Machine Learning For Detecting Credit Card Fraud DOI
Aanchal Gupta, Kanishka Singh,

Nonita Sharma

et al.

Published: Nov. 20, 2022

These days frauds related to credit cards are exponentially increasing as compared earlier scenarios. Like every coin has two faces in a similar way where on one hand the introduction of helped ease online payment make our lives easier, other hand, same technology increased number frauds. Fake identities and various technologies used by criminals or cyber attackers trap users. Henceforth, it become essential find solution for all such abnormal activities so that money user can be protected at time transaction. In order tackle problems, we train machines using Machine Learning Algorithms. This project been designed illustrate analysis dataset taken from Kaggle system accordingly any kind activity during transaction immediately detected. The issue involves examining previous card transactions information both fraudulent ones zeroes were legitimate Here, detecting 100% while lowering erroneous fraud classifications is key goal. Data sets analyzed pre-processed, anomaly detection techniques, like Random Forest algorithm Decision Tree Classifier, get Prompt Corrective Action modified Credit Card Transaction data, have main focuses this procedure. models evaluated based training testing accuracy. It found tree classifier performed better accuracy i.e., 95% random forest demonstrated 94.11%.

Language: Английский

[Retracted] Monitoring Cardiovascular Problems in Heart Patients Using Machine Learning DOI Creative Commons
Ahmed Al Ahdal, Manik Rakhra, Rahul R. Rajendran

et al.

Journal of Healthcare Engineering, Journal Year: 2023, Volume and Issue: 2023(1)

Published: Jan. 1, 2023

The World Health Organization reports that heart disease is the most common cause of death globally, accounting for 17.9 million fatalities annually. fundamentals a cure, it thought, are important symptoms and recognition illness. Traditional techniques facing many challenges, ranging from delayed or unnecessary treatment to incorrect diagnoses, which can affect progress, increase bill, give more time spread harm patient's body. Such errors could be avoided minimized by employing ML AI techniques. Many significant efforts have been made in recent years computer-aided diagnosis detection applications, rapidly growing area research. Machine learning algorithms especially CAD, used detect patterns medical data sources make nontrivial predictions assist doctors clinicians making timely decisions. This study aims develop multiple methods machine using UCI set based on individuals' attributes aid early cardiovascular disease. Various evaluate review results dataset. proposed had highest accuracy, with random forest classifier achieving 96.72% extreme gradient boost 95.08%. will doctor taking appropriate actions. technology only able determine whether not person has issue. severity cannot determined this method.

Language: Английский

Citations

27
Performance Evaluation of Machine Learning Techniques (MLT) for Heart Disease Prediction DOI Creative Commons
Gufran Ahmad Ansari, Salliah Shafi Bhat, Mohd Dilshad Ansari

et al.

Computational and Mathematical Methods in Medicine, Journal Year: 2023, Volume and Issue: 2023(1)

Published: Jan. 1, 2023

The leading cause of death worldwide today is heart disease (HD). recognised as the second‐most significant organ behind brain. A successful outcome treatment can be improved by an early diagnosis which significantly reduce chance in health care. In this paper, we proposed a method to predict disease. We used various machine learning algorithms (MLA), namely, logistic regression (LR), k‐nearest neighbor (KNN), support vector (SVM), Naive Bayes (NB), random forest (RF), and decision tree (DT). With testing data set, evaluated model’s accuracy prediction. When compared other five models, approaches perform better. 99.04% rate, algorithm provide best match algorithms. Six feature selection were for performance evaluation matrix. MCC parameters accuracy, precision, recall, F measure are evaluate models.

Language: Английский

Citations

20
An Analysis of the Impact of Business Analytics on Progress DOI
Manik Rakhra,

Ankita Wadhawan,

Arun Singh

et al.

2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Journal Year: 2022, Volume and Issue: unknown, P. 1 - 6

Published: Oct. 13, 2022

Business analytics is as a rule progressively used to pick up data driven experiences help basic leadership. We are finding new technique which less time-consuming process or effortless process. In based on big data, machine learning, science experts professional people work. As historical consolidate takes more time because it works the basis of decision-making Here, we need improve by comparing all previous technologies already have.

Language: Английский

Citations

23
Heart Disease Prediction Using GridSearchCV and Random Forest DOI Creative Commons
Shagufta Rasheed, Girish Kumar,

D Malathi Rani

et al.

EAI Endorsed Transactions on Pervasive Health and Technology, Journal Year: 2024, Volume and Issue: 10

Published: March 22, 2024

INTRODUCTION: This study explores machine learning algorithms (SVM, Adaboost, Logistic Regression, Naive Bayes, and Random Forest) for heart disease prediction, utilizing comprehensive cardiovascular clinical data. Our research enables early detection, aiding timely interventions preventive measures. Hyperparameter tuning via GridSearchCV enhances model accuracy, reducing disease's burdens. Methodology includes preprocessing, feature engineering, training, cross-validation. Results favor Forest promising applications. work advances predictive healthcare analytics, highlighting learning's pivotal role. findings have implications policy, advocating efficient models management. Advanced analytics can save lives, cut costs, elevate care quality. OBJECTIVES: Evaluate the to enable interventions, METHODS: Utilize hyperparameter enhance accuracy. Employ cross-validation methodologies. performance of SVM, algorithms. RESULTS: The reveals as favored algorithm showing promise contribute improved burden disease. CONCLUSION: underscores role in

Language: Английский

Citations

5
Enhancing Therapeutic Investigation Through AI Driven Convolutional Neural Network in Comparison with Deep Learning Techniques DOI
Mohammad Azhar, Lei Mo

Journal of Machine and Computing, Journal Year: 2025, Volume and Issue: unknown, P. 1055 - 1067

Published: April 5, 2025

This study seeks to enhance an Artificial Intelligence (AI) system for identifying medical issues using deep learning (DL) techniques. Conventional methods often struggle predict health conditions and provide effective solutions. A re-modelled convolutional neural network (RCNN) is introduced, featuring optimized activation functions in its layers incorporating dense, fully connected layers. The efficiency of the RCNN algorithm validated by comparing it with other advanced algorithms. Using available datasets, evaluates accuracy DL detecting within Python Jupyter environment. Performance metrics, including F1 score, recall, accuracy, precision, are used assess effectiveness proposed model.

Language: Английский

Citations

0
Image Steganalysis with Image decoder using LSB and MSB Technique DOI

Abhishek Chhabra,

Shruti,

Tenzin Woeden

et al.

2022 3rd International Conference on Intelligent Engineering and Management (ICIEM), Journal Year: 2022, Volume and Issue: unknown, P. 900 - 905

Published: April 27, 2022

The information has gained a big boom during cyber world. Hiding text into an image or adding payload to the is known as steganography. Steganography started in BC when rulers send hidden from one place another. combines data compression, cryptography technologies fulfill need for privacy on internet. (by definition) hiding of file within In this paper, we have used concept steganalysis which helps us detect that image. This paper attempts use with decoder using LSB and MSB technique analysis various steganography techniques today's

Language: Английский

Citations

16
Design and development an Agriculture robot for Seed sowing, Water spray and Fertigation DOI

Taha Fadhaeel,

Patel C. H,

Ahmed Al Ahdal

et al.

2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), Journal Year: 2022, Volume and Issue: unknown, P. 148 - 153

Published: May 20, 2022

Agriculture is one of the oldest activities practiced by man. Due to its importance in our daily life and reliance on it, many technologists try update a new development based agricultural robots that perform well strict, efficient, timely manner due tremendous field robotics, solution main problems faced those such as random sowing which cost more seeds costly, consumption water quantity fertilization. this paper develop robot can solve problem measure distance between lead save wastage water, determined plants needs fertilization using soil PH sensor. The motion controlled Android Bluetooth connected HC- 05 module raspberry pi 3 B+ for video streaming detected object.

Language: Английский

Citations

15
Machine Learning – Based Diagnosis of Covid-19 using Clinical Data DOI

Mona N Gowda,

Dalwinder Singh, Manik Rakhra

et al.

2022 3rd International Conference on Intelligent Engineering and Management (ICIEM), Journal Year: 2022, Volume and Issue: unknown, P. 910 - 916

Published: April 27, 2022

Coronavirus (COVID-19) is a worldwide pandemic caused by SARS 2. (SARS-CoV-2). The COVID-19 epidemic has put global healthcare systems in jeopardy. This study's purpose to develop and evaluate an automated infection detection system using machine learning chest x-ray images. Early diagnosis treatment may help avert major illness even death. It presently the most favoured accurate approach for diagnosis. X-ray imaging of be used instead rRT-PCR test look early symptoms. A new (ML)-based analytical framework created utilizing pictures likely patients. proposed disease images 99 percent accuracy Covid 92 Non-covid two-class categorization. investigation suggests better.

Language: Английский

Citations

15
A machine learning approach to cardiovascular disease prediction with advanced feature selection DOI Open Access
Abdijalil Abdullahi, M. Barré, Abdikadir Hussein Elmi

et al.

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 33(2), P. 1030 - 1030

Published: Jan. 19, 2024

<div align="center">Cardiovascular diseases (CVDs) pose a significant global public health challenge, necessitating precise risk assessment for proactive treatment and optimal utilization of healthcare resources. This study employs machine learning algorithms sophisticated feature selection techniques to enhance the accuracy comprehensibility CVD prediction models. While traditional tools are valuable, they frequently fail consider myriad intricate factors that contribute heightened CVD. Our methodology analyze diverse data sources produce advanced predictive The salient this research lies in meticulous application techniques, enabling identification pivotal within heterogeneous datasets. Optimizing enhances interpretability model, reduces dimensionality, improves accuracy. area under ROC curve (AUC-ROC) score wrapper method model significantly decreased from 95.1% 75.1% after tuning, based on empirical tests supported suggested method. showcases its capacity as tool assessing premature susceptibility developing tailored strategies. highlights significance integrating with due widespread influence cardiovascular diseases. Integrating system has potential patient care optimize resources.</div>

Language: Английский

Citations

2
Impact of elastic net and LASSO regularization techniques on the NHANES dataset DOI

S. Srivatsaan,

A. Siva Sankar,

M. Karthikeyan

et al.

AIP conference proceedings, Journal Year: 2024, Volume and Issue: 3075, P. 020208 - 020208

Published: Jan. 1, 2024

Language: Английский

Citations

1