DZDmytro Zubov

Dmytro Zubov

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dmytro Zubov has a total of 100 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Autonomous Smart μGreenhouse: Analysis of Power Consumption Cum-sine IoT NodeMCUs ESP8266

    by Dmytro Zubov, Eran Edirisinghe, Sam Goundar, Azamat Azarov, Andrey Kupin, Deepak Kumar Jain, Aruuke Sanzharbekova

    This study presents the results of the first stage of the “COMMON Initiative: Climate-Smart Agriculture Demonstration Plot” project at the University of Central Asia – developing an autonomous smart micro-greenhouse with low-cost IoT equipment (two NodeMCU ESP8266 boards, four 3V relays, and sensors DS18B20/DHT11/LDR/YL-69) and analysing its power consumption in relation to the IoT component. The experiment with eight commonly cultivated plant species (dill, garden strawberry, lettuce, stock, basil, parsley, sorrel, and spinach) in two identical μgreenhouses of size 30x 26x 20cm each (testbed located at the elevation of 800m – Bishkek, Kyrgyz Republic) demonstrated that the power consumption is less with IoT equipment because the use of plant grow lights and heaters is minimised. Observational findings indicate that six plants (except basil and garden strawberry) grew faster in a smart μgreenhouse. The control algorithm employs one-input hysteresis with a neutral zone to automatically regulate the light and temperature inside a μgreenhouse. The percentage change for two time series (cum-sine IoT equipment) varies from -0.92% to -5.78% during the experiment. The data on temperature/soil moisture inside and the temperature/humidity/light intensity outside a μgreenhouse are provided to the human expert to support the decision-making process on plants’ watering. In the second stage of this project, a machine learning algorithm will be employed to further minimise power consumption.

  • Open Access

    Filter-Based Adaptive Fuzzy Control for an Uncertain Robotic Manipulator with Intermittent Input and Output Triggering

    by Jihang Sui, Alain Martinez, Ben Niu, Yunfei Mu, Deepak Kumar Jain, Dmytro Zubov

    This paper investigates the adaptive output feedback control issue for an uncertain robotic manipulator (RM) under input and output triggering. Due to the influence of the output-triggering mechanism, the output state becomes discrete, thereby leading to the non-differentiability problem of the virtual controller. Therefore, a first-order low-pass filter is constructed to generate a filtered version of the sampled output with continuous differentiability for controller design. By utilizing the fuzzy logic systems (FLSs), the unknown robotic dynamics are effectively approximated without requiring the global Lipschitz condition. Subsequently, an adaptive fuzzy state observer is developed based on the filtered output signal to estimate the joint velocity of the RM. Based on the Lyapunov stability analysis method of the hybrid system, it is rigorously proved that all signals of the RM are bounded, and Zeno behavior is precluded. Furthermore, the designed event-triggered control protocol can ensure the desirable system performance and reduce communication resources even under output discretization. Finally, a two-link RM is employed to verify the effectiveness of the control protocol.


  • Avoiding Type I Errors in Image Processing with SIFT/BRISK-keypoints on Android Smartphones

    by Dmytro Zubov, Andrey Kupin

    Avoiding false-positive recognition of objects is a topical problem for specific areas, such as detecting traffic signs for visually impaired pedestrians, fire emergency signs inside buildings, and construction safety signs. Existing solutions show that the percentage of incorrectly recognized traffic signs can reach 25 % for smart vehicles. In this study, SIFT/BRISK-keypoints are employed to design the image descriptor. An experiment with ten images of crosswalk traffic signs and 90 other images (including different traffic signs) showed that the false positive rate is zero and the false negative rate equals 50 %. The implementation is based on the Java Android application with the possibility to correct the knowledge base in case of false alarms. Image analysis was performed on smartphones Doogee S96 Pro and Samsung M31 with an execution time of less than one second. The most likely prospect for further development of this study is the design of the set of image descriptors to improve the false negative rate avoiding type I errors at the same time.


  • Data Acquisition for Condition-Based Maintenance

    by Oleksandr Romanenko, Andrey Kupin, Dmytro Zubov, Vladyslav Holiver

    Data acquisition (DAQ) systems are fundamental to condition-based maintenance (CBM), serving as the critical interface between physical machinery and digital analysis platforms. As industrial systems grow increasingly complex, effective maintenance strategies have evolved from reactive and time-based approaches to predictive methods that rely on real-time asset health monitoring. This shift has been enabled by advances in sensor technology and computational capabilities, making continuous equipment monitoring both technically feasible and economically viable. However, the success of CBM implementations depends heavily on the quality and reliability of their underlying data acquisition infrastructure. Poor data quality, inadequate sampling rates, or incomplete sensor coverage can result in missed failure indicators, false alarms, and suboptimal maintenance decisions, potentially leading to equipment failures, supply chain disruptions, and significant economic losses. This research examines foundational principles of data acquisition systems, addressing their structure, components, and functions. We have decomposed the DAS into three fundamental subsystems: measurement, conditioning and transferring, providing essential knowledge about data acquisition.

  • Open Access

    Indoor Spatial Cognition for the Hearing/Visually Impaired: Google ARCore Augmented Interaction Using WiFi Map

    by Dmytro Zubov, Andrey Kupin, Nurlan Shaidullaev, Rita Ismailova

    Over 430 million people worldwide have disabling hearing loss, and 2.2 billion suffer from vision impairment. Assisting these populations with enhanced indoor navigation tools is critical for improving their independence and quality of life. This research advances existing indoor spatial cognition systems for individuals with hearing or visual impairments by developing two Java-based Android applications on the Android 10 operating system. The first application gathers the WiFi BSSIDs data via the Java Android class WifiManager to design a WiFi map inside the multistage building. In the second application, the WiFi map is employed to localize individuals with impairments and provide audio feedback for the visually impaired; for individuals with disabling hearing loss, the feedback is provided in a form of 3D GLB colored virtual object with textual information via the Google ARCore augmented reality library. Experimental results show a 100 % positioning accuracy in indoor localization at the multistage academic building at the University of Central Asia (Naryn campus, Kyrgyzstan).

  • Open Access

    QUALITY CRITERIA FOR MINIMALLY MANIPULATED BIOTECHNOLOGICAL PRODUCTS BASED ON AUTOLOGOUS BONE MARROW ASPIRATE FOR USE IN TRAUMATOLOGY AND ORTHOPEDICS

    by Sergiy Strafun, Yevhen Holiuk, Dmytro Zubov, Oleksandr Magomedov, Halyna Starodub, Hrystyna Malova

    Autologous biotechnological products based on bone marrow (BM) are a source of stem cells, in particular, hematopoietic and multipotent mesenchymal stromal cells, and act as one of the alternative therapeutic agents that can slow cartilage degeneration, improve its repair and, ultimately, prevent joint replacement. Objective. To develop quality and safety criteria of minimally manipulated biotechnological products from autologous bone marrow for use in patients with pathology of the musculoskeletal system. Methods. The material for the development of quality and safety criteria for the manufacture and use of biotechnological products from autologous red bone marrow aspirate was 85 patients with osteoarthritis and aseptic necrosis of the hip and knee joints, who used biotechnological products made from it. Cell counts in the myelogram and CFU-analysis of MMSCBM were performed in all patients. Results. As a result of the development of quality and safety criteria for biotechnological products from BM aspirate, 3 types of it were established: 1 — polymorphic (with the presence of progenitor cells of all types within the normal range), 2 — moderately cellular (with the presence of all types of progenitor cells, but some of them below the norm), 3 — hypocellular (with the presence of most types of progenitor cells, some of them below the norm). Functional quality criteria of biotechnological products from BM aspirate were developed on the basis of CFU-analysis and calculation of seeding efficiency coefficient (KEP) of MMSK-BM. Conclusions. Quality and safety criteria of biotechnological products based on autologous bone marrow aspirate based on the results of myelograms and CFU analysis have been established. According to the results of myelograms, type 1 BM aspirate was evaluated as excellent for the further manufacture of a biotechnological product, type 2 — good, type 3 — satisfactory. According to the results of the KUOf analysis, the KEP indicator ˂ 0.001 % was evaluated as unsatisfactory, the KEP indicator within the range of 0.001–0.003 % — satisfactory, the KEP indicator ˃ 0.003 % — good. The KEP ˂ 0.001 % — unsuitable for use.

  • Architecture of intelligent system for webservices scaling

    by Andrey Kupin, Dmytro Zubov, Maxim Kosei, Vladyslav Holiver

    The key aspects of web services development, administration structures, and the use of machine learning technologies for server optimization are explored. The tendencies of web services development, scaling options, importance and basic concepts of microservice architecture are considered. The article highlights the general principles of artificial intelligence, machine learning, and deep learning and their impact on the functionality of web services. To enhance the operation of web services, an architecture of an intelligent system for automatic scaling is presented and machine learning algorithms with increased reliability are elaborated. The article optimizes the performance of such a system. Methods for detecting abnormal system behavior are proposed, which allows preventing failures or a decrease in overall performance.


  • Indoor spatial cognition of the hearing/visually impaired: pentest-inspired WiFi heatmap on Android platform

    by Dmytro Zubov, Andrey Kupin, Nurlan Shaidullaev

    This study aims to improve the existing indoor spatial cognition systems for hearing and visually impaired people, especially in unfamiliar spaces where outdoor tools are not functional. The experiment conducted in the academic multistage building of the University of Central Asia (Naryn campus, Kyrgyz Republic) demonstrates a positioning accuracy of 100 % for indoor localization. For this purpose, two Java Android applications were developed on the Android 10 operating system. The first application is employed to design a WiFi heatmap of the building using the Java Android class WifiManager to gather information about BSSIDs (Basic Service Set Identifiers) of WiFi networks indoors (this task might be done by any project team member). The second application also implements the principle of the pentest passive reconnaissance and provides audio feedback to the visually impaired and textual/photo information to people with disabling hearing loss. Java Android applications are freeware and runnable on over 81 % of Android devices and 71 % of smartphones worldwide as of June 2024.