Search Results (3,357)

The opto-mechanical automated manufacturing process, characterized by stringent process constraints, dynamic disturbances, and conflicting optimization objectives, presents significant control challenges for traditional scheduling and control approaches. We formulate the scheduling problem within a closed-loop control paradigm and propose a novel bi-level intelligent control framework integrating Deep Reinforcement Learning (DRL) and Bayesian Optimization (BO). The core of our approach is a bi-level intelligent control framework. An inner DRL agent acts as an adaptive controller, generating control actions (scheduling decisions) by perceiving the system state and learning a near-optimal policy through a carefully designed reward function, while an outer BO loop automatically tunes the DRL’s hyperparameters and reward weights for superior performance. This synergistic BO-DRL mechanism facilitates intelligent and adaptive decision-making. The proposed method is extensively evaluated against standard meta-heuristics, including Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), on a complex 20-jobs × 20-machines flexible job shop scheduling benchmark specific to opto-mechanical automated manufacturing. The experimental results demonstrate that our BO-DRL algorithm significantly outperforms these benchmarks, achieving reductions in makespan of 13.37% and 25.51% compared to GA and PSO, respectively, alongside higher machine utilization and better on-time delivery. Furthermore, the algorithm exhibits enhanced convergence speed, superior robustness under dynamic disruptions (e.g., machine failures, urgent orders), and excellent scalability to larger problem instances. This study confirms that integrating DRL’s perceptual decision-making capability with BO’s efficient parameter optimization yields a powerful and effective solution for intelligent scheduling in high-precision manufacturing environments. Full article

Decision-making under uncertainty, especially when dealing with incomplete or linguistically described data, remains a significant challenge in various fields of science and industry. The increasing complexity of real-world problems necessitates the development of mathematical models and data processing techniques that effectively address uncertainty and incompleteness. Aggregators play a key role in solving these problems, particularly in fuzzy systems, where they constitute fundamental tools for decision-making, data analysis, and information fusion. Aggregation functions have been extensively studied and applied in many fields of science and engineering. Recent research has explored their usefulness in fuzzy control systems, highlighting both their advantages and limitations. One promising approach is the use of ordered fuzzy numbers (OFNs), which can represent directional tendencies in data. Previous studies have introduced the property of direction sensitivity and the corresponding determinant parameter, which enables the analysis of correspondence between OFNs and facilitates inference operations. The aim of this paper is to examine existing aggregate functions for fuzzy set numbers and assess their suitability within OFNs. By analyzing the properties, theoretical foundations, and practical applications of these functions, we aim to identify a suitable aggregation operator that complies with the principles of OFN while ensuring consistency and efficiency in decision-making based on fuzzy structures. This paper introduces a novel aggregation approach that preserves the expected mathematical properties while incorporating the directional components inherent to OFN. The proposed method aims to improve the robustness and interpretability of fuzzy reasoning systems under uncertainty. Full article

The COVID-19 pandemic has highlighted the importance of rapid clinical decision-making to facilitate the efficient usage of healthcare resources. Over the past decade, machine learning (ML) has caused a tectonic shift in healthcare, empowering data-driven prediction and decision-making. Recent research demonstrates how ML was used to respond to the COVID-19 pandemic. This paper puts forth new computer-aided COVID-19 disease screening techniques using six classes of ML algorithms (including penalized logistic regression, random forest, artificial neural networks, and support vector machines) and evaluates their performance when applied to a real-world clinical dataset containing patients’ demographic information and vital indices (such as sex, ethnicity, age, pulse, pulse oximetry, respirations, temperature, BP systolic, BP diastolic, and BMI), as well as ICD-10 codes of existing comorbidities, as attributes to predict the risk of having COVID-19 for given patient(s). Variable importance metrics computed using a random forest model were used to reduce the number of important predictors to thirteen. Using prediction accuracy, sensitivity, specificity, and AUC as performance metrics, the performance of various ML methods was assessed, and the best model was selected. Our proposed model can be used in clinical settings as a rapid and accessible COVID-19 screening technique. Full article

The aim of this research is to develop a preliminary causal loop diagram (PCLD) of the tacit knowledge (TK) provisioning in a firm, from the knowledge-based human resource management (KB-HRM) perspective, which facilitates understanding phenomenon dynamics for designing strategies that ensure attraction, retention, and exploitation of TK. This research is qualitative and exploratory, conducted in two phases. In the first phase, we identified variables and KB-HRM processes involved by reviewing relevant documents from Web of Science to create a PCLD. The second phase involves designing this diagram. Findings suggest positive and negative interactions that favour and disfavour TK provisioning. Thus, organisational innovation is essential, requiring knowledge, particularly TK, and indispensable HR participation, as they possess and generate this knowledge. The diagram’s novelty is based on causality between twenty-three variables, grouped into three systems: (S1) acquisition of new TK, (S2) acquisition of existing TK, and (S3) loss of TK; and six KB-HRM-related processes. Therefore, PCLD presents the first step towards understanding TK provisioning complexity, as knowing TK inflows and outflows is crucial for firms to make better decisions and formulating strategies related to TK acquisition and retention. Full article

Recent advances in automated learning techniques have enhanced the analysis of biomedical signals for detecting sleep stages and related health abnormalities. However, many existing models face challenges with imbalanced datasets and the dynamic nature of evolving sleep states. In this study, we present a robust algorithm for classifying sleep states using electroencephalogram (EEG) data collected from 33 healthy participants. We extracted dynamic, brain-inspired features, such as microstates and Lempel–Ziv complexity, which replicate intrinsic neural processing patterns and reflect temporal changes in brain activity during sleep. An optimal feature set was identified based on significant spectral ranges and classification performance. The classifier was developed using a convolutional neural network (CNN) combined with gated recurrent units (GRUs) within a reinforcement learning framework, which models adaptive decision-making processes similar to those in biological neural systems. Our proposed biomimetic framework illustrates that a multivariate feature set provides strong discriminative power for sleep state classification. Benchmark comparisons with established approaches revealed a classification accuracy of 98% using the optimized feature set, with the framework utilizing fewer EEG channels and reducing processing time, underscoring its potential for real-time deployment. These findings indicate that applying biomimetic principles in feature extraction and model design can improve automated sleep monitoring and facilitate the development of novel therapeutic and diagnostic tools for sleep-related disorders. Full article

Crowdsensing data serves as a crucial resource for supporting spatiotemporal applications and services. However, its inherent heterogeneity and quality uncertainty present significant challenges for data usability assessment: the evaluation methods are difficult to standardize due to the diverse types of data; assessment dimensions are predominantly confined to internal quality attributes; and a comprehensive framework for data usability evaluation remains lacking. To address these challenges, this study proposes an innovative, multi-layered usability assessment framework applicable to six major categories of crowdsensing data: specialized spatial data, Internet of Things (IoT) sensing data, trajectory data, geographic semantic web, scientific literature, and web texts. Building upon a systematic review of existing research on data quality and usability, our framework conducts a comprehensive evaluation of data efficiency, effectiveness, and satisfaction from dual perspectives—data sources and content. We present a complete system comprising primary and secondary indicators and elaborate on their computation and aggregation methods. Indicator weights are determined through the Analytic Hierarchy Process (AHP) and expert consultations, with sensitivity analysis performed to validate the robustness of the framework. The practical applicability of the framework is demonstrated through a case study of constructing a spatiotemporal knowledge graph, where we assess all six types of data. The results indicate that the framework generates distinguishable usability scores and provides actionable insights for improvement. This framework offers a universal standard for selecting high-quality data in complex decision-making scenarios and facilitates the development of reliable spatiotemporal knowledge services. Full article

This study examines decision-making in intelligent virtual agents (IVAs) and formalizes the distinction between tactical decisions (individual actions) and strategic decisions (composed of sequences of tactical actions) using a mathematical model based on set theory and the Bellman equation. Although the equation itself is not modified, the analysis reveals that the discount factor (γ) influences the type of decision: low values favor tactical decisions, while high values favor strategic ones. The model was implemented and validated in a proof-of-concept simulated environment, namely the Snake Coin Change Problem (SCCP), using a Deep Q-Network (DQN) architecture, showing significant differences between agents with different decision profiles. These findings suggest that adjusting γ can serve as a useful mechanism to regulate both tactical and strategic decision-making processes in IVAs, thus offering a conceptual basis that could facilitate the design of more intelligent and adaptive agents in domains such as video games, and potentially in robotics and artificial intelligence as future research directions. Full article

Agrivoltaic systems (AVs) combine agricultural production with photovoltaic energy generation, enabling the dual use of land resources. This approach has gained increasing attention as a promising strategy to address pressing social, environmental, and energy challenges. Although the global expansion of AVs is accelerating, empirical research remains limited—particularly regarding farmers’ perspectives on adopting such systems. This study investigates Greek farmers’ perceptions and attitudes toward the adoption of photovoltaic technologies in agricultural practices. For this purpose, a questionnaire-based survey was conducted on a sample of 287 participants selected using purposive convenience sampling, based on predefined inclusion criteria relevant to the objectives of the study. The data were analyzed using a binary logistic regression model to identify factors positively associated with farmers’ willingness to adopt AVs. The findings reveal that 46.3% of farmers expressed willingness to adopt AVs, indicating a moderate level of acceptance. The logistic regression results indicated that higher education levels (OR = 3.53, p = 0.007), membership in farmers’ organizations (OR = 2.00, p = 0.001), and familiarity with agro-energy concepts (OR = 3.49, p = 0.016) significantly increased farmers’ motivation to engage as renewable energy producers. The model demonstrates a moderate level of explanatory power (Nagelkerke R² = 0.37). The study’s findings provide valuable insights into the key factors influencing farmers’ willingness to adopt AVs, contributing to a deeper understanding of the decision-making processes involved. Based on these findings, it is recommended that agricultural policies and community-based renewable energy initiatives focus on targeted education and extension services, the strengthening of farmers’ organizations to facilitate collective decision-making, and the implementation of focused agro-energy information campaigns. Full article

Non-invasive and intelligent technologies have been utilized to monitor agricultural systems in real time, facilitating expedient decision-making and the reduction in animal stress in diverse climatic conditions. The objective of this study was to develop a deep learning supervised model to classify Nelore cattle (Bos indicus) into two groups: those in comfort and those under thermal stress. Thirty cattle, aged between 18 and 20 months, were evaluated between June and December 2023, resulting in 676 samples collected across four daily periods (6:00, 12:00, 18:00, and 24:00). Biotic variables included rectal temperature (RT) and respiratory rate (RR), while abiotic variables included air temperature (AT) and relative humidity (RH). The neural network model exhibited an accuracy and recall of 72% but a low specificity of 42%. These metrics indicate that while the model is effective in detecting stress situations, it faces challenges in correctly identifying animals in thermal comfort, likely due to class imbalance and the need for additional input features to capture environmental adaptability. Consequently, it can be posited that supervised learning models are valuable tools for precision livestock farming, provided that discriminatory limitations are mitigated by refining input characteristics and data balancing. Full article

Background/Objectives: Pathological complete response (pCR) is an established surrogate marker of neoadjuvant chemotherapy (NACT) efficacy in breast cancer; however, reliable predictors of pCR remain limited. Immune–inflammation- and nutrition-based biomarkers derived from routine blood tests may offer accessible tools for early assessments of treatment response. This study aimed to evaluate both baseline values and dynamic (Δ) changes in multiple immune–nutritional indices to determine their predictive performance with regard topCR. Methods: A retrospective analysis was conducted on 236 early breast cancer patients who received neoadjuvant chemotherapy. Pre-treatment (B), post-treatment (A), and Δ values were calculated for the prognostic nutritional index (PNI), advanced lung cancer inflammation index (ALI), hemoglobin–albumin–lymphocyte–platelet (HALP) score, systemic inflammation response index (SIRI), pan-immune–inflammation value (PIIV), global immune–nutrition-information index (GINI), nutritional risk index (NRI), and related biomarkers. Associations with pCR were examined using chi-square testing and univariate logistic regression, and diagnostic performance was assessed through receiver operating characteristic (ROC) analysis. Results: pCR was achieved in 116 patients (49.2%). Logistic regression identified the NRI (OR = 2.336), ΔGINI (OR = 2.323), ALI (OR = 1.318), PNI (OR = 1.365), HALP score (OR = 1.217), ΔSIRI (OR = 2.207), and ΔPIIV (OR = 2.001) as significant predictors. ROC analysis showed that the NRI (AUC = 0.840) and ΔGINI (AUC = 0.807) were the strongest discriminators of pCR. In aLASSO (Least Absolute Shrinkage and Selection Operator)-penalized logistic regression with 10-fold cross-validation, the NRI and ΔGINI emerged as independent predictors of pCR (OR = 1.28 and OR = 1.23, respectively), showing acceptable calibration particularly in the moderate-to-high probability range. Conclusions: Both baseline and Δ immune–nutritional biomarkers predict pCR following NACT in breast cancer. The NRI and ΔGINI demonstrated the best diagnostic performance, whereas ΔSIRI and ΔPIIV also showed meaningful associations. Easily obtainable, low-cost indices—particularly Δ markers—may support the early identification of responders and facilitate more personalized therapeutic decision-making in breast cancer management. Full article

The advancement of autonomous cargo ships requires dependable anchoring operations, which present significant challenges stemming from reduced maneuverability at low speeds and vulnerability to anchorage disturbances. This study systematically investigates these operational constraints by developing anchoring decision-making methodologies. Safety anchorage areas were quantitatively defined through integration of ship specifications and environmental parameters. An available anchor position identification method based on grid theory, integrated with an anchorage allocation mechanism to determine optimal anchorage selection, was employed. A multi-level guided anchoring trajectory planning algorithm was developed through practical anchoring. This algorithm was designed to facilitate the scientific calculation of turning and stopping guidance points, with the objective of guiding a cargo ship to navigate towards the designated anchorage while maintaining specified orientation. An integrated autonomous anchoring system was established, encompassing perception, decision-making, planning, and control modules. System validation through digital simulations demonstrated robust performance under complex sea conditions. This study establishes theoretical foundations and technical frameworks for enhancing autonomous decision-making and safety control capabilities of intelligent ships during anchoring operations. Full article

While there are many approaches in the use of narratives for children and young people as symbolic forms of real-life education, this article specifically investigates the use of narratives as a public health communication and intervention strategy for young people. This strategy foregrounds imaginative stories based on health education messaging that are told from patient perspectives. Through a thematic analysis of 57 research articles, the article explores the themes and discursive strategies of narrative-based health communication, including digital storytelling, in supporting young people to develop coping and resilience skills. The article identifies five interrelated themes, revealing that narratives are not only effective tools for conveying health information but also foster psychosocial support, patient empowerment, and social connection. Such narratives serve as tools for facilitating change and informing decision-making across various stages of health engagement, including prevention, promotion, and management of chronic conditions. These narratives are socially transformative: in assisting young people; they also educate clinical professionals and organizations and thereby inform public health practice at large. In this way the article both consolidates and clarifies the field of literature concerned with the use of story as a health communication strategy for children and young people. Full article

Background/Objectives: Accurate drug dosage calculation in pediatric dentistry represents an essential component of everyday clinical practice. However, manual calculation methods, reliance on memory, and inconsistent pharmacological education often lead to uncertainty among practitioners. Methods: To support clinicians in this process, a mobile application—Dent.IN CALC—was developed as a rapid, evidence-based, and user-friendly tool. The app allows the input of age and weight to instantly generate recommended and maximum safe dosages of commonly prescribed antibiotics, analgesics, and local anesthetics. Additionally, it includes a list of corresponding pharmaceutical preparations available on the local market. A preliminary evaluation among sixty dentists revealed significant variability in dosage knowledge and confirmed the need for digital tools that facilitate accurate and efficient prescribing. Results: Most users rated the app as intuitive, time-saving, and highly beneficial for daily practice (mean satisfaction score 4.7 ± 0.4; 95% would recommend the app). Conclusions: The Dent.IN CALC app shows strong user acceptance and demonstrates how digital solutions can streamline workflow and support clinicians in routine pediatric pharmacological decision-making. Full article

This research investigates how hybrid review systems integrating human-generated reviews and AI-generated summaries shape consumer trust and decision-related confidence. Across three controlled experiments conducted in simulated e-commerce environments, when and how hybrid reviews enhance consumer evaluations were examined. Study 1 demonstrates that hybrid reviews, which combine the emotional authenticity of human input with the analytical objectivity of AI, elicit greater levels of review trust and decision confidence than single-source reviews. Study 2 employs an experimental manipulation of presentation order and demonstrates that decision confidence increases when human reviews are presented before AI summaries, because this sequencing facilitates more effective cognitive integration. Finally, Study 3 shows that AI literacy strengthens the positive effect of perceived diagnosticity on confidence, while information overload mitigates it. By explicitly testing these processes across three experiments, this research clarifies the mechanisms through which hybrid reviews operate, identifying authenticity and objectivity as dual mediators, and sequencing, literacy, and cognitive load as critical contextual moderators. This research advances current theories on human–AI complementarity, information diagnosticity, and dual-process cognition by demonstrating that emotional and analytical cues can jointly foster trust in AI-mediated communications. This integrative evidence contributes to a nuanced understanding of how hybrid intelligence systems shape consumer decision-making within digital marketplaces. Full article

Background/Objectives: The development of antibody–drug conjugates (ADCs) presents significant scientific and operational challenges, from optimising conjugation chemistry and linker stability to establishing robust analytical controls. Advanced analytical methods, particularly the combination of plasma stability assays with enzymatic studies, are essential for early screening and characterisation of ADC candidates. Integrating these in vitro assays with powerful data analysis software accelerates structure–activity relationship assessments and the identification of stable compounds in plasma. Methods: This article examines how combined analytical and computational approaches enhance candidate selection by offering valuable insights into the metabolic fate and stability risks of ADCs. Results: Our research shows correlation between in vitro stability profiles and in vivo pharmacokinetic (PK) data, demonstrating the predictive power of early-stage analytical studies. Implementation of software-driven visualisation and analysis enables faster, data-informed decision making, streamlining the triage process to prioritise candidates with optimal PK and pharmacodynamics (PD) characteristics. Conclusions: These findings highlight the critical need for integrated in vitro analytics and computational tools in efficient ADC development, supporting the selection of candidates with the greatest potential for clinical success and facilitating a more effective and accelerated path from discovery to clinical application. Full article