Emotion recognition in texts is an important problem in modern natural language processing, currently dominated by transformer architectures. However, their internal mechanisms remain a black box, and classification quality — especially in complex cases — still has room for improvement. This paper proposes a novel hybrid approach that combines the capabilities of modern language models with a deep analysis of their vector representations by adapting the classical statistical pattern recognition method based on decomposition in a space with a generating element (Kunchenko space). The method produces a new set of statistical-geometric features derived from the reconstruction error of vector representations of text messages belonging to the corresponding classes. Experiments conducted on Ukrainian (EMOBENCH-UA) and English (EmoEvent) datasets demonstrate that the proposed hybrid approach yields a statistically significant improvement in classification accuracy. The study also identifies key conditions for the method’s effectiveness: it acts as a powerful refinement mechanism for models fine-tuned on the target task. However, the method is ineffective when applied to raw, non-specialized vector representations. Furthermore, the results indicate that the choice of basis functions for reconstruction is a crucial hyperparameter. This fact allows for adapting the method to the specific geometry of the data space.
Synthetic electrocardiogram generation serves medical AI applications requiring privacy-preserving data sharing and training dataset augmentation. Current diffusion-based methods achieve high generation quality but require hundreds of neural network evaluations during sampling, creating computational bottlenecks for clinical deployment. We propose FlowECG, a flow matching approach that adapts the SSSD-ECG architecture by replacing the iterative diffusion process with continuous flow dynamics. Flow matching learns direct transport paths from noise to data distributions through ordinary differential equation solving. We evaluate our method on the PTB-XL dataset using Dynamic Time Warping, Wasserstein distance, Maximum Mean Discrepancy, and spectral similarity metrics. FlowECG matches SSSD-ECG performance at 200 neural function evaluations, outperforming the baseline on three metrics. The key finding shows that FlowECG maintains generation quality with substantially fewer sampling steps, achieving comparable results with 10–25 evaluations compared to 200 for diffusion methods. This efficiency improvement reduces computational requirements by an order of magnitude while preserving physiologically realistic 12-lead ECG characteristics. The approach enables practical deployment in resource-limited clinical settings where real-time generation or large-scale synthetic data creation is needed.
This paper introduces a unified theoretical perspective that views deep generative models as probability transformation functions. Despite the apparent differences in architecture and training methodologies among various types of generative models - autoencoders, autoregressive models, generative adversarial networks, normalizing flows, diffusion models, and flow matching - we demonstrate that they all fundamentally operate by transforming simple predefined distributions into complex target data distributions. This unifying perspective facilitates the transfer of methodological improvements between model architectures and provides a foundation for developing universal theoretical approaches, potentially leading to more efficient and effective generative modeling techniques.
Labor stimulation is a key element of human resource management in hospitality organizations, where the quality of service directly depends on employee engagement. Despite active interest in the topic of motivation in both domestic and international research, the specifics of the hotel industry remain insufficiently explored; in particular, there is a noticeable lack of interdisciplinary studies that integrate managerial, psychological, and socionic approaches. The relevance of the issue is reinforced by industry-specific challenges such as staff shortages and high turnover rates. The aim of the study is to identify optimal forms and tools of labor stimulation, taking into account the personal characteristics of hotel employees: objective (gender, age, marital status, work experience) and subjective (personality type according to socionics). The methods applied include surveys, data analysis, and generalization. The results confirm the proposed hypothesis: personalized stimulation programs, aligned with employees’ demographic and typological profiles, increase motivation and employment stability. Based on empirical data, a conceptual model of personnel segmentation and selection of a “portfolio of incentives” is proposed: a combination of material (allowances, service quality bonuses, guest feedback rewards) and non-material tools (recognition and public feedback, individualized training and career development paths, mentoring, flexible schedules, participation in decision-making, and expanded areas of responsibility). The practical significance lies in the development of a step-by-step algorithm: diagnostic survey → employee profiling → selection and testing of incentive sets → regular evaluation of effectiveness and adjustment. The limitations of the study are determined by the sample context and cross-sectional design; prospects for further research include expanding the geography and types of hospitality facilities, conducting longitudinal studies, and testing the model in different organizational cultures.
This paper addresses energy efficiency in industrial robotic manipulators under the paradigm of sustainable manufacturing and Industry 4.0/5.0. We first synthesize recent advances in energy-aware actuation, regenerative hardware, trajectory optimization, and adaptive/predictive control – including AI-based methods – to motivate integrated hardware–software solutions. We then present an experimental study on a SCARA robot used for screw-cap sealing. Using the robot’s internal sensors and RT Toolbox3, currents and voltages of all four servo axes (J1–J4) were logged at 3 kHz over full work cycles across speed settings from 10
