Predicting Retinal Diseases using Efficient Image Processing and Convolutional Neural Network (CNN)

Neural networks in image processing are becoming a more crucial and integral part of machine learning as computational technology and hardware systems are advanced. Deep learning is also getting attention from the medical sector as it is a prominent process for classifying diseases. There is a lot of research to predict retinal diseases using deep learning algorithms like Convolutional Neural Network (CNN). Still, there are not many researches for predicting diseases like CNV which stands for choroidal neovascularization, DME, which stands for Diabetic Macular Edema; and DRUSEN. In our research paper, the CNN (Convolutional Neural Networks) algorithm labeled the dataset of OCT retinal images into four types: CNV, DME, DRUSEN, and Natural Retina. We have also done several preprocessing on the images before passing these to the neural network. We have implemented different models for our algorithm where individual models have different hidden layers. At the end of our following research, we have found that our algorithm CNN generates 93% accuracy.

Volume Charge Density in Geometric Product Lorentz Transformation

Lorentz Transformation is the relationship between two different coordinate frames time and space when one inertial reference frame is relative to another inertial reference frame with traveling at relative speed. In this paper, we have derived the transformation formula for the volume charge density in Geometric Product Lorentz Transformation. The changes of volume charge density of moving frame in terms of that rest frame in Geometric Product Lorentz Transformation at various velocities and angles were studied as well.

The Periodicity of the Accuracy of Numerical Integration Methods for the Solution of Different Engineering Problems

Newton-Cotes integration formulae have been researched for a long time, but the topic is still of interest since the correctness of the techniques has not yet been explicitly defined in a sequence for diverse engineering situations. The purpose of this paper is to give the readers an overview of the four numerical integration methods derived from Newton-Cotes formula, namely the Trapezoidal rule, Simpson's 1/3rd rule, Simpson's 3/8th rule, and Weddle's rule, as well as to demonstrate the periodicity of the most accurate methods for solving each engineering integral equation by varying the number of sub-divisions. The exact expressions by solving the numerical integral equations have been determined by Maple program and comparisons have been done using Python version 3.8.

A Review of Methodological Approaches and Modeling Techniques in Service Quality Evaluation of Surface Transportation during the Last Decade

During the duration of the last decade, a growing interest has been noticed among transport practitioners and researchers to better understand the concept of service quality in the field of surface transportation and identify important service quality (SQ) attributes of different transportation services since these results have implications for transport managers. Due to advancements in computer technology and the availability of software packages, researchers are better able to extract meaningful results from passengers’ opinions collected through stated preference surveys and communicate their findings to transport managers looking to ameliorate SQ to boost ridership on a limited budget. Since the concept of SQ is itself complex owing to the nature of the service itself compared to a tangible product and characteristics of SQ attribute, different advanced modelling techniques based on multivariate analysis, machine learning, and artificial intelligence paradigms have become popular tools among researchers. This paper aims to summarize the trends of the SQ research in the field of surface transportation during the last decade with a focus on the methodological approaches and modelling techniques and delineate future directions for research in this field.

Assessment of Arsenic and Copper Pollution of the Benya Lagoon, Ghana By Neutron Activation Analysis

Heavy metal concentrations in some water bodies and the soil beneath these waters. These would have detrimental consequences on these water users and consumers of the fish in that water. Instrumental Neutron Activation Analysis technique using the Ghana Research Reactor-1 was employed to find out the concentrations of two heavy metals, Arsenic (As) and Copper (Cu) in the sediments, fishes, and water collected from the Benya Lagoon in the KEEA, Ghana. Cumulatively, Copper was found to be greater in concentration than Arsenic concerning the three parts of the ecology under study. On the other hand, Arsenic was more concentrated in the sediments than Copper, and Copper was more concentrated in the water and fish than Arsenic. Cumulatively, the level of contamination of Arsenic and Copper decreased in the order fish > sediment > water. Though Arsenic and Copper were found in elevated amounts in both water and fish which rendered the Lagoon water unsuitable for human use and the fish from the Lagoon unsafe for consumption, their concentrations in the sediment were found to have a low ecological risk index on the environment.

Numerical Analysis of Natural Convection Heat Transfer Inside an Inverted T-Shaped Cavity Filled with Nanofluid

This assessment is centered on the characteristics of natural convection heat transfer of Aluminium Oxide-Air nanofluid inside an inverted T-shaped enclosure with differentially heated sidewalls. The left edges of the enclosed cavity have been treated as a heated wall and are kept at a constant temperature. The right edges are also maintained at a constant temperature but lower than the heated wall. The top and bottom faces of the cavity have been considered adiabatic. The evaluation has been numerically investigated using ANSYS fluent. The effect of different significant parameters like volume fraction of nanoparticles, the shape of the enclosure, and Rayleigh number on the heat transfer characteristics inside an inverted T shape enclosure have been investigated. In this numerical analysis, a series of DNS simulations have been conducted for different Rayleigh numbers in the range of 103 to 106, the volume fraction of particles in the range 0≤ φ ≤0.1, and for the different aspect ratios for the inverted T shape have been conducted. The outcomes of this CFD analysis indicate a remarkable rise in the average heat transfer coefficient with the rising volume fraction of Al2O3 particles in the air. An increase of the average Nusselt number was also observed with the increase of Rayleigh number, but it drops slightly at a higher volume fraction of nanoparticles due to an increase in conductive heat transfer. For Rayleigh numbers ≥ 104, both the average Nusselt number and average heat transfer coefficient decrease up to a certain shape of the cavity aspect ratio. After that cavity aspect ratio, both the parameters value increase. But in the case of Rayleigh number = 103, both of the values decrease with the increase in the cavity aspect ratio.

Investigation of Mechanical Properties of Banana-Glass Fiber Reinforced Hybrid Composites

Banana stems are very cheap and abundant in nature which can be used to extract fiber. In this paper, banana fiber is used as a reinforcement and epoxy as a matrix to manufacture banana fiber-reinforced epoxy composite. Glass fiber mat, and roving are also used as reinforcement along with banana fiber to manufacture hybrid composites. The objective of this paper is to compare the mechanical properties of hybrid composites with that of pure banana fiber-reinforced composites. The hand lay-up method is used to manufacture all the composites, and tensile and flexural properties are investigated according to the corresponding ASTM standard. It is found that the tensile and flexural strength of banana and glass fiber roving hybrid composites are much higher compared to pure banana fiber-reinforced epoxy composites which make this hybrid composite suitable for low strength application.

Numerical and Experimental Study on Optimization of Coil Springs used in Vehicles’ Suspension System

In general, the suspension systems are used to absorb vibrations, bump, rolls, dip from shock loads due to road surface irregularities. It performs its major role without affecting the vehicles’ stability and overall handling during operation. Coil springs are used as suspension element in light vehicles to attenuate unwanted vibrations. A spring is an elastic object used to store mechanical energy and it can be twisted, pulled or extended by some force and can return to its initial position when the force is released. In this study, mild steel material was taken into consideration in designing and fabricating coil springs. Theoretical and experimental investigations were conducted to calculate springs’ stiffness and to make validation between them. Three model of springs having coils 10, 11, 14 respectively are designed which have slight stiffness difference both theoretically and experimentally. The models were analyzed to determine mechanical behaviors for randomly chosen loading conditions ranging from 29.4 N to 176.4 N which are better suited with spring size. It is noted from both numerical and experimental investigations that deflection is high when the stiffness is less and vice-versa. In addition, shear stress formation increases with the increment of stiffness and applied load. Hence, springs having high stiffness are used in suspension system to reduce vibration and other disturbances. This study shows springs of having high stiffness are comparatively compact in size and cost economic as well.

De-noising of an Image using Fuzzy Inference System and Performance Comparison with the Conventional system

Noise prevailing in the image can diminish the physical appearance of the objects existing within the image and make them frail. Present research emphasizes a fuzzy inference system eradicating several types of noise from the images. The investigation implies the utilization of different levels of Salt & Pepper noise. Followed by the pixel determination applying a mask, the disparity between the focused pixel's intensity with the minimum, average, and maximum power of the chosen window has been determined. Since two fuzzy valued outputs have been obtained to match them, the one provided by a low noise rate would demonstrate the more accurate filter for the selected window. Utilizing Matlab the Peak Signal-to-Noise ratio (PSNR) and Mean Square Error (MSE) are determined for evaluating the noise reduction performance. However, these values of PSNR and MSE obtained from this research are also compared with the conventional fuzzy filtering system.

Design Optimization of B-series Marine Propeller using NSGA-II, Iterative and Gekko Algorithm

The design of a propeller plays a significant role in naval architecture. Optimization of various design factors is the primary concern for effective and efficient propulsion. This study investigates the optimization of the B-series marine propellers using three different methods, i.e. (i) a non-linear constrained single-objective optimization approach using the Non-Dominated Sorting Genetic Algorithm (NSGA-II), (ii) a python package for dynamic optimization based optimization software ‘Gekko’, (iii) an iterative approach and results were compared with each other. Efficiency is considered as the single objective function whereas three constraints are imposed: cavitation, thrust and strength. Analogous characteristics have been found in the comparison of results from all three methods. Comparing the various factors, this study suggests that, Gekko can be used as the optimization algorithm.