Iterative Model Research Articles

Hidden code vulnerability detection: A study of the Graph-BiLSTM algorithm

Context:The accelerated growth of the Internet and the advent of artificial intelligence have led to a heightened interdependence of open source products, which has in turn resulted in a rise in the frequency of security incidents. Consequently, the cost-effective, fast and efficient detection of hidden code vulnerabilities in open source software products has become an urgent challenge for both academic and engineering communities. Objectives:In response to this pressing need, a novel and efficient code vulnerability detection model has been proposed: the Graph-Bi-Directional Long Short-Term Memory Network Algorithm (Graph-BiLSTM). The algorithm is designed to enable the detection of vulnerabilities in Github’s code commit records on a large scale, at low cost and in an efficient manner. Methods:In order to extract the most effective code vulnerability features, state-of-the-art vulnerability datasets were compared in order to identify the optimal training dataset. Initially, the Joern tool was employed to transform function-level code blocks into Code Property Graphs (CPGs). Thereafter, structural features (degree centrality, Katz centrality, and closeness centrality) of these CPGs were computed and combined with the embedding features of the node sequences to form a two-dimensional feature vector space for the function-level code blocks. Subsequently, the BiLSTM network algorithm was employed for the automated extraction and iterative model training of a substantial number of vulnerability code samples. Finally, the trained algorithmic model was applied to code commit records of open-source software products on GitHub, achieving effective detection of hidden code vulnerabilities. Conclusion:Experimental results indicate that the PrimeVul dataset represents the most optimal resource for vulnerability detection. Moreover, the Graph-BiLSTM model demonstrated superior performance in terms of accuracy, training cost, and inference time when compared to state-of-the-art algorithms for the detection of vulnerabilities in open-source software code on GitHub. This highlights the significant value of the model for engineering applications.

A novel iterative model updating for jointed structures using nonlinear FRFs

A novel iterative model updating method is developed to identify the local nonlinear joint properties using the frequency response functions (FRFs) of assembled structures. In this paper, the least-squares fitting method was used to transform the sensitivity matrix into a square iteration matrix to match the dimensions of the objective functions and nonlinear joint model parameters. Leveraging the Newton’s iteration, the adaptive successive over-relaxation (A-SOR) was used to ensure iteration convergence while the multi-scale parameter adjusting (MPA) strategy was developed to degrade the ill-condition of the iteration matrix. Two updating examples of phenomenological equivalence models were applied to demonstrate the effectiveness of the proposed method. The nonlinear FRFs of a lap-type bolted joint beam system with Iwan model were simulated as the objective functions to identify the local nonlinear joint properties, as well as experimental investigations of a metal rubber isolation system with a high-order polynomial model. The proposed method was validated by the good agreement of the comparison results, and it indicated a better model updating performance with a much smaller condition number of the iteration matrix.

Study on the Determination of Flavor Value of Rice Based on Grid Iterative Search Swarm Optimization Support Vector Machine Model and Hyperspectral Imaging.

In the field of rice processing and cultivation, it is crucial to adopt efficient, rapid and user-friendly techniques to detect the flavor values of various rice varieties. The conventional methods for flavor value assessment mainly rely on chemical analysis and technical evaluation, which not only deplete the rice resources but also incur significant time and labor costs. In this study, hyperspectral imaging technology was utilized in combination with an improved Particle Swarm Optimization Support Vector Machine (PSO-SVM) algorithm, i.e., the Grid Iterative Search Particle Swarm Optimization Support Vector Machine (GISPSO-SVM) algorithm, introducing a new non-destructive technique to determine the flavor value of rice. The method captures the hyperspectral feature data of different rice varieties through image acquisition, preprocessing and feature extraction, and then uses these features to train a model using an optimized machine learning algorithm. The results show that the introduction of GIS algorithms in a PSO-optimized SVM is very effective and can improve the parameter finding ability. In terms of flavor value prediction accuracy, the Principal Component Analysis (PCA) combined with the GISPSO-SVM algorithm achieved 96% accuracy, which was higher than the 93% of the Competitive Adaptive Weighted Sampling (CARS) algorithm. And the introduction of the GIS algorithm in different feature selection can improve the accuracy to different degrees. This novel approach helps to evaluate the flavor values of new rice varieties non-destructively and provides a new perspective for future rice flavor value detection methods.

A Novel Financial Anti-fraud Method based on Machine Learning Algorithms

Digital finance is booming, financial technology is maturing, and the development of information technology has had a massively positive impact on society. However, such progress also introduces a new type of risk: the underground network industry is experiencing explosive growth, and telecommunications network fraud has caused enormous financial losses. In the age of digital finance, although commercial banks have ushered in new possibilities and created momentum, they must also confront new obstacles and needs for digital transformation. In this context, online financial services have emerged as the new primary battleground. In this study, based on the RFM high-dimensional derived features and machine learning techniques, a high-dimensional transaction behavior portraits-based anti-fraud machine learning model is created. Using big data, stream computing, and other technologies, as well as systematic deployment, application strategy, and iterative model optimization, we developed a set of machine learning-based in-event risk control solutions. Confirmed to have an AUC of 0.972, this model provides key insight into fraud risk, identifies fraudulent transactions in milliseconds, and has value and relevance for enhancing the in-transaction risk management capabilities of online digital financial organizations.

Improved Estimates of Sub‐Regional Groundwater Storage Anomaly Using Coordinated Forward Modeling

AbstractGroundwater storage anomaly (GWSA) can be estimated either at the large scale from the Gravity Recovery and Climate Experiment (GRACE) or at the local scale based on in situ observed groundwater level (GWL) and aquifer storage parameters. Yet, the accuracy of GRACE‐based estimate is affected by leakage errors, while that of local GWL‐based estimate requires the reliable specific yield (Sy) data that are usually not available. Here, we developed a novel approach, the coordinated forward modeling (CoFM), based on the iterative forward modeling to improve GWSA estimation at the sub‐regional scale smaller than the typical GRACE footprint. It is achieved by solving Sy through iterative comparisons between GRACE‐based and observation‐based GWSA at 0.5° grid scale, and then re‐calculating GWSA using the updated Sy and observed GWL. The utility of CoFM is explored by using the hypothetical experiments and a real case study in the Piedmont Plain (PP, ∼54,000 km2) and East‐central Plain (ECP, ∼86,000 km2) of North China Plain. Results show that CoFM can detect GWSA at 0.5° grid scale in the hypothetical experiments given the large spatial variability of GWL. While in the real case study, the CoFM distinguishes between the divergent unconfined GWSA trends (2005–2016) in PP (−41.80 ± 0.55 mm/yr) and ECP (−7.57 ± 0.60 mm/yr) caused by the differences in hydrogeological conditions and groundwater use. The improvement made by CoFM can be attributed to the use of the distributed GWL information to constrain GRACE leakage errors. This study highlights a practical important solution for improving sub‐regional GWSA estimation through the joint use of large‐scale GRACE data and local‐scale well observations.

Evaluation of an in-use chest CT protocol in lung cancer screening - A single institutional study.

Lung cancer is the most common cause of cancer-related death worldwide and therefore there has been a growing demand for low-dose computed tomography (LDCT) protocols. To investigate and evaluate the dose and image quality of patients undergoing lung cancer screening (LCS) using LDCT in Norway. Retrospective dosimetry data, volumetric CT dose index (CTDIvol) and dose-length product (DLP), from 70 average-size and 70 large-size patients who underwent LDCT scan for LCS were included in the survey. Effective dose and size-specific dose were calculated for each examination and were compared with the American Association of Physicists in Medicine (AAPM) requirement. For a quantitative image quality analysis, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were determined for different regions in the chest with two iterative reconstruction techniques, iDose and Iterative Model Reconstruction. Differences in dose and image quality between average-size and large-size patients were evaluated by Independent sample t test, and Wilcoxon signed rank test within the same patient group. The independent sample t test revealed significant differences (p < .05) in dose values between average-size and large-size patients. Mean CTDIvol and DLP for average-size patients were 2.8mGy and 115mGy.cm, respectively, with appropriate increment for the large-size patients. Image quality (image noise, SNR, and CNR) did not significantly differ between patient groups when images were reconstructed with a model based iterative reconstruction algorithm. The screening protocol assessed in this study resulted in CTDIvol values that were compliant with AAPM recommendation. No significant differences in objective image quality were found between patient groups.

Creating and Validating a Digital Leadership Model for University Teachers, Liaoning Province

Background and Aims: In the era of digital transformation, digital leadership has emerged as a critical component of educators' ability to navigate and utilize data literacy in increasingly digitalized environments. University teachers, in particular, need digital leadership to adapt to advancements in technology and enhance their teaching and administrative skills. This study focuses on constructing and validating a digital leadership model specifically for university teachers in Liaoning Province. The research aims to identify the key components of digital leadership and develop a model that addresses the current and future needs of educators in this evolving landscape. Methodology: The study employs a grounded theory approach to build a theoretical structure of digital leadership for university teachers. Field interviews with a diverse group of university educators were conducted to gather qualitative data. This data was then analyzed through a series of open, axial, and selective coding processes, allowing the identification of six key categories that form the foundation of digital leadership. These categories were then subjected to quantitative analysis using structural equation modeling (SEM) to assess the fit of the proposed model. Validation was achieved through iterative model testing and refinement, ensuring that the final model accurately represents the digital leadership characteristics of university teachers. Results: The analysis revealed six key dimensions of digital leadership for university teachers: Digital Leading Insight: The ability to foresee digital trends and incorporate them into teaching strategies. Intelligent Teaching Organization: Effective integration of technology in teaching methods to enhance learning outcomes. Industry-Education Integration Promotion: Fostering collaborations between academia and industry to align educational practices with industry needs. Teacher Professional Development Learning: Ongoing self-improvement and learning to stay updated with technological advancements. Digital Cooperation and Communication Influence: Facilitating effective digital communication and collaboration within and across institutions. Digital Education Policy Decision-Making: Engaging in the formulation and implementation of digital policies in education. The model demonstrated a high degree of fit across all indices, confirming its validity as a framework for understanding digital leadership in the context of university educators. Conclusion: The study provides a validated model of digital leadership for university teachers, highlighting six core competencies that educators must develop to succeed in the digital era. Recommendations for fostering digital leadership include offering leadership development training, optimizing blended learning environments, enhancing collaboration, driving organizational change, establishing incentive mechanisms, and promoting an integrated culture of industry-education collaboration. The results suggest that addressing these areas will significantly enhance the digital leadership capacity of university teachers in Liaoning Province, thereby improving educational outcomes in the digital age.

Assessment of the severity of associated ischemia in conditions of atherosclerosis of the carotid arteries and arteries of the lower extremities

The purpose of the research is to develop a method for assessing the severity of ischemic processes in multifocal atherosclerosis against the background of chronic cerebrovascular insufficiency and chronic ischemia of the lower extremities.Methods. The main methods used in this study are the methodology for the synthesis of hybrid fuzzy decision rules, exploratory analysis, and the Delphi expert assessment method; calculations were based on the G. Rush model and the E. Shortliff iterative model.Results. In the course of the research, particular decisive rules were synthesized to assess violations of the regulatory functions of the brain, ischemic disorders of the brain and lower extremities, disorders of the motor functions of the lower extremities, on the basis of which, using the iterative model of E. Shortliff and aggregating decisive rules, intermediate decisive rules were formed, which, in turn, entered the final decisive the rule "severity of ischemic interaction". Further, based on the final decisive rule, an algorithm was developed to assess the severity of ischemic interactions for comorbid patients with disintegration of affective-effector mechanisms of interaction between peripheral organs and regulatory functions of the central nervous system, allowing to assess the severity of the ischemic process and the risk of fatal complications in patients with the pathology in question.Conclusion. In the course of the conducted research, high results were demonstrated in the application of synthesized partial decision rules within the framework of the task set in this study, and the expediency of using the obtained models and methods in the practice of a neurologist, vascular surgeon, angioedrologist, neurosurgeon was also shown.

Major Problems in Clinical Psychological Science and How to Address them. Introducing a Multimodal Dynamical Network Approach

Abstract Background Despite impressive dissemination programs of best-practice therapies, clinical psychology faces obstacles in developing more efficacious treatments for mental disorders. In contrast to other medical disciplines, psychotherapy has made only slow progress in improving treatment outcomes. Improvements in the classification of mental disorders could enhance the tailoring of treatments to improve effectiveness. We introduce a multimodal dynamical network approach, to address some of the challenges faced by clinical research. These challenges include the absence of a comprehensive meta-theory, comorbidity, substantial diagnostic heterogeneity, violations of ergodicity assumptions, and a limited understanding of causal processes. Methods Through the application of multimodal dynamical network analysis, we describe how to advance clinical research by addressing central problems in the field. By utilizing dynamic network analysis techniques (e.g., Group Iterative Multiple Model Estimation, multivariate Granger causality), multimodal measurements (i.e., psychological, psychopathological, and neurobiological data), intensive longitudinal data collection (e.g., Ecological Momentary Assessment), and causal inference methods (e.g., GIMME), our approach could improve the comprehension and treatment of mental disorders. Under the umbrella of the systems approach and utilizing e.g., graph theory and control theory, we aim to integrate data from longitudinal, multimodal measurements. Results The multimodal dynamical network approach enables a comprehensive understanding of mental disorders as dynamic networks of interconnected symptoms. It dismantles artificial diagnostic boundaries, facilitating a transdiagnostic view of psychopathology. The integration of longitudinal data and causal inference techniques enhances our ability to identify influential nodes, prioritize interventions, and predict the impact of therapeutic strategies. Conclusion The proposed approach could improve psychological treatment by providing individualized models of psychopathology and by suggesting individual treatment angles.

Federated Learning for Edge Computing in REST APIs: Investigate the Feasibility of Employing Federated Learning Techniques to Train Machine Learning Models Directly on Edge Devices Interacting with REST APIs, Minimizing Data Transfer and Enhancing Privacy

This research explores the feasibility of using federated learning techniques to train machine learning models directly on edge devices interacting through REST APIs. This article designs an architecture that facilitates federated learning using REST APIs for communication between a central server and edge nodes. The architecture ensures efficient model distribution, update aggregation, and iterative global model refinement. This research implements this system in a simulated environment to evaluate its performance. Initial results show that federated learning significantly reduces data transfer and enhances privacy without compromising model accuracy. The REST API-based communication model effectively coordinates updates between the central server and edge devices, and privacy-preserving techniques maintain data security throughout the process. This study confirms that federated learning is a viable solution for edge computing, addressing key challenges in data privacy and communication efficiency, and opens pathways for scalable and effective distributed learning systems in real-world IoT applications. Federated learning offers a decentralized alternative, enabling local model training on edge devices with only model updates shared with a central server. This approach minimizes data transfer and enhances privacy.

The pressure-volume relationship in an ideal Stirling refrigerator

Hysteresis losses in the heat transfer between compressing or expanding gas and the adjacent wall is said to play an important role in Stirling machines, where it increases the amount of required p-V work. Previous studies have linked hysteresis loss with the pressure phase shift. In the context of this research, the effect of the pressure phase shift on the net p-V work in a single space is examined.A Sage model of a single space piston-cylinder device is used to investigate the underlying mechanisms of the pressure phase shift. The Sage model is validated using an experimental piston seal rig. In addition, the time dependence of heat transfer is discussed along with how it affects the pressure phase shift, using an iterative model. The Schmidt equations were manipulated to determine the phase shift between pressure and volumetric oscillation in an ideal Stirling refrigerator.The results of this investigation are surprising. It was found that even in the case of an idealized Stirling refrigerator, the phase shift between pressure and volume is non-zero in order to produce a refrigeration effect.

Multi-Dimensional Iterative Constitutive Model of Concrete under Complex Stress Conditions in Composite Structures

In composite structures or complex concrete members, some concrete bears multiple forces, called core concrete. The properties of the core concrete are variable under complex stress conditions, which will influence the structure performance analysis. Therefore, it is necessary to establish an accurate and theoretical constitutive model of concrete under complex stress conditions. The elastic–plastic properties of concrete in complex stress conditions were analyzed first. Then, the failure criterion of concrete in complex stress conditions was discussed to identify the key parameters. And the relationship between the stress–strain curve and failure criterion was analyzed through mathematical derivation. Finally, the multi-dimensional iterative constitutive model of concrete under complex stress conditions was established and verified. Based on the analysis results, the concrete under multi-axial stress conditions shows a spindle-shape stress envelope diagram. The failure criterion should be established by the analysis of concrete under high multi-axial compression conditions, tension–compression conditions, and shear–compression conditions. The plastic modulus is the key to reflecting the plastic strain development trend and the stress–strain relationship.

Application of Heterogeneous Data Analysis based on SEA Grid in User Investment Analysis

To solve the problem of yield calculation in complex investment scenarios, a time-cost double-weighted rate of return calculation method based on SEA grid is proposed, and its effectiveness is verified by comparing with traditional methods and researching the quantitative evaluation and analysis method of user investment based on structured data. To solve the above problems, a data-heterogeneous federated learning method based on user investment analysis FedPSG is proposed, which changes the data form transmitted from the client to the server from model parameters to model scores, and only a small number of clients need to upload model parameters to the server in each round of training, thereby reducing communication costs. At the same time, a model retraining strategy is proposed, which uses server data to train the global model for second iteration, and further improves the model performance by alleviating the impact of data heterogeneity on federated learning. The method of event dimension analysis of user investment is designed, and a credibility index is proposed to evaluate the analysis results. Experiments show that by combining event data, it can effectively provide users with event factors in the fluctuation of investment profit and loss, and help users better analyze their own investments.

Bifurcation Analysis and Chaos Control of Carrier Phase-Shifted Cascaded H-Bridge Inverter

Cascaded H-bridge inverters, which belong to strongly nonlinear time-varying system with complex dynamics, have been widely used in high-voltage and high-power engineering fields. In this paper, a carrier phase-shifted sinusoidal pulse-width modulation cascaded H-bridge inverter is taken as an example with piecewise analysis to establish the discrete iterative mathematical model. Furthermore, the nonlinear dynamic behavior of this inverter system is investigated using folding diagrams, spectrum diagrams, bifurcation diagrams, Lyapunov exponents, etc. We find that this inverter can exhibit multiperiod bifurcation, tangential bifurcation and paroxysmal chaos within certain ranges of control coefficients and other circuit parameters, which will influence the system’s stability seriously. On the basis of this discovery, the sinusoidal time-delay feedback control method is proposed. The difference between the load current of the controlled object and its own delay is used to form a feedback term, which is then fed into the sine function and proportional link to obtain the control term. Moreover, the Jacobian matrix of this feedback inverter system is derived, and the constraints on the feedback control coefficient are obtained based on the Jury criterion. Simulation results have verified the effectiveness of such a sinusoidal time-delay feedback control method, which can improve the stability and anti-interference of the system. The research can be used to provide some reference and guidance for the circuit design, debugging and control of cascaded H-bridge inverters.

Product Design for Batch Processes Based on Iterative Learning-Latent Variable Model Inversion (IL-LVMI)

Product Design for Batch Processes Based on Iterative Learning-Latent Variable Model Inversion (IL-LVMI)

Iterative enhancement fusion-based cascaded model for detection and localization of multiple disease from CXR-Images

The lungs are a vital organ of the human body. Malfunctioning of the lungs caused a direct threat to life. In recent years the world has witnessed massive medical insufficiency to handle the lung diseases caused by numerous agents including COVID-19. According to the recommended course of treatment, medical imaging tests including X-rays and CT scans have been very helpful in identifying multiple chest infections. Automatic detection of chest disease is the need of the modern time as it will speed up patient care and reduce doctors’ workload. An Iterative Enhancement Fusion-based Cascaded (IEFCM) model to identify multiple diseases from chest X-ray images is suggested in the present paper. If a chest infection is discovered in the imaging, the suggested model additionally localizes the precise infected area on the CXR image. Experimental outcome clearly demonstrates that the performance of suggested model is significantly superior to the pre-trained model, that is the Golden standard dataset and data from the local population. In terms of sensitivity and specificity, IEFCM achieved 95.62 % sensitivity, which indicates an accurate diagnosis of lung disease, reducing the risk of missing any instances. Similarly, the specificity is 96.23 %, which denotes, the IEFCM model correctly identified the healthy people. It resulted decrease of misdiagnosis and unnecessary follow-up testings.

Modeling and analysis of digital current‐mode controlled single‐inductor dual‐output DC–DC converter with different PWM modulation modes

SummaryCurrent‐mode control is extensively used in dc–dc converters as the merits of fast transient performance, simple control loop, and elimination of right‐half‐plane zeros for boost‐type dc–dc converters. In single‐inductor multiple‐output (SIMO) dc–dc converter, the inductor current would present different trends under different circuit parameters. Therefore, the control logic changes for different inductor current trends, and the corresponding modulations are absolutely different. In this paper, a digital current‐mode control technology for SIMO dc–dc converter is proposed to expend the convenience of current‐mode control with different inductor trends. Choosing continuous conduction mode (CCM) single‐inductor dual‐output (SIDO) dc–dc converter as the research object, the principles are analyzed under different pulse width modulation modes, and the corresponding control algorithms are derived. Moreover, the discrete iterative map model is established to analyze the stability of input and output voltages varying. The results show that not only the digital current‐mode controlled SIDO buck converter has fast load transient response and small cross‐regulation but also the input and output voltages will not affect the stability in the leading edge modulation, which is different from the corresponding analog current‐mode control technology. Finally, the experimental results verify the correctness of the theoretical analysis.

Joint Routing and Pricing Control in Bimodal Mixed Autonomy Networks with Elastic Demand and Three-Dimensional Passenger Macroscopic Fundamental Diagram

The interaction between mixed autonomy traffic and public transport vehicles competing for limited road space is a less explored area of research. To evaluate the traffic dynamics in bimodal networks, a three-dimensional (passenger) network fundamental diagram, known as 3D-NFD (3D-pNFD), can be estimated that relates the accumulation of cars (autonomous and human-driven) and buses to the network vehicular (passenger) travel production. In this study, we propose a 3D-pNFD-based congestion pricing scheme considering three vehicle classes of buses, system-optimal (SO) seeking connected and automated vehicles (CAVs), and user-equilibrium (UE) seeking human-driven vehicles (HVs). We develop an iterative tri-level modeling framework for mode choice, pricing, and route choice in a mixed autonomy network. The lower level generates mixed equilibrium traffic flow through an integrated mixed equilibrium simulation-based dynamic traffic assignment model and a transit assignment model. The mid-level finds the optimal toll rates through a 3D-pNFD feedback-based controller. A nested logit-based mode choice model is also applied to capture travelers’ preferences toward three available modes and incorporates elastic demand. To encourage CAVs to follow the SO routing mode, they are provided with a discount on the congestion toll whereas UE-seeking HVs are subject to full price toll. Buses are also entirely exempt from the toll. We explore three scenarios with different discount rates on SO-seeking CAVs to investigate the effect of the incentive plans on the mode choice behaviors of road users in the pricing zone. The performance of the proposed model is evaluated in a large-scale network in Melbourne, Australia.

Combined Iterative Learning and Model Predictive Control Scheme for Nonlinear Systems

Combined Iterative Learning and Model Predictive Control Scheme for Nonlinear Systems

Clinic Management System

Abstract: As people’s levels of education rise particularly in medical industry the progress of our nation impacted by the inadequate health care patients in government hospitals occasionally have to wait hours to receive care. Although administration must maintain track of a vast number of files containing all patient information, this can occasionally result in redundant data and extra effort. This is the rationale for the proposal for the Online Clinic Management System, which is being developed with a web-based idea. An iterative waterfall model approach, dataflow, logical and entity relationship diagrams were among the techniques utilized in the system’s development. Were employed in the system’s design. Because all manual tasks in this system are being converted to computerized types, there would be no data redundancy during the registration process, records on patient details could be found more quickly, and patient waiting times before receiving medical treatment could be reduced. Keywords: computerized, health care, online clinic management system, and patient record.