Using weakly supervised deep learning to classify and segment single‐molecule break‐junction conductance traces

ChemPhysChem ◽  
2021 ◽  
Author(s):  
Dongying Lin ◽  
Zhihao Zhao ◽  
Haoyang Pan ◽  
Shi Li ◽  
Yongfeng Wang ◽  
...  
Nano Research ◽  
2011 ◽  
Vol 4 (12) ◽  
pp. 1199-1207 ◽  
Author(s):  
Yang Yang ◽  
Zhaobin Chen ◽  
Junyang Liu ◽  
Miao Lu ◽  
Dezhi Yang ◽  
...  

2016 ◽  
Vol 14 (1) ◽  
pp. 172988141769231 ◽  
Author(s):  
Yingfeng Cai ◽  
Youguo He ◽  
Hai Wang ◽  
Xiaoqiang Sun ◽  
Long Chen ◽  
...  

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.


Author(s):  
Rui Guo ◽  
Xiaobin Hu ◽  
Haoming Song ◽  
Pengpeng Xu ◽  
Haoping Xu ◽  
...  

Abstract Purpose To develop a weakly supervised deep learning (WSDL) method that could utilize incomplete/missing survival data to predict the prognosis of extranodal natural killer/T cell lymphoma, nasal type (ENKTL) based on pretreatment 18F-FDG PET/CT results. Methods One hundred and sixty-seven patients with ENKTL who underwent pretreatment 18F-FDG PET/CT were retrospectively collected. Eighty-four patients were followed up for at least 2 years (training set = 64, test set = 20). A WSDL method was developed to enable the integration of the remaining 83 patients with incomplete/missing follow-up information in the training set. To test generalization, these data were derived from three types of scanners. Prediction similarity index (PSI) was derived from deep learning features of images. Its discriminative ability was calculated and compared with that of a conventional deep learning (CDL) method. Univariate and multivariate analyses helped explore the significance of PSI and clinical features. Results PSI achieved area under the curve scores of 0.9858 and 0.9946 (training set) and 0.8750 and 0.7344 (test set) in the prediction of progression-free survival (PFS) with the WSDL and CDL methods, respectively. PSI threshold of 1.0 could significantly differentiate the prognosis. In the test set, WSDL and CDL achieved prediction sensitivity, specificity, and accuracy of 87.50% and 62.50%, 83.33% and 83.33%, and 85.00% and 75.00%, respectively. Multivariate analysis confirmed PSI to be an independent significant predictor of PFS in both the methods. Conclusion The WSDL-based framework was more effective for extracting 18F-FDG PET/CT features and predicting the prognosis of ENKTL than the CDL method.


2019 ◽  
Vol 116 (3) ◽  
pp. 281a
Author(s):  
Peiyi Zhang ◽  
Sheng Liu ◽  
Abhishek Chaurasia ◽  
Donghan Ma ◽  
Michael J. Mlodzianoski ◽  
...  

2014 ◽  
Vol 174 ◽  
pp. 91-104 ◽  
Author(s):  
Kun Wang ◽  
Joseph Hamill ◽  
Jianfeng Zhou ◽  
Cunlan Guo ◽  
Bingqian Xu

The lack of detailed experimental controls has been one of the major obstacles hindering progress in molecular electronics. While large fluctuations have been occurring in the experimental data, specific details, related mechanisms, and data analysis techniques are in high demand to promote our physical understanding at the single-molecule level. A series of modulations we recently developed, based on traditional scanning probe microscopy break junctions (SPMBJs), have helped to discover significant properties in detail which are hidden in the contact interfaces of a single-molecule break junction (SMBJ). For example, in the past we have shown that the correlated force and conductance changes under the saw tooth modulation and stretch–hold mode of PZT movement revealed inherent differences in the contact geometries of a molecular junction. In this paper, using a bias-modulated SPMBJ and utilizing emerging data analysis techniques, we report on the measurement of the altered alignment of the HOMO of benzene molecules with changing the anchoring group which coupled the molecule to metal electrodes. Further calculations based on Landauer fitting and transition voltage spectroscopy (TVS) demonstrated the effects of modulated bias on the location of the frontier molecular orbitals. Understanding the alignment of the molecular orbitals with the Fermi level of the electrodes is essential for understanding the behaviour of SMBJs and for the future design of more complex devices. With these modulations and analysis techniques, fruitful information has been found about the nature of the metal–molecule junction, providing us insightful clues towards the next step for in-depth study.


Author(s):  
Ophir Gozes ◽  
Maayan Frid-Adar ◽  
Nimrod Sagie ◽  
Asher Kabakovitch ◽  
Dor Amran ◽  
...  

Nanoscale ◽  
2020 ◽  
Vol 12 (15) ◽  
pp. 8355-8363 ◽  
Author(s):  
András Magyarkuti ◽  
Nóra Balogh ◽  
Zoltán Balogh ◽  
Latha Venkataraman ◽  
András Halbritter

A combined principal component and neural network analysis serves as an efficient tool for the unsupervised recognition of unobvious but highly relevant trace classes in single-molecule break junction data.


Sign in / Sign up

Export Citation Format

Share Document