Ilkhom Rakhmatullaevich Rakhmatullayev

Prof. Ilkhom Rakhmatullaevich Rakhmatullayev

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
4 July 2024 in IEEE Access
Verified
Journal Article
Open access
AAAkmalbek Abdusalomov
Akmalbek Abdusalomov
DKDusmurod Kilichev
Dusmurod Kilichev
RNRashid Nasimov
Rashid Nasimov
Ilkhom Rakhmatullaevich RakhmatullayevIlkhom Rakhmatullaevich Rakhmatullayev
Ilkhom Rakhmatullaevich Rakhmatullayev
YCYoung Im Cho
Young Im Cho
In this study, we present an innovative network intrusion detection system (IDS) tailored for Internet of Things (IoT)-based smart home environments, offering a novel deployment scheme that addresses the full spectrum of network security challenges. Distinct from existing approaches, our comprehensive strategy not only proposes a model but also incorporates IoT devices as potential vectors in the cyber threat landscape, a consideration often neglected in previous research. Utilizing the harmony search algorithm (HSA), we refined the extra trees classifier (ETC) by optimizing an extensive array of hyperparameters, achieving a level of sophistication and performance enhancement that surpasses typical methodologies. Our model was rigorously evaluated using a robust real-time dataset, uniquely gathered from 105 IoT devices, reflecting a more authentic and complex network scenario compared to the simulated or limited datasets prevalent in the literature. Our commitment to collaborative progress in cybersecurity is demonstrated through the public release of our source code. The system underwent exhaustive testing in 2-class, 8-class, and 34-class configurations, showcasing superior accuracy (99.87%, 99.51%, 99.49%), precision (97.41%, 96.02%, 96.07%), recall (98.45%, 87.14%, 87.1%), and f1-scores (97.92%, 90.65%, 90.61%) that firmly establish its efficacy. Thiswork marks a significant advancement in smart home security, providing a scalable and effective network IDS solution that is adaptable to the intricate dynamics of modern IoT networks. Our findings pave the way for future endeavors in the realm of cyber defense, ensuring that smart homes remain safe havens in an era of digital vulnerability.

19 December 2025 in Sensors
Verified
Journal Article
Open access
PDF file
ABAbror Buriboev
Abror Buriboev
DSDjamshid Sultanov
Djamshid Sultanov
Ilkhom Rakhmatullaevich RakhmatullayevIlkhom Rakhmatullaevich Rakhmatullayev
Ilkhom Rakhmatullaevich Rakhmatullayev
OYOzod Yusupov
Ozod Yusupov
EEErali Eshonqulov
Erali Eshonqulov
ACAndrew Jaeyong Choi
Andrew Jaeyong Choi
Rapid urban expansion has heightened the demand for accurate, scalable, and real-time methods to assess tree health and the provision of ecosystem services. Urban trees are the major contributors to air-quality improvement and climate change mitigation; however, their monitoring is mostly constrained to inherently subjective and inefficient manual inspections. In order to break this barrier, we put forward a lightweight multimodal deep-learning framework that fuses RGB imagery with environmental and biometric sensor data for a combined evaluation of tree-health condition as well as the estimation of the daily oxygen production and CO2 absorption. The proposed architecture features an EfficientNet-B0 vision encoder upgraded with Mobile Inverted Bottleneck Convolutions (MBConv) and a squeeze-and-excitation attention mechanism, along with a small multilayer perceptron for sensor processing. A common multimodal representation facilitates a three-task learning set-up, thus allowing simultaneous classification and regression within a single model. Our experiments with a carefully curated dataset of segmented tree images accompanied by synchronized sensor measurements show that our method attains a health-classification accuracy of 92.03% while also lowering the regression error for O2 (MAE = 1.28) and CO2 (MAE = 1.70) in comparison with unimodal and multimodal baselines. The proposed architecture, with its 5.4 million parameters and an inference latency of 38 ms, can be readily deployed on edge devices and real-time monitoring platforms.

9 June 2026 in Sensors
Verified
Journal Article
Open access
PDF file
ABAbror Buriboev
Abror Buriboev
FRFarkhat Farmanovich Rajabov
Farkhat Farmanovich Rajabov
DJDjumanov Xudaykulovich Jamoljon
Djumanov Xudaykulovich Jamoljon
KJKhudoyorkhon Muzaffar uglu Jamolov
Khudoyorkhon Muzaffar uglu Jamolov
AAAkmal Abduvaitov
Akmal Abduvaitov
CLCheolwon Lee
Cheolwon Lee
Accurate and reliable groundwater-level monitoring in deep observation wells remains difficult for conventional non-contact ultrasonic systems because narrow tubular geometries intensify multipath reflections, signal attenuation, and echo ambiguity. This study proposes a dual-signal direct time-of-flight (ToF) method that combines radiofrequency (RF) synchronization with one-way airborne ultrasonic propagation to a floating receiver located at the groundwater surface. In the proposed architecture, the RF signal provides a near-instantaneous time reference, whereas the ultrasonic signal defines the propagation delay, thereby eliminating dependence on echo-based ranging. The system integrates a wellhead surface unit for synchronized transmission and control, a floating unit for ToF acquisition and embedded processing, and an optional reference channel for in situ estimation of the effective sound speed. A duty-cycled power architecture is used to support low-power long-term deployment, while a multi-shot acquisition strategy with a median-like estimator improves robustness against startup transients, timing jitters, and false detections. Field validation was conducted over a 12-month period under actual groundwater-monitoring conditions, during which the groundwater depth varied between 14 m and 30 m below the wellhead datum. Within this field-validation interval, the proposed system achieved a mean absolute error of 0.048 m, a maximum absolute error of 0.050 m, and an overall valid detection rate of 99.4% over 358 valid cycles out of 360 scheduled cycles. In addition, a separate range-dependent confined-tubular propagation test was conducted to evaluate the extended detection capability of the RF-synchronized one-way ultrasonic ToF architecture. This test demonstrated stable acoustic-link ToF detection up to 300 m inside the tested 170 mm confined plastic pipeline. Therefore, the 300 m result should be interpreted as a range-dependent valid-detection result rather than as a 12-month groundwater-depth validation over the full 300 m interval. These results demonstrate that the proposed direct-ToF method provides an RF-synchronized one-way ultrasonic ToF framework with a floating receiver for groundwater-level monitoring in deep observation wells, while remaining compatible with low-power and IoT-based environmental monitoring systems.

30 July 2024
Verified
Book Chapter
Closed access
PDF file
ABAlexander Bogdanov
Alexander Bogdanov
NSNadezhda Shchegoleva
Nadezhda Shchegoleva
VKValery Khvatov
Valery Khvatov
JKJasur Kiyamov
Jasur Kiyamov
GDGennady Dik
Gennady Dik
OUOybek Umurzakov
Oybek Umurzakov

1 April 2025
Verified
Conference Paper
Closed access
Ilkhom Rakhmatullaevich RakhmatullayevIlkhom Rakhmatullaevich Rakhmatullayev
Ilkhom Rakhmatullaevich Rakhmatullayev
This article describes a streaming encryption algorithm called NHSA consisting of a total length of 3 shift registers, 6 AND elements and 14 XOR elements. The results of evaluating sequences developed using this algorithm for the level of randomness and conclusions about the portability of certain cryptanalysis methods, as well as information about the number of elements required to implement the algorithm on hardware devices are presented.

7 July 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
ABAbror Buriboev
Abror Buriboev
NRNormakhmad Ravshanov
Normakhmad Ravshanov
AAAkmal Abduvaitov
Akmal Abduvaitov
MUMalik Ubaydullaev
Malik Ubaydullaev
Farrukh MuradovFarrukh Muradov
Farrukh Muradov
Ilkhom Rakhmatullaevich RakhmatullayevIlkhom Rakhmatullaevich Rakhmatullayev
Ilkhom Rakhmatullaevich Rakhmatullayev
Accurate and computationally efficient prediction of radioactive plume dispersion is essential for rapid risk assessment and emergency response in the event of accidental atmospheric releases. This study presents a three-dimensional, mass-conservative numerical framework for simulating mesoscale transport and transformation of radionuclides under varying meteorological conditions. The proposed model is based on the advection–diffusion equation and incorporates key physical processes, including turbulent diffusion, gravitational settling, precipitation washout, radioactive decay, surface absorption, and re-emission. A hybrid numerical scheme is developed that combines a semi-implicit Crank–Nicolson discretization for diffusion terms with a second-order Total Variation Diminishing (TVD) scheme employing a Van Leer limiter for advection. To ensure computational efficiency and stability, the governing equations are solved using an alternating direction implicit (ADI) strategy, leading to tridiagonal systems efficiently handled via the Thomas algorithm. In addition, a modified parameterization of turbulent diffusion coefficients is introduced, extending classical Pasquill–Gifford formulations to better represent mesoscale atmospheric behavior with bounded dispersion characteristics. Computational experiments simulating iodine-131 release under different atmospheric stability classes and meteorological conditions demonstrate that the proposed framework reproduces physically consistent plume structures and maintains strict mass conservation with negligible numerical errors. The results highlight the dominant role of advective transport and precipitation scavenging under moderate wind conditions, as well as strong localization effects under stable atmospheric stratification. The proposed model provides a practical compromise between the simplicity of Gaussian plume approaches and the high computational cost of full-physics atmospheric models, making it suitable for rapid engineering calculations and integration into decision-support systems for radiological emergency management.