Browse Items (11808 total)
Sort by:
-
Analysis of MRI Images to Discover Brain Tumor Detection Using CNN and VGG-16
Brain tumor is a malignant illness where irregular cells, excess cells and uncontrollable cells are grown inside the brain. Now-a-days Image processing plays a main role in discovery of breast cancer, lung cancer and brain tumor in initial stage. In Image processing even the smallest part of tumor is sensed and can be cured in early stage for giving the suitable treatment. Bio-medical Image processing is a rising arena it consists of many types of imaging approaches like CT scans, X-Ray and MRI. Medical image processing may be the challenging and complex field which is rising nowadays. CNN is known as convolutional neural network it used for image recognition and that is exactly intended for progression pixel data. The performance of model is measured using two different datasets which is merged as one. In this paper two models are used CNN and VGG-16 and finding the best model using their accuracy. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Analysis of multilayer convective flow of a hybrid nanofluid in porous medium sandwiched between the layers of nanofluid
AgBr acts as a good sensitizer for titanium oxide, hence TiO2AgBr nanoparticles exhibit high photocatalytic activity which helps decompose methyl orange under visible light irradiation. Methyl orange is a chemical compound that is hard to degrade and has high stability. It is photoreactive and can capture photons from the sun and is highly used as a light harvester in solar cells, hence, it is used in solar applications. In view of this, the present article deals with the analysis of heat transfer in a multilayer flow of two immiscible nanofluids in a vertical channel that finds application in the fields of solar reactors, electronic cooling, and so on. The mathematical model involving the effect of thermal radiation and the presence of heat source is in the form of a system of ordinary differential equations. This system of equations is simplified using the differential transform method-Padapproximant and the resulting equations are solved algebraically. It is observed that the temperature of the coolant does not reach its saturation point faster due to the presence of different base fluids that differ in their thermal conductivity. This helps in maintaining theoptimum temperature of the system. 2021 Wiley Periodicals LLC -
Analysis of multimode oscillations caused by subsynchronous resonance on generator shaft
Series capacitors are installed in high voltage alternating current transmission lines to counteract the inductive reactance of the line. The resonance caused by series capacitors between electric system and mechanical system at frequencies less than the synchronous speed, leads to torsional oscillations. Undamped oscillations ma y cause a severe fatigue in the turbine generator shaft system. Rotating component undergoes various modes of oscillations when it is subjected to resonance. Rotor oscillate in different modes such as swing mode, super synchronous mode, electromechanical mode and torsional mode. Rotor dynamics of rotating structure depends on several factors like Coriolis Effect, moment of inertia and stiffness coefficient. Modal analysis using finite element method gives the natural frequency and mode shapes of any rotating structures. In this paper, a two mass rotating system which is analogous to turbine generator is subjected to resonance by adding series capacitors and its dynamic behavior is studied using finite element method. 2018 Lavoisier. -
Analysis of Multinomial Classification for Legal Document Categorization
A major area of research today is the application of Machine Learning Techniques for Document or Text Classification. Document Classification is an important aspect of Electronic Discovery in the Legal domain. The need for the process to be automated has been realized over the past few years. Multinomial Classification is a well-known Supervised Machine Learning Technique that helps us classify if there are more than two classes used for the purpose of Classification. Evaluation metrics such as Precision, Recall, and F1 Score have been used to measure the efficiency of Classification. Logistic Regression and Gradient Boosting Algorithms have outperformed other Multiclass Classification techniques. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Analysis of native advertising on buzzfeed and its impact on the brand image of 7 companies /
In today's world, the social web space has become a competitive platform for companies engaged in a plethora of activities to promote and sell their products and, more importantly, create a brand image. In tandem with the rapid development that has been observed in social media, the advertising industry has also evolved to accommodate the needs of the internet. Native advertising has emerged as a viable and lucrative alternative for companies to communicate with their audiences. -
Analysis of Nifty 50 index stock market trends using hybrid machine learning model in quantum finance
Predicting equities market trends is one of the most challenging tasks for market participants. This study aims to apply machine learning algorithms to aid in accurate Nifty 50 index trend predictions. The paper compares and contrasts four forecasting methods: artificial neural networks (ANN), support vector machines (SVM), naive bayes (NB), and random forest (RF). In this study, the eight technical indicators are used, and then the deterministic trend layer is used to translate the indications into trend signals. The principal component analysis (PCA) method is then applied to this deterministic trend signal. This study's main influence is using the PCA technique to find the essential components from multiple technical indicators affecting stock prices to reduce data dimensionality and improve model performance. As a result, a PCA-machine learning (ML) hybrid forecasting model was proposed. The experimental findings suggest that the technical factors are signified as trend signals and that the PCA approach combined with ML models outperforms the comparative models in prediction performance. Utilizing the first three principal components (percentage of explained variance=80%), experiments on the Nifty 50 index show that support vector classifier (SVC) with radial basis function (RBF) kernel achieves good accuracy of (0.9968) and F1-score (0.9969), and the RF model achieves an accuracy of (0.9969) and F1-Score (0.9968). In area under the curve (AUC) performance, SVC (RBF and Linear kernels) and RF have AUC scores of 1. 2023 Institute of Advanced Engineering and Science. All rights reserved. -
Analysis of Nine Level Single-Phase Cascaded H-Bridge Inverters for EVs
This paper explores the design and operation of a Modular Nine-Level Inverter (MLI)-Electric Vehicle (EV) charging system, incorporating solar energy to power domestic loads and charge EVs. The system comprises a solar panel, DC-DC regulator, and MLI for efficient energy conversion. The MLI's modular design reduces complexity and enhances efficiency. Equivalent circuits illustrate voltage level generation, while PWM control regulates power device switching for precise output control. Performance metrics, including regulated DC supply voltage and staircase nine-level output voltage, demonstrate the system's capability for diverse applications. A nearly sinusoidal current waveform and harmonic analysis underscore the system's effectiveness in delivering stable power with reduced harmonic distortion. Comparisons between filtered and unfiltered output highlight the importance of filtering techniques in improving power quality. Overall, the MLI-EV charging system showcases advancements in renewable energy integration, offering a versatile solution for sustainable electricity generation and EV charging. 2024 IEEE. -
Analysis of nonlinear compartmental model using a reliable method
The goal of this work is to investigate nonlinear models and their complexity using techniques that are universal and have connections to historical and material aspects. Using the premise of a constant population that is uniformly mixed, a nonlinear compartmental model that depicts the movement between voter classes is taken into consideration. In the current work, we investigate the dynamical framework that supports the interactions between the three parties. It is discussed how rate change affects various metrics. The conditions for boundedness, stability, existence, and other dynamics are obtained. We derive the effects of generalizing the model in any order. The current study supports investigations into complex real-world issues and forecasts of necessary plans. 2023 The Author(s) -
Analysis of nonlinear convection and diffusion in viscoelastic fluid flow with variable thermal conductivity and thermal radiations
The study offers a thorough evaluation of the complex fluid dynamics and heat transfer phenomena in Williamson viscoelastic fluid flow, taking into account thermal radiations and variable thermal conductivity. The paper extends its analysis to include heat transfer effects, which are critical in several engineering and industrial applications, and digs into the complexity of non-Newtonian fluid behavior, with a special focus on thermal radiation, heat production, diffusion and viscous dissipation. The study makes use of mathematical models and numerical method RK4 to clarify the nonlinear interactions between convection and diffusion processes in this viscoelastic fluid. The energy and concentration equations are simulated in the presence of the modified Fourier and Fick laws. Moreover, the predicted heat flow is based on the Cattaneo-Christov theory. This research also sheds light on the interaction between rheological properties and thermal characteristics, providing important new knowledge to the broader field of fluid dynamics and heat transfer. 2024 World Scientific Publishing Company. -
Analysis of Online In-Destination Booking Service Processes in the Travel Industry: A Case Study
This article presents a comprehensive analysis of the online in-destination booking service processes within the dynamic landscape of the travel industry. Utilizing a case study approach, the research investigates the various stages involved in providing travel-related services, focusing on the key players. The study employs a quantitative method to assess the information quality, system quality, service quality, customer satisfaction, and purchase intention of online in-destination booking. The research highlights the investigation of the usability of online travel booking systems and identifies the purchase intention of customers towards online travel booking websites. To address the research objectives, the participants are selected using a nonprobability sampling method. The sample size of the study is 225 from in and around Coimbatore. The sampling procedure used is convenience sampling. The sampling is selected based on convenience and accessibility to the residents. The findings reveal that there exists a significant difference in respondents opinions on quality criteria: system quality and service quality. Additionally, the study finds that the loading time of online travel booking websites is positively correlated with quality criteria and features of travel apps. By examining a specific case within the travel sector, this study contributes valuable insights that can inform strategic decision-making for businesses operating in the online in-destination booking space. The results aim to guide industry players in enhancing their operational efficiency, leveraging technology advancements, and aligning their services with evolving customer expectations, ultimately fostering sustainable growth in the competitive travel market. 2024, Bentham Books imprint. -
ANALYSIS OF ORGANISATION BLOGS AS A PR TOOL
Organisation blogs have been used by organisations constantly at present times with the evolution of the digital world taking place. Every organisation involves various mediums through which they are constantly kept in the minds of the people. The researcher aims to find out the patterns and strategies used in organisation blogs as a Public relations tool. There are many public relations tools like in house publications, press conferences, Press releases, PR campaigns have been used by organisations since decades. The researcher aims to find out the growing importance of organisation blogs in the current scenario. The researcher would adopt qualitative method for the study. The researcher would analyse the blogs of top brands and conduct expert interviews. -
Analysis of Perceptions and Attitudes of Scheduled Commercial Bank Personnel Toward Provision of Credit to Poor and Toward Financial Inclusion Process in India
Journal of Investment and Management, Vol-1 (1), pp. 1-11. -
Analysis of Reinforced Concrete Structure Subjected to Blast Loads Without and with Carbon Fibres
In the past few decades, the terrorist attack on buildings has significantly increased. Blast loads due to explosions cause severe damage to the buildings structural and non-structural elements which may also lead to progressive collapse of the building. Hence, there is a need for the structures to be analysed and designed for blast loads in addition to the conventional loads. An investigation is undertaken to minimize the damage of a G+3 storied building and by improving the mechanical properties such as compressive strength, nonlinear behaviour of M40 grade concrete by adding carbon fibres in different dosages. A finite element model of G+3 storied building has been created using Ansys/LS Dyna to analyse the structure subjected to a blast load with charge weights of 50 kg, 100 kg, 150 kg at 3000 mm standoff distance. The lateral deflections and strains of the structure are determined for different charge weights to study the behaviour of the structure when subjected to blast loads. The addition of carbon fibres has improved the behaviour of structure by reducing the strains and deflections and optimum dosage of fibres is also determined in this paper. 2023, Springer Science and Business Media Deutschland GmbH. All rights reserved. -
Analysis of Routing Protocols in MANET Networks
The scientific article is a review and comparative analysis of routing protocols for MANETs. The study examines the main protocols connected to mobile ad hoc networks such as B.A.T.M.A.N, BMX7, OLSRv1, Babel and provides a detailed analysis of their characteristics, advantages and disadvantages. To empirically evaluate performance, tests were carried out in a network simulator. The results of the study allow us to draw conclusions about the effectiveness and reliability of each of the monitoring protocols under various operating conditions of MANET. This article is a valuable contribution to the field of MANET research and can be used in the development of new technologies and solutions for mobile wireless networks. The work is relevant and practically significant because it helps researchers and engineers make informed decisions when choosing the optimal routing protocol in MANET networks. The results obtained can be useful in the design of mobile applications, emergency communication systems, transport management and other areas where the efficient operation of wireless networks is important. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Analysis of secure cloud storage provisioning for medical image management system
Medical images are considered to be the most sensitive images as it contains various health related sensitive information of an individual and it is necessary for the health care organization to maintain the sensitivity of these images without anybody misusing these data. When these images are transferred digitally through a network in order to store it in cloud for easy access for the authorities of the health care system, it is important to compress and encrypt these images to reduce the size and safeguard the information before storing and make sure that these images are transferred securely. In this paper, we use Huffman Coding technique in order to compress the image for easy transmission and to consume less storage space in cloud. To maintain the confidentiality of these images Blowfish encryption methodology is used. Once the image undergoes compression and encryption, the encrypted image is transferred and stored in a cloud storage. IAEME Publication. -
Analysis of SH-waves Propagating in Multiferroic Structure with Interfacial Imperfection
This article presents the study of wave mechanics in a multiferroic structure having imperfection in the structures interface. This article reflects the study of shear horizontal (SH) wave propagation in a layered cylindrical structure consisting of thin layers of different materials (reinforced material and piezomagnetic material) with an imperfect interface. The interface considered between both materials is mechanically imperfect. Dispersion relations are achieved analytically. Distinct graphs are drawn (numerically) to exhibit the influence of parameters like rotation, initial stress, and mechanically imperfect parameters on phase velocity. Numerical results are drawn analytically and explained for each affecting distinct parameters for materials and interface. Parametric results on the phase velocities yield a significant conclusion of which some are: (a) Performance of Piezo with reinforcement material have an influential impact on wave velocity. (b) The mechanical imperfection affects the significantly on wave velocity (c) The Reinforcement/PM stiffening can monotonically up the velocity of phase velocity. 2022 Published by Semnan University Press. -
Analysis of Social Media Marketing Impact on Customer Behaviour using AI & Machine Learning
The study of client behaviour has been revolutionized by the combination of social media marketing with cutting-edge technology like Artificial Intelligence (AI) and Machine Learning (ML) in today's age of digital transformation. This study delves into the complex interplay between AI/ML, consumer involvement, and social media marketing methods. Our research exposes crucial insights via careful data collecting, sentiment analysis, and the construction of prediction models. By stressing the importance of catering content to individual interests, AI-driven customization emerges as a potent tool, increasing user engagement by 18%. Analysis of online sentiment shows how important it is to keep people feeling good about a business; postings with positive feelings get 30% more likes and comments on average. Accurate and time-saving insights from machine learning models provide up new avenues for optimizing marketing's use of available resources. As a result of the study's conclusions, companies will be able to better connect with their customers, use their resources more efficiently, and behave ethically moving forward. Promising new developments in the subject include the next steps, which include sophisticated AI models, temporal dynamics analysis, and investigation of long-term consequences, ethical issues, and multichannel techniques. This study helps companies, marketers, and policymakers better understand the convergence of technology and marketing in today's ever-changing digital world so that they may better serve their customers and build a successful brand over time. 2024 IEEE. -
Analysis of some important fluid flow problems using differential geometry based methods
In this thesis we have studies MHD and EMFD flow of viscous and inviscid fluid for different cases when magnetic field and velocity are variably or constantly inclined. In particular magnetic and velocity vector are orthogonal. The pattern of streamlines and magnetic lines are derived in every problem and the effect of density and magnetic permeability on the variation of pressure is studied. The problems studied in this thesis give further investigation on the analytical solution of magnetohydrodynamic and electromagnetic fluid dynamic flow. -
Analysis of some important fulid flow problems using differential geometry based methods
In this thesis we have studied MHD and EMFD flow of viscous and inviscid fluid for different cases when magnetic field and velocity are variably or constantly inclined. In particular magnetic and velocity vector are orthogonal. The pattern of streamlines and magnetic lines are derived in every problem and the effect of density and magnetic permeability on the variation of pressure is studied. The problems studied in this thesis give further investigation on the analytical solution of magnetohydrodynamic and electromagnetic fluid dynamic flow. The problems that studied analytically in this thesis have possible application in theoretical analysis of fluid dynamics and the analytical findings in this thesis can be applied in engineering fields such as aeronautics, plasmas, liquid metals and salt water or electrolytes. We have studied five problems here in this thesis. These problems are to find analytical solution of different types of fluid flows in the presence of magnetic field. Here we give a brief summary about the problems discussed in detail in this research work. (i) GEOMETRY OF CONSTANTLY INCLINED VISCOUS MHD FLOWS newlineProblems on incompressible MHD flow of viscous and inviscid fluids having newlinefinite or infinite electrical conductivity have been investigated by many researchers newlineusing different transformation methods. Transformation method is applied from newlineone plane to another plane for studying the flows by reducing the order of the equation. In this problem we have studied a viscous MHD flow having infinite electrical conductivity when the magnetic field is inclined to the velocity vector in a constant angle. Hodograph transformation is applied to shift variables from the physical plane to the hodograph plane. Streamlines and magnetic lines are analyzed along with determining the solutions to the flow problems. Finally the newlinepressure variation is analyzed graphically. Flow pattern along with pressure variation, also studied in this problem for an orthogonal MHD flow. -
Analysis of Statistical and Deep Learning Techniques for Temperature Forecasting
In the field of meteorology, temperature forecasting is a significant task as it has been a key factor in industrial, agricultural, renewable energy, and other sectors. High accuracy in temperature forecasting is needed for decision-making in advance. Since temperature varies over time and has been studied to have non-trivial long-range correlation, non-linear behavior, and seasonal variability, it is important to implement an appropriate methodology to forecast accurately. In this paper, we have reviewed the performance of statistical approaches such as AR and ARIMA with RNN, LSTM, GRU, and LSTM-RNN Deep Learning models. The models were tested for short-term temperature forecasting for a period of 48 hours. Among the statistical models, the AR model showed notable performance with a r2 score of 0.955 for triennial 1 and for the same, the Deep Learning models also performed nearly equal to that of the statistical models and thus hybrid LSTM-RNN model was tested. The hybrid model obtained the highest r2 score of 0.960. The difference in RMSE, MAE and r2 scores are not significantly different for both Statistical and Vanilla Deep Learning approaches. However, the hybrid model provided a better r2 score, and LIME explanations have been generated for the same in order to understand the dependencies over a point forecast. Based on the reviewed results, it can be concluded that for short-term forecasting, both Statistical and Deep Learning models perform nearly equally. 2024 Bentham Science Publishers.