Sabina Mahmudova

Sabina Mahmudova

Auto-generated profile, based on publicly available information

Sabina Mahmudova

Nakhcivan State University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 June 2025 in ScienceRise
Verified
Journal Article
Open access
PDF file
KVKanan Valiyev
Kanan Valiyev
SMSabina Mahmudova
Sabina Mahmudova
The object of research: the impact of artificial intelligence on people's lives and to evaluate its potential risks along with its benefits. Investigated problem: This research will examine the challenges, ethical and legal issues, technological risks and social issues facing artificial intelligence. Each issue will be explained in detail and the implications of AI on these issues will be discussed. The main scientific results: Here, scientific research that plays an important role in the development of artificial intelligence and the results of these studies will be presented. The transparency of algorithms and the investigation of "dark box" problems will come to the fore. Understanding how algorithms work, explaining how they make decisions, is important in terms of increasing the reliability of artificial intelligence. The area of practical use of the research results: In medicine, extensive space will be given to cases where artificial intelligence is used in the early stages of disease detection and the development of individual treatment plans. In the field of finance, information will be provided on how artificial intelligence is developing in risk analysis, automation of investment decisions, and algorithmic trading in financial markets. Practical approaches will be presented regarding the application of autonomous vehicles in the fields of transport and logistics and the future integration of these systems into people's daily lives. At the same time, the development and application of intelligent teaching systems and individual learning environments in the field of education will also be considered. Innovative technological product: Autonomous weapons systems controlled by artificial intelligence eliminate the human factor in war and can lead to inhumane consequences. Drones called "slaughterbots" that can select and destroy targets on their own are already in the prototype stage. Scope of the innovative technological product: The emergence of new fields related to the development of artificial intelligence in the future and the development trends in existing fields will be discussed. The scope of application of artificial intelligence in fields such as cybersecurity, healthcare, and education will further expand, and the innovations that this technology will bring to our lives will be analyzed in detail.artificial intelligence

22 October 2026 in SCIENTIFIC WORK
Verified
Journal Article
Closed access
MAMaftun Aliyev
Maftun Aliyev
JZJavanshir Zeynalov
Javanshir Zeynalov
YCYigitcan Cakmak
Yigitcan Cakmak
IPIshak Pacal
Ishak Pacal
SMSabina Mahmudova
Sabina Mahmudova
Cucumber (Cucumis sativus) is an important horticultural crop, and disease-related losses can reduce both yield and market quality. Image-based deep learning methods have been increasingly used for plant disease recognition, yet practical model selection requires attention to both predictive performance and computational cost. In this study, four pretrained deep learning architectures were evaluated for eight-class cucumber disease classification: DenseNet201, Inception v4, ConvNeXt v2 Base, and DeiT Base. The experiments were conducted on a public dataset containing 7,689 images, including two healthy and six diseased categories, using a 70% training, 15% validation, and 15% test split. DeiT Base achieved the highest test accuracy among the evaluated models, with an accuracy of 0.9957. Inception v4 followed closely with an accuracy of 0.9948, whereas DenseNet201 provided a lower but still competitive accuracy of 0.9846 with the smallest computational burden, requiring 18.11M parameters and 8.58 GFLOPs. The results indicate that highly accurate cucumber disease classification can be achieved with both convolutional and Transformer-based models, but the preferred architecture depends on whether the priority is maximum accuracy or lower computational cost. Since the experiments were limited to a single public dataset, further validation on fieldacquired images is needed before drawing conclusions about real-world deployment.

30 October 2026 in Electrica
Verified
Journal Article
Closed access
PDF file
JZJavanshir Zeynalov
Javanshir Zeynalov
MAMaftun Aliyev
Maftun Aliyev
LILeyla Ibrahimova
Leyla Ibrahimova
GZGultaj Zeynalzada
Gultaj Zeynalzada
SMSabina Mahmudova
Sabina Mahmudova
TNTofiqa Nadirova
Tofiqa Nadirova
Accurate estimation of photovoltaic (PV) power output is crucial for improving the reliability and efficiency of solar energy systems, especially in regions exposed to high dust loads and temperature variability. This study is scoped as a concurrent power-estimation (soft-sensor) study, inferring instantaneous direct current (DC) power from synchronous environmental measurements rather than multi-step-ahead forecasting; extension to horizon-based forecasting is left for future work. A comparative modeling framework is presented to estimate the power output of a 280 W polycrystalline-silicon PV module in the semi-arid climate of Nakhchivan, using a sixmonth, high-resolution time series of synchronized environmental parameters, irradiance, ambient temperature, humidity, wind, and dust, collected via the Nakhchivan State Meteorological Service and a Benning PV-2 tester. Five supervised learning models were evaluated: multiple linear regression, Ridge, Lasso, Random Forest (RF), and Gradient Boosting, assessed using mean absolute error (MAE), root mean square error (RMSE), symmetric mean absolute percentage error (sMAPE), and Theil’s U1 (the inequality coefficient, bounded from zero to one; no random-walk baseline is claimed). Random Forest showed the lowest error among the models compared, with RMSE of 27.93 W and Theil’s U1 of 0.0896, though this evaluation used a random, non-blocked, train/test split; the magnitude of the RF advantage should be interpreted as an upper bound pending re-evaluation under a leakagefree, blocked time-series protocol. Plane-of-array irradiance, ambient temperature, and dust concentration emerged as the most significant predictors. Ensemble-based models show promising generalization within the sampled December to May window; performance under a leakage-free protocol and generalization to genuine forecasting horizons and to summer remain to be established. These findings can support solar power estimation, fault detection, and performance optimization in distributed energy systems, particularly in dust-prone or datasparse regions. Physics and Astronomy Classification Scheme (PACS) numbers: numbers: 88.40.−j [Solar energy], 88.40.fc [Modelling and analysis].

7 May 2025 in ScienceRise
Verified
Journal Article
Open access
PDF file
SIShafiga İmAnova
Shafiga İmAnova
SMSabina Mahmudova
Sabina Mahmudova
The object of research. This study focuses on various types of cyberattacks, such as phishing, malware, DDoS attacks, password cracking, and security threats to social media accounts, including phishing attacks, information theft, and account takeovers. It also examines security mechanisms and modern defense strategies, such as AI-based cybersecurity systems and data protection technologies. Investigated problem. The problem being investigated is the increasing intensity of cyberattacks and the risks they pose to the security of social media accounts. Main Scientific Results. The main scientific results obtained as a result of the research include several general conclusions. Based on these, 5 main scientific results were obtained: As a result of the increasing intensity and development of cyberattacks, attacks against social media platforms have become increasingly complex and targeted in modern times, and the effectiveness of phishing and password cracking attacks using artificial intelligence and automated tools has increased. The security vulnerabilities of social media accounts have become more prominent. Thus, today the vast majority of users do not use strong passwords and do not activate two-step verification. As a result, users' personal information is stolen through social engineering rules. The role of phishing and malicious software (malware) is increasing. Phishing attacks are increasingly spread through social platforms and users usually believe these fake (spam) messages. The effectiveness of security measures continues to develop in innovative ways. There are many methods, it is possible to cite 2 of the most popular methods as examples: 1) The application of strong password generation methods and multi-factor authentication significantly increases the security of social media accounts. 2) Artificial intelligence-based security systems can more clearly and accurately identify phishing attacks and the activity of unreal users. The importance of increasing the cybersecurity literacy of users. Both awareness and training on cybersecurity help protect users from attacks. Also, users with a high level of security knowledge are less likely to be attacked and can minimize the likelihood of threats. The area of practical use of the research results: promote VPN use when accessing accounts on public networks; educate students on the dangers of connecting to free, unsecured Wi-Fi; encourage enabling login alerts to detect unauthorized access. Innovative technological product may be biometric authentication for social media security. Biometric authentication, such as fingerprint, facial recognition, and voice recognition, is an innovative security technology that enhances social media account protection. Instead of relying solely on passwords, which can be stolen or guessed, biometric security ensures that only the authorized user can access their account. Example: Apple Face ID for Social Media Login. Apple's Face ID allows users to log into social media apps like Instagram, Facebook, and WhatsApp without entering a password. It scans and recognizes unique facial features, making unauthorized access nearly impossible. Scope of the innovative technological product: The scope of biometric authentication in social media security is vast, covering multiple industries, user applications, and future advancements. This innovative technology is revolutionizing online security by reducing reliance on traditional passwords and enhancing user authentication.