Appl. Syst. Innov., Volume 9, Issue 7 (July 2026) – 27 articles

As generative AI technologies become increasingly embedded in educational cloud platforms, understanding their impact on teacher professional development is essential. Grounded in the stimulus–organism–response (S–O–R) framework, this study investigates how AI-driven stimuli—hedonicity, interactivity, and immersion—influence teachers’ self-regulation and resilience. Using structural equation modeling, data were collected from in-service teachers in Taiwan who actively utilize educational cloud platforms. The results reveal that all three AI-driven stimuli significantly enhance teachers’ self-regulation and resilience, which in turn are significantly associated with perceived value co-creation intentions. Specifically, self-regulation enables teachers to manage goals effectively, while resilience supports their recovery from technical setbacks. The findings indicate that self-regulation positively influences resilience, and both appear to mediate the relationship between perceived AI-driven stimuli and teachers’ value co-creation intentions. This study highlights the potential role of teachers’ psychological adaptability in AI-enhanced environments. Practical implications suggest that platform developers and administrators should prioritize AI features that foster self-directed learning and emotional engagement to promote collaborative willingness and professional alignment within modern educational ecosystems rather than implying proven macro-level transformation. Full article

To address the challenges of data security governance under new conditions and align with technological trends in data security, this paper proposes a graph algorithm-based method for identifying key personnel with critical permissions in the practical applications of large state-owned enterprises. This method can uncover potential permission influence factors within the system and evaluate the weight of influence from different perspectives, providing highly interpretable identification results. To tackle the issue of detecting anomalous user and entity behaviors in data security governance, a user and entity behavior anomaly detection method based on Generative Adversarial Networks (GAN) is introduced. Experimental results show that the proposed method achieves higher precision, recall, and F1-score averages compared to baseline models; specifically, an average F1-score of 0.75 versus 0.72 for LSTM-based TadGAN, 0.62 for ARIMA, and 0.65 for a commercial UEBA baseline across the three evaluation datasets. A data security platform was designed and developed, which plays a significant role in reducing data security risks, assisting enterprise compliance, and promoting data development and utilization. This platform has been applied in various centralized data management projects and meets the big data processing requirements in secure environments, demonstrating strong application and promotional value. Full article

Facility Layout Planning (FLP) remains a complex task for manufacturers seeking to improve productivity, reduce daily operating costs, and stay competitive in fast-changing markets. Traditional methods such as Systematic Layout Planning (SLP) offer useful guidelines for designing department layouts but still rely heavily on judgment and experience. At the same time, modern optimization and simulation techniques provide valuable quantitative insights. These techniques are often used separately rather than as part of an integrated process. In this work, a hybrid layout-planning approach that combines these techniques is developed and validated through an industrial case study, providing a practical decision-support process for facility layout planning. The process starts with SLP, which develops an initial layout using activity relationship charts, material-flow analysis, and handling-cost estimates. A simulation model then evaluates throughput, machine utilization, and work-in-progress, providing early indications of the layout’s real-world performance. A Genetic Algorithm (GA) is used to find improved configurations that reduce distances and costs. The optimized layouts are further tested through simulation. To demonstrate practical use, the framework was applied at a transformer manufacturing plant. It resulted in an approximately 35% reduction in material-handling costs. The results show that the optimized layout reduced material-handling costs from 7062.5 to approximately 4560 L.E. per transformer while increasing monthly throughput by 2.46% (approximately 11 transformers per month). Additionally, a what-if analysis was performed to identify opportunities for improvement, such as increasing production by using an automatic laser-cutting machine. The findings support data-driven decisions in facility layout design and long-term operational planning. Full article

This article develops a structural optimization algorithm for designing intelligent and adaptive radio communication systems. In modern tactical crisis operations characterized by high environmental dynamics and intense electromagnetic countermeasures, as well as in emergency response networks, static communication planning approaches prove increasingly ineffective. The paper introduces a stable normalization method for performance estimates and a mechanism for rapid algorithmic adaptation to shifting operational priorities. A key feature of the proposed approach is an adaptive objective function based on the weighted sum of normalized criteria for survivability, noise immunity, and reliability. The use of weighting coefficients enables rapid adjustment of optimization priorities in response to extreme conditions, whilst the application of a normalization method based on threshold values ensures the stability and comparability of evaluations. It is practical that the proposed algorithm will enable the synthesis of functionally stable and robust structures, thereby enhancing the reliability of command and control of forces and assets in both mission-critical operations and civil crisis situations. Full article

During the recruitment process, it is possible for CVs to appear well-organized. However, it is not always straightforward to compare them. The same competence may be denoted by different designations, and the levels of competence are not universally employed in the same manner. Natural Language Processing (NLP) methodologies can extract these data points; however, ensuring the consistency of this data across multiple CVs remains a challenge. In a multitude of cases, the comparability of two profiles remains ambiguous. In the present study, an ontological approach is adopted to solve this issue. The concept under discussion is that of the extraction of entities from CVs and their subsequent representation in a more structured form, utilizing RDF and an ontology aligned with ESCO—the multilingual classification of European Skills, Competences, and Occupations. Subsequently, the rules of SHACL are applied to verify the semantic coherence of the data; the validated data are transmitted to a model for classification. At this stage, the dataset becomes smaller, but semantically cleaner, more traceable, and enriched with validation indicators that can be used by the classification model. The proposed system is implemented as a set of microservices. A Spring Boot component coordinates the flow, whilst the Python services, implemented using Python 3.10.12 are responsible for the primary processing stages including extraction, validation and classification. A same-corpus ablation was conducted to separate ontology-guided profile selection from the contribution of the validation-derived quality features. On the same 35,770 filtered CV–job pairs, adding these features increased external benchmark accuracy from 0.794 to 0.809, recall from 0.760 to 0.865, F1-score from 0.749 to 0.786, and ROC-AUC from 0.881 to 0.887. A p-value of 0.00540 paired with a 1.54 effect ratio from McNemar’s test showed a statistically significant paired difference between the two configurations. However, precision decreased from 0.739 to 0.720 while Average Precision compressed from 0.851 down to 0.844. Rather than scaling performance uniformly across the entire evaluation suite, the ontology layer acts as a targeted traceability and semantic refinement filter that contributes information beyond filtered-profile selection alone and produces a metric-dependent change in classifier behaviour at the validation-selected threshold. Full article

This study presents an integrated design-to-operation framework for a PV–battery solar highway lighting system supported by IoT-based monitoring for highway-scale deployment. The proposed framework combines pole-level PV-battery sizing, annual energy-reliability simulation, road-level techno-economic optimization, and IoT-based digital monitoring. The Shoubra–Banha Freeway in Egypt, a 40 km corridor with a two-sided lighting arrangement, was selected as the case study. In the pole-level phase, dimming strategies, PV capacities, battery sizes, and battery technologies were evaluated using sequential parametric analysis under a reliability constraint of Loss of Load Probability (LLP) below 1%. The S2 aggressive dimming profile achieved the best operating performance, with an LLP of 0.003, energy reliability of 99.70%, and 2.89 kWh annual unmet load. The minimum feasible PV capacity was 0.8 kW, while the smallest acceptable storage capacity was 4.8 kWh nominal capacity, corresponding to approximately 3.84 kWh usable capacity under an 80% allowable depth of discharge. Among the tested battery technologies, LiFePO₄ achieved the best reliability performance, with an LLP of 0.007 and a 99.25% battery deficit coverage ratio. In the road-level phase, three deployment configurations were compared. Case B, using 12 m pole height and 36 m spacing, was selected as the best-balanced solution, requiring 2224 poles, achieving 99.30% energy reliability, an LLP of 0.007, annual PV generation of 3,178,341 kWh, and total CAPEX of approximately 2.88 × 10⁸ EGP, equivalent to about 5.76 million USD based on an assumed exchange rate of 1 USD = 50 EGP. Lastly, the development of an IoT-based monitoring system design utilizing sector gateways, telemetry variables, alarm conditions, MQTT protocols, and dashboard displays was carried out. The scenario for gateways at 5 km intervals was advised due to its better fault isolation, lower gateway workload, and scalability. This indicates that the suggested approach offers a viable, cost-efficient, and technologically enabled solution for automated solar-powered street lighting systems. Full article

The increasing adoption of collaborative robotics is reshaping the relationship between technology, organization, and human work in industrial environments. Within the transition from Industry 4.0 to Industry 5.0, Humanized Robots (HuRs) are understood not as a distinct technological category, but as a human-centered interpretation of existing collaborative robotics and human–robot collaboration configurations, emphasizing proximity, adaptability, transparency, ergonomic support, and socio-technical integration. However, the literature on human–robot collaboration remains fragmented across technical-regulatory, human factors, and organizational perspectives, with limited attention to how risk assessment outputs are translated into operational practices and decision-making support over time. To address this gap, this paper proposes a preliminary conceptual socio-technical framework for the safe integration of HuRs in industrial human-centered systems. The framework is structured around five interdependent operational levels: hazard identification, risk measures, validation and testing, KPI-based monitoring, and operational control. At its core, the framework adopts and extends the concept of safety readiness, defining it as the organizational capability to translate, sustain, and update risk-related decisions across the system lifecycle while preserving alignment between assessed risk and managed risk under changing operational conditions. The framework, its KPI-based operationalization, and the scenario-based application are conceptual and illustrative in nature. Their operational validity remains to be established through empirical studies in real HuR/HRC settings. This paper’s core contribution lies in formalizing the integration layer through which risk assessment outputs are translated into validation, KPI-based monitoring, and operational-control decisions across the system lifecycle, with safety readiness serving as the bridging construct between assessed risk and managed risk. This paper contributes by reconceptualizing safety in HuR systems as a dynamic and lifecycle-based property, formalizing the integration layer through which risk assessment outputs are translated into validation, KPI-based monitoring, and operational-control decisions across the system lifecycle, with safety readiness serving as the bridging construct between assessed risk and managed risk. Full article

The rapid digitalization and decarbonization of electrical power systems have brought increased operational complexity and new occupational risk dynamics. This transition renders traditional compliance-based safety models inadequate for managing the emerging complexities of cyber–physical and socio-technical systems. This paper develops a conceptual socio-technical safety architecture for occupational risk management in electrical power systems, grounded in the concepts of systems innovation and socio-technical modeling. A structured narrative review of international standards, accident investigations, and emerging technologies is conducted to reinterpret hazards as interacting subsystems within a dynamic, adaptive framework. The proposed framework synthesizes technical safety controls, human reliability factors, and artificial intelligence-driven predictive maintenance within a single architecture, supported by dynamic feedback loops. The model addresses nonlinear risk propagation across smart grid applications, hydrogen systems, and battery energy storage systems. By transitioning from a reactive to a proactive, adaptive approach to safety governance, the architecture enhances the resilience of electrical power systems, reduces the potential for cascading failures, and aligns occupational safety with infrastructure modernization strategies for electrical power systems. The framework provides a conceptual basis for integrating technology innovation with occupational risk management across complex energy infrastructures undergoing digital transformation. Full article

The increasing influence of social media has amplified the risks associated with automated accounts that spread misinformation, manipulate public opinion and carry out malicious activities. To address this challenge, this study presents an explainable, feature-based approach for detecting social bots on $\mathbb{X}$ (formerly Twitter) using user-profile information derived from account metadata and content characteristics. We consolidate and extend existing research by bringing together one of the most comprehensive feature sets explored to date, combining raw attributes, features proposed in the literature, and newly introduced credibility and engagement indicators, together with a previously unexploited profile-personalisation signal. Through a feature engineering and selection process that integrates Mutual Information, Random Forest Importance, and SHAP values, we evaluate the contribution of each feature category and assess its generalisation capacity across three benchmark datasets. Our experiments demonstrate that classical machine learning models enriched with the selected features can match or surpass several state-of-the-art approaches while preserving interpretability. Furthermore, we propose and validate, on the more recent and challenging TwiBot-22 dataset, three categories of features (universal, common, and dataset-specific) that provide a transparent and adaptable basis for generalisable bot detection. Full article

Structural equation modeling (SEM) studies commonly derive constructs and paths from the manually reviewed literature. Expert judgment remains essential, but incomplete coverage and undocumented selection decisions can make this stage difficult to evaluate. We therefore develop a theory-guided, AI-assisted procedure for generating SEM candidate models from systematic literature evidence. PICOC defines the scope, and queries identify the primary records. Backward citation searching adds foundational studies, whereas forward searching adds recent applications. Sentence-BERT and BERTopic are then used to examine semantic structure. Topic terms, representative documents, concept evidence, and theoretical criteria inform the mapping from topics to candidate constructs. The retained constructs are assigned possible SEM roles and assembled into candidate paths. The result is a documented front-end method for candidate model development, not an empirically validated SEM model. Full article

Railway logistics terminals are crucial nodes in the national logistics system. Prior to the market-oriented reform of railway logistics, the warehousing operations at these stations primarily focused on temporary storage services before and after shipment, making it difficult to provide customers with integrated warehousing and transportation logistics services. With the advancement of railway marketization reforms, railway logistics terminals have gradually begun to offer socialized warehousing services, acquiring the capability to provide integrated warehousing and transportation services. In response to market development needs and the requirements for green development in railway logistics, an optimization design model for obtaining green railway logistics solutions is established, considering factors such as carbon emission costs, integrated warehousing and transportation logistics service costs, fuzzy constraints on logistics network capability, transportation time windows and the customer’s risk tolerance level. The model takes minimizing carbon emission costs and railway logistics service costs as dual-objective functions and uses a standardized weighting method to convert the dual-objective functions into a single-objective function for solving using triangular fuzzy numbers to characterize the ability constraints of network nodes, making the model more realistic. This model aims to minimize these costs and assesses the impact of factors such as changes in delivery time limits, shipment quantity, shipment batches, the superposition of multiple goods batches and customer preferences on the railway logistics solution for different scenarios. Research indicates that reasonably designing delivery time limits and aligning shipment times with railway transportation time windows can effectively reduce carbon emissions and logistics costs, and the risk tolerance level has a significant impact on the reliability of railway logistics solutions. Full article

Driver fatigue is a major cause of road accidents, and in-cabin monitoring is increasingly embedded into the Internet-of-Things (IoT) ecosystem of modern vehicles. Deploying such monitoring directly on microcontroller-class devices is challenging: models must fit tight memory and compute budgets, provide reliable confidence estimates, and adapt online to new drivers and conditions. We propose KAN-CLUE, an uncertainty-aware continual TinyML framework for driver fatigue detection from near-infrared periocular images at the IoT edge. KAN-CLUE combines a compact convolutional backbone with a Kolmogorov–Arnold Network (KAN) classification head that outputs Dirichlet-distributed class probabilities and a principled predictive uncertainty measure. A lightweight activation-histogram mechanism provides an additional out-of-distribution (OOD) score, and both signals drive an on-device continual learning scheme that selectively updates a small subset of parameters under a KAN-specific EWC-style regularization. On the ULg DROZY drowsiness database, the quantized KAN-CLUE model uses roughly 167k parameters (about 165 kB in Flash), requires on the order of ${10}^6$ MACs, and achieves around 3.1 ms latency on a Cortex-M–class microcontroller, while reaching 97.7% test accuracy with improved calibration and OOD detection compared with softmax-based TinyML baselines. Full article

The rapid growth of digital transformation (Dx) initiatives across sectors has created an urgent need for structured, scalable, and accurate management of project knowledge. Without effective organization, valuable insights from Dx projects remain fragmented, limiting their reuse and hindering informed decision-making. This research addresses the gap by designing, developing, and validating Dx-Onto, a domain-specific core ontology implemented in OWL and purpose-built for representing and managing knowledge about Dx projects. Dx-Onto models entities, relationships, and attributes from diverse project documentation into a unified knowledge graph, enabling semantic search, cross-project analysis, and context-aware retrieval. To assess performance, a two-pronged evaluation strategy was adopted: (1) scalability experiments using synthetic datasets measured query execution times across volumes ranging from 10 to 1000 projects, and (2) a comparative benchmark against the Core Ontology of Organisational Transformation (COOT) was conducted using a heterogeneous real-world corpus of Thai digital transformation documents. The results confirm Dx-Onto’s capacity to scale and demonstrate a higher domain fit (85.2% vs. 77.3%) and superior analytical utility—including transformation-phase and strategic-dimension diagnostics that are structurally impossible under a general-purpose baseline. By positioning Dx-Onto as the core semantic layer for a future Hybrid LLM-Ontology framework, this work lays the groundwork for intelligent, scalable, and reliable knowledge management solutions in the digital transformation domain. Full article

Social media generates massive amounts of unstructured, multilingual textual data that contain many sentiments, emotions, and opinions from users that provide insights for enterprises undergoing digital transformation. In this paper, we evaluate a variety of commercially available, lightweight large language models (LLMs) for sentiment, emotion, aspect-based sentiment, and toxic speech detection on noisy, real-world social media datasets. These lightweight models are compared (against traditional RoBERTa-based classifiers and heavyweight “pro” LLMs) in terms of performance, latency, and cost trade-offs that are key for scalable deployment across the enterprise. Our results show that lightweight LLMs achieve good accuracy with considerably lower response times and costs, which makes them suitable as the next step in digital transformation for real-time social media analytics. Additionally, we investigate the importance of prompt engineering and show that preprocessing can be very limited for LLMs. This study provides operational guidelines regarding model selection based on latency, accuracy, and cost trade-offs as well as optimal prompt engineering techniques. Finally, it evaluates the intersection of operational performance and resource efficiency to help researchers and developers integrate LLM-based social media analytics into digitized business practices. Full article

Generative artificial intelligence (GenAI) has transformed design education, yet growing evidence suggests that the fluency of AI-generated outputs may create a “fluency illusion”—a metacognitive bias whereby learners conflate polished AI artifacts with genuine cognitive mastery. A critical unresolved question is how to quantitatively diagnose this AI-induced fluency illusion without disrupting the natural learning process. This study introduces MBS-AIGC, a purpose-built AI-supported design education platform grounded in the Meaning–Behavior–Spirit (MBS) cultural cognition model for Chinese intangible cultural heritage. Drawing on the industrial soft-sensor paradigm, we computationally formalized six behavioral soft-sensor indicators from the digital interaction traces of 71 undergraduate design students over a four-week instructional period and applied K-means clustering to identify latent engagement patterns. Three distinct human–AI collaboration profiles emerged: Deep Explorers (n = 41), Progressive Builders (n = 16), and Surface Operators (n = 14). Crucially, expert-assessed cognitive flexibility significantly differentiated the three groups (F(2, 68) = 5.66, p = 0.005, η² = 0.143), whereas a conventional self-report questionnaire failed to distinguish among them (F(2, 36) = 0.29, p = 0.748), providing preliminary empirical evidence for the fluency illusion in design education. By addressing the lack of objective diagnostic tools for metacognitive miscalibration, this research contributes a scalable, zero-intrusion behavioral soft-sensor framework that enables educators to decode human–AI collaboration patterns and mitigate the fluency illusion in creative learning environments. Full article

Despite recent advancements in solving the Capacitated Vehicle Routing Problem (CVRP), state-of-the-art learning-based methods remain hindered by costly offline training, while classical population solvers rely on implicit mechanisms and rigid parameter tuning. To bridge this methodological gap, this paper introduces the Group Learning Algorithm hybridized with a Multi-Armed Bandit (GLA-MAB), a training-free metaheuristic that transforms evolutionary search into an explicit, controllable learning process. The framework partitions the population into leader-learner groups to extract and inject proven topological structures directly into weaker solutions. Simultaneously, a hierarchical MAB layer oversees the search online, utilizing real-time reward feedback to dynamically manage operator selection and stagnation recovery. Furthermore, a spatial decomposition wrapper ensures strict scalability, extending the framework’s applicability to massive topologies of up to 1200 nodes. Comprehensive evaluations across 117 established CVRP benchmark instances validate the architecture’s efficacy. GLA-MAB achieves near-optimal convergence on classical instances, maintaining mean gaps below 0.03% on Sets A and E, and delivers highly competitive performance on large-scale heterogeneous sets such as Set Li. Ultimately, GLA-MAB provides the dynamic adaptability of modern artificial intelligence while completely eliminating the prohibitive overhead of offline dataset generation. Full article

Existing Kansei-oriented product design studies often rely on simplified styling–color associations or weighted matching of perceptual imagery, making it difficult to capture users’ multi-affective requirements. To address this limitation, this study proposes a product form innovation design method based on a multi-domain coupling network model and establishes a mapping framework from target Kansei images to design solutions. Taking electric mopeds as a case study, the KJ method, k-means clustering, fuzzy Kano analysis, probabilistic hesitant fuzzy entropy weighting, and game-theoretic weighting were employed to identify the target Kansei image. Product form was then decomposed into styling, color, and material domains, and a multi-domain coupling network was constructed based on a form-element co-occurrence matrix. Through topological analysis and the LH-index, 14 key form elements associated with the target image were identified. Quantification Theory Type I was subsequently applied to establish the mapping relationship between form elements and Kansei images, while the Bee Evolutionary Genetic Algorithm (BEGA) was used to generate optimal design solutions. The results indicate that “elegance” is the dominant Kansei image for electric mopeds. The proposed model achieved strong predictive performance (R² = 0.923), and the optimized design obtained an 85% user recognition rate, showing high consistency across multiple validation methods. The proposed framework effectively reveals the coupling effects of styling, color, and material and provides a systematic approach for data-driven product form innovation. Full article

This theory-oriented, methodological and conceptual survey explores the application of Multi-Criteria Decision-Making (MCDM) methods in vehicle routing, transportation and robot navigation. Multi-criteria decision aid brings significant added value in applications where robots and autonomous agents execute missions with multiple objectives in multi-cost and multi-criteria environments. Logistic operations and multi-modal transportation tasks, where multiple factors influence mission success, also benefit from multi-criteria decision aid. Decisions are inherently complex, and MCDM methods capture certain aspects of the decision contexts as they inherently encode different contextual priorities. An evaluation on the effectiveness of MCDM methods may prove to be uninformative without information on contextual preferences. Direct MCDM method comparison may fail to reveal insight over method effectiveness without contextual information. The survey presents an interpretive synthesis over decision modeling constructs and introduces a new context-oriented analytical synthesizing perspective to establish a meaningful base for comparison. Through conceptual abstraction over decision roles, latent decision structures and recurring decision patterns, two stable explanatory constructs emerged: ‘governing aspects’and ‘application attitudes’. Governing aspects characterize decision influences, whereas application attitudes characterize decision architectures. We analyze attitudes pertaining to different application domains from the perspective of responsiveness and computation demand, and discuss some key governing aspects, such as robust decision-making and behavior elicitation. We aim to provide a rich landscape of multi-criteria decision scenarios, and identify future research areas based on our findings. The outlined synthesizing framework functions both as a methodological taxonomy and a conceptual compass and case repository for navigating MCDM applications. Full article

The inverse kinematics (IK) problem of the UR3 collaborative manipulator is addressed through a singularity-aware optimization framework and a statistically grounded benchmarking methodology. The IK task is formulated as a full-pose optimization problem minimizing a physically scaled residual combining Cartesian position and orientation errors. Emphasizing consistency between error formulation and optimization paradigms, a matrix-based pose-error representation is adopted as a numerically stable residual for stochastic search. Simultaneously, a smooth Jacobian-conditioning penalty is incorporated to mitigate instability near ill-conditioned configurations. Five metaheuristic solvers (PSO, GWO, GA, JADE, ALO) are implemented under a unified, reproducible experimental protocol with common maximum search settings. The Levenberg–Marquardt (LM) numerical method is included as a deterministic baseline to compare gradient-based precision against derivative-free global exploration. Performance is evaluated across nominal, industrial, and near-singular poses using 1000 Monte Carlo runs per configuration. Final-solution accuracy, variability, and computational time are analyzed directly from the Monte Carlo outcome distributions, descriptive statistics, and nonparametric rank-based tests. Results indicate that LM achieves superior numerical precision and computational speed. Among the metaheuristics, GA provides the lowest mean objective values and the smallest objective dispersion across the three tested poses, whereas JADE is the fastest solver. GWO provides an intermediate solution profile, with competitive objective values and substantially shorter execution times than GA and ALO. The optimized solutions are first verified in a RoboDK virtual environment. Subsequently, representative GWO-based configurations are experimentally validated on a physical UR3 robot through both isolated static poses and a continuous multi-pose trajectory tracking task, confirming practical kinematic feasibility and sequential stability. The proposed framework establishes a reproducible benchmark for statistically robust evaluation of metaheuristic-based IK optimization in collaborative robotics. Full article

Accurate thermal management is crucial for ensuring the safety, longevity, and performance of lithium-ion batteries, especially in compact embedded systems like USB chargers, power banks, and IoT nodes. Despite extensive research on predictive thermal models and intelligent control frameworks, their implementation in resource-constrained microcontroller-class devices has been limited. Existing strategies in the literature, such as threshold-based or PID logic, cloud-enabled analytics, machine learning models, and observer-based estimators, are often reactive, computationally intensive, or dependent on external infrastructure, making them unsuitable for low-power, standalone applications. This study introduces a novel Scalable Embedded Thermal Intelligence architecture designed for real-time battery thermal regulation in locally executable, without cloud dependency, low-cost platforms. Unlike conventional methods, the proposed system operates entirely on-device using closed-form models implemented on an ESP32 microcontroller. It combines two synergistic algorithms: a static preemptive model that calculates a safe C-rate at startup based solely on ambient and initial battery temperature, and a dynamic disturbance-aware model that monitors temperature rise per SOC step and adjusts airflow or current adaptively without requiring high memory, floating-point units, or supervisory control. The architecture achieves sub-second response times, <7% RAM, and <25% Flash usage, and does not need cloud connectivity, simulation backend, or complex thermal-management infrastructures such as liquid cooling circuits, phase-change systems, or cloud-supervised architectures. The significant contribution of this work is not the introduction of a new electrochemical–thermal formulation, but the effective integration and application of previously validated closed-form thermal predictors on low-cost microcontroller-class hardware, designed for anticipatory battery thermal regulation while adhering to strict computational limitations. Compared to traditional battery thermal management systems using PCM, liquid-cooling circuits, or cloud-based predictive estimators, the proposed approach eliminates the need for complex thermal hardware, fluidic systems, external computing infrastructure and resource-efficient edge operation. This makes the system suitable for deployment in real-world embedded applications like USB-C smart charging cables, compact IoT power banks, and portable medical devices, where form factors, energy efficiency, and cost are critical. The proposed SETI framework offers a firmware-integrated architecture and a firmware-integrated solution that provides a lightweight embedded alternative for predictive thermal regulation for distributed energy systems and miniaturized electronics. Full article

In this study, we analyze the production process capability of sandpaper manufacturing, with an emphasis on material removal from the finished product and the identification of manufacturing variables that most influence grinding performance and final quality. To this end, the CRISP-DM methodology was applied along with linear regression, stepwise analysis, and principal component analysis (PCA) to a sample of 62 operational variables collected between 2024 and 2025. These variables were reduced to 12 critical dimensions that explain 80% of the process variability. This study highlights the interaction between chemical properties of the adhesive system (gel time, pH, and formaldehyde concentration) and fine mechanical adjustments (blade and roller clearance), showing how these variables jointly affect sanding performance. By integrating these factors into a multivariate framework, PCA allows for the identification of latent relationships, reduces process complexity, and establishes a statistical basis for standardization and continuous improvement, with the aim of supporting the transfer of technical knowledge in industrial manufacturing environments. The proposed framework is intended to support technical knowledge transfer in industrial manufacturing environments. Full article

A recurring challenge in the development of information systems (ISs) across complex organizational domains is the lack of integration and alignment between strategic, tactical, and operational levels, resulting in methodological fragmentation that constrains traceability, innovation, and organizational value generation. This study proposes and applies to the Integrated Innovation Framework for Information System Development (IIF-ISD) to overcome this gap. The research was structured through a systematic literature review, following the PRISMA and ROSES protocols, and validated through an exploratory single-case study involving the development of an IS supporting the Selo Casa Azul (SCA) environmental certification process in a Brazilian construction company, a context chosen for its multi-level organizational complexity and ESG compliance requirements, representative of broader certification IS development challenges. The framework integrates DSRM, agile methodologies, Design Thinking, and Lean Startup through three governing principles—Hierarchical Embedding, Functional Complementarity, and Traceability by Design—achieving cross-level alignment between strategic objectives, tactical performance monitoring, and operational execution. Empirical evaluation (n = 9; 14 weeks) yielded SUS scores of 76.8–82.1/100, a 76% reduction in data entry error rates, and a 78% stakeholder engagement rate, providing initial support for the framework’s practical effectiveness. Full article

Wildfires pose serious risks to ecosystems, air quality, and human health. Effective wildfire monitoring requires accurate detection and timely validation, but current approaches are often constrained by fragmented data sources, false alarms, and delays in field verification. This study presents WildfireGO, a multi-source wildfire detection and validation system that integrates crowdsourced observations, satellite hotspot data, and image-based classification in a geospatial monitoring environment. The system combines user-submitted images, Sentinel-2 imagery, and Moderate Resolution Imaging Spectroradiometer (MODIS) hotspot data processed through Google Earth Engine (GEE) to support wildfire detection and verification. Four classification models, namely Convolutional Neural Network (CNN), Random Forest (RF), K-Nearest Neighbors (KNN), and Gradient Boosting (GB), were evaluated using 10-fold cross-validation and an independent test dataset of 800 wildfire-related images. The CNN model produced the best result, with an accuracy of 97.5% on the independent test dataset. By combining image-based classification with crowdsourced reporting, the system helps screen user-submitted wildfire information and reduce false detections. Satellite-derived hotspot data provide spatial evidence for cross-checking reported events and improving spatial situational awareness for wildfire monitoring and response planning. WildfireGO supports near real-time data submission, automated processing, and interactive map-based visualization through a web-based interface. The findings indicate that combining crowdsourced reports, satellite observations, and image classification in a single geospatial system has the potential to support more reliable wildfire detection and provide practical support for environmental monitoring, disaster response, and spatial decision-making. Full article

Economic dispatch in grid-connected microgrids is challenged by the variability of renewable generation, the uncertainty of demand, and the need to simultaneously satisfy technical and economic constraints under different operating conditions. This study proposes an integrated predictive economic dispatch strategy for power grids with interconnected microgrids, structured as a unified optimization framework. The approach integrates nodal electrical modeling, Optimal Power Flow (OPF)-based optimization, multi-scenario analysis, and post-optimization feasibility verification based on performance indicators within a single decision-support structure. The methodology is applied to a modified 14-node power grid interconnected with a microgrid, where simulations are conducted under three representative load scenarios (100%, 70%, and 40%) and two operational configurations (hybrid and renewable-only), enabling a comprehensive assessment of system behavior. Results show that the hybrid configuration consistently outperforms the renewable-only case, achieving loss reductions of up to 7.3 MW, increases in spinning reserve exceeding 50 MW, and a transition from net power import to export of approximately 50 MW under high demand. Additionally, the microgrid plays an active operational role, dynamically switching between import and export modes based on load levels and the generation mix. The proposed framework enables identification of operationally efficient and technically feasible configurations by incorporating bidirectional power exchange, electrical constraints, and reserve requirements. The main contribution lies in integrating technical, operational, and interaction variables within a single deterministic Optimal Power Flow (OPF)-based assessment scheme to support decision-making in interconnected microgrid-based power grids. Full article

This paper proposes an intelligent time-series early warning framework based on a production LSTM–Transformer network for petrochemical refining processes. A cascaded encoder–decoder architecture is designed, where the LSTM extracts local temporal patterns and medium-term memory from noisy industrial data, while the Transformer models global dependencies and cross-unit interactions via multi-head self-attention. An adaptive feature fusion layer bridges the representational gap between the two networks. A multi-stage preprocessing pipeline tailored for refining MES data handles missing values, outliers, and mixed operating conditions. Using 120 variables from five units of a fluid catalytic cracking unit, the framework predicts the regenerator bed temperature up to 8 h (48 steps) ahead. Comparative experiments show that the production LSTM–Transformer achieves a mean MAE of 0.088, a mean RMSE of 0.113, and the lowest median MAPE of 19.91% among all models, outperforming standalone LSTM (MAE 0.095, MAPE 20.85%) and Transformer (MAE 0.088, MAPE 20.49%). Robustness analysis confirms stable performance under strong noise (down to 5 dB) and missing rates up to 50%, with a median MAE of 0.1027 across tags. This work provides an effective, end-to-end predictive early warning solution that balances accuracy, production importance coverage, and industrial robustness, offering a generalizable data-driven paradigm for process industries. Full article

Machine learning has become a field of growing interest in asphalt pavement engineering, spanning mix design, material characterization, performance prediction, distress detection, sustainability, quality control, and maintenance planning. However, a lack of transparency can undermine engineering trust, defensibility, and field implementation. This systematic scoping review aims to synthesize explainable artificial intelligence (XAI) and interpretable machine-learning applications for asphalt pavement materials and systems, following the PRISMA-ScR guidelines. Major scientific databases were used to identify relevant peer-reviewed studies, which were screened against a set of inclusion and exclusion criteria and categorized into seven research dimensions. A final library of 163 publications was compiled, comprising 73 core evidence studies and 90 supporting references. The review covers techniques such as SHAP, LIME, partial-dependence analysis, attention mechanisms, surrogate models, sensitivity analysis, symbolic modeling, and physically informed interpretation. The use of XAI in performance prediction, material-property interpretation, and modeling for mix design is well developed, while distress/damage analysis, life cycle sustainability, field validation, uncertainty-aware explanation, maintenance decision support, and human-centered evaluation are still relatively underdeveloped. The main contribution is a five-layer framework linking data provenance, model performance, explanation quality, physical plausibility, and decision utility. The review proposes moving from post hoc feature ranking to validated, physically centered, uncertainty-aware, and engineer-in-the-loop decision support for asphalt XAI. Full article

Predictive quality systems are central to Industry 4.0 manufacturing, yet detecting rare defects that pass established quality gates remains an open problem. This study addresses post-quality-gate failure detection in automotive brake manufacturing, where 310 faulty units (1.20%) among 25,756 production records create a naturally occurring extreme class imbalance of 1:82. Fault labels are derived from warranty reports and linked to multi-station production line measurements, while negative samples may include latent failures, motivating a recall-focused evaluation. We propose a Quality 4.0 machine learning framework that compares five resampling methods (ADASYN, SMOTE-Tomek, KMeans-SMOTE, CTGAN, and TVAE) plus a no-resampling baseline across 24 classifiers and stacking ensembles. In total, 504 configurations are tested on a held-out test set. The proposed SVM-RBF model trained on ADASYN-augmented data achieves recall of 0.871, specificity of 0.982, balanced accuracy of 0.926, and ROC-AUC of 0.952, producing only 93 false positives (FPR = 1.8%). Stacking ensembles provide alternative operating points maximizing the detection rate (93.5%) and a separate operating point with the highest discrimination capacity (ROC-AUC = 0.975). Feature importance analysis through Permutation Importance and SHAP identifies Force Increment as the leading feature under both attribution methods. Friedman and Wilcoxon tests confirm statistically significant differences among strategies. The framework offers a practical way to add predictive capability to existing quality control systems. Full article