Models Of Different Domains Research Articles

UVLHub: A feature model data repository using UVL and open science principles

Feature models are the de facto standard for modelling variabilities and commonalities in features and relationships in software product lines. They are the base artefacts in many engineering activities, such as product configuration, derivation, or testing. Concrete models in different domains exist; however, many are in private or sparse repositories or belong to discontinued projects. The dispersion of knowledge of feature models hinders the study and reuse of these artefacts in different studies. The Universal Variability Language (UVL) is a community effort textual feature model language that promotes a common way of serializing feature models independently of concrete tools. Open science principles promote transparency, accessibility, and collaboration in scientific research. Although some attempts exist to promote feature model sharing, the existing solutions lack open science principles by design. In addition, existing and public feature models are described using formats not always supported by current tools. This paper presents ▪ , a repository of feature models in UVL format. ▪ provides a front end that facilitates the search, upload, storage, and management of feature model datasets, improving the capabilities of discontinued proposals. Furthermore, the tool communicates with Zenodo – one of the most well-known open science repositories – providing a permanent save of datasets and following open science principles. ▪ includes existing datasets and is readily available to include new data and functionalities in the future. It is maintained by three active universities in variability modelling.

Using reactive links to propagate changes across engineering models

AbstractCollaborative model-driven development is a de facto practice to create software-intensive systems in several domains (e.g., aerospace, automotive, and robotics). However, when multiple engineers work concurrently, keeping all model artifacts synchronized and consistent is difficult. This is even harder when the engineering process relies on a myriad of tools and domains (e.g., mechanic, electronic, and software). Existing work tries to solve this issue from different perspectives, such as using trace links between different artifacts or computing change propagation paths. However, these solutions mainly provide additional information to engineers, still requiring manual work for propagating changes. Yet, most modeling tools are limited regarding the traceability between different domains, while also lacking the efficiency and granularity required during the development of software-intensive systems. Motivated by these limitations, in this work, we present a solution based on what we call “reactive links”, which are highly granular trace links that propagate change between property values across models in different domains, managed in different tools. Differently from traditional “passive links”, reactive links automatically propagate changes when engineers modify models, assuring the synchronization and consistency of the artifacts. The feasibility, performance, and flexibility of our solution were evaluated in three practical scenarios, from two partner organizations. Our solution is able to resolve all cases in which change propagation among models were required. We observed a great improvement of efficiency when compared to the same propagation if done manually. The contribution of this work is to enhance the engineering of software-intensive systems by reducing the burden of manually keeping models synchronized and avoiding inconsistencies that potentially can originate from collaborative engineering in a variety of tool from different domains.

Transfer component analysis-driven domain adaptation approach for estimating the life of tunnel boring machine disc cutters

Estimating the life of disc cutters in tunnel boring machines is crucial for tunnel excavation efficiency. Accordingly, generating accurate predictions of the state of disc cutters can prevent unexpected downtimes while optimizing cutting performance. The literature presents investigations of the application of machine learning (ML) for estimating the disc cutter life. Nevertheless, diverse excavation conditions and data scarcity have stimulated research on transfer learning (TL) frameworks that tailor models for different domains, that is, domain adaptation (DA), by generating a common subspace in which the discrepancies among them are minimized. This study presents an end-to-end framework to estimate the disc cutter life through transfer component analysis, a DA-based method for projecting different domains by considering excavation project datasets in a common space; then, different ML models are trained, including linear, probabilistic, and neural methods. The results revealed that the Gaussian process regression model was superior to other methods, with R2 = 0.99. In conclusion, TL is a valuable tool for estimating disc cutter life across different domains, enabling accurate predictions and leveraging knowledge to mitigate data scarcity challenges. In addition, an explainable AI analysis is conducted to quantify and identify relevant features impacting negatively on the disc cutter life, evidencing great contribution from the cutter rotation speed, quartz content, screw rate and specific energy.

A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions

Deep learning has seen significant growth recently and is now applied to a wide range of conventional use cases, including graphs. Graph data provides relational information between elements and is a standard data format for various machine learning and deep learning tasks. Models that can learn from such inputs are essential for working with graph data effectively. This paper identifies nodes and edges within specific applications, such as text, entities, and relations, to create graph structures. Different applications may require various graph neural network (GNN) models. GNNs facilitate the exchange of information between nodes in a graph, enabling them to understand dependencies within the nodes and edges. The paper delves into specific GNN models like graph convolution networks (GCNs), GraphSAGE, and graph attention networks (GATs), which are widely used in various applications today. It also discusses the message-passing mechanism employed by GNN models and examines the strengths and limitations of these models in different domains. Furthermore, the paper explores the diverse applications of GNNs, the datasets commonly used with them, and the Python libraries that support GNN models. It offers an extensive overview of the landscape of GNN research and its practical implementations.

A new steady-state gas–particle partitioning model of polycyclic aromatic hydrocarbons: implication for the influence of the particulate proportion in emissions

Abstract. Gas–particle (G–P) partitioning is a crucial atmospheric process for semi-volatile organic compounds (SVOCs), particularly polycyclic aromatic hydrocarbons (PAHs). However, accurately predicting the G–P partitioning of PAHs has remained a challenge. In this study, we established a new steady-state G–P partitioning model based on the level-III multimedia fugacity model, with a particular focus on the particulate proportion (ϕ0) of PAHs in emissions. Similar to previous steady-state models, our new model divided the G–P partitioning behavior into three domains based on the threshold values of log KOA (octanol–air partitioning coefficient), with slopes of 1, from 1 to 0, and 0 for the three domains. However, our model differed significantly from previous models in different domains. We found that deviations from the equilibrium-state G–P partitioning models were caused by both gaseous interference and particulate interference, with ϕ0 determining the influence of this interference. Different forms of the new steady-state model were observed under different values of ϕ0, highlighting its significant impact on the G–P partitioning of PAHs. Comparison of the G–P partitioning of PAHs between the prediction results of our new steady-state model and monitored results from 11 cities in China suggested varying prediction performances under different values of ϕ0, with the lowest root mean square error observed when ϕ0 was set to 0.9 or 0.99. The results indicated that the ϕ0 was a crucial factor for the G–P partitioning of PAHs. Furthermore, our new steady-state model also demonstrated excellent performance in predicting the G–P partitioning of PAHs with entirely gaseous emission and polybrominated diphenyl ethers with entirely particulate emission. Therefore, we concluded that the ϕ0 should be considered in the study of G–P partitioning of PAHs, which also provided a new insight into other SVOCs.

Analyzing the Utility of Inventory Models in Different Domains

Analyzing the Utility of Inventory Models in Different Domains

A Transfer-Based Framework for Underwater Target Detection from Hyperspectral Imagery

The detection of underwater targets through hyperspectral imagery is a relatively novel topic as the assumption of target background independence is no longer valid, making it difficult to directly detect underwater targets using land target information. Meanwhile, deep-learning-based methods have faced challenges regarding the availability of training datasets, especially in underwater conditions. To solve these problems, a transfer-based framework is proposed in this paper, which exploits synthetic data to train deep-learning models and transfers them to real-world applications. However, the transfer becomes challenging due to the imparity in the distribution between real and synthetic data. To address this dilemma, the proposed framework, named the transfer-based underwater target detection framework (TUTDF), first divides the domains using the depth information, then trains models for different domains and develops an adaptive module to determine which model to use. Meanwhile, a spatial–spectral process is applied prior to detection, which is devoted to eliminating the adverse influence of background noise. Since there is no publicly available hyperspectral underwater target dataset, most of the existing methods only run on simulated data; therefore, we conducted expensive experiments to obtain datasets with accurate depths and use them for validation. Extensive experiments verify the effectiveness and efficiency of TUTDF in comparison with traditional methods.

Forget less, count better: a domain-incremental self-distillation learning benchmark for lifelong crowd counting

Crowd counting has important applications in public safety and pandemic control. A robust and practical crowd counting system has to be capable of continuously learning with the new incoming domain data in real-world scenarios instead of fitting one domain only. Off-the-shelf methods have some drawbacks when handling multiple domains: (1) the models will achieve limited performance (even drop dramatically) among old domains after training images from new domains due to the discrepancies of intrinsic data distributions from various domains, which is called catastrophic forgetting; (2) the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of the domain shift; and (3) it leads to linearly increasing storage overhead, either mixing all the data for training or simply training dozens of separate models for different domains when new ones are available. To overcome these issues, we investigated a new crowd counting task in the incremental domains training setting called Lifelong Crowd Counting. Its goal is to alleviate the catastrophic forgetting and improve the generalization ability using a single model updated by the incremental domains. Specifically, we propose a self-distillation learning framework as a benchmark (Forget Less, Count Better, or FLCB) for lifelong crowd counting, which helps the model sustainably leverage previous meaningful knowledge for better crowd counting to mitigate the forgetting when the new data arrive. In addition, a new quantitative metric, normalized backward transfer (nBwT), is developed to evaluate the forgetting degree of the model in the lifelong learning process. Extensive experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

An approach for cross-data querying and spatial reasoning of tunnel alignments

In mechanized tunneling projects, finding a low-risk and cost-effective alignment is an important task. Several alignment variants are usually created and each one is intensely scrutinized. Variants often have individual advantages and disadvantages and can lead to different constructive designs of a tunnel. In order to find the best alignment possible the variants have to be analyzed and evaluated based on requirements and evaluation criteria, such as safety, cost, built environment and operational requirements. To perform this evaluation and to enable comprehensive decision making, a holistic planning environment is examined that includes documents and models of different domains. In general, these domain specific data differ schematically and semantically, which consequently makes it challenging to combine and compare such diverse data. For this purpose, information from different sources must be linked and evaluated in a structured way. In particular, spatial relationships have to be investigated. Therefore, in this paper, ontology databases are utilized to merge BIM and GIS at data level to create an integrated model of the entire tunneling project. Relevant information for decision-making can then be derived, such as the location of private and public buildings that are in a certain vicinity of the planned alignment. On the one hand, the implementation of queries is a popular and frequently used approach to check for semantic properties. On the other hand, using a query language to derive information from geometric data can be challenging, due to the necessity of processing geometric data prior to and during query execution. Additionally, geometric definitions can differ in the considered coordinate reference system, the dimension or the structure. To handle geometry information by employing query languages, representations are methodically transformed to well-known text literals. A simplified and uniform geometric representation can be utilized for spatial reasoning, for example by adopting GeoSPARQL methods.

Ensemble deep learning: A review

Ensemble learning combines several individual models to obtain better generalization performance. Currently, deep learning architectures are showing better performance compared to the shallow or traditional models. Deep ensemble learning models combine the advantages of both the deep learning models as well as the ensemble learning such that the final model has better generalization performance. This paper reviews the state-of-art deep ensemble models and hence serves as an extensive summary for the researchers. The ensemble models are broadly categorized into bagging, boosting, stacking, negative correlation based deep ensemble models, explicit/implicit ensembles, homogeneous/heterogeneous ensemble, decision fusion strategies based deep ensemble models. Applications of deep ensemble models in different domains are also briefly discussed. Finally, we conclude this paper with some potential future research directions.

Design and implementation of a portable, large-scale wind tunnel for wildfire research

Connecting the results from laboratory wildland fire experiments with in-situ field experiments under natural conditions remains an important challenge in wildland fire science, particularly because of differences in flow and boundary-layer conditions in the local atmosphere. Thus, as part of a broader investigation involving laboratory and field experimentation, a large-scale, portable wind tunnel capable of use in both the laboratory and the field was designed and implemented to bridge the two experimental domains. Two axial fans generate flow speeds of up to 8 m/s within the test section. Thorough flow-field characterization revealed good uniformity and minimal spatial variability within the flow field. Uniquely, the wind tunnel is portable; due to its modular design, the entire wind tunnel can be broken down to fit onto two shipping pallets for transportation. This portability allows for future experiments to be conducted in the field under the same boundary conditions as in the laboratory. These same boundary conditions created a unique research environment to iteratively test the effects of boundary conditions to validate computational models in different domains. The results from some of the wildland fire spread experiments conducted in the wind tunnel are presented to demonstrate and validate its laboratory capabilities.

Xamã : Optical character recognition for multi-domain model management

The development of systems following model-driven engineering can include models from different domains. For example, to develop a mechatronic component one might need to combine expertise about mechanics, electronics, and software. Although these models belong to different domains, the changes in one model can affect other models causing inconsistencies in the entire system. Only few tools, however, support management of models from different domains. Indeed, these models are created using different modeling notations and it is not plausible to use a multitude of parsers geared toward each and every modeling notation. Therefore, to ensure maintenance of multi-domain systems, we need a uniform approach that would be independent from the peculiarities of the notation. Notation independence implies that such a uniform approach can only be based on elements commonly present in models of different domains, i.e., text, boxes, and lines. In this study, we investigate the suitability of optical character recognition (OCR) as a basis for such a uniformed approach. We select graphical models from various domains that typically combine textual and graphical elements. We start by analyzing the performance of Google Cloud Vision and Microsoft Cognitive Services, two off-the-shelf OCR services. Google Cloud Vision performed better than Microsoft Cognitive Services being able to detect text of 70% of model elements. Errors made by Google Cloud Vision are due to absence of support for text common in engineering formulas, e.g., Greek letters, equations, and subscripts. We identified the multi-line text error as one of the main issues of using OCR to recognize textual elements in models from different domains. This error happens when OCR misinterprets one textual element as two separate elements. To address the multi-line text error, we build Xamã on top of Google Cloud Vision. Xamã includes two approaches to identify whether the elements are positioned on a single line or multiple lines, and merge those identified as positioned on multiples lines. With and without shape detection, Xamã correctly identified 956 and 905 elements, respectively, out of 1171. Additionally, we compared the accuracy of Xamã and state-of-the-art tool img2UML, and we observe that Xamã outperformed img2UML in both precision and recall, being able to recognize 433 out of 614 textual elements as opposed to 171 by img2UML.

Telehealth Business Models and Their Components: Systematic Review.

BackgroundTelehealth technology is an excellent solution to resolve the problems of health care delivery. However, this technology may fail during large-scale implementation. As a result, business models can be used to facilitate commercialization of telehealth products and services.ObjectiveThe purpose of this study was to review different types of business models or frameworks and their components used in the telehealth industry.MethodsThis was a systematic review conducted in 2020. The databases used for searching related articles included Ovid, PubMed, Scopus, Web of Science, Emerald, and ProQuest. Google Scholar was also searched. These databases and Google Scholar were searched until the end of January 2020 and duplicate references were removed. Finally, articles meeting the inclusion criteria were selected and the Critical Appraisal Skills Programme (CASP) checklist was used for appraising the strengths and limitations of each study. Data were extracted using a data extraction form, and the results were synthesized narratively.ResultsInitially, 4998 articles were found and after screening, 23 were selected to be included in the study. The results showed that new telehealth business models were presented in 13 studies, and the applications of the existing business models were reported in 10 studies. These studies were related to different types of services, namely, telemonitoring (4 studies), telemedicine (3 studies), mobile health (3 studies), telerehabilitation (3 studies), telehealth (2 studies), assisted living technologies (2 studies), sensor-based systems (2 studies), and mobile teledermoscopy, teleradiology, telecardiology, and teletreatment (1 study related to each area). In most of the business models, value proposition, financial variables, and revenue streams were the main components.ConclusionsApplying business models in the commercialization of telehealth services will be useful to gain a better understanding of the required components, market challenges, and possible future changes. The results showed that different business models can be used for different telehealth technologies in various health systems and cultures. However, it is necessary to evaluate the effectiveness of these models in practice. Moreover, comparing the usefulness of these models in different domains of telehealth services will help identify the strengths and weaknesses of these models for future optimization.

Development of descriptive mathematical models for different domains of gingival recession using multiple linear regression analysis

Context:Gingival recession (GR) is a common finding seen in the periodontics clinic. It has a significant functional and esthetic impact on the patient's dentition and quality of life.Aims:The current study aimed to develop the descriptive mathematical models for different domains of GR based on the data obtained from the North Indian population.Settings and Design:Cross-sectional observational study.Materials and Methods:Consecutive 130 participants were enrolled between June and August 2019. Complete case history and thorough oral examination were carried out including assessment of periodontal variables, for example, pocket depth (PD), gingival marginal level, clinical attachment level (CAL), simplified oral hygiene index, and gingival index. Prediction models for different domains of GR, namely Miller's class, severity, extent, and distribution of recession were made, and further, the best-fitted model on the basis of “coefficient of determination (R2)” was analyzed.Statistical Analysis Used:Multiple linear regression.Results:Nine factors, i.e., mean CAL, mean PD, tooth mobility, abrasion, width of attached gingiva, number of teeth present, age, type of brush, and socioeconomic status showed a significant association with different domains of the GR. In addition, a high degree of overlap was observed among factors associated with different domains of the GR.Conclusion:Diverse clinical (mean CAL, mean PD, tooth mobility, and abrasion), biological (width of attached gingiva, number of teeth present, and age), and environmental factors (type of brush and socioeconomic status) were found to have a significant association with the occurrence of GR in the North Indian population. Owing to the multifactorial etiology of GR, the identification of susceptible patients based on the presence of risk factors is an essential step in developing action plans for the prevention of the disease.

A three-way convolutional network to compare 4D seismic data and reservoir simulation models in different domains

Four-dimensional seismic (4DS) contains spatial information that provides insights into the location, shape, and movement of fluids (oil, gas, water). It helps engineers to adjust reservoir simulation models and increase their capability of providing reliable production forecasts. Recent probabilistic approaches consider hundreds of numerical simulation model scenarios, which require automated methods to evaluate this large number of numerical models based on observed 4D seismic data. Comparing spatial information of seismic and numerical simulation data is difficult as, usually, these data are converted to maps with different properties. We propose a novel approach to compare 4D seismic data and simulation models using a three-way deep neural network that is trained using a reference image (4D seismic data) with two simulation model candidates. It learns to find the simulation models that best characterize the reference. Our method is underpinned by more than a thousand pairs of simulation models and reference maps evaluated by human specialists for training. For testing, we compare the inter-rater agreement among different specialist groups and generate a reliable test set considering examples in which there was agreement among at least two specialists. We observed that the group with best-trained specialists agree more in their answers and have a considerably higher inter-rater agreement than the less trained groups. When we evaluate our method with the answers from this specialized group, we observe that the simulation model chosen by our method is the one agreed by the specialists in almost 90% of the cases. We also discuss the impact of different noise levels in the input and show that our method outperforms other approaches in the literature if noise is present both in the training and test sets.

Making Deep Learning-Based Predictions for Credit Scoring Explainable

Credit scoring has become an important risk management tool for money lending institutions. Over the years, statistical and classical machine learning models have been the most researched risk management tools in credit scoring literature, and recently the focus has turned to deep learning models. This transition is due to better performances that are shown by deep learning models in different domains. Despite deep learning models' superior performances, there is still a need for explaining how these models make their predictions. The non-transparency nature of deep learning models has created a bottleneck for their use in credit scoring. Explanations of decisions are important for lending institutions since it is a requirement for automated decisions that are generated by non-transparent models to be explained. The other issue in using deep learning models, specifically 2D Convolutional Neural Networks (CNNs), in credit scoring is the need to have the data in image format. We propose an explainable deep learning model for credit scoring which can harness the performance benefits offered by deep learning and yet comply with the legislation requirements for the automated decision-making processes. The proposed method converts tabular datasets into images and thus allowing the application of 2D CNNs in credit scoring. Each pixel of the image corresponds to a feature bin of the tabular dataset. The predictions from the 2D CNNs were explained using state-of-the-art explanation methods. Furthermore, explanations were evaluated using a sanity check methodology and also performances of the explanation methods were compared quantitatively. The proposed explainable deep learning model outperforms the other credit scoring methods on publicly available credit scoring datasets.

A systematic literature review of cross-domain model consistency checking by model management tools

Objective The goal of this study is to identify gaps and challenges related to cross-domain model management focusing on consistency checking. Method We conducted a systematic literature review. We used the keyword-based search on Google Scholar, and we identified 618 potentially relevant studies; after applying inclusion and exclusion criteria, 96 papers were selected for further analysis. Results The main findings/contributions are: (i) a list of available tools used to support model management; (ii) 40% of the tools can provide consistency checking on models of different domains and 25% on models of the same domain, and 35% do not provide any consistency checking; (iii) available strategies to keep the consistency between models of different domains are not mature enough; (iv) most of the tools that provide consistency checking on models of different domains can only capture up to two inconsistency types; (v) the main challenges associated with tools that manage models on different domains are related to interoperability between tools and the consistency maintenance. Conclusion The results presented in this study can be used to guide new research on maintaining the consistency between models of different domains. Example of further research is to investigate how to capture the Behavioral and Refinement inconsistency types. This study also indicates that the tools should be improved in order to address, for example, more kinds of consistency check.

Schema abstraction with productive failure and analogical comparison: Learning designs for far across domain transfer

Although there has been considerable research into knowledge transfer for over a century, there remains a need for specific, validated techniques for teaching for transfer. This article reports on classroom-based research in which students learned about complex systems and climate change with agent-based computer models using two different instructional approaches based on productive failure (PF). In both PF approaches, students initially explored a problem space on their own and then received teacher-led instruction. One treatment group used climate computer models whereas the other group engaged in analogical comparisons between the same climate computer models and complexity computer models in different domains. The study found both groups demonstrated significant learning gains by posttest on assessments of declarative and explanatory knowledge and on within domain near transfer. However, students in the two models treatment group performed at a significantly higher level on an across domain far transfer problem solving task. Theoretical and practical implications are considered.

Semantic Integration of Information Models of Different Domains for the Railway Sector

Although BIM and GIS are from different domains, the interoperability of IFC and CityGML is seen today as a needed step for the plan, design, and construction of an infrastructure project. Such an approach utilizes data from both domains by converting two open data standards. However, the interoperability of GIS/BIM convergence with other domains, such as LandInfra, LADM, RailTopoModel, etc., is becoming increasingly more important, particularly in the projects of railway. Thus, the cooperation is not only for stakeholders within the AECO/MEP industry but also other stakeholders within other domains. A decentralized seamless data flow among different domains must be ensured by linking different domain information models. This study presents a comprehensive approach for incorporating information models with a particular focus on the railways. The approach in the study first asserts project information in BIM to be included in GIS using geospatial ontologies and then extends this approach by integrating other information models from different fields.

Irreversible Port-Hamiltonian Formulation of some Non-isothermal Electrochemical Processes

Abstract Electrochemical processes have been developed for a wide range of applications such as, mineral refining, water purification, energy storage and generation. The development of models to describe these processes is very important for their analysis, optimization and operation. The framework of irreversible port-Hamiltonian systems has proven to be an important tool to analyze and integrate thermal models with models of different domains. This work discusses the modeling of non-isothermal electrochemical processes as irreversible port-Hamiltonian systems. An irreversible port-Hamiltonian model based on the internal energy function is derived for a simple but general example. The irreversible model is obtained from the molar and charge balance equations combined with the entropy balance equation. The resulting model can be interpreted as a thermodynamic system and aspects such as entropy production, thermodynamic driving forces and intensive/extensive variables are encoded in the representation. An electrochemical process with two simultaneous reactions is considered to illustrate the approach. The interconnection with a resistive load is also considered to illustrate the benefit of the port-based formulation of the model.