Model Construction Process Research Articles

On Process Discovery Experimentation

Process mining aims to derive insights into business processes from event logs recorded from information systems. Process discovery algorithms construct process models that describe the executed process. With the increasing availability of large-scale event logs, process discovery has shifted towards a data-oriented research discipline, aiming to design algorithms that are applicable and useful in practice. This shift has revealed a fundamental problem in process discovery research: Currently, contributions can only be considered in isolation. Researchers conduct experiments to show that they move the field forward, but due to a lack of reliability and validity, the individual contributions are hard to generalise. In this paper, we argue that one reason for these problems is the lack of conventions or standards for experimental design in process discovery. Hence, we propose “process discovery engineering”: a research methodology for process discovery, consisting of a shared terminology and a checklist for conducting experiments. We demonstrate its applicability by means of an example experimental evaluation of process discovery algorithms and discuss the implications of the methodology on the field. This paper is not meant to be prescriptive, but to invite and encourage the community to contribute to this discussion to advance the field as a whole.

Enhancing periodic mobility planning: ARIMA-driven prognostications for subway passenger volume dynamics

Abstract. This study aims to accurately predict urban subway passenger flow using the Auto-Regressive Integrated Moving Average (ARIMA) and Seasonal Auto Regressive Integrated Moving Average (SARIMA) model, with the intention of providing a scientific basis for subway operation management. By meticulously sorting and analyzing the existing traffic data of a large city's subway system, this research constructs a model that comprehensively considering the seasonal, trend, and stochastic characteristics of time series data. During the model construction process, data preprocessing is carried out, including stationarity tests, differencing, model order determination, and parameter estimation, ultimately identifying an ARIMA and SARIMA model with good fitting results, effectively identifying and forecasting characteristics such as numerical fluctuations. Additionally, this study conducts a special analysis of the prediction effects at diverse time scales, verifying the applicability and superiority of the ARIMA and SARIMA model in subway passenger flow prediction. This research not only provides a powerful tool for passenger flow prediction for subway operation management departments, aiding in the reasonable allocation of capacity and optimization of operation strategies, but also holds significant reference and application value for the passenger flow prediction and management of other urban public transportation systems.

Explainable machine learning models for predicting the acute toxicity of pesticides to sheepshead minnow (Cyprinodon variegatus).

A quantitative structure-activity relationship (QSAR) study was conducted on 313 pesticides to predict their acute toxicity to Sheepshead minnow (Cyprinodon variegatus) by using DRAGON descriptors. Essentials accounting for a reliable model were all considered carefully, giving full consideration to the OECD (Organization for Economic Co-operation and Development) principles for QSAR acceptability in regulation during the model construction and assessment process. Nine variables were selected through the forward stepwise regression method and used as inputs to construct both linear and nonlinear models. The obtained models were validated internally and externally. Generally, machine learning-based methods, namely support vector machine (SVM), random forest (RF), and projection pursuit regression (PPR), perform better than the multiple linear regression (MLR) model. The statistical results (R2 = 0.682-0.933, Q2LOO = 0.604-0.659, Q2F1 = 0.740-0.796, CCC = 0.861-0.882) of the developed models show that they are robust, reliable, reproducible, accurate and predictive. Comparatively, the RF model performs best, giving predictive correlation coefficient Q2 of 0.814, root mean squared error (RMSE) of 0.658 and mean absolute error (MAE) of 0.534 for the test set, respectively. The RF model (as well as SVM and PPR models) was visualized and explained by using the SHapley Additive explanation (SHAP) analysis to enhance its transparency and credibility. In addition, the applicability domain (AD) range of the RF model was characterized by the Williams plot and the tree manifold approximation and projection (TMAP) technology was utilized to illustrate similarity and diversity of the entire data space, to assist in the analysis of the outliers. Activity cliff detection was investigated by using Arithmetic Residuals in K-groups Analysis (ARKA) descriptors. It was found that none of the pesticides was identified as an activity cliff in the training set or a potential prediction cliff in the test set. Therefore, the RF model fulfills each OECD principle in regulation for QSAR models. The research in this work will aid in the in silico QSAR prediction of the acute toxicity to Sheepshead minnow (Cyprinodon variegatus) for untested and new toxic pesticides and can also be extended to other studies.

Biofuser: a multi-source data fusion platform for fusing the data of fermentation process devices.

In the past decade, the progress of traditional bioprocess optimization technique has lagged far behind the rapid development of synthetic biology, which has hindered the industrialization process of synthetic biology achievements. Recently, more and more advanced equipment and sensors have been applied for bioprocess online inspection to improve the understanding and optimization efficiency of the process. This has resulted in large amounts of process data from various sources with different communication protocols and data formats, requiring the development of techniques for integration and fusion of these heterogeneous data. Here we describe a multi-source fusion platform (Biofuser) that is designed to collect and process multi-source heterogeneous data. Biofuser integrates various data to a unique format that facilitates data visualization, further analysis, model construction, and automatic process control. Moreover, Biofuser also provides additional APIs that support machine learning or deep learning using the integrated data. We illustrate the application of Biofuser with a case study on riboflavin fermentation process development, demonstrating its ability in device faulty identification, critical process factor identification, and bioprocess prediction. Biofuser has the potential to significantly enhance the development of fermentation optimization techniques and is expected to become an important infrastructure for artificial intelligent integration into bioprocess optimization, thereby promoting the development of intelligent biomanufacturing.

Применение имитационного моделирования в процессах постройки судна

This article provides an example of the application of the method of simulation modeling of ship construction processes in AnyLogic software. The process is briefly described and the logistics of building a barge produced at shipyards is characterized, and a map of the production process is prepared. In conclusion, three possible modernization options were proposed, which consist in technological, organizational improvements and a variant combining both of these solutions. AnyLogic software was used for a comparative analysis of the proposed options in relation to the process in the basic version. This method allows you to obtain accurate data for making informed decisions without the need for physical tests. The use of simulation modeling is a key tool for optimizing shipbuilding processes and further development of the industry.

A research and application of a digital failure knowledge model for nuclear power plant

Abstract The accumulation and application of knowledge about equipment component failures in nuclear power plant unit systems is an important way for domestic and foreign nuclear power plants to improve unit availability and economic benefits. Based on the existing equipment component knowledge models in China and the experience of digital transformation, this paper proposes a digital fault knowledge model construction process and method for nuclear power plant components, which is of great significance for standardizing and guiding domestic nuclear power plant knowledge models.

Modeling process for full forming sports underwear

Abstract Most of the sports underwear available is sewn using cutting and sewing techniques. During the exercise process, it is easy to cause discomfort to the skin due to repeated friction at the seam, and at the same time, it is also a waste of manpower and raw material costs. In order to address these issues present in existing sports underwear, during its design and development, combined with fully forming knitting technology, construction process model, so as to realize the integrated knitting of sports underwear. First of all, through the characteristics of the local style of sports underwear, the key points of its prototype were probed. Second, on this basis, its process model was established, including the forming methods and knitting rules of the body, shoulder collar, and bottom circumference. Finally, the feasibility of the technological model is proved by the braiding of a fully formed sports underwear. The change in the body size can be achieved by using the two-side braiding transfer method. The curve contour of the shoulder and neck can be obtained by using the triangular polyline segmentation method. The bottom part is divided into a cylinder part and a supporting part. The local braiding method is used to achieve the knitting. This study puts forward a process model and application method of fully formed sports underwear, which provides a certain method and reference for the design and production of fully formed sports underwear.

Comparison of the Torsional Strength of Material Samples Made Using Selected Rapid Prototyping Methods

In recent years, there has been a marked increase in the use of rapid prototyping techniques that support industrial processes. The analysis of studies on strength tests of parts manufactured using additive techniques from model materials and hybrid composites usually includes tests of material and strength parameters based on uniaxial tension, bending, and compression tests. For elements manufactured from polymeric materials using traditional methods (e.g. injection moulding), data obtained from these tests are sufficient to determine the strength of the material and to apply the results in the product design process. In the case of the layered extrusion method, due to the model construction process, strength data based on standard samples do not have a direct transposition on the strength of machine parts operating under various load ranges, especially torsional loads. The publication presents the results of tests on the torsional strength of cylindrical samples with splines produced by layered extrusion, vacuum casting technology, and hybrid technology, which combines both technologies. The test samples were made using a Prusa i3 MK3 3D printer and the plasticised plastic modelling (fused filament fabrication, FFF) method, while PolyJet technology was used to create a reference model. The findings indicate that hybrid technology, in which a thin-walled mould is filled with a chemically hardened polymer, achieves the desired strength for the manufactured parts while maintaining dimensional accuracy and shape. The research results show that producing rotating elements using the hybrid technology reduces the sample core’s ability to undergo plastic deformation due to the adhesion between the materials and the occurrence of notches resulting from the model production process using the layered extrusion method.

Advanced Predictive Modeling of Concrete Compressive Strength and Slump Characteristics: A Comparative Evaluation of BPNN, SVM, and RF Models Optimized via PSO

This study presents the development of predictive models for concrete performance, specifically targeting the compressive strength and slump value, utilizing the quantities of individual raw materials in the concrete mix design as input variables. Three distinct machine learning approaches—Backpropagation Neural Network (BPNN), Support Vector Machine (SVM), and Random Forest (RF)—were employed to establish the prediction models independently. In the model construction process, the Particle Swarm Optimization (PSO) algorithm was integrated with cross-validation to fine-tune the hyperparameters of each model, ensuring optimal performance. Following the completion of training and modeling, a comprehensive comparison of the predictive accuracy among the three models was conducted, with the aim of selecting the most suitable model for incorporation into an optimized objective function. The findings reveal that among the chosen machine learning techniques, BPNN exhibited superior predictive capabilities for the compressive strength of concrete. Specifically, in the validation set, BPNN achieved a high correlation coefficient (R) of 0.9531 between the predicted and actual outputs, accompanied by a low Root Mean Square Error (RMSE) of 4.2568 and a Mean Absolute Error (MAE) of 2.6627, indicating a precise and reliable prediction. Conversely, for the prediction of the concrete slump value, RF outperformed the other two models, demonstrating a correlation coefficient (R) of 0.8986, an RMSE of 9.4906, and an MAE of 5.5034 in the validation set. This underscores the effectiveness of RF in capturing the complexity and variability inherent in slump behavior. Overall, this research highlights the potential of integrating advanced machine learning algorithms with optimization techniques for enhancing the accuracy and efficiency of concrete performance predictions. The identified optimal models, BPNN for compressive strength and RF for slump, can serve as valuable tools for engineers and researchers in the field of construction materials, facilitating the design of concrete mixes tailored to specific performance requirements.

Innovative processes: economic and legal problems of realization, management and regulation

Problem setting. The scientific work is devoted to researching issues of regulation of innovation processes to achieve and increase the efficiency of innovation activity. In Ukraine, the strategy for the development of the sphere of innovative activity for the period until 2030 is aimed at increasing the use of innovations. A process approach was chosen to achieve the goals of the Strategy. However, it is necessary to generalize the problems using a systemic approach. Analysis of recent researches and publications. Since the middle of the 20th century. scientists have done a lot of work on defining the essence, structure and classifications of innovative processes, features of their management and regulation. A large number of works are devoted to the description, construction and improvement of innovative process models. In connection with the fact that the innovation process as an object of research is heterogeneous, in recent publications the critical rethinking of the theory and practice of management of innovation processes, increasing their efficiency, continues. Purpose of the research is the development of theoretical provisions and practical recommendations for structuring the economic and legal problems of management, implementation and regulation of innovation processes using a systemic approach to improve the state innovation policy and legal regulation of innovation activity. Article’s main body. The definition of the concept of the innovation process in the scientific literature and the international standard the Oslo Manual is considered. The Oslo Manual equates the innovation process with innovation activity. It has been specified that the management of innovative activities is an innovative process. To identify and strategically solve existing economic and legal problems of innovation processes, it is proposed to build a “black box” model according to the IDEF0 functional modeling standard. Models of innovation processes in the economy, at the enterprise, in clusters and ecosystems according to the IDEF0 standard have been developed. The economic and legal problems of innovation processes are structured by groups of problems of resources, executors, regulatory tools, international interaction, economic security of the state, collaboration, interaction of enterprises with the external environment, interaction of subjects in clusters and ecosystems, exercise of powers by authorities, protection of intellectual property rights, safety of innovations, performance and efficiency of innovative activities, informing about innovation processes, reporting of enterprises, reports of state regulators. An analysis of the completeness of the list of problems specified in the Strategy for the Development of the Sphere of Innovative Activity for the period up to 2030 was carried out. The directions for improving the state innovation policy and legal regulation of innovation activities in Ukraine are substantiated. Conclusions and prospects for development. The analysis of the Strategy for the Development of the Sphere of Innovative Activity on the basis of structured groups of problems allowed us to draw a conclusion about the state’s nonsystemic innovation policy, which poses a threat to the sovereignty of Ukraine. To get out of the critical situation, the government should revise the existing Strategy, taking into account the priority of protecting national interests and the safety of innovative products and innovative technologies for consumers and society. Regardless of measures to improve the Strategy, changes should be made to the national legislation regarding the harmonization of conflicting norms, bringing basic concepts and classifications into compliance with international standards, eliminating duplication of powers of authorities and defining a single regulator. Further research will be aimed at the scientific search for effective legal regulation solutions aimed at achieving performance and efficiency implementation of innovative processes in the national economy.

Systematic Literature Review on Knowledge Graphs in Construction Management from a Multi-Modal Perspective

The research of knowledge graph in construction management (KGCM) has become a current research hotspot. However, there are problems of insufficient data sources, low accuracy of information and the need for manual intervention in construction management, which needs to be improved urgently. This article adopts a hybrid review approach to comprehensively analyze the current research status of KGCM and summarizes the research results of KGCM. In addition, the gaps and future development directions are explored from a multi-modal perspective. The study shows that the research on KGCM under the multi-modal perspective still faces three major challenges: (1) Construction process modeling and optimization, (2) construction resource management and scheduling, (3) construction risk identification and response. This research provides new ideas and methods for the planning, design, construction and operation of engineering projects.

CPSGD: A Novel Optimization Algorithm and Its Application in Side-Channel Analysis

In recent years, side-channel analysis based on deep learning has garnered significant attention from researchers. A pivotal reason for this lies in the fact that deep learning-based side-channel analysis requires minimal preprocessing of side-channel data. The automatic feature extraction property of deep learning methods drastically reduces the workload for researchers, enabling them to focus more on the core issues of side-channel analysis, namely, extracting sensitive information by attacking devices. However, in prior studies, most scholars have concentrated more on the model construction process, with little research focusing on the choice of optimizers.This paper explores a novel deep learning-based optimization algorithm—CPSGD (combined projection stochastic gradient descent). The algorithm comprises two variants, designed, respectively, for unprotected side-channel analysis (CPSGD1) and desynchronized side-channel analysis (CPSGD2), and their convergence has been theoretically proven. Experimental results demonstrate that, while maintaining the neural network structure unchanged, CPSGD1 exhibits the best performance on unprotected datasets compared to other publicly available optimizers, whereas CPSGD2 performs optimally on desynchronized datasets.

A data-driven method to construct prediction model of solar stills

The interdisciplinary field between solar desalination and machine learning is the subject of a cutting-edge study. Generally, the studies treat data acquisition and model construction as independent processes, leading to problems such as insufficient dataset size or resource wastage. This study proposes a data-driven method that integrates data acquisition with model construction processes. By using the Bayesian optimization algorithm, the method accelerates the convergence of model accuracy. By comparing the results of 100 pairs of simulations, it is found that the models using the data-driven method are more accurate than traditional expert-driven methods in 70 % of compared results. Additionally, when it makes a model with the mean absolute percentage error as 5 %, the proposed data-driven method requires 220 additional data on average, compared to 258 with the traditional expert-driven method, representing a 14.7 % reduction. This work offers new ways and a broad application of the interdiscipline between solar desalination and machine learning.

Research and implementation of three-dimensional modeling techniques for Chinese dragon

This paper delves into a new trend in the field of computer science, which involves a shift from complex code editing techniques of the past towards more intuitive visual software applications. Under this trend, modeling and rendering techniques have undergone long-term development and continuous iteration, becoming indispensable tools across various domains. Using the construction of a Chinese dragon model as a case study, this paper showcases the application and development of this new trend through a detailed description of the selected software tools' characteristics, classification of production steps, and the modeling process. Special emphasis was placed on shaping key details such as the dragon's body contour, scales, eyes, etc., during the dragon model construction process, as well as how these details are manifested in software applications. Software selection and utilization were carefully aligned with practical needs and technical features to ensure the efficiency and accuracy of the modeling process. In-depth research into the modeling process revealed the potential and advantages of this new technology, receiving widespread acclaim and recognition.

Research and implementation of three-dimensional modeling techniques for Chinese dragon

This paper delves into a new trend in the field of computer science, which involves a shift from complex code editing techniques of the past towards more intuitive visual software applications. Under this trend, modeling and rendering techniques have undergone long-term development and continuous iteration, becoming indispensable tools across various domains. Using the construction of a Chinese dragon model as a case study, this paper showcases the application and development of this new trend through a detailed description of the selected software tools' characteristics, classification of production steps, and the modeling process. Special emphasis was placed on shaping key details such as the dragon's body contour, scales, eyes, etc., during the dragon model construction process, as well as how these details are manifested in software applications. Software selection and utilization were carefully aligned with practical needs and technical features to ensure the efficiency and accuracy of the modeling process. In-depth research into the modeling process revealed the potential and advantages of this new technology, receiving widespread acclaim and recognition.

On Data Driven SIRD Model of Delta and Omicron Variants of COVID-19

The compartmental model stands as a cornerstone in quantitatively describing the transmission dynamics of diseases. Through a series of assumptions, this model can be formulated and subsequently validated against real-world conditions. Leveraging the abundance of COVID-19 data presently available, this study endeavors to reverse engineer the model construction process. Specifically, we analyse the compartmental model governing two notable variants of COVID-19: Delta and Omicron, utilizing empirical data. Employing the SINDy method, we extract parameters that define the model by effectively fitting the available data. To ensure robustness, the obtained model undergoes validation via comparison with real-world data through numerical integration. Additionally, we conduct fine-tuning in regularization techniques and input features to refine model selection. The constructed model then undergoes thorough analysis to gain qualitative insights and interpretations regarding the transmission dynamics of COVID-19.

Precise Modeling and Analysis of Aviation Power System Reliability via the Aviation Power System Reliability Probability Network Model

This study addresses the challenges of accurately analyzing the reliability of aviation power systems (APS) using traditional models by introducing the Aviation Power System Reliability Probability Network Model (APS-RPNM). The model directly transforms the system architecture into an equivalent probability network, aiming to develop a precise reliability model that captures system functions and fault logic. By classifying APS components into five distinct structural patterns and mapping them to corresponding nodes in the APS-RPNM, the model is successfully constructed. Specifically, None-Input-to-Multiple-Output components are transformed into two-state nodes, while Multiple-Input-to-None-Output, Single-Input-to-Multiple-Output, and Multiple-Input-to-Single-Output components are mapped to three-state nodes. For Multiple-Input-to-Multiple-Output components, a novel approach employing multiple two-state sub-nodes is adopted to capture their complex functional logic. A case study comparing the performance of the APS-RPNM with the traditional minimal path set method in reliability analysis was conducted. The results demonstrate that the APS-RPNM not only simplifies the model construction process and eliminates errors stemming from subjective engineering judgments but also enables the efficient computation of power supply reliability for all load points in a single inference by integrating all of the components. This significantly improves computational efficiency and system dependency analysis capabilities, highlighting the APS-RPNM’s tremendous potential in optimizing the reliability design of APS.

Data augmentation based on highlight image models of underwater maneuvering target

With the development of underwater acoustic countermeasure technology, deep learning is applied to recognize echo geometry features of underwater targets, but it faces the problem of sample scarcity. In this paper, we improved the underwater target highlight model, and established the target echo information equation of active sonar. By changing the spatial positions of target and sonar regularly, we performed the highlight image models of underwater maneuvering targets. Taking an underwater vehicle as an example, the model construction process was introduced in detail, and highlight image models of four typical acoustic scale decoys were also established, and five multi-space state highlight image data samples were generated. The eHasNet-5 convolutional classification network was designed, and the network was trained, verified and tested with the generated data. Finally, the experimental data test shows that the target highlight image generation models provide a new data augmentation method for the application of deep learning in active sonar target recognition, and the trained network by generated data has the ability to classify two-dimensional objects.

#88 Establishment of machine learning-based risk prediction model for acute kidney injury after acute myocardial infarction

Abstract Background and Aims Acute kidney injury (AKI) is a common complication of acute myocardial infarction (AMI) with high morbidity, mortality and lack of effective treatment, so prevention is particularly important. This study intends to use machine learning to establish a precise prediction model for AKI after AMI. Method AMI patients were consecutively collected from July 2011 to December 2016 in Beijing Anzhen Hospital, Capital Medical University. First, SelectFromModel and Lasso regression model were used to select features. A predictive model (Model A) was then created using a multivariate logistic regression model in the training set and validated in the test set. At the same time, the prediction model (Model B) is created by machine learning algorithm in the training set. The process of model construction and evaluation is implemented by Python. The algorithm includes MLP, SVM, KNN and SimpleRNN, from which the model with the largest area under the ROC curve (Model B) is selected and verified in the test set. DeLong method was used to compare the model B with model A to compare whether the area under the ROC curve was better than multivariate logistic regression model and select the best model. Results A total of 6014 AMI patients were included in this study, 70% were randomly selected as the training set, and the remaining 30% were used as the test set. Males comprised 80.5% of the total population with a mean age of 58.4 ± 11.7 years. The incidence of AKI in the overall population was 11.2% (674/6014) (Fig. 1). A total of 12 important characteristics were included in the model, including the number of myocardial infarctions, ST-segment elevation myocardial infarction, ventricular tachycardia, third-degree atrioventricular block, decompensated heart failure at admission, admission serum creatinine value, admission urea nitrogen value, admission CK-MB peak value, whether diuretics were used, maximum daily dose of diuretics, days of diuretic use, and whether statins were used. Logistic regression analysis resulted in an area under the ROC curve of 0.80 (95% CI, 0.76-0.84) in the test set (Fig. 2). The models were constructed by MLP, SVM, KNN and SimpleRNN algorithms, respectively, and validated in the test set to calculate the area under the ROC curve of each model in the test set (Fig. 3), and finally the model constructed by MLP algorithm was selected as model B, and its area under the ROC curve was 0.82 (95% CI, 0.78–0.85). The area under the ROC curve of the two models was compared at p=0.363, but the machine learning algorithm constructed models with higher absolute values (Fig. 4). Conclusion The prediction model of AKI risk after AMI constructed based on machine learning is similar to that constructed by logistic regression analysis in terms of prediction ability, but the model constructed by machine learning algorithm has a better trend, indicating that the machine learning algorithm may improve the prediction ability of prediction model and provide an effective tool for early identification of these high-risk patients in clinical practice, early preventive measures, and reduction of morbidity.

Public Bicycle Dispatch Method Based on Spatiotemporal Characteristics of Borrowing and Returning Demands

Public bicycle systems (PBSs) serve as the ‘last mile’ of public transportation for urban residents, yet the problem of the difficulty in borrowing and returning bicycles during peak hours remains a major bottleneck restricting the intelligent and efficient operation of public bicycles. Previous studies have proposed reasonable models and efficient algorithms for optimizing public bicycle scheduling, but there is still a lack of consideration for actual road network distances between stations and the temporal characteristics of demand at rental points in the model construction process. Therefore, this paper aims to construct a public bicycle dispatch framework based on the spatiotemporal characteristics of borrowing and returning demands. Firstly, the spatiotemporal distribution characteristics of borrowing and returning demands for public bicycles are explored, the origin–destination (OD) correlation coefficients are defined, and the intensity of connections between rental point areas is analyzed. Secondly, based on the temporal characteristics of rental point demands, a random forest prediction model is constructed with weather factors, time characteristics, and rental point locations as feature variables, and station bicycle-borrowing and -returning demands as the target variable. Finally, bicycle dispatch regions are delineated based on actual path distances between stations and OD correlation coefficients, and a public bicycle regional dispatch optimization method is established. Taking the PBS in Ningbo City as an example, the balancing optimization framework proposed in this paper is validated. The results show that the regional dispatch optimization method proposed in this paper can achieve optimized dispatch of public bicycles during peak hours. Additionally, compared with the Taboo search algorithm (TSA), the genetic algorithm (GA) exhibits a 11.1% reduction in rebalancing time and a 40.4% reduction in trip cost.