Search Results (21,179)

Generating realistic and diverse driving scenarios is essential for effective scenario-based testing and validation in autonomous driving and the development of driver assistance systems. Traditionally, parametric models are used as standard approaches for scenario generation, but they require detailed domain expertise, suffer from scalability issues, and often introduce biases due to idealizations. Recent research has demonstrated that AI models can generate more realistic driving scenarios with reduced manual effort. However, these models typically focused on single scenario types, such as cut-in maneuvers, which limits their applicability to diverse real-world driving situations. This paper, therefore, proposes a unified generative framework that can simultaneously generate multiple types of driving scenarios, including cut-in, cut-out, and cut-through maneuvers from both directions, thus covering six distinct driving behaviors. The model not only learns to generate realistic trajectories but also reflects the same statistical properties as observed in real-world data, which is essential for risk assessment. Comprehensive evaluations, including quantitative metrics and visualizations from detailed latent and physical space analyses, demonstrate that the unified model achieves comparable performance to individually trained models. The shown approach reduces modeling complexity and offers a scalable solution for generating diverse, safety-relevant driving scenarios, supporting robust testing and validation. Full article

Reliable fault diagnosis of milling machines is essential for maintaining operational stability and cost-effective maintenance; however, it remains challenging due to limited labeled data and the highly non-stationary nature of acoustic emission (AE) signals. This study introduces an optimized Few-Shot Learning framework (FSL) that integrates time–frequency analysis with attention-guided representation learning and distribution-aware classification for data-efficient fault detection. The framework converts AE signals into Continuous Wavelet Transform (CWT) scalograms, which are processed using a self-attention-enhanced ResNet-50 backbone to capture both local texture features and long-range dependencies in the signal. Adaptive prototype computation with learnable importance weighting refines class representations, while Mahalanobis distance-based matching ensures robust alignment between query and prototype embeddings under limited sample conditions. To further strengthen discriminability, contrastive loss with hard negative mining enforces compact intra-class clustering and clear inter-class separation. Comprehensive experiments under 7-way 5-shot settings and 5-fold stratified cross-validation demonstrate consistent and reliable performance, achieving a mean accuracy of 98.86% ± 0.97% (95% CI: [98.01%, 99.71%]). Additional evaluations across multiple spindle speeds (660 rpm and 1440 rpm) confirm that the model generalizes effectively under varying operating conditions. Grad-CAM++ activation maps further illustrate that the network focuses on physically meaningful fault-related regions, enhancing interpretability. The results verify that the proposed framework achieves robust, scalable, and interpretable fault diagnosis using minimal labeled data, offering a practical solution for predictive maintenance in modern intelligent manufacturing environments. Full article

Calibrating cameras accurately requires the identification of projection and distortion models that effectively account for lens-specific deviations. Conventional formulations, like the pinhole model or radial–tangential corrections, often struggle to represent the asymmetric and nonlinear distortions encountered in complex environments such as autonomous navigation, robotics, and immersive imaging. Although neural methods offer greater adaptability, they demand extensive training data, are computationally intensive, and often lack transparency. This work introduces a symbolic model discovery framework guided by physical knowledge, where symbolic regression and genetic programming (GP) are used in tandem to identify calibration models tailored to specific optical behaviors. The approach incorporates a broad class of known distortion models, including Brown–Conrady, Mei–Rives, Kannala–Brandt, and double-sphere, as modular components, while remaining extensible to any predefined or domain-specific formulation. Embedding these models directly into the symbolic search process constrains the solution space, enabling efficient parameter fitting and robust model selection without overfitting. Through empirical evaluation across a variety of lens types, including fisheye, omnidirectional, catadioptric, and traditional cameras, we show that our method produces results on par with or surpassing those of established calibration techniques. The outcome is a flexible, interpretable, and resource-efficient alternative suitable for deployment scenarios where calibration data are scarce or computational resources are constrained. Full article

The global reliance on coal-fired power generation continues to produce vast quantities of fly ash, exceeding 500 million tons annually, with limited recycling rates. Given its high silica (SiO₂) and alumina (Al₂O₃) contents, fly ash represents a promising alternative raw material for sustainable refractory production. In this study, four aluminosilicate refractory castables were formulated using bauxite, calcined flint clay, kyanite, calcium aluminate cement, and microsilica, in which the fine fraction of flint clay was partially replaced by 0, 5, 10, and 15 wt.% fly ash. The specimens were dried at 120 °C and sintered at 850, 1050, and 1400 °C for 4 h. Their physical and mechanical properties were systematically evaluated, while phase evolution and microstructural development were analyzed through X-ray diffraction (XRD) and scanning electron microscopy (SEM). The results revealed that the incorporation of 10 wt.% fly ash (10FAC) provided the optimal balance between densification and strength, achieving compressive strengths of 45.0 MPa and 65.3 MPa after sintering at 1050 °C and 1400 °C, respectively. This improvement is attributed to the formation of a SiO₂-rich liquid phase derived from fly ash impurities, which promoted the in-situ crystallization of acicular secondary mullite and enhanced interparticle bonding among corundum grains. The 10FAC castable also exhibited only a slight increase in apparent porosity (26.39%) compared with the reference (25.74%), indicating effective sintering without excessive vitrification. Overall, the study demonstrates the technical viability of using fly ash as a sustainable substitute for flint clay in refractory castables. The findings contribute to advancing circular economy principles by promoting industrial waste valorization and resource conservation, offering a low-carbon pathway for the development of high-performance refractory materials for structural and thermal applications in energy-intensive industries. Full article

Physical therapy is a critical component of medical rehabilitation, aiding recovery from conditions such as stroke, spinal cord injuries, and musculoskeletal disorders. Effective rehabilitation requires precise monitoring of patient performance to ensure exercises are executed correctly and progress is accurately assessed. This paper presents a novel automated system for controlling the rehabilitation process and evaluating physical therapy exercise quality using computer vision and a customized Human Skeleton-based Balanced Time Warping algorithm. The proposed method quantitatively assesses the similarity between a physiotherapist and patient performance by analyzing skeletal motion data extracted from RGB-D video sequences without requiring pre-alignment or sensor-specific calibration. A motion-dependent, weighted Euclidean distance between 3D skeletal models is used to compute pose dissimilarity, while a modified DTW approach aligns temporal sequences and evaluates dynamic consistency. The total dissimilarity measure is a balanced combination of posture (DP) and dynamics (DT) components. Evaluated on a custom dataset of 136 video recordings from 23 participants performing exercises in sitting and standing positions under varying performance accuracy levels (“good,” “intermediate,” and “bad”), the system demonstrates the strong clustering of accuracy levels. Proposed dissimilarity, together with a fixed reference element (physiotherapist), induces a natural non-strict order on the set of distances between patients and physiotherapists. A high value of Spearman’s rank correlation coefficient between computed dissimilarity and execution accuracy (0.977) indicates that this method is suitable for assessing exercise performance accuracy and for adequately evaluating the patient’s rehabilitation progress. The method enables objective, real-time feedback, reduces therapist workload, and supports remote monitoring, offering a scalable solution for personalized rehabilitation. Future work will involve clinical validation with post-stroke and cardiac patients. Full article

To enhance the thermo-mechanical coupling performance of heavy-duty bearings with smart sensing capability in electric shovel applications, this study proposes a multi-objective optimization methodology for sensor-embedded bearing rings incorporating smart sensor-embedded grooves. Driven by multi-physics coupling analysis and experimental validation, a coupled thermal–mechanical model integrating frictional heat generation, heat transfer, and stress response was established. Parametric finite element simulations were conducted, with varying groove depths and axial positions. A comprehensive performance index combining three metrics—maximum temperature, equivalent stress, and principal strain—was formulated to evaluate design efficacy. Experimental tests on thermal and strain responses were employed to validate the simulation model confirming its predictive ability. Among the 21 parameter combinations, the configuration featuring an 8 mm groove depth located 20 mm from the large end face exhibited relatively optimal synergy across thermal dissipation, structural strength, and strain sensitivity. The proposed framework provides a certain theoretical and practical guidance for the design and optimization of the sensor-embedded groove structure in intelligent heavy-duty bearings. Full article

Macroalgae have low nutrient bioavailability, often requiring pretreatments—physical, chemical, or biological—typically using low-solid loading hydrolysis, which produces separate liquid and solid phases. In contrast, high-solid loading hydrolysis offers a single-phase alternative, though it remains underexplored for macroalgae. This study evaluated the effectiveness of high-solid loading hydrolysis for breaking polysaccharides and increasing the availability of nutrients and antioxidant compounds in Codium tomentosum. Treatments using mixtures containing 25% dry biomass and 75% water or 0.5N and 1N NaOH, autoclaved for 30 or 60 min, were performed. Among the tested treatments, high-solid loading alkaline autoclaved treatment (1N NaOH, 60 min) was most effective in reducing neutral detergent fiber and enhancing the availability of bioactive compounds, particularly soluble proteins and phenols. Based on these results, a sequential enzymatic hydrolysis with Natugrain^® at 0.2 and 0.4% was also applied to pre-treated C. tomentosum with water or 1N NaOH. Enzymatic hydrolysis after autoclaving had no major effect on fiber, soluble protein, or ash, but increased phenol levels. In conclusion, high-solid loading alkaline treatment (1N NaOH) followed by enzymatic hydrolysis with Natugrain^® enzyme reduced fiber content and enhanced soluble protein and phenolic compounds, thereby improving the nutritional and functional potential of C. tomentosum for inclusion in animal feeds. Full article

The central purpose of this study is to develop and validate an advanced numerical model capable of simulating the vibrational behavior of the operator’s seat in a tractor-type agricultural vehicle designed for operation in protected horticultural environments, such as vegetable greenhouses. The three-dimensional (3D) model of the seat was created using SolidWorks 2023, while its dynamic response was investigated through Finite Element Analysis (FEA) in Altair SimSolid, enabling a detailed evaluation of the natural vibration modes within the 0–80 Hz frequency range. Within this interval, eight significant natural frequencies were identified and correlated with the real structural behavior of the seat assembly. For experimental validation, direct time-domain measurements were performed at a constant speed of 5 km/h on an uneven, grass-covered dirt track within the research infrastructure of INMA Bucharest, using the TE-0 self-propelled electric tractor prototype. At the operator’s seat level, vibration data were collected considering the average anthropometric characteristics of a homogeneous group of subjects representative of typical tractor operators. The sample of participating operators, consisting exclusively of males aged between 27 and 50 years, was selected to ensure representative anthropometric characteristics and ergonomic consistency for typical agricultural tractor operators. Triaxial accelerometer sensors (NexGen Ergonomics, Pointe-Claire, Canada, and Biometrics Ltd., Gwent, UK) were strategically positioned on the seat cushion and backrest to record accelerations along the X, Y, and Z spatial axes. The recorded acceleration data were processed and converted into the frequency domain using Fast Fourier Transform (FFT), allowing the assessment of vibration transmissibility and resonance amplification between the floor and seat. The combined numerical–experimental approach provided high-fidelity validation of the seat’s dynamic model, confirming the structural modes most responsible for vibration transmission in the 4–8 Hz range—a critical sensitivity band for human comfort and health as established in previous studies on whole-body vibration exposure. Beyond validating the model, this integrated methodology offers a predictive framework for assessing different seat suspension configurations under controlled conditions, reducing experimental costs and enabling optimization of ergonomic design before physical prototyping. The correlation between FEA-based modal results and field measurements allows a deeper understanding of vibration propagation mechanisms within the operator–seat system, supporting efforts to mitigate whole-body vibration exposure and improve long-term operator safety in horticultural mechanization. Full article

Objectives: The present study analyzes the effects of a high-intensity interval training (HIIT) program based on the Tabata method on physiological and psychological variables in contemporary dancers (n = 10) and sedentary individuals (n = 8), who performed a 10-week protocol, with sessions of self-loading exercises structured in intervals of 20 s of effort and 10 s of rest three times a week. Methods: Parameters of body composition, muscle strength, aerobic and anaerobic capacity, heart rate variability, as well as perceptions of health, anxiety, stress, sleep quality, and levels of physical activity and sedentary lifestyle were evaluated. Results: The results showed that no significant changes occurred in most body composition variables, except for visceral fat, where group differences were observed (F = 5.66, p = 0.030, η²ₚ = 0.261). In the indicators of strength and power, the dancers improved the height and relative power of the jump (F = 5.996, p = 0.026, η²ₚ = 0.273), while the sedentary ones increased the strength of the handgrip (p = 0.023). In terms of functional performance, both groups significantly increased anaerobic endurance (F = 10.374, p = 0.005, η²ₚ = 0.393), although no changes were recorded in maximal oxygen consumption or heart rate variability (p > 0.05). On a psychological level, improvements in healthy lifestyle habits and a decrease in the trait anxiety variable were evidenced in dancers (p = 0.023), while in sedentary participants no relevant effects were found. Conclusions: In conclusion, the Tabata protocol may represent an efficient and complementary strategy to enhance strength, anaerobic power, and psychological well-being, particularly among dancers. The observed improvements suggest potential benefits related to movement quality, injury prevention, and general physical conditioning. Full article

As robotic systems become increasingly integrated into daily life, the need for user experience (UX) assessment methods that are both privacy-conscious and suitable for embedded hardware platforms has grown. Traditional UX evaluations relying on vision, audio, or lengthy questionnaires are often intrusive, computationally demanding, or impractical for low-power devices. In this study, we introduce a novel sensor-based method for assessing UX through direct physical interaction. We designed a robot lamp with a force-sensing button interface and conducted a user study involving controlled robot errors. Participants interacted with the lamp during a reading task and rated their UX on a 7-point Likert scale. Using force and time data from button presses, we correlated force and time data to user experience and demographic information. Our results demonstrate the potential of bodily interaction metrics as a viable alternative for UX assessment in human-robot interaction, enabling real-time, embedded, and privacy-aware evaluation of user satisfaction in robotic systems. Full article

Objective: This short-term prospective observational study aimed to evaluate the efficacy of vestibular rehabilitation therapy (VRT) in Patients Diagnosed with Persistent Postural-Perceptual Dizziness (PPPD). Methods: Given the exploratory design, the small sample (n = 25) and absence of a formal power calculation limit precision, findings should be interpreted as preliminary, and confirmatory trials are warranted. Patients were assessed before (T1), immediately after a five-week vestibular rehabilitation program (T2), and again three months later without continued therapy (T3). Clinical symptoms were assessed using the Dizziness Handicap Inventory (DHI). A Generalized Estimating Equations (GEE) model was used to analyze changes in dizziness-related physical, emotional, and functional impacts over time, accounting for sex and its interaction with time. Statistical significance was tested using the Wald test, with results reported as estimated means and standard errors (SEs), and a significance level set at p ≤ 0.05. Results: The mean age of participants was 44.48 ± 14.43 years, and the majority were women (84%). In the functional domain, the mean score difference was 6.69 points between T1 and T2 (p = 0.018), 7.11 points between T1 and T3 (p = 0.013), and 0.42 points between T2 and T3 (p > 0.05). In the emotional domain, the mean difference was 4.12 points between T1 and T2 (p = 0.008), 4.40 points between T1 and T3 (p = 0.005), and 0.29 points between T2 and T3 (p > 0.05). In the physical domain, the mean difference was 3.77 points between T1 and T2 (p = 0.024), 4.32 points between T1 and T3 (p = 0.009), and 0.55 points between T2 and T3 (p > 0.05). For the total score, the mean difference was 14.58 points between T1 and T2 (p = 0.005), 15.83 points between T1 and T3 (p = 0.003), and 1.25 points between T2 and T3 (p > 0.05). The moment variable had a statistically significant effect across all domains. Sex had a significant effect only in the emotional domain, with women consistently reporting higher scores than men. Conclusions: This study demonstrates that a five-week vestibular rehabilitation program significantly improves the physical, emotional, and functional impacts of dizziness in patients with PPPD, with these benefits largely sustained three months after the intervention. Emotional improvements were particularly notable among women, highlighting potential sex-related differences in response to treatment. These findings underscore the importance of addressing emotional health in PPPD management and support the long-term effectiveness of vestibular rehabilitation in improving patient outcomes. Full article

Expanded polystyrene (EPS) concrete has broad application potential in energy-efficient buildings due to its low density and excellent thermal insulation performance. However, a significant nonlinear trade-off exists between its compressive strength and thermal conductivity. Existing studies are mainly based on empirical mix design or single-objective optimization, and the employed modeling methods generally lack interpretability. To address this challenge, this study proposes a multi-objective optimization model (MOPIA-RA) based on physics-informed constraints and an intelligent evolutionary algorithm, aiming to solve the nonlinear contradiction among compressive strength, thermal conductivity, and production cost encountered in practical engineering. A comprehensive dataset covering different cementitious materials, EPS contents, and particle sizes was established based on experimental data, and a surrogate model (PIA-RA) was developed using this dataset. Finally, the Shapley additive explanation (SHAP) method was used to quantitatively evaluate the effects of key materials on compressive strength and thermal conductivity. The results show that the proposed PIA-RA model achieved coefficients of determination (R²) of 0.95 and 0.98 for predicting compressive strength and thermal conductivity, respectively; EPS particle size was the main factor affecting performance, with a contribution rate of 69%, while EPS content also played an important regulatory role, with a contribution rate of 29%. Based on the constructed MOPIA-RA model, it is possible to effectively resolve the multi-objective trade-offs among strength, thermal performance, and cost in EPS concrete and achieve precise mix design. The proposed MOPIA-RA model not only realizes multi-objective optimization among compressive strength, thermal performance, and cost, but also establishes a physics-informed and interpretable methodology for concrete material design. This model provides a scientific basis for the mix-design optimization of EPS concrete. Full article

Apple juice is widely consumed across global beverage markets. Its colour and cloudy appearance play a crucial role in consumer perception. Various physical treatments are available to modify juice turbidity and preserve colour, among which filtration and high-pressure homogenisation are considered the most respectful to the raw juice composition. In this study, red apple juice from the Kissabel^® Rouge cultivar was filtered using membranes ranging from 100.0 to 0.2 μm and homogenised at pressures from 20 to 60 MPa. The physicochemical properties were then evaluated after 205 days of storage at two different temperatures. Microfiltration (<5.0 μm) increased juice lightness (87 vs. 66), but compromised cloud and colour stability by reducing cloudiness by 15 days compared with the unfiltered juices. Homogenisation increased turbidity, both in absolute value and during storage, which is typically appreciated in 100% apple juices. Finally, colloidal stability was affected by both treatments; combining mild filtration with low homogenisation pressure yielded the highest colloidal repulsion (−16.3 mV). Elevated storage temperatures generally diminished juice quality in terms of colour tone and intensity, and accelerated particle sedimentation. Full article

Background: Three-dimensional (3D) printed scaffolds have emerged as promising tools for bone regeneration, but the optimal structural design and pore size remain unclear. Polylactic acid (PLA) reinforced with graphene oxide (GO) offers enhanced mechanical and biological performance, yet systematic evaluation of architecture and pore size is limited. Methods: Two scaffold architectures (lattice-type and dode-type) with multiple pore sizes were fabricated using UV-curable PLA/GO resin. Physical accuracy, porosity, and mechanical properties were assessed through compression and fatigue testing. Based on in vitro screening, four pore sizes (930 μm, 690 μm, 558 μm, 562 μm) within the dode-type structure were analyzed. The 558 μm and 562 μm scaffolds, showing distinct fracture thresholds, were further evaluated in rat and rabbit calvarial defect models for inflammation and bone regeneration. Results: In vitro testing revealed that while 930 μm and 690 μm scaffolds exhibited superior compressive strength, the 562 μm scaffold showed a unique critical fracture behavior, and the 558 μm scaffold offered comparable stability with higher resistance to premature failure. In vivo studies confirmed excellent biocompatibility in both groups, with early bone formation favored in the 558 μm scaffold and more continuous and mature bone observed in the 562 μm scaffold at later stages. Conclusions: This stepwise strategy—from structural design to pore size screening and preclinical validation—demonstrates that threshold-level mechanical properties can influence osteogenesis. PLA/GO scaffolds optimized at 558 μm and 562 μm provide a translationally relevant balance between mechanical stability and biological performance for bone tissue engineering. Full article

Physical activity trackers are promising for monitoring physical activity in patients after surgery. However, the remobilization of patients following surgery is characterized by low-impact movements. It is often unclear to health care professionals whether a specific physical activity tracker is able to correctly detect steps in this patient population. A protocol is proposed, which allows health care professionals to familiarize themselves with the detection limits of a physical activity tracker. The professional should walk 20 steps under varying conditions mimicking the situation of patients after knee surgery. Conditions vary in step size, walking direction, use of walking aids, and footwear. The protocol was tested in a group of 14 health care professionals. Participants wore four trackers simultaneously, representing different modalities and different locations. For two trackers, the participants could experience a variation in the detection limits across the different conditions. On one hand, the within-participant reproducibility was substantial on average, though the between-participant reproducibility was only fair. On the other hand, experiencing incorrect step counts varied highly across and within participants. In conclusion, the self-familiarization of health care professionals with the detection limits of a physical activity tracker using specific protocols seems to be a feasible approach. Such protocols can provide valuable tools for facilitating the use of physical activity trackers in clinical applications. Additional research may allow for further refinement of the protocol to generate input that is more comparable across participants and closer to the gait of patients. Full article