Study on the Classification Performance of Vibration Lamella Thickener

This paper mainly describes the relation between the overflow quantity, separation size, classification efficiency and Reynolds number under the stable stage of vibration lamella thickener. Using a device with one tilting-narrow flow classification element, experiments on classification of pure quartz slurry have been carried out.we can conclude that the overflow quantity is proportional to the separation and classification is best under the condition of turbulent flow.

Download Full-text

Strategy and Performance across Size Classification of Small Firms in the United States

INTERNATIONAL BUSINESS REVIEW ◽

10.21739/ibr.2004.12.8.2.207 ◽

2004 ◽

Vol 8 (2) ◽

pp. 207

Author(s):

Jin Han Kim

Keyword(s):

United States ◽

Small Firms ◽

The United States ◽

Size Classification ◽

And Performance

Download Full-text

A Study on the Auxiliary Diagnosis of Thyroid Disease Images Based on Multiple Dimensional Deep Learning Algorithms

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405615666190115155223 ◽

2020 ◽

Vol 16 (3) ◽

pp. 199-205

Author(s):

Yuejun Liu ◽

Yifei Xu ◽

Xiangzheng Meng ◽

Xuguang Wang ◽

Tianxu Bai

Keyword(s):

Deep Learning ◽

Learning Algorithms ◽

Region Of Interest ◽

Classification Performance ◽

Thyroid Diseases ◽

Great Success ◽

Learning Models ◽

Good Classification Performance ◽

Spect Images

Background: Medical imaging plays an important role in the diagnosis of thyroid diseases. In the field of machine learning, multiple dimensional deep learning algorithms are widely used in image classification and recognition, and have achieved great success. Objective: The method based on multiple dimensional deep learning is employed for the auxiliary diagnosis of thyroid diseases based on SPECT images. The performances of different deep learning models are evaluated and compared. Methods: Thyroid SPECT images are collected with three types, they are hyperthyroidism, normal and hypothyroidism. In the pre-processing, the region of interest of thyroid is segmented and the amount of data sample is expanded. Four CNN models, including CNN, Inception, VGG16 and RNN, are used to evaluate deep learning methods. Results: Deep learning based methods have good classification performance, the accuracy is 92.9%-96.2%, AUC is 97.8%-99.6%. VGG16 model has the best performance, the accuracy is 96.2% and AUC is 99.6%. Especially, the VGG16 model with a changing learning rate works best. Conclusion: The standard CNN, Inception, VGG16, and RNN four deep learning models are efficient for the classification of thyroid diseases with SPECT images. The accuracy of the assisted diagnostic method based on deep learning is higher than that of other methods reported in the literature.

Download Full-text

Effects of Blade Parameters on the Flow Field and Classification Performance of the Vertical Roller Mill via Numerical Investigations

Mathematical Problems in Engineering ◽

10.1155/2020/3290694 ◽

2020 ◽

Vol 2020 ◽

pp. 1-15

Author(s):

Chang Liu ◽

Zuobing Chen ◽

Weili Zhang ◽

Chenggang Yang ◽

Ya Mao ◽

...

Keyword(s):

Flow Field ◽

Pressure Difference ◽

Continuous Phase ◽

Classification Performance ◽

Field Analysis ◽

Discrete Phase Model ◽

Roller Mill ◽

Discrete Phase ◽

Vertical Roller ◽

Classification Efficiency

The vertical roller mill is an important crushing and grading screening device widely used in many industries. Its classification efficiency and the pressure difference determine the entire producing capacity and power consumption, respectively, which makes them the two key indicators describing the mill performance. Based on the DPM (Discrete Phase Model) and continuous phase coupling model, the flow field characteristics in the vertical roller mill including the velocity and pressure fields and the discrete phase distributions had been analyzed. The influence of blade parameters like the shape, number, and rotating speed on the flow field and classification performance had also been comprehensively explored. The numerical simulations showed that there are vortices in many zones in the mill and the blades are of great significance to the mill performance. The blade IV not only results in high classification efficiency but also reduces effectively the pressure difference in the separator and also the whole machine. The conclusions of the flow field analysis and the blade effects on the classification efficiency and the pressure difference could guide designing and optimizing the equipment structure and the milling process, which is of great importance to obtain better overall performance of the vertical roller mill.

Download Full-text

Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01492-z ◽

2021 ◽

Vol 21 (S2) ◽

Author(s):

Kun Zeng ◽

Yibin Xu ◽

Ge Lin ◽

Likeng Liang ◽

Tianyong Hao

Keyword(s):

Clinical Trial ◽

Ensemble Learning ◽

Metric Learning ◽

Classification Performance ◽

Ensemble Model ◽

Automated Classification ◽

Eligibility Criteria ◽

Data Imbalance ◽

The Impact

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Download Full-text

Space Precession Target Classification Based on Radar High-Resolution Range Profiles

International Journal of Antennas and Propagation ◽

10.1155/2019/8151620 ◽

2019 ◽

Vol 2019 ◽

pp. 1-9

Author(s):

Yizhe Wang ◽

Cunqian Feng ◽

Yongshun Zhang ◽

Sisan He

Keyword(s):

Parameter Extraction ◽

Classification Performance ◽

Support Vector ◽

Electromagnetic Data ◽

Feature Extractor ◽

Different Types ◽

Radar Echo ◽

High Level ◽

Cone Target

Precession is a common micromotion form of space targets, introducing additional micro-Doppler (m-D) modulation into the radar echo. Effective classification of space targets is of great significance for further micromotion parameter extraction and identification. Feature extraction is a key step during the classification process, largely influencing the final classification performance. This paper presents two methods for classifying different types of space precession targets from the HRRPs. We first establish the precession model of space targets and analyze the scattering characteristics and then compute electromagnetic data of the cone target, cone-cylinder target, and cone-cylinder-flare target. Experimental results demonstrate that the support vector machine (SVM) using histograms of oriented gradient (HOG) features achieves a good result, whereas the deep convolutional neural network (DCNN) obtains a higher classification accuracy. DCNN combines the feature extractor and the classifier itself to automatically mine the high-level signatures of HRRPs through a training process. Besides, the efficiency of the two classification processes are compared using the same dataset.

Download Full-text

Numerical and Experimental Analysis of Turbulent Flow in Corrugated Pipes

Journal of Fluids Engineering ◽

10.1115/1.4002035 ◽

2010 ◽

Vol 132 (7) ◽

Cited By ~ 18

Author(s):

Henrique Stel ◽

Rigoberto E. M. Morales ◽

Admilson T. Franco ◽

Silvio L. M. Junqueira ◽

Raul H. Erthal ◽

...

Keyword(s):

Reynolds Number ◽

Pressure Drop ◽

Turbulent Flow ◽

Friction Factor ◽

Turbulence Models ◽

Reynolds Numbers ◽

Velocity Magnitude ◽

Geometric Configurations ◽

Corrugated Surfaces ◽

Friction Factors

This article describes a numerical and experimental investigation of turbulent flow in pipes with periodic “d-type” corrugations. Four geometric configurations of d-type corrugated surfaces with different groove heights and lengths are evaluated, and calculations for Reynolds numbers ranging from 5000 to 100,000 are performed. The numerical analysis is carried out using computational fluid dynamics, and two turbulence models are considered: the two-equation, low-Reynolds-number Chen–Kim k-ε turbulence model, for which several flow properties such as friction factor, Reynolds stress, and turbulence kinetic energy are computed, and the algebraic LVEL model, used only to compute the friction factors and a velocity magnitude profile for comparison. An experimental loop is designed to perform pressure-drop measurements of turbulent water flow in corrugated pipes for the different geometric configurations. Pressure-drop values are correlated with the friction factor to validate the numerical results. These show that, in general, the magnitudes of all the flow quantities analyzed increase near the corrugated wall and that this increase tends to be more significant for higher Reynolds numbers as well as for larger grooves. According to previous studies, these results may be related to enhanced momentum transfer between the groove and core flow as the Reynolds number and groove length increase. Numerical friction factors for both the Chen–Kim k-ε and LVEL turbulence models show good agreement with the experimental measurements.

Download Full-text