Computer-Aided Diagnosis for Tuberculosis Classification with Water Strider Optimization Algorithm

Computer-aided diagnosis(CAD)models exploit artificial intelligence(AI)for chest X-ray(CXR)examination to identify the presence of tuberculosis(TB)and can improve the feasibility and performance of CXR for TB screening and triage.At the same time,CXR interpretation is a time-consuming and subjective process.Furthermore,high resemblance among the radiological patterns of TB and other lung diseases can result in misdiagnosis.Therefore,computer-aided diagnosis(CAD)models using machine learning(ML)and deep learning(DL)can be designed for screening TB accurately.With this motivation,this article develops a Water Strider Optimization with Deep Transfer Learning Enabled Tuberculosis Classification(WSODTL-TBC)model on Chest X-rays(CXR).The presented WSODTL-TBC model aims to detect and classify TB on CXR images.Primarily,the WSODTL-TBC model undergoes image filtering techniques to discard the noise content and U-Net-based image segmentation.Besides,a pre-trained residual network with a two-dimensional convolutional neural network(2D-CNN)model is applied to extract feature vectors.In addition,the WSO algorithm with long short-term memory(LSTM)model was employed for identifying and classifying TB,where the WSO algorithm is applied as a hyperparameter optimizer of the LSTM methodology,showing the novelty of the work.The performance validation of the presented WSODTL-TBC model is carried out on the benchmark dataset,and the outcomes were investigated in many aspects.The experimental development pointed out the betterment of the WSODTL-TBC model over existing algorithms.

Automated Deep Learning Empowered Breast Cancer Diagnosis UsingBiomedical Mammogram Images

Biomedical image processing is a hot research topic which helps to majorly assist the disease diagnostic process.At the same time,breast cancer becomes the deadliest disease among women and can be detected by the use of different imaging techniques.Digital mammograms can be used for the earlier identification and diagnostic of breast cancer to minimize the death rate.But the proper identification of breast cancer has mainly relied on the mammography findings and results to increased false positives.For resolving the issues of false positives of breast cancer diagnosis,this paper presents an automated deep learning based breast cancer diagnosis(ADL-BCD)model using digital mammograms.The goal of the ADL-BCD technique is to properly detect the existence of breast lesions using digital mammograms.The proposed model involves Gaussian filter based pre-processing and Tsallis entropy based image segmentation.In addition,Deep Convolutional Neural Network based Residual Network(ResNet 34)is applied for feature extraction purposes.Specifically,a hyper parameter tuning process using chimp optimization algorithm(COA)is applied to tune the parameters involved in ResNet 34 model.The wavelet neural network(WNN)is used for the classification of digital mammograms for the detection of breast cancer.The ADL-BCD method is evaluated using a benchmark dataset and the results are analyzed under several performance measures.The simulation outcome indicated that the ADL-BCD model outperforms the state of art methods in terms of different measures.

Using Finite Element Analysis and Experimental Analysis on Vibration of a Piezoelectric Micro Pump

Due to the rise of biological and MEMS technology in recent years, some micro flow system components have drawn attention and been developed by many investigators. The importance of micro-pumps manufactured is higher than the other part of micro flow system since it is the power source of the entire micro-flow system and responsible for driving working fluid in the microfluidic system. In actual operation, the instability and bad dynamic characteristics of the micro-pump will cause larger fluid flow mobility error, such as transport behavior and response procedures failure, etc., and even damage the microfluidic system. Therefore, to investigate the stability and dynamic characteristics of a micro pump is necessary. The Finite element analysis (FEA), ANSYS Workbench, is employed to analyze the dynamic characteristics of this micro pump, and experiment is also considered in this study.

Effect of injection angle,density ratio,and viscosity on droplet formation in a microfluidic T-junction

The T-junction microchannel device makes available a sharp edge to form micro-droplets from biomaterial solutions. This article investigates the effects of injection angle, flow rate ratio, density ratio,viscosity ratio, contact angle, and slip length in the process of formation of uniform droplets in microfluidic T-junctions. The governing equations were solved by the commercial software. The results show that contact angle, slip length, and injection angles near the perpendicular and parallel conditions have an increasing effect on the diameter of generated droplets, while flow rate, density and viscosity ratios, and other injection angles had a decreasing effect on the diameter.

Visualization of Methamphetamine-Contaminated Fingermarks on Glass Surfaces by Field Emission Scanning Electron Microscope for Forensic Investigation

Background:Fingermark is an individual’s primary identification source.It is helpful in determining individuals involved in illegal activities and is frequently encountered in clandestine laboratories.During forensic investigation,the critical question to be answered is whether a fingermark was left on a surface before or after the initiation of an unlawful activity.Aims and Objectives:This study aimed to investigate the visualization of methamphetamine-contaminated fingermarks on glass surfaces and estimate the immediacy of their depositions.Materials and Methods:In this study,the prior-deposition contaminated fingermarks,i.e.,fingermarks deposited a surface priorly contaminated by methamphetamine,and the postdeposition contaminated fingermarks,i.e.,fingermarks deposited on a clean surface but subsequently contaminated with methamphetamine were visualized and compared using Field Emission Scanning Electron Microscope(FESEM).Results:Under FESEM,the latent fingermarks and the crystalline structure of methamphetamine were clearly visualized.The postdeposition contaminated fingermarks appeared in smudge conditions in all the three replicate samples,where the ridge and nonridge areas could not be well-distinguished.On the contrary,the prior-deposition contaminated fingermark demonstrated distinct separations between ridges and nonridges.However,the application of fingerprint powders reduced the possibility to determine the immediacy of deposition.Conclusion:To conclude,both prior-deposition contaminated fingermarks and postdeposition contaminated fingermarks can be discriminated,providing information on the instance when a fingermark was left on a surface.

Numerical study of cavitating flow in orifices and its effect on spray characteristics

The bubbly flow regime inside orifices has significant effects on several applications, and studying its trend along an orifice could be helpful in identifying the flow mechanism in various situations. The flow regime inside an orifice depends on the situation which has been specified for the orifice. Orifice geometry has a considerable effect on bubbly flow in injectors. Meanwhile, spray characteristics are influenced by the fuel flow inside an orifice, which has strong effects on the mixture of fuel-air. In this study, spray characteristics are studied for different values of the orifice angle. The cavitation phenomenon which occurs inside an orifice varies in intensity and patterns at different angles of the orifice and consequently has diverse effects on spray characteristics. The governing equations are solved by the SIMPLE algorithm. The spray flow is modeled by the discrete droplet method（DDM）, the droplet breakup is modeled by the WAVE model, and the primary breakup is modeled by the DIESEL BREAK UP model. In order to generate cavitation phenomenon inside orifices and investigate its effect on spray characteristics, the angle of orifice with respect to the injector body is varied and the problem is studied for different angles of orifice.