AAAnorgul Ashirova

Anorgul Ashirova

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anorgul Ashirova has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Tensor analysis models for high-dimensional computer vision tasks

    by Srikanta Sahoo, Aseem Aneja, Ramachandran Thulasiram, Nikhil Govil, Shoyimkulov Asror, Anorgul Ashirova, P. Jeyanthi

    In the field of high dimensional computer vision problems, the feature redundancy, high computation complexity and multidimensional structural loss are responsi...

  • Design of an Underwater Fish Recognition System Based on Intelligent Edge Computing

    by Mughair Aslam Bhatti, Tang Hao, Uzair Aslam Bhatti, Sibghat Ullah Bazai, Anorgul Ashirova, Hayitov Abdulla Nurmatovich, Zafar Hashmi

  • Scalable Data Solutions with APIs, Cloud Pipelines, and Predictive Analytics

    by Peeyush Patel, Laxmi Vanam, Anorgul Ashirova, Yuldoshev Jushkinbek Erkaboy Ugli, Shokhjakhon Akhmedov

  • AI-Driven Digital Commerce: Personalisation and Global Growth

    by Gaurav Dixit, Abinaya Inbamani, Yaswanth Jeganathan, Jamshid Pardaev, Anorgul Ashirova

    Digital commerce is the exemplification of the replacement of fixed websites and bulk marketing with the dynamic Artificial Intelligence (AI)-driven ecosystems. Increasingly, personalization is required to attract the attention of consumers, support engagement and conversion rates, and foster brand loyalty around the world. It is in this connection that the paper will analyze how AI has affected digital commerce by real-time identification of users, modelling, adaptive content delivery, and multilingual processing to scale to address the global market. The ecommerce systems would increase user experience and lifetime value through machine-generated product recommendations, automated pricing strategies, and content delivery through the identification of user sentiment with deep learning, natural language processing, and the recommender system. AI also allows ease of expansion across the borders with localization, currency adaptation, fraud detection, and cultural sentiment analysis to facilitate digital commerce globally and proceed to empower the customer. The study develops a comprehensive AI platform approach centered around scalable and 1:1 approaches to multilingual-focused online shopping and measures the consequence of such application using platformlevel KPIs and customer behavior metrics. The experiments have shown better results in terms of click-through rates, revenue per session, fraud control and customer retention.


  • Testing the viability of f(T,𝒯 ) gravity models via effective equation of state constraints

    by M. Koussour, O. Donmez, S. Bekov, A. Syzdykova, S. Muminov, A. I. Ashirova

    This paper rigorously examines the potential of the [ ] theory as a promising framework for understanding the dark sector of the universe, particularly in relation to cosmic acceleration. The [ ] theory extends gravitational dynamics by incorporating both the torsion scalar [ ] and the trace of the energy-momentum tensor [ ]. Further, we explore the functional form [ ], where [ ] is a free parameter that modulates the matter’s influence on spacetime evolution. To evaluate this model, we employ an effective EoS parameter dependent on redshift [ ], to solve the field equations and analyze the evolution of the Hubble parameter [ ]. Using a joint dataset ([ ]) and the Markov Chain Monte Carlo (MCMC) method with Bayesian analysis, we obtain the best-fit parameter values: [ ], [ ] and [ ], which align well with current observational data. Our findings indicate a deceleration parameter of [ ], supporting a present-day accelerated expansion phase, with a transition redshift [ ] marking the universe’s shift from deceleration to acceleration. Moreover, we confirm a positive cosmic fluid energy density, reinforcing stability, and find an EoS parameter value of [ ], consistent with quintessence-driven acceleration. These results underscore the viability of [ ] as a robust framework for addressing the accelerating universe and dark energy dynamics, paving the way for future investigations into its cosmological implications.


  • Geometric Modeling of Virtual Museum Exhibits Using the Piecewise Polynomial Method

    by J.X. Djumanov, T.R. Xudayberganov, S.H. Ismoilov, A.I. Ashirova, R.R. Raximov, A.B. Xasanov

    In the realm of digital preservation and virtual representation of cultural artifacts, the application of geometric modeling techniques holds significant promise. This paper focuses on the utilization of the piecewise polynomial method for the accurate and detailed modeling of museum exhibits within virtual environments. By leveraging the piecewise polynomial approach, this research aims to provide a comprehensive analysis of how intricate shapes and structures of various museum artifacts can be faithfully reconstructed and interactively presented in the digital space. Furthermore, the study delves into the technical aspects of implementing and optimizing this method for virtual museum applications. Through this rigorous exploration, the research seeks to not only demonstrate the potential of the piecewise polynomial method but also contribute to the advancement of virtual museum experiences, digital conservation, and educational outreach initiatives.

  • Open Access

    Testing the viability of $f(T, \mathcal{T})$ gravity models via effective equation of state constraints

    by M. Koussour, O. Donmez, S. Bekov, A. Syzdykova, S. Muminov, A. I. Ashirova

    This paper rigorously examines the potential of the $f(T, \mathcal{T})$ theory as a promising framework for understanding the dark sector of the universe, particularly in relation to cosmic acceleration. The $f(T, \mathcal{T})$ theory extends gravitational dynamics by incorporating both the torsion scalar $T$ and the trace of the energy-momentum tensor $\mathcal{T}$. Further, we explore the functional form $f(T, \mathcal{T}) = T + β\mathcal{T}$, where $β$ is a free parameter that modulates the matter's influence on spacetime evolution. To evaluate this model, we employ an effective EoS parameter dependent on redshift $z$, to solve the field equations and analyze the evolution of the Hubble parameter $H(z)$. Using a joint dataset ($H(z)+Pantheon^+$) and the Markov Chain Monte Carlo (MCMC) method with Bayesian analysis, we obtain the best-fit parameter values: $H_0 = 68.04 \pm 0.64$, $β= 0.14 \pm 0.17$, and $γ= 0.96^{+0.38}_{-0.69}$, which align well with current observational data. Our findings indicate a deceleration parameter of $q_0 = -0.51$, supporting a present-day accelerated expansion phase, with a transition redshift $z_t = 0.57$ marking the universe's shift from deceleration to acceleration. Moreover, we confirm a positive cosmic fluid energy density, reinforcing stability, and find an EoS parameter value of $ω_0 = -0.76$, consistent with quintessence-driven acceleration. These results underscore the viability of $f(T, \mathcal{T})$ as a robust framework for addressing the accelerating universe and dark energy dynamics, paving the way for future investigations into its cosmological implications.