement mixing (DCM) and precast concrete piles. They comprise precast concrete piles as the core and cast-in-place DCM piles as the outer layer. This study evaluates the bearing characteristics of SDCM piles under vertical loading. The composite modulus of elasticity of SDCM piles is first introduced and determined using the area-weighted average method. Then, the reliability of the proposed method is described by comparing the calculated results with the findings of the existing literature. Furthermore, a nonlinear simplified analysis method based on the load transfer method is proposed for vertical bearing characteristics of equal- and short-core SDCM piles under vertical loading. This method is developed by the finite difference method. The accuracy of the simplified method is validated by comparing its results with those from existing tests, theoretical analysis, and finite element simulations. The results of their study indicated that the area-weighted average method calculates the composite modulus of elasticity of the composite pile section of the SDCM piles with an error below 0.5% compared to the analytical method. This finding represents sufficient accuracy. The simplified calculation method established in this study is computationally stable. When the iteration factor is set to 10−6, as the number of discrete nodes n on the pile increases, the calculation results are stable with a good convergence when n > 30. The vertical bearing capacity and pile top stiffness of SDCM piles increased with the length of the core piles. There was a reasonable core-to-length ratio for SDCM piles in specific scenarios. An excessively long DCM pile section made its lower part force-free for a given length of core piles. The appropriate length of core piles should be determined in actual projects to avoid unnecessary material waste. An optimum ratio of core piles for SDCM piles was determined. Beyond this optimal value, an increase in the ratio of core piles controlled the pile settlement in a limited manner.

show abstract

Section: Calculation Of Composite Modulus Of Elasticity Of Sdcm Pilementioning

confidence: 99%

Nonlinear Analysis of Bearing Characteristics of Stiffened Deep Cement Mixing Piles under Vertical Loading

Jiu,

Gao,

Lei

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…We bring together visual features obtained from the training dataset with text features extracted from subtitles across modalities, and integrate them into joint features for downstream classification tasks. Specifically, the text feature uses the bidirectional encoder representation from the Transformers (BERT) pre-training model, adds context using the attention mechanism, and solves the parallel calculation between sentences [19][20][21]. Video features are extended from image space to spatio-temporal three-dimensional volume through a self-attention mechanism, which treats video as a series of patches extracted from a single frame.…”

Section: Introductionmentioning

confidence: 99%

A Short Video Classification Framework Based on Cross-Modal Fusion

Pang,

Guo,

Yan

et al. 2023

Sensors

View full text Add to dashboard Cite

The explosive growth of online short videos has brought great challenges to the efficient management of video content classification, retrieval, and recommendation. Video features for video management can be extracted from video image frames by various algorithms, and they have been proven to be effective in the video classification of sensor systems. However, frame-by-frame processing of video image frames not only requires huge computing power, but also classification algorithms based on a single modality of video features cannot meet the accuracy requirements in specific scenarios. In response to these concerns, we introduce a short video categorization architecture centered around cross-modal fusion in visual sensor systems which jointly utilizes video features and text features to classify short videos, avoiding processing a large number of image frames during classification. Firstly, the image space is extended to three-dimensional space–time by a self-attention mechanism, and a series of patches are extracted from a single image frame. Each patch is linearly mapped into the embedding layer of the Timesformer network and augmented with positional information to extract video features. Second, the text features of subtitles are extracted through the bidirectional encoder representation from the Transformers (BERT) pre-training model. Finally, cross-modal fusion is performed based on the extracted video and text features, resulting in improved accuracy for short video classification tasks. The outcomes of our experiments showcase a substantial superiority of our introduced classification framework compared to alternative baseline video classification methodologies. This framework can be applied in sensor systems for potential video classification.

show abstract

Analyses of Pile-Supported Structures with Base Isolation Systems by Shaking Table Tests

Song,

Jeong

2024

Buildings

View full text Add to dashboard Cite

The dynamic behavior of a pile-supported structure with a base isolator was investigated by using 1 g shaking table model tests considering soil–structure interaction (SSI). The emphasis was placed on evaluating the effect of the with/without developed base isolator on the dynamic behavior of end-bearing piles and structures. The experiment was performed through sweep tests and sinusoidal wave tests. As a result of the tests, the developed base isolator was found to effectively reduce the structure’s resonant frequencies and damped the response acceleration under resonance frequencies. According to sweep tests, the base shear force of the pile-supported structure system tends to decrease as the relative density of the soil increases during resonance. It showed that the base isolator tends to reduce significantly the response acceleration of not only the rigid-based structure but also the pile-supported structure. It was shown that although the isolated superstructure recorded large horizontal displacements, piles experienced reduced horizontal displacement and bending moments, regardless of soil conditions.

show abstract

Deep learning's fitness for purpose: A transformation problem frame's perspective

Cited by 3 publications

References 38 publications

Nonlinear Analysis of Bearing Characteristics of Stiffened Deep Cement Mixing Piles under Vertical Loading

Nonlinear Analysis of Bearing Characteristics of Stiffened Deep Cement Mixing Piles under Vertical Loading

A Short Video Classification Framework Based on Cross-Modal Fusion

Analyses of Pile-Supported Structures with Base Isolation Systems by Shaking Table Tests

Contact Info

Product

Resources

About