Daniyel Mikhailov

Mr. Daniyel Mikhailov


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
16 September 2026 in Buildings
Verified
Journal Article
Open access
PDF file
AMAinur Montayeva
Ainur Montayeva
ADAgnieszka Dąbska
Agnieszka Dąbska
YAYergen Ashkei
Yergen Ashkei
GZGulnaz Zhakapbayeva
Gulnaz Zhakapbayeva
AIAkniyet Izbassar
Akniyet Izbassar
DMDaniyel Mikhailov
Daniyel Mikhailov
Early-stage selection of pile foundation systems is associated with considerable uncertainty due to limited site information and the need to consider multiple geotechnical, structural, and construction-related factors simultaneously. This study proposes a rule-based decision-support framework, named GeoSupport Decision Platform (GSDP), for transparent and systematic evaluation of pile foundation alternatives across varying engineering conditions. A multicriteria scoring procedure is introduced into the proposed framework to evaluate the recommended pile alternative for the application. The implemented procedure combines compatibility scores and weighting coefficients based on engineering judgement and related to soil type, groundwater conditions, frost depth, load level, vibration/noise restrictions, and site accessibility. The ranked pile alternative list, closely linked to the suitability scores, is an outcome of the framework. The applicability of the GSDP framework is illustrated through two case studies based on construction sites in Kokshetau and Astana, Kazakhstan, representing different geotechnical and construction conditions. For the Kokshetau construction site, the GSDP framework recommends driven piles with a suitability score of 0.975 as the most suitable foundation alternative, followed by bored piles and micropiles, with suitability scores of 0.905 and 0.845, respectively. In contrast, for the Astana case, bored/CFA piles are ranked first with a suitability score of 0.970, followed by micropiles (0.825) and driven piles (0.775). In both cases, the highest-ranked pile alternative corresponds to the pile foundation system adopted at the respective construction site. The results show that the framework generates transparent, interpretable recommendations through a weighted scoring procedure and provides brief explanations that align with the engineering solution chosen for the case study. The contrasting rankings, which demonstrate the ability of the framework to respond to site-specific conditions rather than systematically favoring a single pile type, indicate the GSDP’s practical engineering significance for the preliminary selection of pile foundations when site investigation data are limited.

4 September 2026 in Buildings
Verified
Journal Article
Open access
PDF file
SASungat Akhazhanov
Sungat Akhazhanov
Assel SarsembayevaAssel Sarsembayeva
Assel Sarsembayeva
OBOlzhas Bibalayev
Olzhas Bibalayev
Abdulla OmarovAbdulla Omarov
Abdulla Omarov
MBMeiirrassul Bekov
Meiirrassul Bekov
ZZZhibek Zhamaladinova
Zhibek Zhamaladinova
Automated personal protective equipment (PPE) monitoring can support construction-site safety, but practical deployment requires reproducible performance, reliable confidence estimates, and robustness across varying field acquisition conditions. This study evaluates a modular two-stage framework comprising YOLO26s person detection and MobileNetV3-based multi-label classification of six PPE attributes: helmets, high-visibility vests, gloves, safety boots, goggles, and face masks. The dataset contained 1807 construction-site images and 7580 person crops, partitioned by video recording to prevent temporal and location-based leakage. The same MobileNetV3 architecture was trained in three independent runs using different random seeds. Attribute-specific thresholds were selected on the validation set, and probability calibration was assessed using temperature scaling and Expected Calibration Error. On the test set, Average Precision was highest for vests (0.995) and boots (0.979), followed by gloves (0.908), helmets (0.892), goggles (0.715), and masks (0.695). Calibration improved substantially for boots and vests, slightly for goggles, negligibly for helmets, and unfavourably for gloves and masks. Distance effects were strongly attribute-dependent, with goggles degrading markedly at 30 m, while worker-density effects were non-monotonic. The findings demonstrate the importance of reproducibility, calibration, and operational robustness when evaluating construction-site PPE classifiers.