CUD Digital Repository :: Browsing by Author "Kamalov, Firuz"

Browsing by Author "Kamalov, Firuz"

Now showing 1 - 20 of 72

A Comparative Study of Autoregressive and Neural Network Models: Forecasting the GARCH Process
(Springer Science and Business Media Deutschland GmbH, 2022) Kamalov, Firuz; Gurrib, Ikhlaas; Moussa, Sherif; Nazir, Amril
The Covid-19 pandemic has highlighted the importance of forecasting in managing public health. The two of the most commonly used approaches for time series forecasting methods are autoregressive (AR) and deep learning models (DL). While there exist a number of studies comparing the performance of AR and DL models in specific domains, there is no work that analyzes the two approaches in the general context of theoretically simulated time series. To fill the gap in the literature, we conduct an empirical study using different configurations of generalized autoregressive conditionally heteroskedastic (GARCH) time series. The results show that DL models can achieve a significant degree of accuracy in fitting and forecasting AR-GARCH time series. In particular, DL models outperform the AR-based models over a range of parameter values. However, the results are not consistent and depend on a number of factors including the DL architecture, AR-GARCH configuration, and parameter values. The study demonstrates that DL models can be an effective alternative to AR-based models in time series forecasting. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
A computational numerical performance for solving the mathematical epidemiological model based on influenza disease
(Elsevier B.V., 2022-09) Jain, Sonal; Leung, Ho-Hon; Kamalov, Firuz
Understanding epidemic propagation patterns and assessing disease control measures require the use of mathematical and computational methodologies. In recent years, complexity science, management science, sociology, and computer science have all been progressively merged with epidemiology. The interdisciplinary collaboration has sped up the development of computational and mathematical methods for simulating epidemics. The model with the classical time derivative in the influenza disease model is formulated with the Caputo (power-law kernel), Caputo–Fabrizio (exponential kernel), and the novel Atangana–Baleanu fractional derivatives which combined both nonlocal and non-singular properties. Also this article presents the boundness and positiveness Solutions for the influenza model. The analysis of the equilibrium point is also given. Various published articles have utilized the reproductive number notion to investigate disease-spread stability. There were certain conditions proposed to predict whether there would be stability or instability. It was also advised that an analysis be conducted to discover the conditions under which infectious classes will grow or die out. Some authors pointed out that the reproductive number is limited, including its inability to fairly aid in understanding distribution patterns. The concept of strength number and analysis of derivatives of mathematical models were presented to help in understanding the disease model. Further, the stability of disease-free and endemic equilibrium is presented. Finally, a numerical solution with simulation is given. We hope to use these extra studies in a basic model to forecast the future of this research. © 2022 The Author(s)
A note on time series differencing
(Canadian University of Dubai, 2021-05-11) Kamalov, Firuz
Differencing is one of the key tools time series analysis. It is com-monly used to obtain stationary time series. In this note, we show that the nth difference of a weakly stationary time series is weakly stationary. Similarly we prove that the nth difference of a strictly stationary time series is strictly stationary. We also consider the effect of differencing on the time series auto-covariance. © 2021, Canadian University of Dubai. All rights reserved.
A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning
(Springer, 2023) Elreedy, Dina; Atiya, Amir F.; Kamalov, Firuz
Class imbalance occurs when the class distribution is not equal. Namely, one class is under-represented (minority class), and the other class has significantly more samples in the data (majority class). The class imbalance problem is prevalent in many real world applications. Generally, the under-represented minority class is the class of interest. The synthetic minority over-sampling technique (SMOTE) method is considered the most prominent method for handling unbalanced data. The SMOTE method generates new synthetic data patterns by performing linear interpolation between minority class samples and their K nearest neighbors. However, the SMOTE generated patterns do not necessarily conform to the original minority class distribution. This paper develops a novel theoretical analysis of the SMOTE method by deriving the probability distribution of the SMOTE generated samples. To the best of our knowledge, this is the first work deriving a mathematical formulation for the SMOTE patterns’ probability distribution. This allows us to compare the density of the generated samples with the true underlying class-conditional density, in order to assess how representative the generated samples are. The derived formula is verified by computing it on a number of densities versus densities computed and estimated empirically. © 2023, The Author(s).
A visualization approach to multiplicative reasoning and geometric measurement for primary-school students-a pilot study
(City University of New York, 2022-12) Jain, Sonal; Leung, Ho-Hon; Kamalov, Firuz
Understanding the concept of area requires an understanding of the relationship between geometry and multiplication. The multiplicative reasoning required to find the areas of regular figures is used in many courses in elementary mathematical education. This paper explores various methods in which multiplicative reasoning is incorporated into the measurement of area. The main goal is to provide tasks that encourage the application of multiplicative reasoning when students are asked to measure the areas of geometric figures. Student performance is analyzed in two pilot studies of the relationship between geometric measurement and multiplicative reasoning. © 2022 City University of New York. All rights reserved.
An Ensemble-Based Machine Learning Model for Emotion and Mental Health Detection
(World Scientific, 2022) Jonnalagadda, Annapurna; Rajvir, Manan; Singh, Shovan; Chandramouliswaran S.; George, Joshua; Kamalov, Firuz
Recent studies have highlighted several mental health problems in India, caused by factors such as lack of trained counsellors and a stigma associated with discussing mental health. These challenges have raised an increasing need for alternate methods that can be used to detect a person's emotion and monitor their mental health. Existing research in this field explores several approaches ranging from studying body language to analysing micro-expressions to detect a person's emotions. However, these solutions often rely on techniques that invade people's privacy and thus face challenges with mass adoption. The goal is to build a solution that can detect people's emotions, in a non-invasive manner. This research proposes a journaling web application wherein the users enter their daily reflections. The application extracts the user's typing patterns (keystroke data) and primary phone usage data. It uses this data to train an ensemble machine learning model, which can then detect the user's emotions. The proposed solution has various applications in today's world. People can use it to keep track of their emotions and study their emotional health. Also, any individual family can use this application to detect early signs of anxiety or depression amongst the members. © 2023 World Scientific Publishing Co.
Arithmetic properties of complex fibonacci numbers and fibonacci quaternions
(SAS International Publications, 2021-09) Leung, Ho-Hon; Kamalov, Firuz
In this paper, we investigate certain arithmetic properties of complex Fibonacci numbers and Fibonacci quaternions. More specifically, we look at the divisibility properties of complex Fibonacci numbers and Fibonacci quaternions. Our results make use of some well-known Fibonacci identities. Since quaternions are non-commutative algebra, extra care has been taken to investigate the various divisibility properties of the Fibonacci quaternions. © SAS International Publications.
Autism screening: an unsupervised machine learning approach
(Springer, 2022-12) Thabtah, Fadi; Spencer, Robinson; Abdelhamid, Neda; Kamalov, Firuz; Wentzel, Carl; Ye, Yongsheng; Dayara, Thanu
Autocorrelation for time series with linear trend
(Institute of Electrical and Electronics Engineers Inc., 2021-09-29) Kamalov, Firuz; Thabtah, Fadi; Gurrib, Ikhlaas
The autocorrelation function (ACF) is a fundamental concept in time series analysis including financial forecasting. In this note, we investigate the properties of the sample ACF for a time series with linear trend. In particular, we show that the sample ACF of the time series approaches 1 for all lags as the number of time steps increases. The theoretical results are supported by numerical experiments. Our result helps researchers better understand the ACF patterns and make correct ARMA selection. © 2021 IEEE.
Autoencoder-based Intrusion Detection System
(Institute of Electrical and Electronics Engineers Inc., 2021) Kamalov, Firuz; Zgheib, Rita; Leung, Ho Hon; Al-Gindy, Ahmed; Moussa, Sherif
Given the dependence of the modern society on networks, the importance of effective intrusion detection systems (IDS) cannot be underestimated. In this paper, we consider an autoencoder-based IDS for detecting distributed denial of service attacks (DDoS). The advantage of autoencoders over traditional machine learning methods is the ability to train on unlabeled data. As a result, autoencoders are well-suited for detecting unknown attacks. The key idea of the proposed approach is that anomalous traffic flows will have higher reconstruction loss which can be used to flag the intrusions. The results of numerical experiments show that the proposed method outperforms benchmark unsupervised algorithms in detecting DDoS attacks. © 2021 IEEE.
Autoregressive and neural network models: A comparative study with linearly lagged series
(Institute of Electrical and Electronics Engineers Inc., 2021-09-29) Kamalov, Firuz; Gurrib, Ikhlaas; Thabtah, Fadi
Time series analysis such as stock price forecasting is an important part of financial research. In this regard, autoregressive (AR) and neural network (NN) models offer contrasting approaches to time series modeling. Although AR models remain widely used, NN models and their variant long short-term memory (LSTM) networks have grown in popularity. In this paper, we compare the performance of AR, NN, and LSTM models in forecasting linearly lagged time series. To test the models we carry out extensive numerical experiments based on simulated data. The results of the experiments reveal that despite the inherent advantage of AR models in modeling linearly lagged data, NN models perform just as well, if not better, than AR models. Furthermore, the NN models outperform LSTMs on the same data. We find that a simple multi-layer perceptron can achieve highly accurate out of sample forecasts. The study shows that NN models perform well even in the case of linearly lagged time series. © 2021 IEEE.
Bitcoin price forecasting: Linear discriminant analysis with sentiment evaluation
(Association for Computing Machinery, 2021-08-25) Gurrib, Ikhlaas; Kamalov, Firuz; Smail, Linda
Cryptocurrencies such as bitcoin have garnered a lot of attention in recent months due to their meteoric rise. In this paper, we propose a new method for predicting the direction of bitcoin price using linear discriminant analysis (LDA) together with sentiment analysis. Concretely, we train an LDA-based classifier that uses the current bitcoin price information and Twitter headline news in order to forecast the next-day direction of bitcoin price. The proposed model achieves highly accurate results beating several benchmark targets. In particular, the proposed approach produces forecast accuracy of 0.828 and AUC of 0.840 on the test data. © 2021 Association for Computing Machinery. All rights reserved.
Can the leading US energy stock prices be predicted using the ichimoku cloud?
(Econjournals, 2021) Gurrib, Ikhlaas; Kamalov, Firuz; Elshareif, Elgilani
The aim of this study is to investigate if Ichimoku Cloud can serve as a technical analysis indicator to improve stock price prediction for leading US energy companies. The methodology centers on the application of the Ichimoku Cloud as a trading system. The daily stock prices of the top ten constituents of the S&P Composite 1500 Energy Index-spanning the period from 12th April, 2012 to 31st July, 2019-were sourced for experimentation. The performance of the Ichimoku Cloud is measured using both the Sharpe and Sortino ratios to adjust for total and downside risks. The analysis is split into pre and post oil crisis to account for the drop in energy stock prices during the July 2014-December 2015. The model is also benchmarked against the naïve buy-and-hold strategy. The capacity of the Ichimoku indicator to provide signals during strengthening trends is analyzed. Despite the drop in energy stock prices, number of trades continued to increase along with profit opportunities. The PSX stock ranked first, with the highest Sharpe ratio, Sortino ratio, and Sharpe per number of trade. As expected, a number of buying signals occurred during strengthening bullish periods. Surprisingly, various sell signals also occurred during similar strengthening bullish trends. Most of the buy and sell signals under the Ichimoku indicator occurred outside of strengthening of bullish or bearish trends. The overall findings suggest that speculators can benefit from the use of the Ichimoku Cloud in analyzing energy stock price movements. In addition, it has the potential to reduce susceptibility to changes in energy prices. Last, the strength of the trend in place needs to be captured as it served as an additional layer of information which can improve the decision making process of the trader. © 2021, Econjournals. All rights reserved.
Comparative analysis of activation functions in neural networks
(Institute of Electrical and Electronics Engineers Inc., 2021) Kamalov, Firuz; Nazir, Amril; Safaraliev, Murodbek; Cherukuri, Aswani Kumar; Zgheib, Rita
Although the impact of activations on the accuracy of neural networks has been covered in the literature, there is little discussion about the relationship between the activations and the geometry of neural network model. In this paper, we examine the effects of various activation functions on the geometry of the model within the feature space. In particular, we investigate the relationship between the activations in the hidden and output layers, the geometry of the trained neural network model, and the model performance. We present visualizations of the trained neural network models to help researchers better understand and intuit the effects of activation functions on the models. © 2021 IEEE.
Comparative heat transfer analysis of electroconductive F e 3 O 4 - MWCNT - water and F e 3 O 4 - MWCNT - kerosene hybrid nanofluids in a square porous cavity using the non-Fourier heat flux model
(American Institute of Physics Inc., 2022-12) Thirumalaisamy K.; Ramachandran, Sivaraj; Ramachandra Prasad V.; Anwar Bég O.; Leung, Ho-Hon; Kamalov, Firuz; Panneer Selvam R.
Comparative heat transfer analysis of γ - A l 2 O 3 - C 2 H 6 O 2 and γ - 2 O 3 - H 2 O electroconductive nanofluids in a saturated porous square cavity with Joule dissipation and heat source/sink effects
(American Institute of Physics Inc., 2022-07-01) Thirumalaisamy K.; Ramachandran, Sivaraj; Ramachandra Prasad V.; Anwar Bég O.; Leung, Ho-Hon; Kamalov, Firuz; Vajravelu K.
Inspired by the applications in electromagnetic nanomaterials processing in enclosures and hybrid fuel cell technologies, a mathematical model is presented to analyze the mixed convective flow of electrically conducting nanofluids (γ- A l 2 O 3 - H 2 O and γ- A l 2 O 3 - C 2 H 6 O 2) inside a square enclosure saturated with porous medium under an inclined magnetic field. The Tiwari-Das model, along with the viscosity, thermal conductivity, and effective Prandtl number correlations, is considered in this study. The impacts of Joule heating, viscous dissipation, and internal heat absorption/generation are taken into consideration. Strongly nonlinear conservation equations, which govern the heat transfer and momentum inside the cavity with associated initial and boundary conditions, are rendered dimensionless with appropriate transformations. The marker-and-cell technique is deployed to solve the non-dimensional initial-boundary value problem. Validations with a previous study are included. A detailed parametric study is carried out to evaluate the influences of the emerging parameters on the transport phenomena. When 5 % γ- A l 2 O 3 nanoparticles are suspended into H 2 O base-fluid, the average heat transfer rate of γ- A l 2 O 3 - H 2 O nanoliquid is increased by 25.63 % compared with the case where nanoparticles are absent. When 5 % γ- A l 2 O 3 nanoparticles are suspended into C 2 H 6 O 2 base-fluid, the average heat transfer rate of γ- A l 2 O 3 - C 2 H 6 O 2 nanofluid is increased by 43.20 % compared with the case where nanoparticles are absent. Furthermore, when the heat source is present, the average heat transfer rate of γ- A l 2 O 3 - C 2 H 6 O 2 nanofluid is 194.92 % higher than that in the case of γ- A l 2 O 3 - H 2 O nanofluid. © 2022 Author(s).
Computational study of MHD mixed convective flow of Cu/Al2O3-water nanofluid in a porous rectangular cavity with slits, viscous heating, Joule dissipation and heat source/sink effects
(Taylor and Francis Ltd., 2023) Santhosh N.; Sivaraj R.; Ramachandra Prasad V.; Anwar Bég O.; Leung, Ho-Hon; Kamalov, Firuz; Kuharat S.
A mathematical model is presented to analyze the mixed convective magnetohydrodynamic (MHD) flow of two different nanofluids within a cavity saturated with porous media. The Tiwari–Das model, along with Maxwell and Brinkman formulations, is adopted to feature the characteristics of the considered nanofluids. The two different working fluids of this investigation are considered aluminum oxide (Formula presented.) -water and copper (Formula presented.) -water nanofluids. The impacts of viscous dissipation, internal heat generation/absorption, magnetic field, and Joule heating are examined in this model. The robust, well-tested Marker And Cell (MAC) algorithm is utilized to numerically solve the transformed, dimensionless, nonlinear coupled two-dimensional momentum and energy conservation equations with the prescribed wall boundary conditions. The comparative study finds an upright accordance with the literature. The effect of various pertinent parameters on the rate of heat transfer, isotherms and streamlines contour distributions in the enclosure is graphically displayed. With an increment in nanoparticles volume fraction, the velocity and heat transfer inside the rectangular enclosure are increased. The (Formula presented.) -water nanofluid and (Formula presented.) -water nanofluid in order have (Formula presented.) and (Formula presented.) higher average heat transfer rate when (Formula presented.) (Formula presented.) nanoparticles are suspended into water. This kind of simulation may be useful in electromagnetic nanomaterials processing and hybrid fuel cells. © 2023 Informa UK Limited, trading as Taylor & Francis Group.
Conditional Variational Autoencoder-Based Sampling
(Springer Science and Business Media Deutschland GmbH, 2023) Kamalov, Firuz; Ali-Gombe, Adamu; Moussa, Sherif
Imbalanced data distribution implies an uneven distribution of class labels in data which can lead to classification bias in machine learning models. The present paper proposes an autoencoder-based sampling approach to balance the data. Concretely, the proposed method utilizes a conditional variational autoencoder (VAE) to learn the latent variables underpinning the distribution of minority labels. Then, the trained encoder is employed to produce new minority samples to equalize the sample distribution. The results of numerical experiments reveal the potency of the suggested technique on several datasets. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Covariant representations of C*-dynamical systems with compact groups
(The Theta Foundation, 2013) Kamalov, Firuz
Let (A, G, σ) be a C*-dynamical system, where G is compact. We show that every irreducible covariant representation (π,U) of (A, G, σ) is induced from an irreducible covariant representation (π0,U0) of a subsystem (A, G0, σ) such that π0 is a factor representation. We show that if (π,U) is an irreducible covariant representation of (A, GP, σ) with ker π = P, then π is a homogenous representation. Hence, (A, G, σ) satisfies the strong-EHI property. © THETA, 2013.
COVID-19, Short-selling Ban and Energy Stock Prices
(Asia-Pacific Applied Economics Association (APAEA), 2021) Gurrib, Ikhlaas; Kweh, Qian Long; Contu, Davide; Kamalov, Firuz
We examine the short-selling ban imposed by the National Commission for Companies and the Stock Exchange of Italy, the authority that regulates the Italian securities market, on three Italian energy stocks. We find that the effect of the short-selling ban was temporary.

Browsing by Author "Kamalov, Firuz"

Results Per Page

Sort Options