Kamola Abdurashidova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kamola Abdurashidova has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Farkhat Rajabov
Computer systems, Tashkent University of Information Technology, Tashkent, Uzbekistan, Uzbekistan
2 shared publications - D. A. Tadjibaeva
Tashkent Chemical - Technological Institute
1 shared publication - Durdona Irgasheva
Department of Artificial intelligence, Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Tashkent, Uzbekistan
1 shared publication - Jamoljon Djumanov
Department of Computer Systems, Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi, Tashkent 100200, Uzbekistan
1 shared publication - Nozima Atadjanova
Tashkent University of Information Technologies named after Muhammad al-Khwarizmi
1 shared publication - Nozima Karimova
Tashkent State Technical University Named after Islam Karimov
1 shared publication
Latest Publications
- Open Access
- 8 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 200-208
AI-Driven Behavioral Pattern Analysis for Enhancing IoT Security in Next-Generation Smart Cities
There has been a rapid development of 6G, SDN, and edge/cloud integration, which have simplified the implementation of IoT devices in the entire smart cities. These devices are frequently small, have a wide variety of different communication protocols, and can occur in large numbers, which contributes to their popularity as a subject of attack by cyber-attacks like DDoS, spoofing, and replay attacks. Traditional defenses such as encryption and firewalls are typically ineffective since they require excessive computer processing power and only respond once an attack has taken place. In this paper, the author proposes an active security system in which AI is used to monitor the behavior of devices and safeguard IoT systems in smart cities. We implement LSTM networks together with Isolation Forest algorithms to create a hybrid anomaly detector that trains on normal device behavior and alerts abnormality in real time. The system operates at the edge and latency and bandwidth are low. Experiments on real IoT traffic and simulated LoRaWAN networks demonstrate a 96.7 % detection rate with extremely low false alarms. The framework is policy-enforceable since it operates with SDN and network virtualization. The findings of our work prove that AI-based behavior modeling can be scaled, flexible, and suitable to protect next-generation networks and industrial IoT implementations.
- 8 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 200-208
Open AccessAI-Driven Behavioral Pattern Analysis for Enhancing IoT Security in Next-Generation Smart Cities
There has been a rapid development of 6G, SDN, and edge/cloud integration, which have simplified the implementation of IoT devices in the entire smart cities. These devices are frequently small, have a wide variety of different communication protocols, and can occur in large numbers, which contributes to their popularity as a subject of attack by cyber-attacks like DDoS, spoofing, and replay attacks. Traditional defenses such as encryption and firewalls are typically ineffective since they require excessive computer processing power and only respond once an attack has taken place. In this paper, the author proposes an active security system in which AI is used to monitor the behavior of devices and safeguard IoT systems in smart cities. We implement LSTM networks together with Isolation Forest algorithms to create a hybrid anomaly detector that trains on normal device behavior and alerts abnormality in real time. The system operates at the edge and latency and bandwidth are low. Experiments on real IoT traffic and simulated LoRaWAN networks demonstrate a 96.7 % detection rate with extremely low false alarms. The framework is policy-enforceable since it operates with SDN and network virtualization. The findings of our work prove that AI-based behavior modeling can be scaled, flexible, and suitable to protect next-generation networks and industrial IoT implementations.
- Open Access
- 30 November 2025
- Published by Lattice Science Publication (LSP) in International Journal of Preventive Medicine and Health
- Vol. 6 (1) , 50-54
Problems in the Early Detection of Cancer
This article examines the analysis of existing challenges in early-stage cancer detection and approaches for their resolution. Additionally, the article discusses the probability of metastasis in early cancer detection based on actual tumour volume, as determined through diagnostic examination results. Numerous studies have demonstrated that early-stage detection and timely treatment of cancer significantly improve patients' survival outcomes. However, long-term survival indicators may not always correlate with treatment efficacy. This phenomenon is observed in certain patients as a result of slow disease progression or early diagnosis. While survival statistics appear to improve, actual mortality rates may remain unchanged. Despite decades of scientific research, only select early detection tests demonstrate proven efficacy in reducing cancer-related mortality rates. Nevertheless, such outcomes are sometimes achieved at the cost of detecting clinically insignificant tumour states in patient populations. Detection of cancer before metastasis and surgical resection of the tumour provides the opportunity for a complete cure. If the disease has metastasized, a combination of surgical intervention and systemic therapy (chemotherapy or immunotherapy) is employed; however, a complete cure may not always be achievable. Treatment efficacy is often dependent on the extent of metastatic disease burden. Therefore, cancer detection before the emergence of clinical manifestations and before the onset of metastasis represents the optimal therapeutic approach. In some instances, detection of metastasis at relatively early stages through screening may also enhance the efficacy of systemic therapy. If novel diagnostic tests cannot differentiate between biologically progressive and clinically insignificant tumours, early detection may lead to increased incidence rates without reducing cancer mortality. Detection of small tumours requires screening at short intervals however, this increases the number of overdiagnoses, unnecessary tests, and false-positive results. In the context of biological heterogeneity in tumour growth rates, adapting the screening frequency to tumour kinetics plays a crucial role in balancing the benefit-to-harm ratio.
- 30 November 2025
- Published by Lattice Science Publication (LSP) in International Journal of Preventive Medicine and Health
- Vol. 6 (1) , 50-54
Open AccessProblems in the Early Detection of Cancer
This article examines the analysis of existing challenges in early-stage cancer detection and approaches for their resolution. Additionally, the article discusses the probability of metastasis in early cancer detection based on actual tumour volume, as determined through diagnostic examination results. Numerous studies have demonstrated that early-stage detection and timely treatment of cancer significantly improve patients' survival outcomes. However, long-term survival indicators may not always correlate with treatment efficacy. This phenomenon is observed in certain patients as a result of slow disease progression or early diagnosis. While survival statistics appear to improve, actual mortality rates may remain unchanged. Despite decades of scientific research, only select early detection tests demonstrate proven efficacy in reducing cancer-related mortality rates. Nevertheless, such outcomes are sometimes achieved at the cost of detecting clinically insignificant tumour states in patient populations. Detection of cancer before metastasis and surgical resection of the tumour provides the opportunity for a complete cure. If the disease has metastasized, a combination of surgical intervention and systemic therapy (chemotherapy or immunotherapy) is employed; however, a complete cure may not always be achievable. Treatment efficacy is often dependent on the extent of metastatic disease burden. Therefore, cancer detection before the emergence of clinical manifestations and before the onset of metastasis represents the optimal therapeutic approach. In some instances, detection of metastasis at relatively early stages through screening may also enhance the efficacy of systemic therapy. If novel diagnostic tests cannot differentiate between biologically progressive and clinically insignificant tumours, early detection may lead to increased incidence rates without reducing cancer mortality. Detection of small tumours requires screening at short intervals however, this increases the number of overdiagnoses, unnecessary tests, and false-positive results. In the context of biological heterogeneity in tumour growth rates, adapting the screening frequency to tumour kinetics plays a crucial role in balancing the benefit-to-harm ratio.
- 29 February 2024
- Published by Springer Nature
- p. 65-75
Visual-Sensory Information Processing Using Multichannel EEG Signals
- 29 February 2024
- Published by Springer Nature
- p. 65-75
Visual-Sensory Information Processing Using Multichannel EEG Signals
- 6 February 2021
- Published by Springer Nature
- p. 95-103
Development of the Method, Algorithm and Software of a Modern Non-invasive Biopotential Meter System
- 6 February 2021
- Published by Springer Nature
- p. 95-103
Development of the Method, Algorithm and Software of a Modern Non-invasive Biopotential Meter System