Browse Items (16481 total)
Sort by:
-
A comparative analysis of KFC video advertisements and the impact on its customers of Bengaluru /
In India, today fast food being one of the most successful businesses and also all over the world because of the economic development, increase in per capita income, people having less time to cook, people having no time to wait in restaurants and people are ready to spend. One popular fast food chain in India is KFC and one of the tools of KFC to reach its customers is through visual advertisements. -
A Comparative Analysis of L1, L2, and L1L2 Regularization Techniques in Neural Networks for Image Classification
The research examines how L1, L2, and L1L2 weight regularization methods affect neural network performance, generalization, and sparsity using the CIFAR 10 dataset. A Convolutional Neural Network (CNN) trained with the same environment for each regularization method to evaluate test accuracy, weight sparsity, and computational speed. The study shows that L1 regularization produces sparse weights, which makes models more interpretable, and L2 regularization helps prevent overfitting while improving model generalization. The combination of L1L2 regularization enables individual image classification methods to reach test accuracy. The results indicate that the weight regularization plays a vital role in creating neural networks that are both stable and efficient. They are interpretable, and L2 regularization improves generalization and reduces overfitting. The combined L1L2 regularization achieves the balance between sparsity and performance, leading to higher test accuracy compared to individual techniques for image classification. The research results demonstrate that weight regularization stands as an essential factor for Creating Neural Networks that are robust, efficient, and interpretable, thus helping to enhance Deep Learning model performance. 2025 Seventh Sense Research Group. -
A Comparative Analysis of LSB & DCT Based Steganographic Techniques: Confidentiality, Contemporary State, and Future Challenges
In order to maintain anonymity and security, the steganography is the technique of cloaking confidential data within what seems like harmless digital material. Several steganographic methods have been established devised over time, but those centered around the discrete cosine transformation (DCT) and the least significant bit (LSB) have drawn the most consideration. In this study, two common steganographic methods are compared and contrasted with an emphasis on the secrecy they can keep, the usage they are now receiving, and any potential difficulties in the future. As an alternative, the DCT-based method uses the frequency domain properties of cover media to obfuscate hidden information. Since it spreads the concealed information across several frequency coefficients, it provides greater security than LSB-based techniques. The resilience and imperceptibility of the concealed data are improved by a variety of DCT-based algorithms, such as the modified quantization and matrix encoding approaches, which we explore in detail. We also give a general summary of both approaches'current state in terms of their application, constraints, and areas in which they may be used. We evaluate the benefits and drawbacks of each approach, considering elements like payload size, computing difficulty, and detection resistance. 2023 IEEE. -
A Comparative Analysis of Machine Learning Algorithms for Image Classification: Evaluating Performance
Image classification plays a crucial role in various applications, and selecting the most effective machine learning algorithm is essential for achieving accurate results. In this study, we conducted a comparative analysis of several well-known supervised machine learning techniques, including logistic regression, support vector machine (SVM), k-nearest neighbours (kNN), nae Bayes, decision trees, random forest, AdaBoost, and artificial neural networks (ANN). To assess the performance of these algorithms, we utilised different fonts of the English alphabet as our dataset and performed the analysis using the R programming language. We evaluated the algorithms based on standard performance criteria, such as the area under the Receiver Operating Characteristic curve (ROC), accuracy, F1 score, precision, and recall. Our research findings demonstrated that the classification performance varied depending on the training size of the dataset. Notably, as the training size increased, neural networks exhibited superior performance compared to other machine learning techniques. Consequently, we conclude that neural networks and SVM are the most effective algorithms for image classification based on our study. By conducting this comprehensive analysis, we contribute valuable insights into selecting appropriate machine learning algorithms for image classification tasks. Our findings emphasise the significance of considering the training dataset size and highlight the advantages of neural networks and SVM in achieving high classification accuracy. This study provides valuable guidance for practitioners and researchers in choosing the most suitable machine learning algorithm for image classification, considering their specific requirements and dataset characteristics. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A comparative analysis of opinions and sentiments on clean India campaign and sustainability goals of 2030
Human are blessed with natural intelligence. Artificial Intelligence can help human minds to make a best usage of machines to handle huge amount of data with accuracy and precision. AI has a widespread application in 21st century. Opinion mining is an application of artificial intelligence. The opinions expressed in social media can be extracted using python which can be used as an input for various machine learning algorithms to identify many patterns which can help policy makers to make effective policies. Clean India Campaign started in India with a set of goals to be achieved. Sustainability goals of 2030 given by United Nations puts light on many important aspects which need immediate attention in the next 9 years. Current pandemic Covid-19 has also triggered the necessity behind putting immediate attention for a better tomorrow. Without proper awareness programs, brainstorming knowledge cultivation, orienting minds towards the "what-why-where"aspects of sustainable growth in each sphere of life, aligning industrial development and digital era towards sustainable industrial development in digital era, sustainable economy, sustainable care of each natural resource; it is not easy to accomplish the sustainability goals of 2030 given by United Nations.This work emphasizes on the case study conducted as an initiative to motivate future policy makers to be aware of the different dimension of 2030 United Nations Agenda and the clean India campaign to take initiatives as a professional through the skills learned focusing on India. Realizing Individual social Responsibility can make a big difference in the planning and implementation of the goals and missions. Swachch Bharat Abhiyan (Clean India Campaign) started Swachch Bharat Mission-Urban (SBM-U) with a few objectives to make India Clean.This work has proposed two phases for analyzing opinions. This research have provided a methodology to apply AI to improve the opinion mining. The conventional opinion analysis is limited by reachability but the automated opinion analysis can be scaled up using artificial intelligence based applications. The uniqueness of the work lies in its focus on 'one-three verticals' in phase 1 of the methodology. Many prominent regions of India are considered as a part of the study. It helps us to provide a clearer picture across different regions of India. It also provide an avenue to list tasks to be done for each region and a set of ways which could be adopted by the future professionals and current stakeholders of higher education institute. Phase 2 focusses on more number of opinions collected from across the globe through digital platforms. 2021 Author(s). -
A COMPARATIVE ANALYSIS OF PRINT ADVERTISEMENTS OF THE YEARS 1990 AND 2000
This content analysis of a sample of advertisements of 20 print copies of various Indian products during the 1990s and 2000 examined the impact of the national economic conditions on advertising and its effect on 4 major aspects- text, visuals, typeface and layout. This study suggests that the impact of national economic conditions and the prevailing culture in the 1990s and 2000 on the use of advertisement elements in the different FMCG (Fast Moving Consumer Goods) product advertisements seemed visible. Advertising is part of the changing social, economic, and cultural environment, and its visuals might have been created in a way that could reflect those changes that people would want to adjust themselves to. Another way of linking advertising and its visuals to society and culture is the cultural approach to advertising. Cultural historians argue that advertising is an important window through which different aspects of society and culture can be explained. But also, the advertising itself can be explained to determine how it might have been shaped by society. While identifying the purpose of this study, more knowledge about the evolution in print advertisements is acquired. The research has given a better idea in recognizing the past advertisements which were during the beginning of the Globalization period and has compare it with print advertisements of the year 2000. -
A Comparative Analysis of Sentiment Analysis Using RNN-LSTM and Logistic Regression
Social media analytics makes a big difference in the success or failure of an organization. The data gathered from social media can be used to get a hit type product by analyzing the data and getting important information about the need of the people. This can be done by implementing sentiment analysis on the available data and then accessing the feelings of the customers about the product or service and knowing if it is actually being liked by them or not. Tracking data of the customers helps the organization in many ways. This study was done to get familiarized with the concept of data analytics and how social media plays an important role in it. Furthermore, Web scraping of Twitter and YouTube data was done following which a standard dataset was selected to do the other analytics. The field of sentiment analysis was used to get the emotions of the people. Logistic regression and RNN-LSTM models were used to perform the same, and then, the results were compared. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A COMPARATIVE ANALYSIS OF THE INVESTIGATIVE STYLES OF REPORTING IN MEDIA TODAY - A case study on India today group.
Investigative journalism has become the call of the day as too many scams are being reported. It all started with the ??Watergate scam that was reported by Washington post. In India it was the 1980s period when investigative journalism arose, there have been a few milestone cases. First being Bofors gun scandal, which is considered one of the most influential works of the Indian investigative journalism. Then the other which shook the Indian Sensex, the Harshad Mehta scam. Since 2007 there have been a number of scams which have been investigated by the media. The UPA government has been under the scanner since then. Due to the growing number of scams in the country, investigative journalism has grown in the past few years. This study compares the investigative reporting approach of general magazine and the business magazine using content analysis. This study aims to understand how professional and reader friendly are the approaches of investigative reports today in media. -
A Comparative Analysis of Traditional and Machine Learning Forecasting Techniques
Forecasting is the process of making predictions or estimates about future events or conditions based on historical data, trends, and patterns. It involves analyzing past data and using statistical or other quantitative methods to project future outcomes, such as sales figures, market trends, weather patterns, or financial performance. Forecasting can be used in a wide range of fields, including economics, finance, business, weather forecasting, and sports. The accuracy of a forecast depends on the quality of the data, the methods used, and the assumptions made about the future. 2024 Sachi Nandan Mohanty, Preethi Nanjundan and Tejaswini Kar. -
A Comparative Analysis of Various Soft Computing Techniques for Indian Stock Market Prediction
Soft computing techniques have been increasingly used for stock market analysis in the past few years because they can capture nonlinear aspects which traditional econometric models do not adequately capture. With different techniques like Artificial Neural Networks, Deep Neural Networks and Stacked Autoencoders available, in this paper, the author tries to determine which of the above methods can model the Indian stock market with higher accuracy. In this study, high-frequency data from Nifty 50 is used, and various feature selection techniques such as PCA and linear regression are used for each of the above machine learning models to predict the Nifty 50 data. Finally, all predictions from the different techniques are compared with the actual index movement and the best method for Nifty 50 is suggested. 2025 Seventh Sense Research Group -
A Comparative Analysis On Machine Learning Algorithm for Score Prediction and Proposal of Enhanced Nae Bayes
Sports attracted a lot of people to watch various games all over the world. India is not an exception. Among various games, cricket has special attention. Cricket in India contributes to the Indian economy on a large scale. Cricket is also known for the broad amount of data gathered for each team, season, and player. Hence, cricket is a perfect domain to work on various data analysis and machine learning approaches to acquire useful insights and information. In this paper, algorithms were used to enhance the output of the team in a sports league, particularly, IPL (cricket). It reflects the performance of the team on a deeper analysis of the requirements of T20 cricket. 2022 IEEE. -
A Comparative Assessment of Cascaded Double Voltage Lift Boost Converter
In several power conversion applications, dc-dc boost converters with voltage boost techniques are extensively used in order to meet the growing power demand. The main drawback of conventional dc-dc boost converter is obtaining high DC voltages, when operated at high duty ratio which causes switching losses and decreases overall efficiency because of the switch being used to be in 'ON' state for long time and voltage stresses across switch increases. The main objective of proposed converter is to obtain high voltage without extreme duty ratio. When input voltage of 15V DC is given, 201.1V DC output voltage is attained at duty ratio of 0.4 by the cascaded double voltage lift boost converter. To validate the performance of proposed converter, simulation is carried out in LTspice XVII and a comparative assessment of proposed converter with other converters at different duty ratio are realized. 2020 IEEE. -
A Comparative Benchmark of Deep Learning and Classical Models for BLE-Based Indoor Localization
Bluetooth Low Energy (BLE)-based indoor positioning has gained attention as a cost-effective solution for environments where GPS signals are unreliable. Despite advances in ML and DL techniques, few standardized benchmarks exist for comparing models under uniform conditions. This study evaluates seven models - K-Nearest Neighbor, Random Forest, Deep Neural Network, 1D CNN, Long Short-Term Memory, Bi-LSTM, and Transformer - on a publicly available dataset collected across multiple building floors. A preprocessing pipeline was applied to address missing values, refine RSSI signals, and generate temporal features. Performance was assessed using both accuracy metrics (MAE, RMSE) and efficiency metrics such as processing time, and model size. Results show that KNN, Random Forest, and DNN consistently outperformed complex sequential and attention-based models, achieving RMSE as low as 1.297 m. These findings suggest that simpler architectures align more effectively with BLE RSSI data than deeper models. This study establishes a benchmark that can support future work in developing efficient, lightweight, and generalizable indoor positioning systems. 2025 IEEE. -
A comparative evaluation of machine learning and deep learning models across diverse datasets for early detection of lung cancer
Lung cancer is among the most fatal types of cancer, accounting for millions of fatalities globally. The capacity for its early detection has the potential to greatly enhance the outcome of treatments, and in recent times, machine learning (ML) and deep learning (DL) algorithms have emerged as mighty resources in aiding radiologists and doctors. This article describes a comparison study of research articles in which they employed different ML and DL models in lung cancer detection on a wide range of datasets. The analysis establishes that the variety, quality, and source of the dataset are central to determining how reliable reported model performance is. Reproducibility has been made possible with public datasets such as LIDC-IDRI, NSCLC, and Kaggle datasets, whereas private clinical datasets typically lead to improved accuracy since they consist of high-quality curated annotations. Subsequent research has shown that DL models, especially state-of-the-art architectures such as convolutional neural networks (CNNs) and EfficientNet-B3, are well-suited to image classification tasks and consistently outperform classical ML models when large, well-balanced datasets are available. Hybrid approaches that blend CNN-based feature learning with traditional classifiers like support vector machines have also proven highly promising, particularly when applied to overcome challenges such as small sample sizes and noisy images. Directions for future work point toward the integration of standardized, multicenter datasets, explainable AI models, and multimodal learning techniques to reach reliable in-clinic deployment. 2026 Elsevier Inc. All rights reserved. -
A Comparative Evaluation of Standalone LLMs and Retrieval-Augmented Generation Models Using Hypothetical Gemini Systems
This study assesses the efficacy of two theoretical language models; Gemini Standalone LLM and Gemini RAG (Retrieval Augmented Generation) across diverse natural language inquiries. The assessment centers on three principal metrics: precision, pertinence, and inference duration. The experiment utilizes a controlled simulation to illustrate the benefits and drawbacks of independent language creation versus retrieval augmented generation strategies. The results demonstrate that RAG at trains superior accuracy and relevance by integrating retrieved context, albeit it incurs longer inference durations. This comparative analysis seeks to assist researchers in comprehending the ramifications of including retrieval methods into big language models. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
A comparative heat transfer analysis of rectangular fin through LTE and LTNE model
The objective of this research is to compare the thermal performance of rectangular porous fins through the Local Thermal Equilibrium and the Local Thermal Non-Equilibrium models. The thermal interactions between the solid and fluid phases are represented by two distinct energy equations in the Local Thermal Non-Equilibrium model. Whereas, heat transfer is governed by a single energy equation in the Local Thermal Equilibrium model. The governing equations describing the temperature distribution inside the fin system are developed using basic heat transfer principles. To enhance thermal conductivity and total effectiveness of heat transmission, the fluid phase of water is amalgamated with Al2O3 and TiO2 nanoparticles. The governing nonlinear ordinary differential equations are nondimensionalized, and the RungeKutta Fehlberg fourth-fifth order (RKF45) method is employed to solve these equations numerically. The accuracy and dependability of the obtained solution are confirmed by comparing it with previous findings. The influence of pertinent parameters on the thermal characteristics of the permeable fin is depicted graphically, and the rate of heat transfer is analyzed by Response surface methodology. It has been determined that, for the capturing of phase-wise thermal variations, Local Thermal Non-Equilibrium model performs better, particularly in permeable media with no heat conduction differences. The Author(s), under exclusive licence to SocietItaliana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2025. -
A Comparative Investigation on the use of Machine Learning Techniques for Currency Authentication
In the present banking sector, identifying the real and the fake note is a very challenging task because if we do it manually, it takes a long time to check which is real and which is fake. This research study article aims to authenticate the money between real and fake by using different machine algorithms facilitating learning, such as K-means Clustering, Random Forest Classification, Support Vector Machines, and logistics Regression. Specifically, we consider the banknote dataset. The data of money is extracted from various banknote images by using the wavelet transform tool, which is primarily used to remove elements from the images. However, we are mainly concerned with the different machine learning algorithms, so we take the two variables, where the first variable indicates image variance and the second indicates image skewness. We use these two variables to train our machine learning algorithms. So, majorly, by applying the different machine learning algorithms, which are supervised and unsupervised, we find the accuracy for the respective machine learning algorithms and then visualize and classify the real and fake notes separately. Finally, the prediction is based on integrity, which means the efficiency value is based on how much the mechanism system can uncover the fake notes. Then, after calculating the accuracy of currency authentication, there is a high possibility that the accuracy of the particular algorithm is the best algorithm, so the application of currency authentication will be very useful for the bank to easily find duplicate notes. 2022 IEEE. -
A Comparative Performance Analysis of Convolution W/O OpenCL on a Standalone System
Initial approach of this paper is to provide a deep understanding of OpenCL architecture. Secondly, it proposes an implementation of a matrix and image convolution implemented in C (Serial Programming) and OpenCL (Parallel Programming), to describe detailed OpenCL programming flow and to provide a comparative performance analysis. The implementation is being carried on AMD A10 APU and various algebraic scenarios are created, to observe the performance improvement achieved on a single system when using Parallel Programming. In the related works authors have worked on AMDAPPSDK samples such as N-body & SimpleGL to understand the concept of vector data types in OpenCL and OpenCL-GL interoperability, have also implemented 3-D particle bouncing concept in OpenCL & 3D-Mesh rendering using OpenCL. Lastly, authors have also illuminated about their future work, where they intend to implement a novel algorithm for mesh segmentation using OpenCL, for which they have tried to form a strong knowledge base through this work. 2015 IEEE. -
A Comparative Review of Lossless Text Compression Algorithms: From Classic Techniques to Hybrid Models
The lossless text compression is an essential part of data transmission and storage that allows using resources effectively without losing data integrity. This paper combines the most recent research with the important discoveries of benchmark research that focuses on essential algorithms such as Huffman LZW and Shannon-Fano and advanced hybrid algorithms such as LZW and Burrows-Wheeler Transform (BWT -based algorithms. The trade-offs between compression ratio, speed and adaptability can be observed comparing how algorithmic concepts, operational stages and empirical performance evolve in different datasets. This evaluation ends with recommendations on how to choose algorithms as well as future research recommendations. 2025 IEEE. -
A Comparative Study in Predictive Analytic Frameworks in Big Data
Every information processing sector uses predictive analytic framework in terms of distributed datasets through a variety of applications. These analytic frameworks are effectively used for various analyses of data, parameter, and attributes. Leveraging data to make insightful decisions for maximizing the effectiveness requires the determination of the best predictive framework for any organization. Even a retail unit which wants to scale up its production rely on multiple parameters. These parameters must be analyzed for effective quality control in any domain. Since there are diversities in every domain the data will be in varied form, and these are accumulated as Big Data. These analyses are done using machine learning frameworks. The strategy involved would differ from one domain to another such as in the health care sector the framework might predict the magnitude of patients admitted to the urgent care facility over the upcoming days whereas in the production industry the framework would align quality control measures. This article analyses a few domains and their deployed machine learning impacts in a strategic way. 2023 American Institute of Physics Inc.. All rights reserved.