Components Of Model Research Articles

Knowledge graph driven medicine recommendation system using graph neural networks on longitudinal medical records

Medicine recommendation systems are designed to aid healthcare professionals by analysing a patient’s admission data to recommend safe and effective medications. These systems are categorised into two types: instance-based and longitudinal-based. Instance-based models only consider the current admission, while longitudinal models consider the patient’s medical history. Electronic Health Records are used to incorporate medical history into longitudinal models. This project proposes a novel Knowledge Graph-Driven Medicine Recommendation System using Graph Neural Networks, KGDNet, that utilises longitudinal EHR data along with ontologies and Drug-Drug Interaction knowledge to construct admission-wise clinical and medicine Knowledge Graphs for every patient. Recurrent Neural Networks are employed to model a patient’s historical data, and Graph Neural Networks are used to learn embeddings from the Knowledge Graphs. A Transformer-based Attention mechanism is then used to generate medication recommendations for the patient, considering their current clinical state, medication history, and joint medical records. The model is evaluated on the MIMIC-IV EHR data and outperforms existing methods in terms of precision, recall, F1 score, Jaccard score, and Drug-Drug Interaction control. An ablation study on our models various inputs and components to provide evidence for the importance of each component in providing the best performance. Case study is also performed to demonstrate the real-world effectiveness of KGDNet.

Life-Cycle Performance Modeling for Sustainable and Resilient Structures under Structural Degradation: A Systematic Review

The performance of structures degrades during their service life due to deterioration and extreme events, compromising the social development and economic growth of structure and infrastructure systems. Buildings and bridges play a vital role in the socioeconomic development of the built environment. Hence, it is essential to understand existing tools and methodologies to efficiently model the performance of these structures during their life cycle. In this context, this paper aims to explore the existing literature on the life-cycle performance modeling, assessment, enhancement, and decision making of buildings and bridge infrastructure systems under deterioration and extreme events for a sustainable and resilient built environment. The main objectives are to (1) systematically review the existing literature on life-cycle performance modeling of buildings and bridges based on the PRISMA methodology, (2) provide a bibliometric analysis of the systematically assessed journal articles, (3) perform an analysis of the included articles based on the identified components of life-cycle performance modeling, and (4) provide a discussion on the utilized tools, techniques, methodologies, and frameworks for buildings and bridge infrastructure systems in the life-cycle context. The provided systematic literature review and subsequent discussions could provide an overview to the reader regarding the individual components and existing methodologies of life-cycle performance management under deterioration and extreme events.

Fostering Dialogic Reading Through Older Siblings in Immigrant Latino Families: A Pilot Study

To promote children’s language development through designs that consider familial contexts, the authors explored the effectiveness of a dialogic reading intervention customized for older siblings in immigrant Latino families. The dialogic reading intervention, developed with components of training, modeling, and coaching, systematically supported older siblings’ dialogic reading use while reading with their younger siblings. Using the CROWD mnemonic, older siblings were taught to use a range of dialogic reading prompts, thereby nurturing diverse forms of engagement during shared interactive book reading (SIBR) sessions. Moreover, older siblings were taught the PEER mnemonic to enhance their ability to respond to their younger siblings’ input in manners conducive to promoting the latter’s language development. Effects of the intervention program on three older siblings’ (1) prompting and (2) responsiveness during SIBR were assessed using a multiple-baseline across participants design. Results indicate that two out of three older siblings increased prompt frequency and demonstrated improved responsiveness after receiving coaching and modeling support. Challenges faced by one older sibling are discussed, potentially attributed to individual language and literacy difficulties. Results tentatively indicate that older siblings have the capacity to acquire and apply dialogic reading skills if given appropriate instruction and support. These results illuminate opportunities to enhance SIBR techniques among siblings, underscoring the significant role older siblings in immigrant Latino families can play in providing enriched language input during SIBR.

The Attend-PE model: A feasibility study of a structured follow-up care model for patients with pulmonary embolism.

BackgroundPulmonary embolism may have both physical and psychological consequences for the affected person. Guidelines recommend structured follow-up care, yet this is still not widely practised. Therefore, a national research project was initiated in Denmark in 2021, with the aim of developing, testing, implementing, and evaluating a structured post-pulmonary embolism follow-up care model, ‘Attend-PE’. The objective of this feasibility study was to examine the fidelity, acceptability, and appropriateness of the Attend-PE model in a Danish hospital setting. MethodsThis feasibility study was conducted in two Danish hospitals, using a prospective study design with six months' follow-up. The fidelity, acceptability, and appropriateness of the Attend-PE model's components were evaluated using surveys, registrations sheets, and interviews with two physicians, three nurses, and 29 patients. Qualitative data were analysed using a deductive content analysis, while quantitative data were analysed using descriptive statistics. ResultsFidelity with the Attend-PE model was good, with a high participation rate of patients in all components of the model. Acceptability was likewise good, as both patients and health care professionals expressed a high level of satisfaction with the model. The health care professionals considered the model to be relevant and suitable in a Danish hospital setting, confirming appropriateness of the model. ConclusionThis study showed that the Attend-PE model for patients with pulmonary embolism is feasible and acceptable in a Danish hospital setting.

OpenECAD: An efficient visual language model for editable 3D-CAD design

Computer-aided design (CAD) tools are utilized in the manufacturing industry for modeling everything from cups to spacecraft. These programs are complex to use and typically require years of training and experience to master. Structured and well-constrained 2D sketches and 3D constructions are crucial components of CAD modeling. A well-executed CAD model can be seamlessly integrated into the manufacturing process, thereby enhancing production efficiency. Deep generative models of 3D shapes and 3D object reconstruction models have garnered significant research interest. However, most of these models produce discrete forms of 3D objects that are not editable. Moreover, the few models based on CAD operations often have substantial input restrictions. In this work, we fine-tuned pre-trained models to create OpenECAD models (0.55B, 0.89B, 2.4B and 3.1B), leveraging the visual, logical, coding, and general capabilities of visual language models. OpenECAD models can process images of 3D designs as input and generate highly structured 2D sketches and 3D construction commands, ensuring that the designs are editable. These outputs can be directly used with existing CAD tools’ APIs to generate project files. To train our network, we created a series of OpenECAD datasets. These datasets are derived from existing public CAD datasets, adjusted and augmented to meet the specific requirements of vision language model (VLM) training. Additionally, we have introduced an approach that utilizes dependency relationships to define and generate sketches, further enriching the content and functionality of the datasets.

Accurate synthesis of dysarthric Speech for ASR data augmentation

Dysarthria is a motor speech disorder often characterized by reduced speech intelligibility through slow, uncoordinated control of speech production muscles. Automatic Speech Recognition (ASR) systems can help dysarthric talkers communicate more effectively. However, robust dysarthria-specific ASR requires a significant amount of training speech, which is not readily available for dysarthric talkers.This paper presents a new dysarthric speech synthesis method for the purpose of ASR training data augmentation. Differences in prosodic and acoustic characteristics of dysarthric spontaneous speech at varying severity levels are important components for dysarthric speech modeling, synthesis, and augmentation. For dysarthric speech synthesis, a modified neural multi-talker TTS is implemented by adding a dysarthria severity level coefficient and a pause insertion model to synthesize dysarthric speech for varying severity levels.To evaluate the effectiveness for synthesis of training data for ASR, dysarthria-specific speech recognition was used. Results show that a DNNHMM model trained on additional synthetic dysarthric speech achieves relative Word Error Rate (WER) improvement of 12.2 % compared to the baseline, and that the addition of the severity level and pause insertion controls decrease WER by 6.5 %, showing the effectiveness of adding these parameters. Overall results on the TORGO database demonstrate that using dysarthric synthetic speech to increase the amount of dysarthric-patterned speech for training has significant impact on the dysarthric ASR systems. In addition, we have conducted a subjective evaluation to evaluate the dysarthricness and similarity of synthesized speech. Our subjective evaluation shows that the perceived dysarthricness of synthesized speech is similar to that of true dysarthric speech, especially for higher levels of dysarthria. Audio samples are available at https://mohammadelc.github.io/SpeechGroupUKY/

G-Net: Implementing an enhanced brain tumor segmentation framework using semantic segmentation design.

A fundamental computer vision task called semantic segmentation has significant uses in the understanding of medical pictures, including the segmentation of tumors in the brain. The G-Shaped Net architecture appears in this context as an innovative and promising design that combines components from many models to attain improved accuracy and efficiency. In order to improve efficiency, the G-Shaped Net architecture synergistically incorporates four fundamental components: the Self-Attention, Squeeze Excitation, Fusion, and Spatial Pyramid Pooling block structures. These factors work together to improve the precision and effectiveness of brain tumor segmentation. Self-Attention, a crucial component of G-Shaped architecture, gives the model the ability to concentrate on the image's most informative areas, enabling accurate localization of tumor boundaries. By adjusting channel-wise feature maps, Squeeze Excitation completes this by improving the model's capacity to capture fine-grained information in the medical pictures. Since the G-Shaped model's Spatial Pyramid Pooling component provides multi-scale contextual information, the model is capable of handling tumors of various sizes and complexity levels. Additionally, the Fusion block architectures combine characteristics from many sources, enabling a thorough comprehension of the image and improving the segmentation outcomes. The G-Shaped Net architecture is an asset for medical imaging and diagnostics and represents a substantial development in semantic segmentation, which is needed more and more for accurate brain tumor segmentation.

Redefining Neural Architecture Search of Heterogeneous Multinetwork Models by Characterizing Variation Operators and Model Components.

With neural architecture search (NAS) methods gaining ground on manually designed deep neural networks-even more rapidly as model sophistication escalates-the research trend is shifting toward arranging different and often increasingly complex NAS spaces. In this conjuncture, delineating algorithms which can efficiently explore these search spaces can result in a significant improvement over currently used methods, which, in general, randomly select the structural variation operator, hoping for a performance gain. In this article, we investigate the effect of different variation operators in a complex domain, that of multinetwork heterogeneous neural models. These models have an extensive and complex search space of structures as they require multiple subnetworks within the general model in order to answer different output types. From that investigation, we extract a set of general guidelines whose application is not limited to that particular type of model and are useful to determine the direction in which an architecture optimization method could find the largest improvement. To deduce the set of guidelines, we characterize both the variation operators, according to their effect on the complexity and performance of the model; and the models, relying on diverse metrics which estimate the quality of the different parts composing it.

A model of collaborative immigration advocacy to prevent policy-based trauma and harm.

Research suggests that antiimmigrant policies enacted in the United States, magnified during the 2016-2020 period, propagate widespread trauma across communities of immigrants (von Werthern et al., 2018). While these policies harm all groups of immigrants, structural conditions (e.g., lack of documentation status, race, ethnicity, country of origin, and other social and legal determinants) shape how they are experienced. To address the widespread traumatic harm inflicted by racist and xenophobic policies, a group of leaders from eight Divisions of the American Psychological Association (APA) and the National Latinx Psychological Association (NLPA) launched an Interdivisional Immigration Project (IIP). The IIP served to develop a model for collaborative advocacy, bringing together mental health providers (i.e., psychologists, social workers), allied professionals, and immigration activists from community organizations across the country. This model was developed over the course of 1 year, coinciding with the global coronavirus disease 2019 (COVID-19) pandemic and the amplified movement for racial justice. This article describes the key components of the IIP collaborative advocacy model: (a) structuring leadership in a democratic and egalitarian manner, (b) centering and uplifting immigrant voices, (c) forming teams across five U.S. regions, (d) facilitating critical dialogues grounded in liberatory practices, (e) centering trauma and empowerment, and (f) developing advocacy strategies. The IIP collaborative advocacy model is informing advocacy to protect immigrants from harm. This model may be used as the basis for ongoing humane immigration policy activism that centers the voices of community activists, and that pushes psychologists and allied professionals to use their positionality to support community-based efforts. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Dynamic financial modeling and feasibility studies for affordable housing policies: A conceptual synthesis

The escalating demand for affordable housing necessitates innovative approaches to financial modeling and feasibility analysis to ensure the success and sustainability of housing policies. This abstract presents a conceptual synthesis of dynamic financial modeling and feasibility studies, exploring their pivotal role in shaping effective affordable housing policies. Dynamic financial modeling involves creating flexible and adaptive financial models that account for varying economic conditions, policy changes, and market fluctuations. These models are essential for predicting financial outcomes, assessing the viability of housing projects, and guiding investment decisions. By incorporating real-time data and scenario analysis, dynamic financial models help stakeholders understand potential risks and opportunities, enabling more informed decision-making. Key components of dynamic financial modeling include cash flow analysis, sensitivity testing, and scenario planning, which together provide a comprehensive view of a project's financial viability over time. Feasibility studies complement financial modeling by evaluating the practical aspects of affordable housing projects, such as site selection, regulatory compliance, and market demand. These studies assess the alignment of housing projects with community needs and regulatory requirements, ensuring that proposed developments are both feasible and beneficial. Feasibility studies often include market analysis, cost estimates, and risk assessments, providing a detailed understanding of project constraints and opportunities. The synthesis of dynamic financial modeling and feasibility studies offers a robust framework for evaluating affordable housing policies. It allows for the integration of financial projections with practical considerations, ensuring that policies are not only economically viable but also aligned with social and regulatory objectives. Case studies from various regions demonstrate the effectiveness of this approach in identifying successful strategies and addressing common challenges. In conclusion, dynamic financial modeling and feasibility studies are crucial tools for developing and implementing effective affordable housing policies. They provide a comprehensive understanding of financial and practical dimensions, facilitating informed decision-making and enhancing the sustainability and impact of affordable housing initiatives. This conceptual synthesis underscores the importance of integrating these methodologies to achieve long-term success in addressing housing affordability challenges. Keywords: Policies, Affordable Housing, Feasibility Studies, Dynamic Financial Modeling, conceptual Synthesis.

Comparing components for seismic risk modelling using data from the 2019 Le Teil (France) earthquake

Abstract. Probabilistic seismic hazard and risk models are essential to improving our awareness of seismic risk, to its management, and to increasing our resilience against earthquake disasters. These models consist of a series of components, which may be evaluated and validated individually, although evaluating and validating these types of models as a whole is challenging due to the lack of recognized procedures. Estimations made with other models, as well as observations of damage from past earthquakes, lend themselves to evaluating the components used to estimate the severity of damage to buildings. Here, we are using a dataset based on emergency post-seismic assessments made after the Le Teil 2019 earthquake, third-party estimations of macroseismic intensity for this seismic event, shake maps, and scenario damage calculations to compare estimations under different modelling assumptions. First we select a rupture model using estimations of ground motion intensity measures and macroseismic intensity. Subsequently, we use scenario damage calculations based on different exposure models, including the aggregated exposure model in the 2020 European Seismic Risk Model (ESRM20), as well as different site models. Moreover, a building-by-building exposure model is used in scenario calculations, which individually models the buildings in the dataset. Lastly, we compare the results of a semi-empirical approach to the estimations made with the scenario calculations. The post-seismic assessments are converted to EMS-98 (Grünthal, 1998) damage grades and then used to estimate the damage for the entirety of the building stock in Le Teil. In general, the scenario calculations estimate lower probabilities for damage grades 3–4 than the estimations made using the emergency post-seismic assessments. An exposure and fragility model assembled herein leads to probabilities for damage grades 3–5 with small differences from the probabilities based on the ESRM20 exposure and fragility model, while the semi-empirical approach leads to lower probabilities. The comparisons in this paper also help us learn lessons on how to improve future testing. An improvement would be the use of damage observations collected directly on the EMS-98 scale or on the damage scale in ESRM20. Advances in testing may also be made by employing methods that inform us about the damage at the scale of a city, such as remote sensing or data-driven learning methods fed by a large number of low-cost seismological instruments spread over the building stock.

Joyful Learning Model for Javanese Speech Levels Course

As one of Indonesia’s cultural heritages, regional languages, including Javanese, need to be preserved. The cultural richness of Javanese includes the politeness and manners values, as reflected in the so-called unggah-ungguh (speech levels). While it is taught as a course in the country’s 12-year mandatory education, the teaching and learning process still follows the traditional, less appealing model. This research aims to create a Javanese speech levels learning model based on joyful learning. The model was both innovative and entertaining. The research used R&D ADDIE design with the following steps: analysis, designing, development, implementation, and evaluation. The model was developed based on two philosophies: progressivism and analytic philosophy. Syntagmatic, social system, support system, reaction principle, instructional impact, and accompaniment impact served as the model's components. Orientation, presentation of material, explanation of how to play, playing vocabulary, playing sentences, dialogue, assessment, and reflection comprised the syntagmatic model. The principles of joyful learning and the norms of honing, loving, and nurturing are included in the model social system. The model reaction principle included the teacher serving as a facilitator, planner, and assessor. Tools, media, and learning resources are all part of the model support system. Some of the instructional effects were increased Javanese vocabulary, fun learning activities, and some impacts of model accompaniment, including increased emotional sharpness, imagination, and cooperation.

Contaminated Gibbs-Type Priors

Gibbs-type priors are combinatorial processes widely used as key components in several Bayesian nonparametric models. By virtue of their flexibility and mathematical tractability, they turn out to be predominant priors in species sampling problems and mixture modeling. We introduce a new family of processes which extends the Gibbs-type one, by including a contaminant component in the model to account for an excess of observations with frequency one. We first investigate the induced random partition, the associated predictive distribution, the asymptotic behavior of the total number of blocks and the number of blocks with a given frequency: all the results we obtain are in closed form and easily interpretable. A remarkable aspect of contaminated Gibbs-type priors relies on their predictive structure, compared to the one of the standard Gibbs-type family: it depends on the additional sampling information on the number of observations with frequency one out of the observed sample. As a noteworthy example we focus on the contaminated version of the Pitman-Yor process, which turns out to be analytically tractable and computationally feasible. Finally we pinpoint the advantage of our construction in different applications: we show how it helps to improve predictive inference in a species-related dataset exhibiting a high number of species with frequency one; we also discuss the use of the proposed construction in mixture models to perform density estimation and outlier detection.

The Dynamic Model of Health Assets: a model development.

Epidemiological research on resistance and resilience can build on models of health developed in health promotion. Nevertheless, these models need to be adjusted to approaches currently employed in epidemiology; namely, included concepts should be easy to operationalize, and links between them should be simple enough to enable statistical modeling. In addition, these models should include both individual and environmental assets. The objective of this study is to consolidate the current knowledge on health assets, adjust them to epidemiological research needs, and propose a new model of health assets for epidemiological studies on health. The conceptual paper was conducted according to the guidelines for the model development. The development of the new model was made from the perspective of salutogenesis - the branch of health promotion studying the origins of health. The analysis of literature on health promotion, public health, and positive psychology was conducted to find the links connecting individual and environmental assets. The newly developed Dynamic Model of Health Assets circularly links individual characteristics, actions, environments, and support. Each preceding component of the model contributes to the following one; each component also independently contributes to resistance and resilience. The new model may guide large-scale epidemiological research on resistance and resilience. The model's components are easy to operationalize; the model allows for constructing multilevel models and accounting for the dynamic nature of the relationships between components. It is also generic enough to be adjusted to studying contributors to resistance and resilience to different specific diseases. The new model can guide epidemiological studies on resistance and resilience.

Maintaining Local Languages Through Local Content Curriculum: Analysis of Contextual Approaches and Field Learning

It is not impossible that language undergoes changes over time. The existence of local languages among teenagers and young people is no longer a communicative language choice in the environment where they are. The purpose of this research is to elaborate on the role of education, especially local curriculum, in preserving the local language by involving contextual approaches and field learning to teach the local language in schools. This study applies qualitative description with a literature review approach. Data is obtained by collecting reference materials such as books, theses, and journals manually and online. Manual data collection is done at the library, while online data collection involves downloading e-books and scientific journals from the last 10 years. The data are analyzed using content analysis, which involves reviewing books, journals, and theses to answer formulated questions. The results of this study indicate that an effective method for implementing local language learning is a method with contextual approaches and field learning. The contextual method applies components of constructivism, questioning, exploration, modeling, and authentic assessment. Meanwhile, field learning brings students closer to the relevance of context in learning the local language

Effects of Surface Turbulence Flux Parameterizations on the MJO: The Role of Ocean Surface Waves

Abstract This study investigates the sensitivity of the Madden–Julian oscillation (MJO) to changes to the bulk flux parameterization and the role of ocean surface waves in air–sea coupling using a fully coupled ocean–atmosphere–wave model. The atmospheric and ocean model components of the Energy Exascale Earth System Model (E3SM) are coupled to a spectral wave model, WAVEWATCH III (WW3). Two experiments with wind speed–dependent bulk algorithms (NCAR and COARE3.0a) and one experiment with wave-state-dependent flux (COR3.0a-WAV) were conducted. We modify COARE3.0a to include surface roughness calculated within WW3 and also account for the buffering effect of waves on the relative difference between air-side and ocean-side momentum flux. Differences in surface fluxes, primarily caused by discrepancies in drag coefficients, result in significant differences in MJO’s properties. While COARE3.0a has better convection–circulation coupling than NCAR, it exhibits anomalous MJO convection east of the date line. The wave-state-dependent flux (COR3.0-WAV) improves the MJO representation over the default COARE3.0 algorithm. Strong easterlies over the Pacific Ocean in COARE3.0a enhance the latent heat flux (LHFLX). This is responsible for the anomalous MJO propagation after the date line. In COR3.0a-WAV, waves reduce the anomalous easterlies, leading to a decrease in LHFLX and MJO dissipation after the date line. These findings highlight the role of surface fluxes in MJO simulation fidelity. Most importantly, we show that the proper treatment of wave-induced effects in bulk flux parameterization improves the simulation of coupled climate variability.

Lightweight two-stage transformer for low-light image enhancement and object detection

In low-light conditions, due to the loss of image details the visual tasks are challenging. To achieve real-time image enhancement and improve the accuracy of object detection task, we propose a lightweight two-stage Transformer. First, we use dynamic convolution to improve the adaptability of the network to different samples and preliminarily enhance the image through predicting the multiplicative and additive maps of the least squares method. In the second stage, we propose a FFT-Guidance Block (FGB) to obtain frequency components for explicit modeling, guiding the recovery of image potential information. In addition, joint our model with YOLOv3 to build a dark object detection framework, and we only use normal detection loss to simplify the training process. On the LOLv2 dataset, our model achieves advanced results. The enhanced model maintains good performance while the parameters are only 0.050M, and increase the accuracy of the downstream object detection task. The detection framework reaches 77.9% and 60.2 in mAP and FPS respectively on ExDark dataset, which can be better robust in dark conditions.

LogGT: Cross-system log anomaly detection via heterogeneous graph feature and transfer learning

Automated system log anomaly detection plays a crucial role in ensuring service reliability. Existing methods incompletely utilize structured log entries, resulting in the loss of key information such as components and time. Besides, due to the limitations of labeled data, models trained by a single system are difficult to apply to other systems. Therefore, we propose a cross-system log anomaly detection method named LogGT, which simultaneously models log events, components and time, leveraging labeled system knowledge to achieve anomaly detection in unlabeled systems. Specifically, we firstly design a heterogeneous graph to accurately represent the interactions between different events and components in the log sequence. Then, in order to avoid noise interference and conduct cross-system semantic analysis, we employ BERT to extract log sentence vectors, and Normalizing Flow is used to optimize them for smoother node embedding. A Graph Transformer Architecture with Time Intervals (GTAT) is proposed to model heterogeneous graphs by integrating time feature, allowing for a comprehensive analyze of execution order and time anomalies. Additionally, we design a semantic weighting method and utilize a novel domain-adapted transfer learning technology to effectively transfer the heterogeneous graph features of the source system to the target system. Experimental results demonstrate that LogGT outperforms five log anomaly detection methods, achieving an average anomaly detection F1-score higher than 0.95. Moreover, the AUC value of GTAT exceeds the sequence model by more than 2.3%.

Generalized Weakly Supervised Object Localization.

With the goal of learning to localize specific object semantics using the low-cost image-level annotation, weakly supervised object localization (WSOL) has been receiving increasing attention in recent years. Although existing literatures have studied a number of major issues in this field, one important yet challenging scenario, where the test object semantics may appear in the training phase (seen categories) or never been observed before (unseen categories), is still beyond the exploration of the existing works. We define this scenario as the generalized WSOL (GWSOL) and make a pioneering effort to study it in this article. By leveraging attribute vectors to associate seen and unseen categories, we involve threefold modeling components, i.e., the class-sensitive modeling, semantic-agnostic modeling, and content-aware modeling, into a unified end-to-end learning framework. Such design enables our model to recognize and localize unconstrained object semantics, learn compact and discriminative features that could represent the potential unseen categories, and customize content-aware attribute weights to avoid localizing on misleading attribute elements. To advance this research direction, we contribute the bounding-box manual annotations to the widely used AwA2 dataset and benchmark the GWSOL methods. Comprehensive experiments demonstrate the effectiveness of our proposed learning framework and each of the considered modeling components.

Contributing Components of Metabolic Energy Models to Metabolic Cost Estimations in Gait.

As metabolic cost is a primary factor influencing humans' gait, we want to deepen our understanding of metabolic energy expenditure models. Therefore, this paper identifies the parameters and input variables, such as muscle or joint states, that contribute to accurate metabolic cost estimations. We explored the parameters of four metabolic energy expenditure models in a Monte Carlo sensitivity analysis. Then, we analysed the model parameters by their calculated sensitivity indices, physiological context, and the resulting metabolic rates during the gait cycle. The parameter combination with the highest accuracy in the Monte Carlo simulations represented a quasi-optimized model. In the second step, we investigated the importance of input parameters and variables by analysing the accuracy of neural networks trained with different input features. Power-related parameters were most influential in the sensitivity analysis and the neural network-based feature selection. We observed that the quasi-optimized models produced negative metabolic rates, contradicting muscle physiology. Neural network-based models showed promising abilities but have been unable to match the accuracy of traditional metabolic energy expenditure models. We showed that power-related metabolic energy expenditure model parameters and inputs are most influential during gait. Furthermore, our results suggest that neural network-based metabolic energy expenditure models are viable. However, bigger datasets are required to achieve better accuracy. As there is a need for more accurate metabolic energy expenditure models, we explored which musculoskeletal parameters are essential when developing a model to estimate metabolic energy.