Deep learning of dispersion engineering in two-dimensional phononic crystals

The emergence and development of deep learning theory in machine learning field provide new method for visual-based pedestrian recognition technology. To achieve better performance in this application, an improved weakly supervised hierarchical deep learning pedestrian recognition algorithm with two-dimensional deep belief networks is proposed. The improvements are made by taking into consideration the weaknesses of structure and training methods of existing classifiers. First, traditional one-dimensional deep belief network is expanded to two-dimensional that allows image matrix to be loaded directly to preserve more information of a sample space. Then, a determination regularization term with small weight is added to the traditional unsupervised training objective function. By this modification, original unsupervised training is transformed to weakly supervised training. Subsequently, that gives the extracted features discrimination ability. Multiple sets of comparative experiments show that the performance of the proposed algorithm is better than other deep learning algorithms in recognition rate and outperforms most of the existing state-of-the-art methods in non-occlusion pedestrian data set while performs fair in weakly and heavily occlusion data set.

Download Full-text

Low frequency phononic band structures in two-dimensional arc-shaped phononic crystals

Physics Letters A ◽

10.1016/j.physleta.2012.05.037 ◽

2012 ◽

Vol 376 (33) ◽

pp. 2256-2263 ◽

Cited By ~ 26

Author(s):

Zhenlong Xu ◽

Fugen Wu ◽

Zhongning Guo

Keyword(s):

Low Frequency ◽

Phononic Crystals ◽

Two Dimensional ◽

Band Structures

Download Full-text

Complex dispersion analysis of topologically protected interface states in two-dimensional viscoelastic phononic crystals

Journal of Physics D Applied Physics ◽

10.1088/1361-6463/ac2f67 ◽

2021 ◽

Author(s):

Tian-Xue Ma ◽

Yan-Feng Wang ◽

Li Xiao-Shuang ◽

Chuanzeng Zhang ◽

Yue-Sheng Wang

Keyword(s):

Dispersion Analysis ◽

Interface States ◽

Phononic Crystals ◽

Two Dimensional ◽

Complex Dispersion

Download Full-text

Robustly Tuning Bandgaps in Two-Dimensional Soft Phononic Crystals with Criss-Crossed Elliptical Holes

Acta Mechanica Solida Sinica ◽

10.1007/s10338-018-0044-4 ◽

2018 ◽

Vol 31 (5) ◽

pp. 573-588 ◽

Cited By ~ 9

Author(s):

Nan Gao ◽

Yi-lan Huang ◽

Rong-hao Bao ◽

Wei-qiu Chen

Keyword(s):

Phononic Crystals ◽

Two Dimensional ◽

Elliptical Holes

Download Full-text

Tunable Band Gaps of Acoustic Waves in Two-Dimensional Phononic Crystals With Reticular Band Structures

Volume 15: Sound, Vibration and Design ◽

10.1115/imece2009-13102 ◽

2009 ◽

Cited By ~ 1

Author(s):

Zi-Gui Huang ◽

Yunn-Lin Hwang ◽

Pei-Yu Wang ◽

Yen-Chieh Mao

Keyword(s):

Acoustic Waves ◽

Composite Structures ◽

Phononic Crystals ◽

Band Gaps ◽

Sound Insulation ◽

Two Dimensional ◽

The Finite Element Method ◽

Elastic Band ◽

Band Structures ◽

Elastic Band Gaps

The excellent applications and researches of so-called photonic crystals raise the exciting researches of phononic crystals. By the analogy between photon and phonon, repetitive composite structures that are made up of different elastic materials can also prevent elastic waves of some certain frequencies from passing by, i.e., the frequency band gap features also exist in acoustic waves. In this paper, we present the results of the tunable band gaps of acoustic waves in two-dimensional phononic crystals with reticular band structures using the finite element method. Band gaps variations of the bulk modes due to different thickness and angles of reticular band structures are calculated and discussed. The results show that the total elastic band gaps for mixed polarization modes can be enlarged or reduced by adjusting the orientation of the reticular band structures. The phenomena of band gaps of elastic or acoustic waves can potentially be utilized for vibration-free, high-precision mechanical systems, and sound insulation.

Download Full-text