first_pagesettingsOrder Article Reprints Open AccessArticle An Adaptive Task Difficulty Model for Personalized Reading Comprehension in AI-Based Learning Systems by Aray M. Kassenkhan 1,*ORCID,Mateus Mendes 2,3,*ORCID andAkbayan Bekarystankyzy 4,* 1 Department of Software Engineering, Institute of Automation and Information Technologies, Satbayev University, Almaty 050013, Kazakhstan 2 Polytechnic University of Coimbra, Rua da Misericórdia, Lagar dos Cortiços, S. Martinho do Bispo, 3045-093 Coimbra, Portugal 3 RCM2+, Polytechnic University of Coimbra, Rua Pedro Nunes, 3030-199 Coimbra, Portugal 4 School of Digital Technologies, Narxoz University, Almaty 050035, Kazakhstan * Authors to whom correspondence should be addressed. Algorithms 2026, 19(2), 100; https://doi.org/10.3390/a19020100 Submission received: 24 December 2025 / Revised: 7 January 2026 / Accepted: 21 January 2026 / Published: 27 January 2026 (This article belongs to the Section Algorithms for Multidisciplinary Applications) Downloadkeyboard_arrow_down Browse Figures Versions Notes Abstract This article proposes an interpretable adaptive control model for dynamically regulating task difficulty in Artificial intelligence (AI)-augmented reading-comprehension learning systems. The model adjusts, on the fly, the level of task complexity associated with reading comprehension and post-text analytical tasks based on learner performance, with the objective of maintaining an optimal difficulty level. Grounded in adaptive control theory and learning theory, the proposed algorithm updates task difficulty according to the deviation between observed learner performance and a predefined target mastery rate, modulated by an adaptivity coefficient. A simulation study involving heterogeneous learner profiles demonstrates stable convergence behavior and a strong positive correlation between task difficulty and learning performance (r = 0.78). The results indicate that the model achieves a balanced trade-off between learner engagement and cognitive load while maintaining low computational complexity, making it suitable for real-time integration into intelligent learning environments. The proposed approach contributes to AI-supported education by offering a transparent, control-theoretic alternative to heuristic difficulty adjustment mechanisms commonly used in e-learning systems.

The article reports on a bilingual and interpretable book recommendation platform for schoolchildren. This platform uses a lightweight K-Nearest Neighbors algorithm combined with gamification and learning analytics. This application has been designed for a bilingual learning environment in Kazakhstan, supporting learning in Kazakh and Russian languages, and is intended to improve reading engagement through culturally adjusted personalization. The recommendation engine combines content and collaborative filtering in that it leverages structured book data (genres, target age ranges, authors, languages, and semantics) and learner attributes (language of instruction, preferences, and learner history). A hybrid ranking function combines the similarity to the user and the item similarity to produce top-N recommendations, whereas gamification elements (points, achievements, and reading challenges) are used to foster sustained activity.Teacher dashboards show learners’ overall reading activity and progress through real-time data visualization. The initial calibration of the model was carried out using an open-source book collection consisting of 5197 items. Thereafter, the model was modified for a curated bilingual collection of 600 books intended for use in educational institutions in the Kazakh and Russian languages. The validation experiment was carried out on a pilot test involving 156 children. The experimental outcome suggests a stable level of recommendation in terms of the Precision@10 and Recall@10 values of 0.71 and 0.63 respectively. The computational complexity remained low. Moreover, the bilingual normalization technique increased the relevance of recommendations of non-majority language items by 12.4%. In conclusion, the proposed approach presents a scalable and transparent framework for AI-assisted reading personalization in bilingual e-learning systems. Future research will focus on transparent recommendation interfaces and more adaptive learner modeling.

Gamification and artificial intelligence (AI) are transforming modern education by increasing student motivation, supporting personalized learning, and fostering the development of critical thinking. In the context of rapid digitalization, analytical skills and the ability to evaluate information have become essential competencies across all educational levels. This article presents a bibliometric analysis of 101 academic publications that explore the integration of game-based learning and AI technologies into educational environments. The study identifies dominant research themes, methodological trends, and the distribution of publications in educational sectors, including schools, universities, and corporate training. It also examines how these technologies are being used to improve cognitive engagement and support the development of independent decision-making. The results highlight the growing global interest in applying gamification and AI to improve learning outcomes. This work provides evidence-based information for the development of adaptive educational platforms and instructional strategies aimed at cultivating critical thinking and enhancing student engagement. The findings are particularly relevant for educators, policymakers, and developers working at the intersection of education and technology.

The presence of natural organic matter (NOM) poses many challenges in the process of purifying water intended for drinking. The presence of NOM leads to high coloration due to natural conditions. During the coagulation and flocculation processes, NOM stabilizes dispersed and colloidal particles. Currently, there are many methods for removing natural organic matter. In Kazakhstan, coagulation is commonly used for treating most waters, which effectively reduces color and NOM. It is known that the efficiency of ozonation and coagulation is high when they are used together. The impact of ozonation on the properties of coagulation is significant because coagulation is the most widespread process for treating drinking water. The combination of ozonation with coagulation has been proposed as an improved method for reducing coloration and removing surfactants. The studies were conducted at the K.I. Satpayev Kazakh National Technical University, where a liquid phase ozonation laboratory system was developed. The aim of the research was to demonstrate the positive effect of combining ozonation with coagulation on the removal of color and surfactants in surface waters. Studies were conducted on model waters with different contents of humic substances. Positive results were obtained at low concentrations of ozone (0.1…0.8 mg/l) and low doses of coagulant. A low dose of ozone showed improvement for coagulation. The results of the study indicate that ozonation, combined with coagulation, has a positive effect on color removal, enhances the removal of NOM, and reduces the necessary dose of coagulant. © The Authors, published by EDP Sciences.

Along with the evolution of renewable energy technologies and some other systems such as electric vehicle, demands for batteries as storage unit has increased. Keeping the temperature of batteries in a specific range is necessary to have reliable performance and prevent degradation. In regard to the enhanced thermophysical specifications compared with pure heat transfer fluids, nanofluids would be attractive alternatives for them in thermal management of batteries. The purpose of this article is to identify the impact of using nanofluids for thermal management of batteries as heat transfer fluid with improved properties and evaluate the impactful factors in their cooling performance both as direct coolant or operating fluid of heat pipes as cooling mediums. In this regard, this article reviews the studies implemented on the thermal management of batteries by use of nanofluids. Reduction in maximum temperature of battery packs and temperature difference, due to elevation of heart transfer as a consequence of increment in the thermal conductivity, are the most remarkable outcome of using nanofluids for battery thermal management. Although nanofluids could be advantageous in term of heat transfer intensification, increment in the pressure drop can be one of the disadvantages in conditions of using liquid flow. In cases of using nanofluidic thermal mediums like heat pipes, the enhancement in the cooling performance can be attributed to some other factors, e.g. increase of nucleation sites for promotion of two-phase heat transfer, as well as thermal conductivity elevation. Concentration of the nanomaterials, operating condi tions, specifications of the solid phase are among the most significant items in the effectiveness of the cooling techniques with nanofluids. In design of nanofluidic thermal management units of batteries, the mentioned influential factors must be taken into account to reach the optimal performance.

Microchannel heat sinks (MCHSs) are effective and compact thermal management devices that are broadly developed in recent years. Performance of these equipment is impacted by a variety of the factors that have been investigated and evalu ated by the scholars and researches. Use of coolant with improved thermal properties can elevate heat transfer rate and consequently the thermal performance. One of the attractive techniques for improvement of convective heat transfer is use of nanofluids, with higher thermal conductivity in comparison with the conventional heat transfer fluid, as the coolant. The aim of the current article is to comprehensively review the applications of the hybrid nanofluids, containing more than single nanomaterial in the base fluid, in the MCHSs. Findings of the research works on the use of these nanofluids in MCHSs have revealed considerable potential for elevation in heat transfer rate. Several factors impact the modification of heat transfer in MCHSs with hybrid nanofluids including the characteristics of the coolant, configuration of the system and operating conditions. As well as heat transfer, other factors such as the pressure drop and entropy generation would be impacted due to the existence of the hybrid nanomaterials in the working fluid. Some recommendations are presented in this article for the forthcoming researches in order to further enhance the heat transfer and modify the characteristics of these systems.

The research considers an hourly residential load demand with a daily average of 988kWh/day and investigates possible standalone systems, including solar panels (photovoltaic [PV]), wind turbines (WTs), diesel generator (DG), biogenerator (BG), and battery bank (Bat), to provide the load demand, for a case study located in Tabuk, Saudi Arabia, where the monthly solar radiation and wind speed are 5.74kWh/m2/day and 5.33m/s, respectively. In this study, enviroeconomic factors, including inflation and discount rates, capacity shortage and load demand, CO2 and SO2 penalties, diesel and biomass prices are considered, while they were not considered in the previous studies in Saudi Arabia. The results show that the net present cost and cost of energy of the optimized system are $1.03M and 0.178$/kWh, respectively. Additionally, the prices of diesel fuel and biomass have a significant impact on the CO2 emissions of the system, even with a 10% increase in the renewable fraction. The results of sensitivity analyses show that increasing the CO2 emission penalty from 20 to 80$/ton leads to a decrease in CO2 emissions by 50%. The effect of the initial cost of WT on the configuration of the optimal system is higher than that of PV, and increasing both prices significantly leads to an increase in CO2 emissions.

renewed interest in lateritic ores, yet Kazakhstan’s substantial resources remain underused due to the lack of effective extraction technologies. This study provides the first comprehensive mineralogical and processing evaluation of laterite ore from the Kempirsay deposit and demonstrates the applicability of the sulfation roasting-water leaching (SR-WL) method to Kazakh high-iron laterites. Physicochemical analysis showed that Ni and Co are mainly hosted in Fe-bearing phases goethite, hematite, and trevorite with minor incorporation in silicates; the ore contains, (in wt.%):1.08 Ni, 0.104 Co, and 20.2 Fe. Roasting at 500 °C with 30 wt.% H2SO4 generated readily leachable sulfates, and subsequent leaching at 85 °C (180 min, S: L = 1:6) extracted 93.3% Ni, 92.0% Co, and 84% Fe. Selective dissolution was achieved by roasting at 700 °C with 50 wt.% H2SO4, yielding 90.08% Ni and 90.01% Co while limiting Fe dissolution to 6.12%, producing a low-iron pregnant leach solution (PLS) containing, g·L−1: 2.11 Ni, 0.35 Co, 2.12 Fe. Overall, the results show that the SR-WL process is a viable and newly validated pathway for converting low-grade Kazakh laterites into Ni-Co intermediates suitable for modern metallurgical supply chains.