Comparison of methods for vibration analysis of electrostatic precipitators

The paper presents two methods for the formulation of free vibration analysis of collecting electrodes of precipitators.The first,called the hybrid finite element method, combines the finit element method used for calculations of spring deformations with the rigid finite element method used to reflect mass and geometrical features,which is called the hybrid finite element method.As a result,a model with a diagonal mass matrix is obtained.Due to a specific geometry of the electrodes,which are long plates of complicated shapes,the second method proposed is the strip method which is a semi-analytical method.The strip method allows us to formulate the equations of motion with a considerably smaller number of generalized coordinates.Results of numerical calculations obtained by both methods are compared with those obtained using commercial software like ANSYS and ABAQUS.Good compatibility of results is achieved.

Cell Segmentation and Tracking in Microfluidic Platform

In this research, we have concentrated on trajectory extraction based on image segmentation and data association in order to provide an economic and complete solution for rapid microfluidic cell migration experiments. We applied region scalable active contour model to segment the individual cells and then employed the ellipse fitting technique to process touching cells. Subsequently, we have also introduced a topology based technique to associate the cells between consecutive frames. This scheme achieves satisfactory segmentation and tracking results on the datasets acquired by our microfluidic platform.

Deep Learning Approach for COVID-19 Detection in Computed Tomography Images

With the rapid spread of the coronavirus disease 2019(COVID-19)worldwide,the establishment of an accurate and fast process to diagnose the disease is important.The routine real-time reverse transcription-polymerase chain reaction(rRT-PCR)test that is currently used does not provide such high accuracy or speed in the screening process.Among the good choices for an accurate and fast test to screen COVID-19 are deep learning techniques.In this study,a new convolutional neural network(CNN)framework for COVID-19 detection using computed tomography(CT)images is proposed.The EfficientNet architecture is applied as the backbone structure of the proposed network,in which feature maps with different scales are extracted from the input CT scan images.In addition,atrous convolution at different rates is applied to these multi-scale feature maps to generate denser features,which facilitates in obtaining COVID-19 findings in CT scan images.The proposed framework is also evaluated in this study using a public CT dataset containing 2482 CT scan images from patients of both classes(i.e.,COVID-19 and non-COVID-19).To augment the dataset using additional training examples,adversarial examples generation is performed.The proposed system validates its superiority over the state-of-the-art methods with values exceeding 99.10%in terms of several metrics,such as accuracy,precision,recall,and F1.The proposed system also exhibits good robustness,when it is trained using a small portion of data(20%),with an accuracy of 96.16%.

Cardiovascular Diseases Detecting via Pulse Analysis

In this research, we have performed pulse analysis on the data of 127 subjects collected from Department of Cardiology at Shandong Provincial Hospital in China. By taking the first and third derivatives of an entire pulse wave, we have firstly identified the locations of wave foot, systolic peak, and reflected point. Then we calculated Reverse Shoulder Index (RSI) and Ratio of Distance of the evaluated subjects, and correlated them to age, the history of hypertension, and different cardiovascular diseases of the subjects.