Accurate remaining useful life (RUL) prediction of rolling bearings is essential for predictive maintenance and reliable operation of industrial rotating machinery. However, variations in operating conditions introduce substantial differences in vibration characteristics and degradation patterns, limiting the applicability of models trained under individual operating conditions. This study investigates a multi-source transfer learning approach for bearing RUL prediction across different operating conditions. A framework termed deep residual shrinkage network with multi-source weighted screening (DRSN-MW) was developed by integrating a deep residual shrinkage network with multi-source domain screening, subdomain alignment, and physical monotonicity constraints. An adaptive feature extraction module was constructed to capture degradation characteristics from vibration signals, while weighted extension correlation and dynamic time warping (DTW) were combined to identify source domains with similar degradation patterns. Degradation-stage partitioning and entropy-weighted local maximum mean discrepancy (LMMD) were employed to align source and target features within corresponding degradation stages. Physical monotonicity and decision consistency constraints were further incorporated to regulate the predicted RUL trajectories. The framework was evaluated using the 2012 Prognostics and Health Management (PHM2012) bearing dataset and Xi’an Jiaotong University–Sumyoung (XJTU-SY) bearing dataset under single-source and multi-source transfer scenarios. Average mean absolute errors (MAEs) of 0.126 and 0.129 and root mean square errors (RMSEs) of 0.150 and 0.156 were obtained on the two datasets, respectively. On the PHM2012 dataset, the proposed method reduced the average root mean square error by 33.6% compared with the strongest baseline in the reported comparison. The results indicate that combining source-domain screening with degradation-stage alignment and physical constraints can improve RUL prediction across operating conditions. The proposed framework provides a data-driven approach to bearing health prognostics and predictive maintenance in industrial rotating machinery.

Human-robot interaction has become a fundamental component of Industry 5.0. Although recent advances in generative artificial intelligence have substantially improved contextual reasoning and interactive capabilities, existing human-robot interaction decision-making frameworks remain predominantly task-oriented and rarely account for human emotional responses during collaborative decision processes. To address this limitation, a regret-based human-robot interaction framework driven by generative artificial intelligence was proposed for adaptive decision-making in Industry 5.0 environments. A dual-regret mechanism was introduced by jointly modeling human regret $\left(R_h\right)$ and robot task regret $\left(R_{t r}\right)$. Contextual knowledge was dynamically retrieved through a retrieval-augmented generation architecture, enabling interaction strategies to be generated according to task conditions, historical user preferences, and evolving human emotional states. Personalized regret profiles were constructed, while explainable counterfactual action generation was incorporated. Furthermore, real-time reinforcement learning was employed to continuously minimize cumulative regret. Experimental evaluations conducted under multiple interaction scenarios demonstrated that the proposed framework effectively improved decision quality, enhanced user satisfaction, and increased task execution efficiency. Compared with conventional human-robot interaction decision-making approaches, cumulative interaction regret was reduced by approximately 20%, while greater robustness and adaptability were achieved under dynamically changing operational conditions. These findings suggest that the proposed framework provides an effective paradigm for integrating emotional intelligence, generative reasoning, and adaptive optimization into human-centered robotic systems, thereby offering a promising decision-making architecture for next-generation collaborative robotics in Industry 5.0.

Prediction of product life cycle (PLC) at the early stage is important to support the planning of production, inventory control, launch timing, and decisions of product renewal. However, newly introduced batik products often have little historical sales data; therefore, it is difficult to apply conventional forecasting methods. This study introduced the Diffusion Bubble Model for Product Diffusion (DBM-PD) as a low-data diffusion model for predicting cumulative product adoption in batik fashion small and medium enterprises (SMEs). The DBM-PD adapts the bubble-decomposition logic into a product diffusion context, where each adoption bubble represents a possible market response at a specific stage of the PLC. To assess the model performance, this study compared the DBM-PD with three benchmark models: the Bass Diffusion Model, Triangle Model, and Circle Model. Four datasets of PLC from batik fashion products were used as empirical cases. Each dataset was transformed into a cumulative adoption ratio to ensure comparable model evaluation. The results showed that the DBM-PD achieved the lowest prediction error across all four datasets. The Bass Diffusion Model ranked second, indicating that innovation and imitation effects remain relevant in batik product adoption. The Triangle and Circle Models were useful as simple geometric benchmarks, but their assumptions were less able to capture irregular adoption patterns. These findings revealed that the DBM-PD could establish a more flexible prediction structure for estimating PLC at the early stage when only limited data were available. A parameter sensitivity check discovered that the number and width of bubbles affected in-sample accuracy: additional bubbles could reduce errors but also increased model complexity, while the seven-bubble, $\sigma=0.08$ configuration offered a transparent balance between accuracy and parsimony. The root mean square error (RMSE) rankings were identical across the four datasets, and a Friedman test indicated a significant overall difference among the models $\left(\chi^2(3)=12.00, p=0.007\right)$. This study contributes to the management of technology-based PLC by offering a practical framework of diffusion modelling for batik fashion SMEs.

Traditional public health disinfection tasks relying on fixed-area coverage often suffer from resource waste, delayed intervention, and low response efficiency. This study proposes a case-density-driven closed-loop intelligent strategy for air-ground-human collaborative disinfection, establishing an end-to-end framework from case perception to task scheduling. Firstly, a spatiotemporal risk field is constructed based on reported case data and population mobility information, and high-risk areas are adaptively identified and prioritized through dynamic evaluation. Secondly, for coordinated execution by unmanned aerial vehicles (UAVs), ground vehicles, and personnel, a multi-objective coupled optimization model is designed, targeting coverage efficiency, suppression timeliness, path conflicts, and resource cost to generate executable collaborative schedules. Furthermore, a closed-loop execution mechanism is developed, enabling real-time rolling re-planning and adaptive strategy correction in response to task feedback, unexpected disturbances (area lockdown, equipment failure, chemical shortage), and risk field updates. Experimental results demonstrate that the proposed closed-loop approach significantly improves coverage, suppression time, and resource utilization compared with traditional static scheduling and single-entity planning methods across multiple scenarios, and exhibits robustness against environmental uncertainties and resource disturbances. This framework provides a feasible theoretical and methodological foundation for intelligent, precise, and resilient public health disinfection operations.

Unmanned aerial vehicles (UAVs) have gained increasing importance due to their expanding application areas and operational flexibility. Selecting the most suitable UAV, however, represents a complex multi-criteria decision-making (MCDM) problem that involves numerous technical and performance-related factors. This study addresses the UAV selection problem by employing four distinct MCDM approaches: Evidential fuzzy MCDM based on Belief Entropy, Intuitionistic Fuzzy Dempster-Shafer Theory (DST), Spherical Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), and Type-2 Neutrosophic Fuzzy CRITIC-MABAC. Each method incorporates different fuzzy set theories, while a common seven-point linguistic scale is utilized to ensure consistency across models. The evaluation criteria were determined through a comprehensive literature review, and expert opinions were collected from experienced UAV pilots and technical personnel. The analysis identified the most suitable UAV alternative among the considered options. Sensitivity analyses were conducted to assess the robustness of the obtained results. The findings demonstrate that the proposed framework enables a simultaneous comparison of different fuzzy set environments on a unified linguistic scale. Overall, the results are consistent, reliable, and practically applicable, offering valuable insights and methodological contributions to the field of UAV selection and fuzzy MCDM applications.

Automated unmanned aerial vehicle (UAV) docking systems play an important role in unattended industrial inspection and monitoring. However, coordinating mechanical movements, maintaining landing-platform stability, and securing aircraft during deployment and recovery remain challenging. This study investigates the mechanical design and coordinated motion control of a four-position UAV docking system. An integrated architecture comprising a sliding roof, a three-degree-of-freedom (3-DOF) landing platform, and a mechanical centering and locking mechanism was developed. The roof and centering drives were analysed through mechanical load calculations and parameter sensitivity analysis, while a supervisory control framework was formulated to coordinate actuator movements through position feedback and operating interlocks. A representative three-actuator model was also established to evaluate platform levelling under static inclination and periodic disturbances using proportional (P) and proportional-derivative (PD) control. The calculated roof resistance and driving torque were 250 N and 6.75 $\mathrm{N\cdot m}$, respectively, while the centering resistance was 325 N and the estimated motor torque was 4.51 $\mathrm{N\cdot m}$ under an assumed unit transmission ratio. In the simplified numerical model, P and PD control achieved static settling times of 1.02 s and 1.21 s, respectively. Under periodic disturbances, the combined root-mean-square (RMS) attitude error decreased from 2.599$^\circ$ without compensation to 1.299$^\circ$ with P control and 1.185$^\circ$ with PD control. The results indicate that coordinated mechanical operation and feedback-based platform levelling can be integrated within a common docking framework. The study provides a basis for the development of unattended industrial UAV docking systems, although the predicted control performance requires validation using the actual platform geometry and actuator characteristics.

The digital transformation of logistics is increasingly driven by interconnected technologies that support workforce coordination, data-driven decision-making, operational integration, and human-centered industrial management. However, logistics companies face difficulties in selecting digital technologies because their adoption involves simultaneous technological, organizational, economic, and employee-related considerations. This study develops an intelligent multi-criteria decision-support framework for evaluating and prioritizing digital technologies for workforce management in logistics companies. Five technology alternatives—artificial intelligence (AI)-based human resources (HR) systems, Internet of Things (IoT) and wearable technologies, enterprise resource planning (ERP)/HR information system (HRIS), digital learning and training, and digital workforce management—are assessed against eight criteria covering implementation complexity, employee productivity, employee satisfaction and retention, implementation and operating costs, scalability and flexibility, data security and privacy risks, legal and ethical risks, and integration capability. The criteria importance through intercriteria correlation (CRITIC) method is applied to derive objective criterion weights from the decision matrix, while interactive and multicriteria decision making (TODIM) is used to rank the alternatives by incorporating the asymmetric effects of gains and losses in the decision process. The results show that Digital Workforce Management achieves the highest overall dominance value (1.000), followed by Digital Learning and Training (0.967) and ERP/HRIS (0.921) systems, whereas AI-based HR systems and IoT and Wearable Technologies rank fourth and fifth, respectively. Robustness analysis using alternative weighting schemes and the technique for order preference by similarity to ideal solution (TOPSIS) and weighted aggregated sum product assessment (WASPAS) methods confirms a relatively stable separation between the three higher-ranked and two lower-ranked alternatives, although the relative positions of the leading technologies vary across methodological settings. The findings demonstrate that digital technology selection in logistics should be treated as an industrial intelligence problem in which operational integration, workforce performance, organizational adaptability, and human-centered risks are evaluated jointly. The proposed framework provides structured decision support for logistics organizations seeking to align digital workforce technologies with broader Industry 4.0 and Industry 5.0 transformation objectives.

Intelligent expressway management requires reliable prediction of travellers' route choices and quantitative assessment of their responses to operational interventions. This study investigates a data-driven route choice framework that links large-scale toll transaction data with ensemble learning to support differentiated tolling and route management. Actual vehicle routes were reconstructed from toll transaction records, electronic toll collection (ETC) gantry records, and expressway network topology, from which revealed-preference candidate route sets were derived. A total of 28 features were constructed to characterize route attributes, relative differences among candidate routes, choice-set composition, and trip attributes. A Light Gradient Boosting Machine (LightGBM) model was then developed using each “trip $\times$ candidate route” pair as the unit of observation, and its predictive performance was compared with random forest, Extreme Gradient Boosting (XGBoost), multinomial logit (MNL), nested logit, and binary logistic regression. The empirical analysis used 329,699 trips from the Guangdong expressway network, including 32,473 trips in the test set. The Light Gradient Boosting Machine (LightGBM) model achieved a route-level hit rate of 85.71%, exceeding the random-guessing benchmark by 43.81 percentage points and outperforming the three conventional discrete-choice and logistic models, while showing performance comparable to random forest and XGBoost. The sensitivity analysis further showed that toll responses varied substantially with a route’s competitive position, choice-set size, and vehicle type. Routes with baseline choice probabilities of 50%–80% were more responsive to toll changes than strongly dominant routes, while trucks showed greater toll sensitivity than cars. The results demonstrate that large-scale operational data and ensemble learning can provide a reproducible framework for route choice prediction and scenario-based evaluation of differentiated toll policies. The proposed framework supports data-driven decision-making for intelligent expressway operations and provides a practical basis for evaluating route-level traffic management strategies.