Rizwan Ayazuddin

Mr. Rizwan Ayazuddin

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 September 2025 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
MQMOHID QADEER
MOHID QADEER
RARizwan Ayazuddin
Rizwan Ayazuddin
MTMuhammad Ikhsan Thohir
Muhammad Ikhsan Thohir
The heart is essential to human life, so it is important to protect it and understand any kind of damage it can have. All the diseases related to hearts leads to heart failure. To help address this, a tool for predicting survival is needed. This study explores the use of several classification models for forecasting heart failure outcomes using the Heart Failure Clinical Records dataset. The outcome contrasts a deep learning (DL) model known as the Convolutional Neural Network (CNN) with many machine learning models, including Random Forest (RF), K-Nearest Neighbors (KNN), Decision Tree (DT), and Naïve Bayes (NB). Various data processing techniques, like standard scaling and Synthetic Minority Oversampling Technique (SMOTE), are used to improve prediction accuracy. The CNN model performs best by achieving 99%. In comparison, the best-performing ML model, Naïve Bayes, reaches 92.57%. This shows that deep learning provides better predictions of heart failure, making it a useful tool for early detection and better patient care.

11 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
YAYaraib Arif
Yaraib Arif
RARizwan Ayazuddin
Rizwan Ayazuddin
This research investigates the application of machine learning methods in predicting the intention of online shoppers, a very important task in the fast-growing e- commerce industry. In this paper, the performance of some machine learning algorithms, namely K-Nearest Neighbors, Decision Tree, Naive Bayes, Random Forest, Random Tree, Gradient Boosting Tree, and Logistic Regression, is explored for forecasting online purchase behaviors. The features involved in the creation of the dataset for this study are enumerated as the traffic source, session time, amount of product pages visited, and finally, users' feedback. In such a way, the best models that were successful within the framework of the current paper were Gradient Boosting Tree with the rate 88.89% and Decision Tree with the following rate 88.89%, which helped predict their likelihood to buy. These models can help reduce predictive errors and mitigate the variations that exist in consumer behavior-for instance, on personal tastes or browsing behaviors-since they make the targeting of potential buyers better. It also pointed to how machine learning is powerful enough to enhance decision- making in e-commerce by offering more insight into the understanding of consumer intention, thus allowing marketers to shape a better strategy toward increasing sales.

30 September 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
RARizwan Ayazuddin
Rizwan Ayazuddin
Sorting algorithms play a fundamental role in computer science and are extensively applied in data processing tasks. This study provides a detailed experimental analysis of four classical algorithms: Bubble Sort, Quick Sort, Merge Sort, and Heap Sort, using real world datasets obtained from the UCI Machine Learning Repository. We evaluated the algorithms based on multiple performance metrics, including execution time, memory usage, stability, and the number of comparisons or swaps, across multiple runs to ensure reliability. We further examined algorithmic behavior on different input cases, highlighting best, worst, and random scenarios. Results show that Quick Sort achieves the fastest execution time, while Merge Sort maintains stability with moderate memory consumption. Bubble Sort, though stable, demonstrates high computational effort, and Heap Sort offers a trade-off between efficiency and stability. Visualizations such as bar charts, box plots, scatter plots, and heatmaps are employed to provide a clear comparative understanding. This research provides valuable insights for selecting appropriate sorting algorithms based on performance, stability, and computational requirements in practical applications.

20 November 2025 in TechRxiv
Verified
Preprint
Open access
ZIZameer Iftikhar
Zameer Iftikhar
RARizwan Ayazuddin
Rizwan Ayazuddin
The financial industry primarily relies on accurate assessments of borrower risk to minimize loan defaults. In this work, we analyze a wide range of factors reflecting the credit, financial, and demographic conditions of loan applicants and their relationship with the risk level associated with loan approvals. We present extensive datasets that include debt-to-income ratios, employment information, loan details, annual income, and credit scores, which are particularly useful when included in the analysis. To understand the relationship between these components, we employ machine learning models to derive a risk score as the primary outcome measure. The purpose of this study is to improve financial quality, reduce the share of risky loans, and simplify the decision-making process through statistical and predictive analysis.

11 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
MTMuhammad Tayyab
Muhammad Tayyab
RARizwan Ayazuddin
Rizwan Ayazuddin
Heart disease remains a leading cause of mortality worldwide, with early identification of at-risk individuals being critical for prevention. This study applies machine learning techniques to a comprehensive dataset to identify key predictors of heart attack risk. Logistic regression analysis identified BMI, age, hypertension, family history, and cholesterol levels as significant predictors of heart attack risk. Notably, individuals with BMI > 30 were 2.5 times more likely to be in the high-risk category, and the risk increased by 8% with each additional year of age. The model achieved strong predictive performance and highlighted that regular physical activity reduced heart attack risk by up to 20%. These findings offer valuable insights for targeted prevention strategies and public health policy, underscoring the potential of machine learning in cardiovascular risk assessment.

17 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
MKMuhammad Khizer
Muhammad Khizer
RARizwan Ayazuddin
Rizwan Ayazuddin
This raises serious concerns for public health and environmental sustainability in an increasingly polluted atmosphere. Therefore, advanced monitoring systems must be developed. This research paper presents a novel framework that integrates Machine Learning and Internet of Things (IoT) technologies to monitor and manage air quality and waste in real time. The proposed system utilizes a network of sensors to collect high-resolution data on air pollutants such as PM2.5, PM10, NOx, and CO2, along with waste management parameters such as bin occupancy, using a publicly available dataset from Kaggle. Following rigorous data preprocessing and feature engineering, the framework achieves a peak prediction accuracy of 93.53% using an ANN. The web-based platform enables automated analysis of continuous data, allowing for immediate alerts when pollutant thresholds are exceeded facilitating timely interventions.