Sagar Yeruva - Academia.edu (original) (raw)

Papers by Sagar Yeruva

International journal of engineering and advanced technology, Apr 30, 2023

Evolving technologies make human life easier with increasing challenges. Online payments have bec... more Evolving technologies make human life easier with increasing challenges. Online payments have become an integral part of our lives in the era of digitalization. The credit card payment system has made transactions hassle-free. This led to E-Commerce appraisal. Digitalization of transactions has given rise to new forms of fraud and cyberattacks that can affect individuals and organizations. This had set hackers at a great deal to steal the cardholder details using different schemes. Credit card companies must recognize these fraudulent transactions at the earliest to retain credibility among the stakeholders. Traditional methods of fraud detection have proven ineffective in identifying and preventing these fraudulent activities and cyberattacks in real time. This paper discusses various Machine Learning algorithms that predict fraudulent transactions in real-time. Fraudulent activities are solved using data science and machine learning techniques with substantial processing power and the capacity to manage massive datasets. The model is trained on large volumes of the dataset. This paper emphasizes comparison of various machine learning algorithms' performance over the input. The accuracy and efficiency of several machine learning algorithms are measured and analyzed through tabulation and comparison. The trained model is integrated with a website to categorize financial transactions as either legitimate or fraudulent. On utilizing advanced machine learning algorithms, credit card fraud detection systems have become more refined and accurate in recent years. As a result, financial organizations and customers are protected against such fraudulent activities, leading to increased trust and confidence in utilization credit card payments.

Communications in Computer and Information Science, 2011

In Medical Diagnosis a plenty of complex diseases could not be predicted properly. Now a days in ... more In Medical Diagnosis a plenty of complex diseases could not be predicted properly. Now a days in India one of the major diseases is Asthma. In order to diagnose the disease asthma with Expert Systems, identifying using Machine learning algorithms such as Auto-associative memory neural networks, Bayesian networks, ID3 and C4.5. We present a comparative study among these algorithms with

Lecture notes in networks and systems, 2023

International Journal of Computer Applications, 2019

Credit card fraud is a serious problem in financial services. Billions of dollars are lost due to... more Credit card fraud is a serious problem in financial services. Billions of dollars are lost due to credit card fraud every year. There is a lack of research studies on analyzing real-world credit card data owing to confidentiality issues. In this paper, machine learning algorithms are used to detect credit card fraud. Standard models are firstly used. Then, hybrid methods which use AdaBoost and majority voting methods are applied. To evaluate the model efficacy, a publicly available credit card data set is used. Then, a real-world credit card data set from a financial institution is analyzed. In addition, noise is added to the data samples to further assess the robustness of the algorithms. The experimental results positively indicate that the majority voting method achieves good accuracy rates in detecting fraud cases in credit cards.

Information

In an industrial setting, consistent production and machine maintenance might help any company be... more In an industrial setting, consistent production and machine maintenance might help any company become successful. Machine health checking is a method of observing the status of a machine to predict mechanical mileage and predict the machine’s disappointment. The most often utilized traditional approaches are reactive and preventive maintenance. These approaches are unreliable and wasteful in terms of time and resource utilization. The use of system health management in conjunction with a predictive maintenance strategy allows for the scheduling of maintenance times in such a way that device malfunction is avoided, and thus the repercussions are avoided. IoT can help monitor equipment health and provide the best outcomes, especially in an industrial setting. Internet of Things (IoT) and machine learning models are quite successful in providing ongoing knowledge and comprehensive study on infrastructure performance. Our suggested technique uses a mobile application that seeks to antic...

International Journal of Innovative Technology and Exploring Engineering

Generally, only feature values obtained from photos are used to identify fish species. But, it is... more Generally, only feature values obtained from photos are used to identify fish species. But, it is challenging to identify fish species based on an image alone because fish of the same species can have varying hues or seem quite similar to other species. Additionally, it can be a tedious task that might lead to wrong predictions. Since various fish species exist, it is difficult to determine a fish without a proper model. Fast-growing computing and sensing technologies have improved most embedded systems, which help us solve more complicated algorithms. The main challenge is to perceive and analyze corresponding information for better judgment. An advanced system with better computing power can facilitate identifying fish species. Using the Teachable machine, a web-based tool for creating machine learning models, we can ensure that this application gives accurate results in classifying various fish species. An application that uses machine learning to identify fish categories is deve...

Emerging Computational Approaches in Telehealth and Telemedicine: A Look at The Post-COVID-19 Landscape

Pandemics are large-scale infectious disease outbreaks that can dramatically increase morbidity a... more Pandemics are large-scale infectious disease outbreaks that can dramatically increase morbidity and mortality over a wider geographic region and trigger substantial economic, social, and political damage. Currently, the world is facing the coronavirus (COVID-19) pandemic. COVID-19 is considered a dangerous disease affecting all entire humanity and reports death cases in the thousands each day (as per the source from Wikipedia, it is 3,690,000 deaths and 172,000,000 cases identified as COVID-19 positive as of 04-June-2021) and quietly throws dangerous bells on the entire humanity, causing health emergencies in every country, worldwide. Due to the ongoing pandemic, the healthcare infrastructure has been stretched. With the limited healthcare infrastructure and the number of COVID-19 cases spiking up, many countries have opted to treat their patients from the patient home, providing at-home medical facilities and continuous monitoring by medical officials at regular intervals. Health i...

Journal of Physics: Conference Series

Lung carcinoma, generally known as lung cancer, is the most common cause of cancer which is relat... more Lung carcinoma, generally known as lung cancer, is the most common cause of cancer which is related to mortality worldwide. Lung carcinoma is an extremely complex problem to solve and Lung cancer patients appear to be the most vulnerable to SARS-CoOVID-19 infection early discovery, on the other hand, has a high rate of survivability. Lung carcinoma detection in computed tomography (CT) has emerged as an emerging research subject in the field of medical imaging systems in recent years. The ability to accurately detect the size and location of lung cancer plays a critical role in lung cancer diagnosis. As a result, there is a requirement to rapidly read, detect, classify and evaluate CT scans. In this paper, we suggest a method for detecting and classifying lung nodules (or lesions) using a multi-strategy system. It has two parts: nodule detection (finding nodules) and classification (classifying nodules into Benign / non-cancerous or Malignant / cancerous). Lung CT scan images are ut...

International Journal of Recent Technology and Engineering (IJRTE)

Nowadays, people are constantly moving towards various fashion products as a result the e-commerc... more Nowadays, people are constantly moving towards various fashion products as a result the e-commerce market for garments is growing rapidly. Online stores must update their features according to user requirements and preferences. However, there are too many options for users to select from these online stores which may leave them in a dilemma to identify the correct outfit, save the user time, and increase sales, efficient recommendation systems are becoming a necessity for online retailers. In this paper, we proposed an Apparel Recommendation System that generates recommendations for users based on their input. We used a real-world data set taken from the online market giant Amazon using Amazon’s Product Advertising API. We aim to use keywords like brand, color, size, etc., to recommend. Data exploration to get detailed information about our dataset, Data Cleaning(pre-processing) to remove invalid sections, Model selection (We have compared different feature extraction techniques lik...

Proceedings of Second International Conference on Advances in Computer Engineering and Communication Systems

Proceedings of Second International Conference on Advances in Computer Engineering and Communication Systems, 2022

2021 IEEE Mysore Sub Section International Conference (MysuruCon), 2021

By addressing problems that have previously been highlighted in the literature review, the most i... more By addressing problems that have previously been highlighted in the literature review, the most important objective of this research is to create a MapReduce Framework that is closer to reality than it has been so far. Because the proposed ERDFMF method professionally stabilizes the scheme and has better MapReduce performance in both data storage and data processing than the other RDF Stores, this technique is a preferable choice over the other alternatives. How much data is to be stored and processed, as well as how many times data from the databases will be retrieved from the databases, is determined by the main objective of the planned task. This will reduce the loading time of queries, the response time of queries, and the pace at which memory is used. In addition, it will improve scalability and CPU usage, as well as providing the greatest strength (robustness) for Query Evaluation Engines over the long term. There was a lot of discussion about the intended ERDFMF and how it was created with the help of the Java programming language and the Hadoop 2.7.1 tool in this research. The LUBM data collection contains information about universities that are generated via the usage of ontologies. 14 questions are typical of the test. The SP2B data set is helpful for scalability testing since it enables the testing of complex queries and data access patterns. There are a total of 16 questions, the vast majority of which have complex frameworks to them. This results in more secure and efficient storage solutions than existing storage technologies such as Jena Sesame, Allegro Graph, and Oracle Triple Store, among others. The purpose of this research is to find an efficient recommended new ERDFMF that will be more effective than previous RDF Stores by analyzing existing data.

The distributed data warehouse supports the decision makers by providing a single view of data ev... more The distributed data warehouse supports the decision makers by providing a single view of data even though that data is physically distributed across multiple data warehouses in multiple systems at different branches. This environment has changed the face of computing and offered quick and precise solutions for a variety of complex problems for different fields. This paper reviews distributed data warehouse systems in view of its appearance compared to centralized data warehouses, frame work for distributed warehouse systems, data base designs and a good discussion on recent developments in distributed data warehouse architectures. It also concentrates the latest systems and various optimization methods.