Typical Data Research Articles

Posterior Predictive Checking for Partially Observed Stochastic Epidemic Models

We address the problem of assessing the fit of stochastic epidemic models to data. Two novel model assessment methods are developed, based on disease progression curves, namely the distance method and the position-time method. The methods are illustrated using SIR (susceptible-infective-removed) models. We assume a typical data observation setting in which case-detection times are observed while infection times are not. Both methods involve Bayesian posterior predictive checking, in which the observed data are compared to data generated from the posterior predictive distribution. The distance method does this by calculating distances between disease progression curves, while the position-time method does this pointwise at suitably selected time points. Both methods provide visual and quantitative outputs with meaningful interpretations. The performance of the methods benefits from the development and application of a time-shifting method that accounts for the random time delay until an epidemic takes off. Extensive simulation studies show that both methods can successfully be used to assess the choice of infectious period distribution and the choice of infection rate function.

Modular Data Plane Verification for Compositional Networks

Modern networks are increasingly using layering and bridging to form a compositional architecture. Layering protocols like VXLAN create multiple overlay networks on top of a single underlay network infrastructure. This makes network configurations even more complex, and error-prone. To check the correctness of such compositional networks, one needs to model the dependency across multiple layers (underlay and overlay) and multiple domains (different VPNs/VPCs). Existing verifiers, which are optimized to scale in single-layer single-domain networks, exhibit scalability limitations when applied to compositional networks. This paper proposes MNV, a modular network verifier that scales to large compositional networks. At its core is a new verification method termed decompose-merge reasoning, which decomposes the network into self-contained modules, verifies each module independently, and merges the verification results. Our experiments show that for a typical data center network virtualized with VXLAN, to check reachability for more than 100 million pairs of subnets, MNV is at least 100x faster than state-of-the-art tools.

Optimization of Energy Storage Allocation in Wind Energy Storage Combined System Based on Improved Sand Cat Swarm Optimization Algorithm

In order to improve the operation reliability and new energy consumption rate of the combined wind–solar storage system, an optimal allocation method for the capacity of the energy storage system (ESS) based on the improved sand cat swarm optimization algorithm is proposed. First, based on the structural analysis of the combined system, an optimization model of energy storage configuration is established with the objectives of the lowest total investment cost of the ESS, the lowest load loss rate and the lowest new energy abandonment rate, which not only takes into account the economy of energy storage construction for investors and builders, but also reduces the probability of blackout for users to protect their interests and improves the utilization rate of the natural resources of wind and light, which can achieve a multi-win–win situation. The model can realize the win–win situation in many aspects. Secondly, an improved k-means clustering algorithm is used to cluster the renewable energy power and load data to realize the typical day data extraction. Then, for the proposed multi-objective optimization model, an SCSO is proposed based on the triangular wandering strategy, Lévy flight strategy and lens imaging reverse learning improvement, which can help the algorithm to jump out of the local optimum while improving its global optimization ability, and these improvements can significantly improve the optimization effect of the SCSO. Finally, simulation analysis is carried out in combination with typical daily extraction data, and the results verify the advantages and effectiveness of the proposed model and algorithm.

Comparison of external dose estimates using different retrospective dosimetry methods in the settlements located near Semipalatinsk Nuclear Test Site, Republic of Kazakhstan.

For correct assessment of health risks after low-dose irradiation, calculation of radiation exposure estimates is crucial. To verify the calculated absorbed doses, instrumental methods of retrospective dosimetry are used. We compared calculated and instrumental-based estimates of external absorbed doses in the residents of Dolon, Mostik and Cheremushki villages, Kazakhstan, affected by the first nuclear weapon test performed at the Semipalatinsk Nuclear Test Site (SNTS) on August 29, 1949. The 'instrumental' doses were retrospectively estimated using the Luminescence Retrospective Dosimetry (LRD) and Electron Spin Resonance (ESR) methods. Correlation between the calculated individual cumulative external absorbed whole-body doses based on typical input data and ESR-based individual doses in the same people was strong (r = 0.782). It was even stronger between the calculated doses based on individual questionnaires' input data and the ESR-based doses (r = 0.940). Application of the LRD method is useful for validation of the calculated settlement-average cumulated external absorbed dose to air. Reconstruction of external exposure can be supplemented with the data from later measurements of soil contamination with long-lived radionuclides, such as, 137Cs. Our results show the reliability of the calculational method used for the retrospective assessment of individual external doses.

Study of the Applications of Alternative Data in the Field of Economics and Finance

The term "alternative data" sometimes known as alternative data or non-traditional data, is most often used to describe regionally specific, valuable information that is distinct from typical financial data. Alternative data does not require a specialized data network or administration and may be collected and processed in real time. As a result, "alternative data" has quickly evolved in the financial sector in recent years. "Alternative data" is a well-known illustration of "big" data since, to start, it's enormously large in quantity as shown by its scope and transmission. The second element is the real-time or very close-to-real-time nature of the data collection and transmission. Data types and data structures come in a huge diversity, which is the third component. This paper studies the different classifications and acquisition methods of alternative data, focusing on the different applications of alternative data in the economic and financial fields, respectively, the application of alternative data in forecasting, especially in macro-economic forecasting and user income forecasting, and the application of alternative data in capital markets, business analysis and decision-making.

A multi-objective optimization framework for building performance under climate change

Most building energy simulations utilize typical meteorological year data, overlooking the impacts of climate change. This can lead to inaccurate predictions and suboptimal designs. This study develops an optimization framework to identify robust building designs under varying climate scenarios. A case study is presented for residential buildings in Huangshan, China under 2020, 2050 and 2020–2050 conditions. A general circulation model provides future weather data. Multi-objective optimization maximizes energy efficiency and minimizes life cycle costs. Machine learning models predict heating, cooling and cost as functions of envelope parameters. Optimization is performed using a genetic algorithm. Results reveal the optimum insulation thickness, wall properties and window specifications. Compared to 2020 data, the ideal roof insulation increases from 40 mm to 90 mm by 2050. The optimal heating transmittance decreases from 0.38 W/m2K to 0.19 W/m2K. The approach highlights the significant influence of evolving climate on building design. It provides architects with accurate projections to make informed design decisions for energy efficiency and cost savings over the building lifespan.

Does digital transformation make enterprises greener? Evidence from China

The widespread introduction of new digital economic technologies in enterprises has reshaped their engagement in environmental protection, with significant implications for fulfilling their environmental responsibilities. This study focused on the relationship between digital transformation (DT) and corporate environmental responsibility based on sample data of A-share listed companies during 2010–2018, considering the typical data of corporate DT in recent years. DT can effectively incentivize firms, particularly heavy polluters, mature firms, and bear markets, to fulfill their environmental responsibilities, and the findings hold after the robustness tests. DT can also ultimately enhance the level of corporate environmental responsibility through micro-paths such as improved internal disclosure and enhanced attention from external investors. Simultaneously, local governments have significantly strengthened the incentive effect of DT on enterprises’ fulfillment of environmental responsibility by actively practicing green development and increasing environmental protection investments. These results provide an important theoretical and practical basis for promoting environmental pollution management and strengthening the policy support for DT.

Enhancing Confidentiality and Privacy Preservation in e-Health to Enhanced Security

Electronic health (e-health) system use is growing, which has improved healthcare services significantly but has created questions about the privacy and security of sensitive medical data. This research suggests a novel strategy to overcome these difficulties and strengthen the security of e-health systems while maintaining the privacy and confidentiality of patient data by utilising machine learning techniques. The security layers of e-health systems are strengthened by the comprehensive framework we propose in this paper, which incorporates cutting-edge machine learning algorithms. The suggested framework includes data encryption, access control, and anomaly detection as its three main elements. First, to prevent unauthorised access during transmission and storage, patient data is secured using cutting-edge encryption technologies. Second, to make sure that only authorised staff can access sensitive medical records, access control mechanisms are strengthened using machine learning models that examine user behaviour patterns. This research's inclusion of machine learning-based anomaly detection is its most inventive feature. The technology may identify variations from typical data access and usage patterns, thereby quickly spotting potential security breaches or unauthorised activity, by training models on past e-health data. This proactive strategy improves the system's capacity to successfully address new threats. Extensive experiments were carried out employing a broad dataset made up of real-world e-health scenarios to verify the efficacy of the suggested approach. The findings showed a marked improvement in the protection of confidentiality and privacy, along with a considerable decline in security breaches and unauthorised access events.

Experimentally trained hybrid machine learning algorithm for predicting turbulent particle-laden flows in pipes

A hybrid learning algorithm consisting of a preprocessor, a k-nearest neighbors regressor, a noise generator, and a particle–wall collision model is introduced for predicting features of turbulent single-phase and particle–liquid flows in a pipe. The hybrid learning algorithm has the ability to learn and predict the behavior of such complex fluid dynamic systems using experimental dynamic databases. Given a small amount of typical training data, the algorithm is able to reliably predict the local liquid and particle velocities as well as the spatial distribution of particle concentration within and without the limits of the range of training data. The algorithm requires an order of magnitude less training data than a typical full set of experimental measurements to give predictions on the same level of accuracy (typically, 20 cf. 100 trajectories for phase velocity distribution and 40 cf. 500 trajectories for phase concentration distribution), thus leading to huge reductions in experimentation and simulation. A feature importance analysis revealed the effects of the different experimental variables on the particle velocity field in a two-phase particulate flow, with particle–liquid density ratio and particle vertical radial position being the most influential and particle concentration the least. The algorithm is amenable to extension by using more complex databanks to address a much more comprehensive range of flow situations.

Single- and combined-source typical metrological year solar energy data modelling

Single- and combined-source typical metrological year solar energy data modelling

3D Mineral Prospectivity Mapping from 3D Geological Models Using Return–Risk Analysis and Machine Learning on Imbalance Data

Three-dimensional Mineral Prospectivity Mapping (3DMPM) is an innovative approach to mineral exploration that combines multiple geological data sources to create a three-dimensional (3D) model of a mineral deposit. It provides an accurate representation of the subsurface that can be used to identify areas with mineral potential. These 3D geological models are the typical data source for 3D prospective modeling. Geological data sets from multiple sources are used to construct 3D geological models. Since in practice there is a significant imbalance in the ratio of mineralized to non-mineralized classes, the classification results will be biased in favor of the more observed classes. Borderline-SMOTE (BLSMOTE) is an oversampling technique used to solve the problem of unbalanced datasets and works by generating synthetic data points along the boundary line between the minority and majority classes. This helps to create a more balanced dataset without introducing too much noise. Non-mineralized samples can be generated by randomly selecting non-mineralized locations, which means that uncertainties are generated. In this paper, we take the shallow-forming low-temperature hydrothermal deposit Guizhou Lannigou gold deposit as an example to extract the ore-controlling elements and establish a 3D geological model. A total of 50 training samples are generated using the sampling method described above, and 50 mineralization prospects are generated using Random Forests. A return–risk analysis was used to explore the uncertainties associated with synthetic positive samples and randomly selected negative samples, and to determine the final mineral potential values. Based on the evaluation metrics G-mean and F-value, the model using BLSMOTE outperforms the model without the synthetic algorithm and the models using SMOTE and KMeansSMOTE. The optimal model BLSMOTE18 has an AUC of 0.9288. The methodology also performs superiorly with different levels of class imbalance datasets. Excluding the predictions where the results highly overlap with known deposits, five target zones were circled for the targets using a P-A plot, all of which have obvious metallogenic geological features. Among them, Target1 and Target2 have good potential for mineralization, which is of great significance for future mineral exploration work.

Quantifying the phase assemblage in the hydrated cement paste by an interpretable and automatic EDS image analysis framework

The Energy dispersive X-ray spectroscopy (EDS) data, characterized by high dimensionality, low resolution, and large scale, necessitates a robust characterization method that is both easy to understand and delicate to reveal the underlying information. Here, we present a practical and interpretable framework for quantitative EDS (QEDS) image analysis. To improve the quality of data, we employ sequential processing techniques including guided filter, linear enhancement, and super-pixel segmentation. For phase identification and classification, the dimensionality reduction algorithm Potential of heat-diffusion for affinity-based transition embedding (Phate) was integrated with cluster analysis algorithm Gaussian Mixture Model (GMM). This integration cleanly and clearly reveals typical data patterns such as linear progressions and local clusters, indicating the presence of phase evolution and representative phases. We expect that this QEDS image analysis offers an intuitive and visual way to quantify the phase assemblage in cementitious systems, thereby shifting the quantification process from expert knowledge-dominated “black boxes” into data structure-dominated “glass boxes”.

An Expressway ETC Missing Data Restoration Model Considering Multi-Attribute Features

Electronic toll collection (ETC) data mining has become one of the hotspots in the research of intelligent expressway extension applications. Ensuring the integrity of ETC data stands as a critical measure in upholding data quality. ETC data are typical structured data, and although deep learning holds great potential in the ETC data restoration field, its applications in structured data are still in the early stages. To address these issues, we propose an expressway ETC missing transaction data restoration model considering multi-attribute features (MAF). Initially, we employ an entity embedding neural network (EENN) to automatically learn the representation of categorical features in multi-dimensional space, subsequently obtaining embedding vectors from networks that have been adequately trained. Then, we use long short-term memory (LSTM) neural networks to extract the changing patterns of vehicle speeds across several continuous sections. Ultimately, we merge the processed features with other features as input, using a three-layer multilayer perceptron (MLP) to complete the ETC data restoration. To validate the effectiveness of the proposed method, we conducted extensive tests using real ETC datasets and compared it with methods commonly used for structured data restoration. The experimental results demonstrate that the proposed method significantly outperforms others in restoration accuracy on two different datasets. Specifically, our sample data size reached around 400,000 entries. Compared to the currently best method, our method improved the restoration accuracy by 19.06% on non-holiday ETC datasets. The MAE and RMSE values reached optimal levels of 12.394 and 23.815, respectively. The fitting degree of the model to the dataset also reached its peak (R2 = 0.993). Meanwhile, the restoration stability of our method on holiday datasets increased by 5.82%. An ablation experiment showed that the EENN and LSTM modules contributed 7.60% and 9% to the restoration accuracy, as well as 4.68% and 7.29% to the restoration stability. This study indicates that the proposed method not only significantly improves the quality of ETC data but also meets the timeliness requirements of big data mining analysis.

Comparative Study of the Seismic Response Characteristics of Three Special Soils

Because of its special material composition, formation environment and special structure, special soil usually shows different seismic response characteristics from general soil, and sometimes causes serious seismic disasters. Therefore, the study of seismic response characteristics of special soil has important practical significance for engineering construction and disaster prevention in special land areas, and a site seismic response analysis is an important way to study the impact of site conditions on ground motions. Based on the existing research work, the uniform and single ideal soil layer profiles of three special soils are established, and the seismic response analysis program of the soilquake soil layer is used to study the effects of the dynamic shear module ratio, damping ratio and shear-wave velocity of soft soil, loess and laterite on the characteristic period and platform value of the design response spectrum under different input ground motion intensities. At the same time, three typical actual drilling data values are selected to establish the calculation model of the site soil layer. On the basis of the seismic response analysis and calculation of the soil layer, three special soil dynamic characteristics are compared from the aspects of peak acceleration and characteristic parameters. Based on the research results of this paper, the recommended values of the dynamic shear module ratio and damping ratio of three special soils are given. This work has important reference value for seismic design in soft soil, loess and laterite areas, and also enriches the research results of soil dynamic parameters.

A Big Data Grided Organization and Management Method for Cropland Quality Evaluation

A new gridded spatio-temporal big data fusion method is proposed for the organization and management of cropland big data, which could serve the analysis application of cropland quality evaluation and other analyses of geographic big data. Compared with traditional big data fusion methods, this method maps the spatio-temporal and attribute features of multi-source data to grid cells in order to achieve the structural unity and orderly organization of spatio-temporal big data with format differences, semantic ambiguities, and different coordinate projections. Firstly, this paper constructs a dissected cropland big data fusion model and completes the design of a conceptual model and logic model, constructs a cropland data organization model based on DGGS (discrete global grid system) and Hash coding, and realizes the unified management of vector data, raster data and text data by using multilevel grids. Secondly, this paper researches the evaluation methods of grid-scale adaptability, and generates distributed multilevel grid datasets to meet the needs of cropland area quality evaluation. Finally, typical data such as soil organic matter data, road network data, cropland area data, and statistic data in Da’an County, China, were selected to carry out the experiment. The experiment verifies that the method could not only realize the unified organization and efficient management of cultivated land big data with multimodal characteristics, but also support the evaluation of cropland quality.

Novel cross-domain fault diagnosis method based on model-agnostic meta-learning embedded in adaptive threshold network

Fault diagnosis of rotating machinery based on deep learning requires many identical labeled data to achieve satisfactory results. However, in engineering scenarios, few typical fault data have been manually marked, resulting in a poor on-site diagnosis consequence. Thus, training an efficient cross-domain diagnosis model under limited data is extremely challenging. This paper proposes a novel cross-domain fault diagnosis method based on model-agnostic meta-learning embedded in Adaptive threshold network (ATN-MAML). The threshold acquisition module is built to determine the signal's irrelevant information threshold adaptively. The designed threshold function is embedded in the network to filter out invalid information effectively as a non-linear layer. Then, MAML's training strategy is optimized to prevent overfitting. Finally, many cross-domain comparison experiments are conducted to verify the effectiveness of the proposed method on two datasets. The results show the model can maintain high accuracy even when the source and target domain data are from different devices.

A novel mixing rule model to predict the flowability of directly compressed pharmaceutical blends

In the pharmaceutical industry, powder flowability is an essential manufacturability attribute to consider when selecting the suitable manufacturing route and formulation. The selection of the formulation is usually based on the physical and chemical properties of the Active Pharmaceutical Ingredient (API) under consideration. Current industrial practice heavily relies on experimental work, which often results in significant labor and API consumption that results in higher costs. In this study we describe the development of a mixing rule to predict powder blend flowability from the flow properties of the individual components for industrial formulations manufactured via Direct Compression (DC). The mixing rule assumes that the granular solids’ interactions are dominated by cohesive forces but are pragmatic to calibrate from the perspective of the typical data collated in an industrial environment. The proposed model was validated using a range of different APIs and the results show that the model can effectively predict the flowability properties of any formulation across the space of DC-relevant formulation compositions. Finally, a connection between the model and APIs properties (shape and size) was investigated via a linear correlation between the API particle properties and interparticle forces.

A visual-based toolkit to support mobility data analytics

The Knowledge Discovery from Data (KDD) process is widely used across various domains to get valuable insights from data. Many platforms, like KNIME or RapidMiner, offer effective tools for KDD analysts, allowing them to perform data analytics tasks in a visual fashion, without writing code. In recent years, the increasing availability of mobility data has led to a surge in KDD-based initiatives from both industry and academia in the Intelligent Transportation Systems (ITS) domain. Still, KDD platforms lack comprehensive support for some typical mobility data manipulation tasks. As a result, mobility data analysis still requires a significant coding phase, with reduced productivity and hindered replicability of results.To address this gap, this paper presents a novel solution aimed at supporting ITS data analysts in defining KDD processes more efficiently. More in detail, we extended the KNIME platform by introducing a collection of new components explicitly tailored to facilitate some peculiar KDD tasks from mobility data. These components encompass critical functionalities such as map coverage analysis, trajectory partitioning and map-matching.To showcase the effectiveness of the proposed solution, we used it to replicate a study published in the ITS data analytics domain. Thanks to our proposal, such replication can be accomplished in a few minutes and with just a few clicks, without any manual coding, resulting in a pipeline that is easier to understand, distribute and re-execute, also for domain experts with no programming experience.Our solution is open-source and freely downloadable from the Knime Hub. In this way, we aim to foster data-driven research and practice in the ITS field, by providing researchers and practitioners with more effective analytics tools to handle mobility data.

Flow-aware Segment Routing in SDN-enabled Data Center Networks

The underlying objective of segment routing is to avoid maintenance of the per-flow state at forwarding devices. Segment routing (SR) enables the network devices to minimize their forwarding table size by generalizing the forwarding rules and making them applicable to multiple flows. In existing works, optimizing the trade-off between segment length and the number of co-flows sharing the segment is considered the key to determining optimal segment endpoints. However, the flow characteristics like the lifetime of flows, and dynamically altering routing paths are critical and impact the performance of SR. Ideally, network flows considered for SR are expected to persist for a longer duration and adhere to static routing paths. But our analysis of flow characteristics at a typical data center reveals that the majority of flows are short-lived. Also, network flows are subject to alter their routing paths frequently for several reasons. Considering short-lived flows and flows that dynamically alter their routing paths may lead to choosing unstable segment endpoints. Hence, it is necessary to study the flow characteristics for determining more stable segment endpoints. In this paper, the authors implemented the SR technique considering the flow characteristics at an SDN-enabled data center and the results show a significant improvement with respect to the stability of segment endpoints.

ROP-GAN: an image synthesis method for retinopathy of prematurity based on generative adversarial network

Objective. Training data with annotations are scarce in the intelligent diagnosis of retinopathy of prematurity (ROP), and existing typical data augmentation methods cannot generate data with a high degree of diversity. In order to increase the sample size and the generalization ability of the classification model, we propose a method called ROP-GAN for image synthesis of ROP based on a generative adversarial network. Approach. To generate a binary vascular network from color fundus images, we first design an image segmentation model based on U2-Net that can extract multi-scale features without reducing the resolution of the feature map. The vascular network is then fed into an adversarial autoencoder for reconstruction, which increases the diversity of the vascular network diagram. Then, we design an ROP image synthesis algorithm based on a generative adversarial network, in which paired color fundus images and binarized vascular networks are input into the image generation model to train the generator and discriminator, and attention mechanism modules are added to the generator to improve its detail synthesis ability. Main results. Qualitative and quantitative evaluation indicators are applied to evaluate the proposed method, and experiments demonstrate that the proposed method is superior to the existing ROP image synthesis methods, as it can synthesize realistic ROP fundus images. Significance. Our method effectively alleviates the problem of data imbalance in ROP intelligent diagnosis, contributes to the implementation of ROP staging tasks, and lays the foundation for further research. In addition to classification tasks, our synthesized images can facilitate tasks that require large amounts of medical data, such as detecting lesions and segmenting medical images.