A new imbalanced data oversampling method based on Bootstrap method and Wasserstein Generative Adversarial Network.

Due to their high bias in favor of the majority class, traditional machine learning classifiers face a great challenge when there is a class imbalance in biological data. More recently, generative adversarial networks (GANs) have been applied to imbalanced data classification. For GANs, the distribution of the minority class data fed into discriminator is unknown. The input to the generator is random noise ($ z $) drawn from a standard normal distribution $ N(0, 1) $. This method inevitably increases the training difficulty of the network and reduces the quality of the data generated. In order to solve this problem, we proposed a new oversampling algorithm by combining the Bootstrap method and the Wasserstein GAN Network (BM-WGAN). In our approach, the input to the generator network is the data ($ z $) drawn from the distribution of minority class estimated by the BM. The generator was used to synthesize minority class data when the network training is completed. Through the above steps, the generator model can learn the useful features from the minority class and generate realistic-looking minority class samples. The experimental results indicate that BM-WGAN improves the classification performance greatly compared to other oversampling algorithms. The BM-WGAN implementation is available at: https://github.com/ithbjgit1/BMWGAN.git.

Correlation between craniocervical posture and upper airway dimension in patients with bilateral anterior disc displacement.

OBJECTIVE: To investigate the relationship between upper airway dimension and craniocervical posture in adult patients with bilateral anterior disc displacement and to provide some references for clinical diagnosis and plan formulation in orthodontics. METHODS: Based on RDC/TMD (Research Diagnostic Criteria for Temporomandibular Disorder), 98 Patients were divided into three groups by two experienced TMJ (Temporomandibular Joint) specialists: bilateral disc normal position group (BN), bilateral anterior disc displacement with reduction group (ADDWR) and bilateral anterior disc displacement without reduction group (ADDWoR). Inter-group comparison and correlation analysis were performed after 11 craniocervical posture and 15 upper airway dimension measurements finished with Dolphin and Uceph software in Two or Three-dimensional. RESULTS: Anterior disc displacement often accompanied with extension of craniocervical posture, as ADDWR and ADDWoR groups have significantly higher cervical curvature and inclination than BN group (P < 0.05). Simultaneously anterior disc displacement often associated with constrained upper airway dimension for the total and each segment upper airway volume were significantly smaller in ADDWR and ADDWoR than BN group (P < 0.05). Correlation analysis revealed that C0-C1 (the distance from the base of the occipital bone (C0) to the posterior arch of the atlas (C1)) is significantly related to the total and each segment upper airway volume reduction (P < 0.05). CONCLUSION: There exists markedly close correlation between anterior disc displacement and craniocervical posture forward extension, which may be physiologically adaptive cervical extension to keep oropharyngeal airway unobstructed as upper airway dimension constrained by anterior disc displacement. CLINICAL RELEVANCE: These findings allow us to infer the potential consequences if the treatment of anterior disc displacement would result in an improvement of intervertebral relationships and upper airway constraint.

A new Monte Carlo sampling method based on Gaussian Mixture Model for imbalanced data classification.

Imbalanced data classification has been a major topic in the machine learning community. Different approaches can be taken to solve the issue in recent years, and researchers have given a lot of attention to data level techniques and algorithm level. However, existing methods often generate samples in specific regions without considering the complexity of imbalanced distributions. This can lead to learning models overemphasizing certain difficult factors in the minority data. In this paper, a Monte Carlo sampling algorithm based on Gaussian Mixture Model (MCS-GMM) is proposed. In MCS-GMM, we utilize the Gaussian mixed model to fit the distribution of the imbalanced data and apply the Monte Carlo algorithm to generate new data. Then, in order to reduce the impact of data overlap, the three sigma rule is used to divide data into four types, and the weight of each minority class instance based on its neighbor and probability density function. Based on experiments conducted on Knowledge Extraction based on Evolutionary Learning datasets, our method has been proven to be effective and outperforms existing approaches such as Synthetic Minority Over-sampling TEchnique.

Multiple fluorescence and hydrogen peroxide-responsive properties of novel triphenylamine-benzothiazole derivatives.

A novel fluorescent dye molecule - triphenylamine (TPA)-benzothiazole (BZT) - based on excited state intramolecular proton transfer (ESIPT) was prepared by the Suzuki coupling reaction. The photophysical property assay indicates that BZT-TPA appeared in distinguishable colors in mixed solvents with different water contents. Moreover, BZT-TPA exhibited observable AIE behavior. On this basis, a fluorescent probe BZT-TPA-BO was synthesized for detecting H2O2. This probe molecule was found to have excellent selectivity, rapid response, and good linear relationship (R2 = 0.989) for detecting H2O2 in aqueous medium. Through DFT calculation, fluorescence spectrum, nuclear magnetic titration and HR-MS, the mechanism of recognition of H2O2 by the probe BZT-TPA-BO is proposed. In addition, the probe BZT-TPA-BO to some extent exhibited better performance for detecting exogenous H2O2 in HeLa cells.