Hasan Kurban

Verified

Hasan verified their affiliation via an institutional email.

Learn more

Verified

Hasan verified their affiliation via an institutional email.

Learn more

• Ph.D. in Computer Science
• Assistant Professor at Hamad bin Khalifa University

Machine learning (ML) has been recently used to make sense of large volume of data as data-driven methods to identify correlations and then examine material properties in detail. Herein, we analyze the correlations between structural and electronic properties of ZnO nanoparticles (NPs) obtained from density-functional tight-binding method using Dat...

This interdisciplinary study is conducted to find answers to two important questions which researchers often face in Machine Learning (ML) and Material Science (MS) fields . In this work, we measure the performance of the most popular ML algorithms (more than a dozen) on rare-class learning problem and determine the best learning algorithm for atom...

Existing data mining techniques, more particularly iterative learning algorithms, become overwhelmed with big data. While parallelism is an obvious and, usually, necessary strategy, we observe that both (1) continually revisiting data and (2) visiting all data are two of the most prominent problems especially for iterative, unsupervised algorithms...

Using a large volume of bus data in the form of GPS coordinates (over 100 million data points) and automated passenger count data (over 1 million data points) we have developed (1) a system of analysis and prediction of future public transportation demand (2) a new model that uses concepts specific to college campuses that maximizes passenger satis...

Bazı hastalık belirtilerinin birçok tıbbi tedavi alanıyla ilgili olması, hastaların tedavi için randevu alırken zorlanmalarına sebep olmaktadır. Örneğin; karın ağrısı rahatsızlığı bulunan bir hastanın rahatsızlığı dahiliye, hariciye ya da intaniye bölümlerinden herhangi birisiyle ilgisi bulunabilmektedir. Bu çalışmada T.C. Sağlık Bakanlığına bağlı...

Large Language Models (LLMs) are increasingly used in various contexts, yet remain prone to generating non-factual content, commonly referred to as "hallucinations". The literature categorizes hallucinations into several types, including entity-level, relation-level, and sentence-level hallucinations. However, existing hallucination datasets often...

Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs - commonly known as "hallucinations." Among existing mitigation strategies, uncertainty-based methods are particularly attractive due to their ease of implementation, independence from external data, and compat...

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for detecting and mitigating hallucinations by leveraging Sparse Autoencoders (SAEs). While hallucination detection tec...

This paper introduces \(p\)-ClustVal, a novel data transformation technique inspired by \(p\)-adic number theory that significantly enhances cluster discernibility in genomics data, specifically single-cell RNA sequencing (scRNASeq). By leveraging \(p\)-adic-valuation, \(p\)-ClustVal integrates with and augments widely used clustering algorithms an...

Pediatric diabetes I is an endemic and an especially difficult disease; indeed, at this point, there does not exist a cure, but only careful management that relies on anticipating hypoglycemia. The changing physiology of children producing unique blood glucose signatures, coupled with inconsistent activities, e.g., playing, eating, napping, makes “...

Simulating complex and large materials is a challenging task that requires extensive domain knowledge and computational expertise. This study introduces Pure2DopeNet, an innovative multimodal neural network that tackles these challenges by integrating image and text data to accurately predict the physical properties of doped compounds, specifically...

This paper introduces p-ClustVal, a novel data transformation technique inspired by p-adic number theory that significantly enhances cluster discernibility in genomics data, specifically Single Cell RNA Sequencing (scRNASeq). By leveraging p-adic Valuation, p-ClustVal integrates with and augments widely used clustering algorithms and dimension redu...

This paper introduces p -ClustVal, a novel data transformation technique inspired by p-adic number theory that significantly enhances cluster discernibility in genomics data, specifically Single Cell RNA Sequencing (scRNASeq). By lever-aging p-adic-valuation, p -ClustVal integrates with and augments widely used clustering algorithms and dimension r...

In this study, an innovative approach is explored that combines Density Functional Tight Binding (DFTB) with Computer Vision (CV) techniques to analyze the electronic structure and enhance the photocatalytic capabilities of carbon-doped titanium oxide nanoparticles (C-doped TiO2 NPs). The findings reveal that C doping, in levels ranging from 0.1% t...

In this study, we introduce a novel de Bruijn graph (dBG) based framework for feature engineering in biological sequential data such as proteins. This framework simplifies feature extraction by dynamically generating high-quality, interpretable features for traditional AI (TAI) algorithms. Our framework accounts for amino acid substitutions by effi...

Data-centric AI (DCAI) is an emerging paradigm that prioritizes the quality, diversity, and representation of data over model architecture and hyperparameter tuning. DCAI emphasizes upstream data operations such as cleaning, balancing, and preprocessing, rather than solely focusing on downstream model selection and optimization. This work aims to p...

This paper addresses the challenge of optimizing user grouping in Index Modulation-based Orthogonal Frequency-Division Multiple Access (IM-OFDMA) systems within dynamic and stochastic noise environments. Utilizing the eXtreme Gradient Boosting (XGBoost) machine learning algorithm, we devised a framework capable of accurately predicting the optimali...

Fantasy Sports has a current market size of $27B and is expected to grow more than $84B in less than a decade. The intent is to create virtual teams that somehow reflect what would happen if the constituent players actually played in a team. Using individual player and team statistics, models can be trained to predict an outcome. But fans are left...

Sports awards have become almost as popular as the sports themselves bringing not only recognition, but also increases in salary, more control over decisions usually in the hands of coaches and general managers, and other benefits. Awards are so popular that even at the start of a season pundits and amateurs alike predict or argue for athletes. It...

The Least Squares method is the oldest ML algorithm but remains the most popular and ubiquitous across domains. Now, with powerful, cheap technology and the popular open-source language Python, users of every sort have access to various libraries, all serving ordinary least squares. In this work, we ask the question of whether users can count on th...

Impedance spectroscopy is a powerful technique and broadly used for battery characterization. In this study, we introduce a novel machine framework we call the duplex (for paired outputs) that constructs a linear ensemble of the best k models. Several impedance spectra of commercial lithium-ion battery coin cells at various states of charge and amb...

Impedance spectroscopy is a powerful technique and broadly used for battery characterization. In this study, we introduce a novel methodology that devise a system to utilize the experimental impedance data by processing each one of the parameters with the most favorably designated machine learning techniques. Several impedance spectra of commercial...

This paper describes and provides the data on the regenerated-impedance spectra that is computed from experimental results of electrochemical impedance spectroscopy measurements taken from a commercial Li-ion battery. The empirical impedance data of secondary coin type Li-ion batteries were collected in different states of charge ranging from empty...

The experimental impedance data were collected in cell potentials as 3.2V, 3.4V, 3.6V, 3.8V, 4.0V, and 4.2V (corresponding state of charge values: 0%, 3%, 8%, 40%, 78%, 100%). Impedance data is generated by a Machine Learning model.

The use of Electrochemical Impedance Spectroscopy on rechargeable Lithium-ion battery characterization is an extensively recognized non-destructive procedure for both in-situ and ex-situ analyses. In an impedance measurement for a rechargeable battery, the oscillating current with an accompanying phase angle is the response for a potential perturba...

Predicting material properties by solving the Kohn‐Sham (KS) equation, which is the basis of modern computational approaches to electronic structures, has provided significant improvements in materials sciences. Despite its contributions, both DFT and DFTB calculations are limited by the number of electrons and atoms that translate into increasingl...

In recent years, the introduction of single-cell RNA sequencing (scRNAseq) has enabled the analysis of a cell’s transcriptome at an unprecedented granularity and processing speed. The experimental outcome of applying this technology is a M × N matrix containing aggregated mRNA expression counts of M genes and N cell samples. From this matrix, scien...

Background: In recent years, the introduction of single-cell RNA sequencing (scRNA-seq) has enabled the analysis of a cell's transcriptome at an unprecedented granularity and processing speed. The experimental outcome of applying this technology is a $M \times N$ matrix containing aggregated mRNA expression counts of $M$ genes and $N$ cell samples....

Clustering is intractable, so techniques exist to give a best approximation. Expectation Maximization (EM), initially used to impute missing data, is among the most popular. Parameters of a fixed number of probability distributions (PDF) together with the probability of a datum belonging to each PDF are iteratively computed. EM does not scale with...

To deal with the unimaginable continual growth of data and the focus on its use rather than its governance, the value of data has begun to deteriorate seen in lack of reproducibility, validity, provenance, etc. In this work, we aim to simply understand what is the value of data and how this basic understanding might affect existing AI algorithms, i...

In this work, we perform a theoretical analysis of structural, electronic, and optical properties of pure and Mg-doped amorphous ZnO nanoparticles (a-ZnO NPs) using DFTB method. Our results show that Zn atoms are more preferential for Mg atoms than for O atoms because the number of Mg-Zn bonds is greater than that of Mg-O. The rise in the content o...

In this study, we built a variety of Machine Learning (ML) systems over 23 different sizes of CH3NH3PbI3 perovskite nanoparticles (NPs) to predict the atoms in the NPs from their geometric locations. Our findings show that a specific type of ML algorithms, tree-based models which are Random Forest (RF), Extreme Gradient Boosting (XGBoost), Decision...

Machine learning (ML) has recently made a major contribution to the fields of Material Science (MS). In this study, ML algorithms are used to learn atoms types over structural geometrical data of anatase TiO2 nanoparticles produced at different temperature levels with the density-functional tight-binding method (DFTB). Especially for this work, Ran...

Structural, energetic, electronic, reactivity and stability properties of armchair (3,3), (4,4), (5,5), (6,6), (7,7), (8,8), (9,9) and (10,10) aluminum nitride nanotubes (AlNNTs) with different diameter have been probed using density functional theory (DFT) in terms of Moreover, the chemical reactivity characteristics of AlNNTs have performed via s...

In this work, we analyze the correlations between structural and electronic properties of anatase, brookite and rutile phases TiO2 nanoparticles (NPs) using data science techniques. For this purpose, we use the geometries of three phases TiO2 NPs under heat treatment obtained from molecular dynamics (MD) simulations in the frame of DFTB+ code. We i...

In this work, we used the density-functional tight-binding (DFTB) and investigate ZnO nanoparticle (NP) properties, i.e., the structural and electronic properties. First, a ZnO NP with ~0.9 nm including 258 atoms was characterized from 30×30×30 supercell based on the hexagonal crystal structure of ZnO. Second, HOMO, LUMO electronic properties, band...

We carried out a thorough examination of the structural and electronic features of undoped and Nitrogen (N)-doped ZnO nanoparticles (NPs) by the density-functional tight-binding (DFTB) method. By increasing the percent of N atoms in undoped ZnO NPs, the number of bonds (n), order parameter (R) and radial distribution function (RDF) of two-body inte...

We perform a theoretical investigation using the density functional tight binding (DFTB) approach for the structural analysis and electronic structure of copper hydride (CuH) metallic nanoparticles (NPs) of different size (from 0.7 to 1.6 nm). By increasing the size of CuH NPs, the number of bonds, segregation phenomena and radial distribution func...

Without question, astronomy is about Big Data and clustering is a very common task over astronomy domain. The expectation-maximization algorithm is among the top 10 data mining algorithms used in scientific and industrial applications, however, we observe that astronomical community does not make use of it as a clustering algorithm. In this work, w...

Iterative machine learning algorithms, i.e., kmeans (KM), expectation maximization (EM), become overwhelmed with big data since all data points are being continually and indiscriminately visited while a cost is being minimized. In this work, we demonstrate (1) an optimization approach to reduce training run-time complexity of iterative machine lear...

Stellar data, only a few years ago, measured in the .1M of objects. Now, sets are routinely 1M. With the launch of ESA’s Gaia in 2013, we expect 1000M stellar objects measured more precisely and with more measurements.Without question, astronomy is about Big Data and clustering is a very common task over astronomy domain. The expectation-maximizati...

Existing data mining techniques, more particularly iterative learning algorithms, become overwhelmed with big data. While parallelism is an obvious and, usually, necessary strategy, we observe that both (1) continually revisiting data and (2) visiting all data are two of the most prominent problems especially for iterative, unsupervised algorithms...

Existing data mining techniques, more particularly iterative learning algorithms, become overwhelmed with big data. While parallelism is an obvious and, usually, necessary strategy, we observe that both (1) continually revisiting data and (2) visiting all data are two of the most prominent problems especially for iterative, unsupervised algorithms...

The challenges presented by data to scientific inquiry and hypothesis testing in an oceanographic setting are not new problems. Indeed, the challenges are at least a century old. The problems are not with the data itself, but rather with the attention to the management of the "data ecology" in the information systems. Data needs to be accessible as...

Random Forests have been used as effective ensemble models for classification. We present in this paper a new type of Random Forests (RFs) called Red(uced)-RF that adopts a new dynamic data reduction principle and a new voting mechanism called Priority Vote Weighting (PV) which improve accuracy, execution time and AUC values compared to Breiman’s R...

Random forests have been used as effective models to tackle a number of classification and regression problems. In this paper, we present a new type of Random Forests (RFs) called Red(uced)-RF that adopts a new voting mechanism called Priority Vote Weighting (PV) and a new dynamic data reduction principle which improve accuracy and execution time c...

Dramatic increases in the amount and complexity of stellar data must be matched by new or refined algorithms that can help scientists make sense of this data and so better understand the universe. ParaHeap-k is a parallel cluster algorithm for analyzing big data that can potentially prove useful to astronomical research.