Browse Items (11809 total)
Sort by:
-
Brain Tumor Classification Using an Ensemble of Deep Learning Techniques
The article reflects on the classification of brain tumors where several deep learning (DL) approaches are used. Both primary and secondary brain tumors reduce the patient's quality of life, and therefore, any sign of the tumor should be treated immediately for adequate response and survival rates. DL, especially in the diagnosis of brain tumors using MRI and CT scans, has applied its abilities to identify excellent patterns. The proposed ensemble framework begins with the image preprocessing of the brain MRI to enhance the quality of images. These images are then utilized to train seven DL models and all of these models recognize the features related to the tumor. There are four models which are General, Glioma, Meningioma, and Pituitary tumors or No Tumor model, which helps in reaching a joint profitable prediction and concentrating solely on the strength of the estimation and outcome. This is a significant improvement over all the individual models, attaining a 99. 43% accuracy. The data used in this research was gotten from Kaggle website and comprised of 7023 images belonging to four classes. Future work will focus on increasing the dataset size, investigating additional DL architectures, and enhancing real-Time detection to improve the accuracy of diagnostic scans and their overall relevance to clinical practice. 2013 IEEE. -
Brain Tumor Classification: A Comparison Study CNN, VGG 16 and ResNet50 Model
Brain tumors pose a severe threat to global health and may be lethal. Early detection and classification of brain tumors are essential for successful therapy and better patient outcomes. The good news is that advances in deep learning techniques have shown tremendous promise in medical image analysis, particularly in the detection and classification of brain tumors. Convolutional Neural Networks (CNN), a class of deep learning models, are used to process and analyze visual input, notably images, and movies. They excel in computer vision tasks like object detection, image segmentation, and categorization. Popular and efficient image analysis methods include CNNs. VGG 16 and ResNet 50 are two examples of deep convolutional neural network architectures used for image categorization applications. A number of image identification problems have been successfully solved using the 16 layer VGG 16. ResNet50, a well known 50 layer architecture, employs residual connections to get over the vanishing gradient issue and permits the training of deeper networks. A proprietary CNN model, VGG 16, and ResNet50 were compared in studies to see how well they performed on a dataset. The VGG 16, ResNet50, and the tailored CNN model were the most precise models. As a consequence, VGG 16 accurately detects brain cancers in the dataset that was supplied. Overall, this study highlights the value of deep learning techniques for medical image processing and their potential to improve the accuracy and efficacy of brain tumor diagnosis and treatment. 2023 IEEE. -
Brain Tumor Detectin Using Deep Learning Model
Brain tumor is a life-threatening disease that can disrupt normal brain functioning and have a significant impact on a patient's quality of life. Early detection and diagnosis are crucial for effective treatment. In recent years, deep learning techniques for image analysis and detection have played a vital role in the medical field, supplying more accurate and reliable results. Segmentation, the process of distinguishing between normal and abnormal brain cells or tissues, is a critical step in the detection of brain tumors. In this research, we aim to investigate various techniques for brain tumor detection and segmentation using Magnetic Resonance Imaging (MRI) images. The detection process begins by analyzing the symmetric and asymmetric shape of the brain to identify abnormalities. We will then classify the cells as either Tumored or non-Tumored. This research is aimed at finding a more accurate and efficient method for detecting brain tumors. Four Keras models are compared side by side to find out the best deep learning model for providing a suitable outcome. The models are ResNet50, DenseNet201, Inception V3 and MobileNet. These models gave training accuracy of 85.30%, 78%, 78%, and 77.12% respectively. 2023 IEEE. -
Brain Tumor Detection and Classification Using a Hyperparameter Tuned Convolutional Neural Network
Brain tumor detection using MRI scans when integrated with a deep learning approach can be immensely applied in identifying the tumor at early stages, with minimum medical professional aid. This research paper aims to develop an advanced predictive model that accurately classify brain tumors as benign or malignant using MRI scans. Here, a novel convolutional neural network (CNN) model is proposed to automate tumor detection and improve diagnosis accuracy. The model used a dataset of around 7000 brain cancer data classified into 4 labels which include glioma, meningioma, pituitary, and no tumor. Data wrangling and pre-processing are then applied to unify the images into a single format and remove any inconsistencies. Further the records are segregated into train and test samples with a 70-30 split. The proposed model recorded an optimum accuracy of 94.82%, precision of 94.2%, recall value of 93.7% and f-score metric of 93.9% respectively. In conclusion, the paper concluded that the proposed model can be applied to enhance the precision of both brain tumor diagnosis and prognosis. 2023 IEEE. -
Brain Tumor Detection using Hyper Parameter Tuning and Transfer Learning
Brain Tumor is the development of abnormal cells in our brain. There are cancerous and noncancerous brain tumors. Because they can press against healthy brain tissue or spread there, brain tumors are harmful. The early diagnosis of brain tumors is a highly challenging assignment for radiologists. The typical size of a brain tumor doubles in just twenty-five days due to its rapid growth. If not properly cared for, the patient's survival rate typically does not exceed six months. It may quickly result in death. For the purpose of early brain tumor identification, an automatic method is necessary. In this study, an automated strategy is suggested for quickly distinguishing between malignant and non-cancerous brain images. Most of the time, it can be treated if caught during the early stages. Hence the need for more and improved brain tumor detection. The most crucial part here is image processing. The medical images obtained during the test have to be appropriately analysed. Various methods such as MobileNet, EfficientNetB7, and EfficientNetV2 have been used and their efficiency has been analysed. Here we classify the dataset containing 300 images into two. The suggested system will offer improved clinical support for the field of medicine. 2023 IEEE. -
Brain Tumor Localization Using Deep Ensemble Classification and Fast Marching Segmentation
A brain tumor is an unusual and excessive growth of brain cells, which can be cancerous (malignant) or noncancerous (benign). These growths can be risky as they press on healthy brain tissue or expand in the brain. Detecting brain tumors early is tough for radiologists. A typical brain tumor can double in size in just 25days, and without the right treatment, patients often have limited chances of survival, about six months. Initial symptoms can be confused with other illnesses, and brain cancer is difficult to diagnose because of the complex nature of the brain and tumor locations. In this study, we propose a strategy where we first sort medical images based on the presence of a brain tumor. Then, we pinpoint the part of the image containing the tumor through segmentation. We use a combined model of MobileNet-V3 and EfficientNetV2 for image classification. To segment the tumor in the image, we use a fast marching method. The combined model's classification accuracy is 98%, and the segmentation accuracy is 99.6%. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Brain Tumor Prediction Using CNN Architecture and Augmentation Techniques: Analytical Results
The brain, a complex organ central to human functioning, is susceptible to the development of abnormal cell growth leading to a condition known as brain cancer. This devastating disease poses unique challenges due to the intricate nature of brain tissue, making accurate and timely diagnosis critical for effective treatment. This research explores automated brain tumor prediction through Convolutional Neural Networks (CNNs) and augmentation techniques. Utilizing a task reused learning approach with the help of VGG-16, Mobile-Net and Xception architecture, the proposed model achieves exceptional accuracy (99.54%, 99.72%) and robust metrics. This Research explores the Augmentation techniques to enhance the precision and accuracy of the model used. The study surveys related models, emphasizing advancements in automated brain tumor classification. Results demonstrate the efficacy of the model, showcasing its potential for real-world applications in medical image analysis. Future directions involve dataset expansion, alternative architectures, and incorporating explanation techniques. This research contributes to the evolving landscape of artificial intelligence in healthcare, offering a promising avenue for accurate and efficient brain tumor diagnosis. 2024 IEEE. -
Brain tumor segmentation and detection using MRI images
Brain tumor is caused due to the increased abnormal in brain. It is not something that we might say is limited to aged people alone, but is known to affect newborn babies as well. It affects many people worldwide. With the applications of Machine Learning (ML) and Image Processing (IP), the early detection of brain tumor is possible. In this research work, the different stages in image processing which help to detect brain tumor, is addressed vividly. This work provides information about the various sets of filtering and segmentation methods which can be used to detect whether it is brain tumor or not. All of the filtering methods are defined in image preprocessing techniques. The next procedure is to apply segmentation methods namely watershed segmentation and gray level threshold segmentation. After this, certain features are considered for feature extraction such as area, major axis, minor axis and eccentricity. According to the outcomes from the feature extraction technique, the classification of the tumor is done. In this paper, we achieve an accuracy of 92.35 by using K-Nearest Neighbor (KNN) algorithm. IAEME Publication. -
Brain-based learning method: Opportunities and challenges
The chapter examines the concept of brain-based learning to bridge the gap between neuropsychology and education while understanding the best way to use our brain for meaningful learning. It suggests learning as a developmental process that enhances in a challenging but less threatening environment. Brain plasticity suggests that repeated exposure to a stimulus in a conducive environment helps in better recall and retrieval, as the repeated exposure allows the formation of new neural connections and strengthening the old ones while engaging in the task. As the application of brain-based learning moves away from the traditional style of learning, it focuses on a more holistic understanding of the process of learning. The chapter talks about applying a brain-based learning model to enhance learning in a stimulating surrounding to explore and stimulate various sense organs and further enhance neural connections. It discusses strategies to incorporate to allow engagement of sensory organs and problem-solve to enhance learning. Another perspective suggests attaching emotion to a situation which leads to forming a meaningful association in our brain. Depending on the strength of this connection, it becomes easier to recall and retrieve the memory. When compared to the traditional style of teaching, brain-based learning has shown to better academic accomplishment. The Author(s), under exclusive license to Springer Nature Switzerland AG 2021. All rights reserved. -
Brand activism and millennials: An empirical investigation into the perception of millennials towards brand activism
The reckless pursuit of social, environmental, political and cultural issues and brands may alienate the very customer base, whom they try to impress, especially the millennials. Hence, this study intends to study the perceptions of millennials towards brand activism, so that the findings from the study can help the brand managers to steer their brands into the troubled waters of brand activism. The methodology followed is HTAB (Hypothesize, Test, Action, Business), a popular analysis framework given by Ken Black in his book titled "Business Statistics: Contemporary Decision Making (6th ed.)" A sample comprising of 286 respondents was collected. The final data had 286 observations and 45 features across seven categories. It was found that millennials prefer to buy a brand if it supports a cause or purpose and they stop buying if brand behaves unethically. It was also observed that there is no gender difference amongst the millennials towards their perceptions concerning brand activism. Moreover, millennials across different income categories have similar perceptions of brand activism. It was also substantiated that the emotional tie of the millennials with the brand existing for a cause goes beyond price shifts and brands taking a political stance, cherry-picking of issues and being disruptive prompts and creates profound backlash for the brands. Shivakanth Shetty, Nagendra Belavadi Venkataramaiah, Kerena Anand, 2019. -
Brand activism and millennials: an empirical investigation into the perception of millennials towards brand activism /
Problems And Prespectives In Management, Vol.17, Issue 4, pp.163-175, ISSN No: 1727-7051.
-
Brand anthropomorphisms impact on real estate purchase decisions of young buyers in India and the underlying reliance on spatial memory
Purpose: Assessing anthropomorphic tendency in relation to real estate purchase decisions and analysing the elements of friendliness, aggressiveness, pleasure and arousal as a link to the spatial memory of the consumer. This study aims to help brands and advertisers in the real estate industry to create meaningful consumer relationships by using elements that are associated with positive spatial experience. By formulating a detailed questionnaire with adapted variables from proven research and a multilayered approach of theoretic and practical analysis, this paper situates the identified variables in the plane of space and customer experience. Design/methodology/approach: By using structural equation modeling, this study analyses a sample data of 411 consumers and their response to elements of housing. Findings: The findings of this study showed that variables of friendliness, aggressiveness, pleasure and arousal significantly impact consumers real estate purchase decision; however, anthropomorphic tendency does not have a significant impact. Through theoretical analysis, it was found that spatial memory may have a role in the visual and display of the variables. Originality/value: The merit of this paper lies in the discussion it has raised with regard to the intersection between theoretics of space and the chosen variables. In the field of business and management, often philosophical implications of spatiality may not be actively associated with numerical computation. This paper not only looks at brand anthropomorphisms impact on real estate purchase decisions but also looks at friendliness and other mentioned variables as significantly impacting purchase decisions and linked to memory, space and affiliation. 2023, Emerald Publishing Limited. -
Brand awareness of 'generation y' customers towards doughnut retail outlets in India
The Research is all about knowing the customers acquiring top of mind recall about doughnut retail outlets in Bangalore city, India through various methods. Once the brand is established in the minds of the consumers, it occupies a unique position and special meaning and value is generated. Brand awareness is the consumer's conscious or unconscious decision, expressed through intention or behavior, to repurchase a brand continually. In order to create brand loyalty, advertisers must break consumer habits, help them to acquire new habits and reinforce those habits by reminding consumers of their purchase and encourage them to continue purchasing those products in the future. 'Generation Y' refers to customers millennial, the generation of people born during the 1980s and early 2000s. 'Generation Y' consumer's access social media on daily basis but they often ignore advertisements that are targeted to them. The previous research works on' Generation Y' customers emphasize that marketers must focus on social media marketing to draw the attention of these customers. Determining the brand awareness of 'Generation Y' customers was considered, in order to know the present level of awareness about the doughnut brands, increase the customer traffic and sales as 'Generation Y' customers are the target customers for doughnut retail outlets. -
Brand awareness of 'generation y' customers towards doughnut retail outlets in India /
The Journal Of Business And Retail Management Research, Vol.11, Issue 4, pp.108-113, ISSN: 2056-6271 (Online) 1751-8202 (Print). -
Brand equity seen through advertising proceedings and analysis on brand attitude and brand experience /
Brand equity had been viewed from various perspectives. In general brand equity is defined as marketing effect which has been uniquely attributed to brand the product. Brand equity leads to two general motivation. One is financial base motivation to estimate the value of a brand. The second motivation creates a strategy based motivation to improve the market status and productivity. -
Brand Identities and Facebook: A Content Analysis of Photographs and Comments on Brand Pages on Facebook
Construction of a brand image using different forms of media has become one of the crucial factors of branding today. The social media is a promising tool to promote ideas to a wider audience, thus it becomes vital for advertising bodies to understand the petite nuances of the medium. This study looks at the role, the profile photos and the cover photos play in the process of identity construction of a brand on Facebook. The Facebook comments are designed in such a way that there are multiple access options to them. The study was conducted on leading brand pages to look for the ways in which the message was decoded in the form of comments. These comments were categorized into different positions of the encoding and decoding theory and were also analyzed for the appeals of rhetoric. The study showed the balance in the comments that are for and against the brand ideology. The study also shows the presence of too much noise in the comments which have no role to play in the brands identities. -
Brand Love for Sports Apparels Among Indians: A Triangular Theory of Love Perspective
This study aims to evaluate the concept of brand love among the Indians in sports apparel industry. Drawing on Sternbergs (1986) triangular theory of love, we propose a three-dimensional brand love model. We further discuss the interrelationship between these variables and provide a theoretical model for explaining the concept using sports apparels. Then, this theoretical model is tested using empirical research undertaken among 327 respondents. These exploratory results indicated that the concept of brand love in India is similar to that of interpersonal love, contradicting the earlier finding in the field of brand love. These contradicting findings were attributed to the cultural differences between Eastern and Western cultures, especially in the field of extended self (Markus & Kitayama, 1991). These findings create the possibility for future research into brand love via the triangular theory of love to understand how the changes in the perceptions of self influence the brand love. 2022 Management Development Institute. -
Brand review scale for brand management /
Patent Number: 202211039578, Applicant: Dr. Mahesh Chandra Joshi.
Big firms have enough resources for various activities such as branding, market research, innovation, product development etc. which are very important for survival and growth of an organization. Small firms also wish to execute these activities but many times resource constraints refrain them form activities like market research which either requires inhouse research team or hiring of external agency for the task. -
Brand review scale for brand management /
Patent Number: 202211039578, Applicant: Dr. Mahesh Chandra Joshi.
Big firms have enough resources for various activities such as branding, market research, innovation, product development etc. which are very important for survival and growth of an organization. Small firms also wish to execute these activities but many times resource constraints refrain them form activities like market research which either requires inhouse research team or hiring of external agency for the task. -
Brand together: How co-creation generates innovation and re-energizes brands /
Vels Management Journal, Vol-1 (2), pp. 98-100. ISBN-978-0-7494-6325-0