Machine Learning–Based Approach for Identifying Research Gaps: COVID-19 as a Case Study by Alaa Abd-alrazaq (17058018)

“…Furthermore, future studies could evaluate more efficient modeling algorithms, especially those combining topic modeling with statistical uncertainty quantification, such as conformal prediction.…”

DNA Base-Calling Techniques by Odeh, Fadi

Get full text

Nonlinear analysis of shell structures using image processing and machine learning by M.S. Nashed (16392961)

“…The proposed approach can be significantly more efficient than training a machine learning algorithm using the raw numerical data. To evaluate the proposed method, two different structures are assessed where the training data is created using nonlinear finite element analysis. …”

Design and analysis of entropy-constrained reflected residual vector quantization by Mousa, W.A.H.

“…Jointly optimized RVQ (JORVQ) is an effective design algorithm for minimizing the overall quantization error. …”
Get full text
Get full text

Design and Analysis of Lightweight Authentication Protocol for Securing IoD by Saeed Ullah Jan (9079260)

“…We proposed a hash message authentication code/secure hash algorithmic (HMACSHA1) based robust, improved and lightweight authentication protocol for securing IoD. …”

StackDPPred: Multiclass prediction of defensin peptides using stacked ensemble learning with optimized features by Muhammad Arif (769250)

“…Additionally, we applied the local interpretable model-agnostic explanations (LIME) algorithm to understand the contribution of selected features to the overall prediction. …”

Combinatorial method for bandwidth selection in wind speed kernel density estimation by El Dakkak, Omar

“…This goal calls for devising probabilistic models with adaptive algorithms that accurately fit wind speed distributions. …”
Get full text

Role of authentication factors in Fin-tech mobile transaction security by Habib Ullah Khan (12024579)

“…In addition, this also ensures the user is legitimate using advanced technologies and algorithms to predict and discover transaction risks and discourage fraudsters from trying.…”

Developing an online hate classifier for multiple social media platforms by Joni Salminen (7434770)

“…We then experiment with several classification algorithms (Logistic Regression, Naïve Bayes, Support Vector Machines, XGBoost, and Neural Networks) and feature representations (Bag-of-Words, TF-IDF, Word2Vec, BERT, and their combination). …”

Neural Networks as a Convex Problem by Khalil, Baha

Get full text

Design of A Theoretical Framework For A Real-Time Fire Evacuation Guidance System by Abougharib, Arwa

Get full text

Lagrangian tracking in stochastic fields with application to an ensemble of velocity fields in the Red Sea by Issa, Leila

Get full text
Get full text
Get full text
Get full text

Adaptive Video Streaming Over Cognitive Radio Networks by Mohamed, Ala Eldin Omer

Get full text

A COMPLETE INSPECTION PLAN FOR DEPENDENT MULTICHARACTERISTIC CRITICAL COMPONENTS by Duffuaa, S. O.

“…A mathematical model and an algorithm for obtaining the optimal number of repeat inspections are developed and demonstrated by an example. …”
Get full text

Connectionist technique estimates of hydrogen storage capacity on metal hydrides using hybrid GAPSO-LSSVM approach by Sina Maghsoudy (21393539)

“…So the HGAPSO-LSSVM model had the highest accuracy. In this model, the statistical factors of R², STD, MSE, RMSE, and MRE were 0.980, 0.043, 0.0020, 0.045, and 0.972%, respectively. …”

QU-GM: An IoT Based Glucose Monitoring System From Photoplethysmography, Blood Pressure, and Demographic Data Using Machine Learning by Md Nazmul Islam Shuzan (21842426)

“…Bagged Ensemble Trees outperform other algorithms in estimating blood glucose level with a correlation coefficient of 0.90. …”

Artificial Intelligence for Assessing the Correlation Between Sleep Apnoea and Comorbidities by Ramesh, Jayroop

Get full text

Degree-Based Network Anonymization by Halawi, Ola

“…Enormous amounts of data collected from social networks or other online platforms are being published publicly for the sake of statistics, marketing, and research, among other objectives. …”
Get full text
Get full text
Get full text

Con-Detect: Detecting adversarially perturbed natural language inputs to deep classifiers through holistic analysis by Hassan, Ali

“…In summary, we note that minimally perturbing an input to change a model’s output—a major strength of adversarial attacks—is a weakness that leaves unique statistical marks reflected in the cumulative contribution scores of the input. …”
Get full text
Get full text
Get full text

Con-Detect: Detecting Adversarially Perturbed Natural Language Inputs to Deep Classifiers Through Holistic Analysis by Hassan Ali (3348749)

“…In summary, we note that minimally perturbing an input to change a model’s output—a major strength of adversarial attacks—is a weakness that leaves unique statistical marks reflected in the cumulative contribution scores of the input. …”