IJSRET » November 20, 2022

Daily Archives: November 20, 2022

Uncategorized

IJSRET Volume 8 Issue 6, Nov-Dec-2022

Brain Tumor Detection Based on Watershed Segmentation and Classification Using Deep Learning
Authors:- Shivam Tamrakar, Prof. Mahesh Prasad Parsai

Abstract- The computer-aided diagnostic-based that supports deep learning (DL) algorithms consists of several processing layers, which symbolize data with several stage of construct. In current years, the use of deep learning has increased speedily in almost all areas, especially in the field of medical imaging, medical image investigation or bioinformatics. Therefore, deep learning has effectively untouched or enhanced the methods of recognition, calculation or diagnosis in many medical and health areas such as pathology, brain tumors, lung cancer, stomach, heart or retina. Given wide application of deep learning, the purpose of this paper is to appraise the most important deep learning perception related to tumour analysis detection and classification In recent applications of pre-trained models, normally features are extracted from bottom layers which are different from natural images to medical image. To overcome this difficulty, in the proposed method GLCM feature and Resnet-50 techniques used for feature extraction and watershed based segmentation is used for brain tumour detection and its classification. A significant, practical deep learning model is proposed which uses back propagation neural network feature to predict brain stroke through CT/MRI scan images. The performance and accuracy of the proposed model is evaluated and compared with existing models and it produces high sensitivity, specificity, precision and accuracy.

Study of Factors Affecting to Behavioural Intention on Adopt Mobile Payment
Authors:- P.K.C. Adeesha Rathnasinghe

Abstract- This paper provides an analysis and evaluation of the factors that influence mobile payment adoption in Sri Lanka, as well as an examination of the customer-driven characteristics of mobile payment solutions and their associated value proposition. The convenience feature of mobile payment has replaced interactions with actual currency and shortened transaction times, which better satisfies the convenience needs of modern people. As mobile payments play a major part in mobile business, gaining an understanding of the characteristics that attract consumers to mobile payment will provide mobile businesses with additional chances for growth and substantially increase their output value. Based on the core theoretical framework of the Theory of Acceptance and Use of Technology, this study investigates how to further affect customer behavioural intention in Sri Lanka (UTAUT2). In this investigation, data analysis is conducted to validate the research model and hypotheses. Social influence, facilitating conditions, hedonic motivation, compatibility, innovation, relative benefit, complexity, performance expectations, and observability have been identified as dependent variables that influence customer desire to use mobile payment. One hundred eighty samples will be chosen using a random sampling technique for the investigation. Utilizing statistical analysis and regression analysis, the impact of these nine parameters on mobile payment adoption was confirmed. Perceived danger, perceived cost, perceived advantage, perceived ease of use, perceived usefulness, perceived behaviour, social influence, credibility, and compatibility have a major impact on mobile payment uptake, according to the results of a study.

Detection of Glaucoma by the Use of Convolutional Neural Network
Authors:- M.Tech. Scholar Pankaj Goud, Asst. Prof. Miss Priyanshu Dhameniya

Abstract- Glaucoma is a disease that affects human eyes and makes it difficult for people to see clearly. In recent years, the prevalence of this condition has increased significantly. The result of this illness is a permanent impairment of vision that cannot be reversed once it has taken place. In the past, the diagnosis of glaucoma was carried out with the assistance of a number of different deep learning (DL) algorithms. The results of our research on recognising glaucoma illness are presented in this journal. For the purpose of recognising the ailment, we used a deep learning model known as a Convolutional neural network (CNN). The convolutional neural network provides us with a distinct pattern for both eyes afflicted by glaucoma and eyes that are not impacted by glaucoma. This pattern may be used by us to diagnose glaucoma. When CNN is used, a hierarchical framework is provided for distinguishing between images of glaucoma-affected eyes and photographs of eyes that are not affected by glaucoma. This facilitates more accurate categorization. Using the method that we offer, it is possible to do a review in a total of six phases. The dropout mechanism is used in the study that is advised in order to improve the overall efficiency of the performance. This is done in the context of glaucoma disease detection. In order to carry out an analysis of the work that was intended, this study made use of the datasets provided by SCES and ORIGA. The values acquired for the ORIGA dataset come in at 92.3, while the SCES dataset has values that come in at 94.2.

Load Balancing in Cloud Computing Through Multiple Gateways
Authors:- Research Scholar Rani Danavath, Asst. Prof. Dr. V. B. Narsimha

Abstract- Cloud computing is a structured model that defines computing services, in which data as well as resources are retrieved from cloud service provider via internet through some well formed web-based tool and application. As the numbers of users are increasing on the cloud, the load balancing has become the challenge for the cloud provider. As most of the traffic is oriented towards the Internet and may not be distributed evenly among different IGWs, some IGWs may suffer from bottleneck problem. To solve the IGW bottleneck problem, we propose an efficient scheme to balance the load among different IGWs within a WMN Our proposed load-balancing scheme consists of two parts: a traffic load calculation module and a traffic load migration algorithm. The IGW can judge whether the congestion has occurred or will occur by using a linear smoothing forecasting method. When the IGW detects that the congestion has occurred or will occur, it will firstly select another available IGW that has the lightest traffic load as the secondary IGW and then inform some mesh routers (MPs) which have been selected by using the Knapsack Algorithm to change to the secondary IGW. The MPs can return to their primary IGW by using a regression algorithm.

Blockchain and Its Use in Financial World
Authors:- Lokesh Yadav

Abstract- A Blockchain Is Essentially A Digital Ledger That Is Replicated And Distributed Across A Networkof Computer Systems On The Blockchain. Each Block On The Chain Contains A Set Oftransactions, And Each Time A New Transaction Occurs On The Blockchain, A Record Of Thattransaction Is Added To Each Participant’s Ledger. A Distributed Database Managed By Multipleparticipants Is Called Distributed Ledger Technology (Dlt).

Control Strategy for Bidirectional AC-DC Interlinking Converter in AC-DC Hybrid Microgrid Using PV System
Authors:- Vikram Sirohi, Asst. Prof. Somya Agarwal, Dr. Raghavendra Patidar

Abstract- In this article, a single-stage bidirectional converter that is connected to the grid is suggested. This converter would have a power conversion stage and an unfolding circuit. The power conversion stage would be a two-way DC-DC converter. The goal of this research is to get the most energy out of photovoltaic (PV) energy systems as possible. When the temperature, the amount of sunlight, or the load changes, so does the maximum amount of power that the photovoltaic module can produce. The photovoltaic system uses a maximum power point tracker (MPPT) to keep getting the most power out of the solar panel and send it to the load. This is done so that the system is as efficient as possible. The Maximum Power Point Tracking (MPPT) system is made up of a controller and a DC-DC converter, which are its two main parts. The DC-DC converter is a piece of electronic equipment that changes the voltage of DC energy from one level to another. MPPT uses a tracking algorithm so that it can find the place with the most power and keep working there even when the weather changes. Many different algorithms for MPPT have been made and talked about in published research, but most of these methods have problems with how well they work, how precise they are, and how well they can be changed. Conventional controllers can’t give the best response because the PV module’s current-voltage characteristics don’t behave in a linear way and switching makes the DC-DC converter behave in a non-linear way. This is especially true when the line parameters and transients change in a lot of different ways. The goal of this work is to make a maximum power point tracker and then use it. This will be done by using fuzzy logic control algorithms. When fuzzy logic is used, it is natural that a good controller will be made for nonlinear applications. This method also uses techniques from artificial intelligence, which can make modeling nonlinear systems easier and offer other benefits. Simulink was used to build an MPPT system with solar modules, DC-DC converters, batteries, and fuzzy logic controllers, and to simulate it. This had to be done so that the job could be done well. Characterize the buck, boost, and buck-boost converters to find out which topology is best for the PV system being used. In MATLAB, a model of the PV module, the indicated converter, and the battery were all put together to get the experience needed to build and tune the fuzzy logic controller. The results of the simulation show what happens when the parameters are changed.

Energy Optimization of Underwater WSN by Wolf Based Clustering
Authors:- M.Tech. Scholar Kush Paliwal, Asst. Prof. Sumit Sharma

Abstract- Communication is basic need of any age, although medium and technique is different. In this era wireless communication is common and acceptance of this in various applications is also wide. Out of different field of WSN (Wireless Sensor Network), underwater is highly desirable as study of such area may give new material or learning. This paper has developed a model that works for underwater WSN optimization by clustering and routing. Clustering of nodes were done by Wolf optimization technique, algorithm is able to provide solution dynamic situation. Cluster nodes selection done on the basis of device energy, distance from the base station. Routing of packet is also done from the nodes by means of cluster centers. In order to reduce the load of cluster nodes, shuffling of nodes were done time to time. Experiment was done on different environment of underwater and varying number of nodes. Model was compared with existing technique of underwater WSN network optimization.

An Analytical Study Using Dynamic Analysis on Buildings With and Without Expansion Joints
Authors:- Ashutosh Dabral , Rashmi Sakalle

Abstract- Vibration is effectively dampened by expansion joints, which also serve to keep individual building components together while allowing for their natural movement in response to things like ground settlement and earthquakes. In addition to protecting against moisture and water damage, this facilitates the transportation of live cargo. Expansion joints may be used to completely separate many different construction components, including ceilings, floors, roofs, walls, and facades. Additionally, they may be set up wall to wall, ceiling to ceiling, roof to roof, or roof to wall. They’re versatile enough to do more than one thing at once. These connections separate a frame into individual segments with sufficient breadth to accommodate the building’s thermal expansion and contraction. This thesis presents an experimental software analysis on the expansion joint of a hospital building to find: Displacement, Bending moment, Shear force and Axial force. Two samples were designed on STAAD PRO and a comparative study was made to find the expansion joint design with better performance.

A Comprehensive and Novel Approach to Design of Carbon Reinforced Alloy Wheel with Material Selection
Authors:- Anurag Tiwari, Prof. G.R. Kesheorey

Abstract-Main objective is to selection of material, analyze the reason of failures of the rim. Mainly the cracks on the surface, bending due to impact loading. Vibration and the hold pressure of the tire can damage the rim. The damage such as rust, dents, etc. which results in increased vibration while running, loss of air pressure and even sometimes the complete structural failure. This can damage the rims which could result in failure of the Rim during running conditions. Changes can be made to a rim and visible damage could lead to greater damage which can’t be seen by naked eye, so a repaired rim will never be structurally sound as original rim. There are some more causes of failure, this project will discuss about these failures which can arise in rim. This project is all about the design, analysis and calculation of von-mises stresses and deflections with the help of CATIA and ANOVA method. The part which is under maximum stress as well as respective deformation value can be easily detected.

Mitigating Shear Failure of Flexurally Strengthened Reinforced Concrete Beams Using Carbon Fibre Reinforced Polymer
Authors:- Dr. Muhammad Ashiqur Rahman, Dr. A. B. M. Saiful Islam, Prof. Ir. Dr. Mohd Zamin Bin Jumaat

Abstract- Shear failure is sudden, brittle and catastrophic in nature, which starts without advance warning of any distress. Hence, ensuring shear failure will not happen in reinforced concrete (r.c.) beams must be given due consideration in design. Practically beams can be allowed to take more loads if they are flexurally strengthened. Premature shear failure will occur when the shear reinforcements present can no longer take the increased shear loads due to flexural strengthening. Hence, when a r.c. beam is flexurally strengthened, care must be taken to ensure it does not fail under premature shear. Eight beams were prepared and tested in this research. Technical Report -55 (TR-55) was used to design the carbon fibre reinforced polymer (CFRP) plate for flexural strengthening. According to TR-55, the design strain for flexural plate is 0.006 for preventing intermediate crack (IC) debonding. Experimental data showed that the flexural CFRP plate strain reached 0.0072 without IC debonding. The CFRP strips for shear strengthening were designed using ACI 440-2R, 2008 and fib TG 9.3 2001. The key parameter for designing shear was the effective strain of the CFRP shear strips. Experimentally, CFRP shear strips experienced strain about half of the designed value according to ACI 440-2R, 2008 and fib TG 9.3 2001. The internal stirrups and external CFRP shear strips had almost the same strain values before failure. Overall, the strengthened beam capacity was increased by 160% compared with the control unstrengthened beam by mitigating the shear failure using CFRP.

Energy Optimization of Underwater WSN by Wolf Based Clustering
Authors:- Kushagra Paliwal, Asst. Prof. Sumit Sharma

Abstract- Communication is basic need of any age, although medium and technique is different. In this era wireless communication is common and acceptance of this in various applications is also wide. Out of different field of WSN (Wireless Sensor Network), underwater is highly desirable as study of such area may give new material or learning. This paper has developed a model that works for underwater WSN optimization by clustering and routing. Clustering of nodes were done by Wolf optimization technique, algorithm is able to provide solution dynamic situation. Cluster nodes selection done on the basis of device energy, distance from the base station. Routing of packet is also done from the nodes by means of cluster centers. In order to reduce the load of cluster nodes, shuffling of nodes were done time to time. Experiment was done on different environment of underwater and varying number of nodes. Model was compared with existing technique of underwater WSN network optimization.

Grade Recommendation Using Privacy Preserving Mining and Genetic Algorithm
Authors:- M.Tech. Scholar Priyanka Vishwakarma, Asst. Prof. Sumit Sharma

Abstract- Data analysis depends on quality of input data but this increase chance of privacy break of organization or individual or community. So reverse mining process is applied that performs both the data privacy preserving and knowledge extraction. In order to improve education quality student data analysis is more sensitive and needs good set of features for prediction. This paper has proposed a model that extracts features from the different city schools and trains a model for grade prediction. Proposed model has not shared student data to any third party, instead of this random features selected by the genetic algorithm were used for the training of model. These features were taken in form of presence and absence of student activities. Experiment was done on real dataset of Maharashtra Districts School Students. Comparisons result shows that proposed model has improved the prediction accuracy by % as compared to similar models of privacy preserving.

Multi-modal medical image analysis using Wavelet Fusion
Authors:-M.Tech. Scholar Khurshed Akhtar, Prof .Deepak Mishra

Abstract-Techniques for pixel-level image fusion have been the most important for remote sensing data processing and analysis up until this point. Typically based on empirical or heuristic rules, feature based fusion techniques are utilized for this purpose. Multimodal transport image registration and fusion technologies play an important role in routine screening, screening, screening and evaluation of chronic disease radiotherapy, surgical and radiotherapy programmes. Multimedia media algorithms and tools have made great strides in supporting the reliability of clinical decisions on medical imaging and will continue to make great strides. Combining the two types of information and mixing the two images. Image aggregation methods include simple methods (e.g. pixels) and complex methods (such as wavelet transforms). The advantage of using wavelet manipulation is it has a large part of each image. Its main objective is to improve the understanding of medical images through the use of discrete wavelet transformation technology. DWT uses mainly consolidation rules involving average pixels. The discrete wavelet transformation was carried out using fusion techniques designed specifically for integrated medical images. The fusion performance is calculated based on PSNR, MSE and whole progression moment.

Review on Renewable Energy Based Electric Vehicles Charging Technology
Authors:- Kuldeep Gautam, HOD Ravi Hada

Abstract-Many different types of electric vehicle (EV) charging technologies are described in literature and implemented in practical applications. This paper presents an overview of the existing and proposed EV charging technologies in terms of converter topologies, power levels, power flow directions and charging control strategies. An overview of the main charging methods is presented as well, particularly the goal is to highlight an effective and fast charging technique for lithium ions batteries concerning prolonging cell cycle life and retaining high charging efficiency. Once presented the main important aspects of charging technologies and strategies, in the last part of this paper, through the use of genetic algorithm, the optimal size of the charging systems is estimated and, on the base of a sensitive analysis, the possible future trends in this field are finally valued.

Published by: