Multidisciplinary Digital Publishing Institute (Switzerland)
Multidisciplinary Digital Publishing InstituteNot a member yet
1861300 research outputs found
Sort by
Atten-LTC-Enhanced MoE Model for Agent Trajectory Prediction in Autonomous Driving
No full textThe development of sensor technology and deep learning has significantly improved the reliability and practicality of automatic driving technology. In an autonomous driving system, agent trajectory prediction is a complex challenge, which includes the understanding of different and unpredictable behavior patterns of various entities, including vehicles, pedestrians, and other traffic participants, among the data collected by sensors. In this paper, we deeply study two kinds of problems: Single-Agent Trajectory Prediction (SATP) and Multi-Agent Trajectory Prediction (MATP). We propose an innovative model, which combines the attention mechanism and integrates the Liquid Time-Constant (LTC) network with spatio-temporal features and the Mixture of Experts (MoE) framework, termed the Atten-LTC-MoE model. The model is general and extensible to support SATP and MATP problems in different autonomous driving environments. In order to improve computational efficiency and prediction accuracy, lane and agent vectorization, spatio-temporal features, agent data fusion, and trajectory endpoint generation technologies are studied. The effectiveness of our method is verified by comprehensive experiments on Argoverse and Interaction datasets. Our proposed model has been superior to the state-of-the-art models in terms of minADE6 and minFDE6 metrics and has shown significant advantages in the accuracy of agent trajectory prediction and computational performance
Sleep Apnea Pathophysiology in Patients with a History of COVID-19
No full textBackground: Emerging evidence suggests that COVID-19 may influence obstructive sleep apnea (OSA) pathophysiology by affecting upper airway collapsibility, ventilatory control, and arousal responses, raising the possibility of a bidirectional relationship. This study examined whether individuals with a history of COVID-19 show altered OSA-related physiological traits compared with those without prior infection. Methods: In a case–control study, 60 participants with a history of COVID-19 were compared to 60 matched controls who underwent overnight in-hospital polysomnography before the pandemic. The matching criteria included age (±5 years), gender, body mass index (BMI) (±5 kg/m2), and OSA presence. Key pathophysiological traits (collapsibility, loop gain, arousal threshold, muscle compensation) estimated from polysomnographic signals were compared, with adjustment for age, sex, BMI, and apnea–hypopnea index. Results: The participants (78% male, mean age 55 ± 12 years, BMI 29.4 ± 5.0 kg/m2) exhibited no meaningful differences in their average levels of collapsibility (Adj dif [95% CI]; Vpassive: −1 [−4, 2] %eupnea, p = 0.7), loop gain (LG1: 0.01 [−0.04, 0.06], p = 0.7), or arousal threshold levels (−1 [−7, 4] %eupnea) and showed similar levels of muscle compensation (Vcomp: 5 [−1, 11], p = 0.12). However, a greater ventilatory response to arousal (7 [1, 12] %eupnea) was associated with COVID-19 history. Conclusions: COVID-19 history is not associated with differences in key OSA pathophysiological traits, suggesting it is unlikely to explain observed differences in OSA presentation. The increased ventilatory response to arousal may have implications for treatment responses and outcomes
Formation Mechanisms of Chilled Layer on the Perimeter of Superalloy Seed
No full textThe seeding technique is the only way to precisely control the crystal orientation of single-crystal superalloy castings. However, an inevitable assembly gap exists between the seed and the mold cavity in practice, whose role in defect formation remains insufficiently understood. To elucidate the mechanism and impact of this gap, superalloy seeds were machined to different extents, aiming to create varying gaps with the mold. After the seeding experiment, the chilled layers formed on the perimeter of the pre-processed seeds were detected, exhibiting two distinct microstructural zones: a eutectic aggregation region at the bottom and an equiaxed grain at the top. The thicker the layer, the more pronounced the differences in microstructure between these two regions. This can be explained by the fact that during preheating, the γ/γ′ eutectic-rich interdendritic region (enriched with Al + Ti + Ta) in the original seed melted first due to its lower melting point. The molten fluid flowed downward into the gap, solidifying rapidly into the chilled layer. The leading portion of the fluid, melting from the interdendritic zone, formed the eutectic zone in the lower part of the chilled layer. The subsequently poured charge alloy melt (non-enriched with Al + Ti + Ta) generated the upper equiaxed zone with only a little γ/γ′ eutectic. These equiaxed grains in the chilled layer subsequently grew upward and potentially developed into stray grains of the casting
Alkali-Activated Materials and CDW for the Development of Sustainable Building Materials: A Review with a Special Focus on Their Mechanical Properties
No full textAlkali-activated materials (AAMs) or geopolymers have been considered for many years as a sustainable substitution for the traditional ordinary Portland cement (OPC) binder. However, their production needs energy consumption and creates carbon emissions. Since construction and demolition waste (CDW) can become precursors for manufacturing alkali-activated materials, their use as substitutes for traditional AAM (such as metakaolin, blast furnace slag, and fly ash) can solve both the problem of their disposal and the problem of sustainability. Furthermore, CDW can also be used as aggregate replacement, avoiding the exploitation of natural river sand and gravel. A new circular economy could be created based on CDW recycling, creating a new eco-friendly building practice. Unfortunately, this process is quite difficult owing to several variables that should be taken into consideration, such as the possibility of separating and sorting the CDW, the great variability of CDW composition, the cost of the mechanical and thermal treatment, the different parameters that compose an alkali-activated mix-design, and public opinion still being skeptical about the use of recycled materials in the construction sector. This review tries to describe all these aspects, summarizing the results of the most interesting studies performed on this subject. Today, thanks to a comprehensive protocol, the use of building information modeling (BIM) software and machine learning models, a large-scale reuse of CDW in the building industry appears more feasible
Background Error Covariance Matrix Structure and Impact in a Regional Tropical Cyclone Forecasting System
No full textThe background error covariance matrix (BE) is a fundamental component of data assimilation (DA) systems. Its impact on both the DA process and subsequent forecast performance depends on model configuration and the types of observations assimilated. However, few studies have specifically examined BE behavior in the context of satellite DA for regional tropical cyclone (TC) prediction. In this study, we develop the BE and evaluate its structure for a TC forecasting system over the western North Pacific. A total of six BEs are modeled using three control variable (CV) schemes (aligned with the CV5, CV6, and CV7 options available in the Weather Research and Forecasting DA system (WRFDA)) with training data from two distinct periods: the TC season and the winter season. Results demonstrate that the BE structure is sensitive to the training data used. The performance of TC-season BEs derived from different CV schemes is assessed for TC track forecasting through the assimilation of microwave sounder satellite brightness temperature data. The evaluation is based on a set of 14 cases from 2018 that exhibited large official track forecast errors. The CV7 BE, which uses the x- and y-direction wind components as CVs, captures finer small-scale momentum error features and yields greater forecast improvement at shorter lead-times (24 h). In contrast, the CV6 BE, which employs stream function (ψ) and unbalanced velocity potential (χu) as CVs, incorporates more large-scale momentum error information. The inherent multivariate couplings among analysis variables in this scheme also allow for closer fits to satellite microwave brightness temperature data, which is particularly crucial for forecasting TCs that primarily develop over oceans where conventional observations are scarce. Consequently, it enhances the large-scale environmental field more effectively and delivers superior forecast skill at longer lead times (48 h and 72 h)
Constructing Artificial Features with Grammatical Evolution for Earthquake Prediction
No full textEarthquakes are the result of the dynamic processes occurring beneath the Earth’s crust; specifically, the movement and interaction of tectonic/lithospheric plates. When one plate shifts relative to another, stress accumulates and is eventually released as seismic energy. This process is continuous and unstoppable. This phenomenon is well recognized in the Mediterranean region, where significant seismic activity arises from the northward convergence (4–10 mm per year) of the African plate relative to the Eurasian plate along a complex plate boundary. Consequently, our research will focus on the Mediterranean region, specifically examining seismic activity from 1990 to 2015 within the latitude range of 33–44° and longitude range of 17–44°. These geographical coordinates encompass 28 seismic zones, with the most active areas being Turkey and Greece. In this paper, we applied Grammatical Evolution for artificial feature construction in earthquake prediction, evaluated against machine learning approaches including MLP(GEN), MLP(PSO), SVM, and NNC. Experiments showed that feature construction (FC) achieved the best performance, with a mean error of 9.05% and overall accuracy of 91%, outperforming SVM. Further analysis revealed that a single constructed feature Nf=1 yielded the lowest average error (8.21%), while varying the number of generations indicated that Ng=200 provided an effective balance between computational cost and predictive accuracy. These findings confirm the efficiency of FC in enhancing earthquake prediction models through artificial feature construction. Our results, as will be discussed in greater detail within the research, yield an average error of approximately 9%, corresponding to an overall accuracy of 91%
Analysis of Soft Tissue N-Glycome Profiles in Oral Squamous Cell Carcinoma, a Pilot Study
No full textOral squamous cell carcinoma (OSCC) is an aggressive disease with a glycoproteomically unmapped progression and a low five-year survival rate. Thus, the aim of this pilot study was to explore the N-glycosylation pattern differences in malignant, adjacent mucosal and healthy tissues in the context of OSCC. Oral mucosal soft tissue samples was obtained by incisional biopsy from five patients with OSCC, both from the malignant and the opposite healthy gingival sides, and from seven age-sex-matched healthy controls. The collected tissues were homogenized, followed by N-glycan profiling of the endoglycosidase-released and fluorophore-labeled carbohydrates using capillary electrophoresis with ultra-sensitive laser-induced fluorescent detection (CE-LIF). Six out of the twenty-two identified N-glycan structures, including glycogens, showed significant (p < 0.05) differences between the malignant tissue samples of the OSCC patients and the healthy controls. Comparing the healthy and the positive control oral mucosal samples, differences in four N-glycan structures were revealed, while only one alteration was observed between the N-glycan profiles of the malignant tumor and positive control samples. However, the results are presented descriptively, reflecting the limited sample size of the pilot study, it shows the potential of high-resolution CE-LIF-based glyocoanalytical protocol to be highly efficient and sensitive for glycobiomarker-based molecular diagnostics of oral malignant lesions
Beyond the Usual Suspects: A Narrative Review of High-Yield Non-Traditional Risk Factors for Atherosclerosis
No full textBackground: Cardiovascular risk models, such as the Framingham and atherosclerotic cardiovascular disease (ASCVD) calculators, have improved risk prediction but often fail to identify individuals who experience ASCVD events despite low or intermediate predicted risk. This suggests that underrecognized, non-traditional risk factors may contribute significantly to the development of atherosclerosis. Objective: This narrative review synthesizes and summarizes recent evidence on high-yield non-traditional risk factors for atherosclerosis, with a focus on clinically significant, emerging, and applicable contributors beyond conventional frameworks. This review is distinct in that it aggregates a wide array of non-traditional risk factors while also consolidating recent data on ASCVD in more vulnerable populations. Unlike the existing literature, this manuscript integrates in a single comprehensive review various domains of non-traditional atherosclerotic risk factors, including inflammatory, metabolic, behavioral, environmental, and physical pathways. An additional unique highlight in the same manuscript is the discussion of non-traditional risk factors for atherosclerosis in more vulnerable populations, specifically South Asians. We also focus on clinically actionable factors that can guide treatment decisions for clinicians. Results: Key non-traditional risk factors identified include inflammation and biomarker-based risk factors such as C-reactive protein or interleukin-6 levels, metabolic and microbial risk factors, behavioral factors such as E-cigarette use, and environmental or infectious risk factors such as air and noise pollution. We explore certain physical exam findings associated with atherosclerotic burden, such as Frank’s sign and Achilles tendon thickness. Conclusions: Atherosclerosis is a multifactorial process influenced by diverse and often overlooked factors. Integrating non-traditional risks into clinical assessment may improve early detection, guide prevention and personalize care. Future risk prediction models should incorporate molecular, behavioral, and environmental data to reflect the complex nature of cardiovascular disease
Active Inference and Functional Parametrisation: Differential Flatness and Smooth Random Realisation
No full textThis paper is a first attempt to marry constructive nonlinear control theory techniques with active inference. Specifically, we are interested in the relationship between differential flatness and the design of generative models for use in control settings. We place specific emphasis on the pathwise properties of differentially flat systems that inherit from their definition in terms of successive temporal derivatives and relate this to the use of generalised coordinates of motion in formulating continuous-time generative models in active inference. To illustrate the basic concepts, we appeal to the example of oculomotor control
Oblique Wave Scattering by a Floating Rectangular Porous Box with an Impermeable Bottom
No full textBased on linear wave theory and potential flow theory, the wave scattering performance of a rectangular floating porous box with an impermeable bottom is investigated analytically. The mathematical formulation of the physical problem is well established and solved, and its analytical solutions are appropriately obtained using the matched eigenfunction expansion method. The convergency and accuracy of the analytical solutions are carefully verified and thoroughly validated. It is found that the present analytical solutions converge up to three decimal places and agree well with the numerical results published in the previous literature. Furthermore, important numerical results are calculated to thoroughly analyze the oblique wave scattering performance of the proposed rectangular floating porous box with an impermeable bottom and its efficiency in preventing incident waves when used as a floating breakwater. It is concluded that the dimensionless width (L/h), submergence depth (d/h), and frictional coefficient (f) have a significant influence on the scattering performance and the transmission coefficient of the proposed porous box. This work is beneficial for the design and future development of floating rectangular porous box breakwaters