Machine learning based approach to exam cheating detection

F Kamalov, H Sulieman, D Santandreu Calonge - Plos one, 2021 - journals.plos.org
The COVID-19 pandemic has impelled the majority of schools and universities around the
world to switch to remote teaching. One of the greatest challenges in online education is …

Kernel density estimation based sampling for imbalanced class distribution

F Kamalov - Information Sciences, 2020 - Elsevier
Imbalanced response variable distribution is a common occurrence in data science. In fields
such as fraud detection, medical diagnostics, system intrusion detection and many others …

Least Loss: A simplified filter method for feature selection

F Thabtah, F Kamalov, S Hammoud, SR Shahamiri - Information Sciences, 2020 - Elsevier
Identifying the relevant set of features in a dataset is an important part of data analytics.
Discarding significant variables or kee** irrelevant variables has significant effects on the …

Gamma distribution-based sampling for imbalanced data

F Kamalov, D Denisov - Knowledge-Based Systems, 2020 - Elsevier
Imbalanced class distribution is a common problem in a number of fields including medical
diagnostics, fraud detection, and others. It causes bias in classification algorithms leading to …

Stock price forecast with deep learning

F Kamalov, L Smail, I Gurrib - 2020 International Conference on …, 2020 - ieeexplore.ieee.org
In this paper, we compare various approaches to stock price prediction using neural
networks. We analyze the performance fully connected, convolutional, and recurrent …

Multi-modal anomaly detection for unstructured and uncertain environments

T Ji, ST Vuppala, G Chowdhary… - arxiv preprint arxiv …, 2020 - arxiv.org
To achieve high-levels of autonomy, modern robots require the ability to detect and recover
from anomalies and failures with minimal human supervision. Multi-modal sensor signals …

Automatic and precise data validation for machine learning

S Shankar, L Fawaz, K Gyllstrom… - Proceedings of the 32nd …, 2023 - dl.acm.org
Machine learning (ML) models in production pipelines are frequently retrained on the latest
partitions of large, continually-growing datasets. Due to engineering bugs, partitions in such …

Detecting Outliers in Non-IID Data: A Systematic Literature Review

S Siddiqi, F Qureshi, S Lindstaedt, R Kern - IEEE Access, 2023 - ieeexplore.ieee.org
Outlier detection (outlier and anomaly are used interchangeably in this review) in non-
independent and identically distributed (non-IID) data refers to identifying unusual or …

A hybrid detection system for DDoS attacks based on deep sparse autoencoder and light gradient boost machine

RK Batchu, H Seetha - Journal of Information & Knowledge …, 2023 - World Scientific
In the internet era, network-based services and connected devices are growing with many
users, thus it became an increase in the number of cyberattacks. Distributed Denial of …

Forecasting with deep learning: S&P 500 index

F Kamalov, L Smail, I Gurrib - 2020 13th International …, 2020 - ieeexplore.ieee.org
Stock price prediction has been the focus of a large amount of research but an acceptable
solution has so far escaped academics. Recent advances in deep learning have motivated …