Search

Prolonged droughts and water scarcity have become more frequent in recent years, exacerbating the problem of the artificial reservoirs management in the Mediterranean area. This study proposes a methodology which combines a Nonlinear AutoRegressive network with eXogenous input (NARX) data-driven model with Seasonal Forecasts (SFs) data, with the aim to predict the water volume stored in reservoirs at a mid-term scale, as requested by the local authority. The methodology is applied to four Sicilian reservoirs that experienced water scarcity in the recent past. SFs produced at the European Centre for Medium-Range Weather Forecasting are used to force the NARX models. Also, the reservoirs are in a typical data-scarce environment, where very scarce or no measures at all are available. The results show that the NARXs have the capability to reproduce the volumes stored in the considered reservoirs for the investigated period up to four months in advance. The performance of the modeling system strictly depends on: (i) the goodness of climate forecasts and (ii) the strength of the autocorrelation for the water volumes.

This work leads with the application of Learning Analytics (LA) methods in high education as data driven for making decision, where a real case study is presented. The LA method has been applied to a course on HVAC Facilities and Energetic Certification of the Master in Industrial Engineering at the Polytechnic University of Valencia (UPV), Spain. Thus, data collected during the whole academic year 2020-2021 by the institutional LMS platform of UPV have been analyzed. Results show that LA can be a successful data driven for detecting the students at risk, boosting their retention, personalizing contents and improving students learning. Finally, a tailored dashboard is proposed for students’ improvement monitoring.

Decision making based on data driven deals with a large amount of data will evaluate the process's effectiveness. Evaluate effectiveness in this paper is measure of performance efficiency of data envelopment analysis (DEA) method in this study is the approach with uncertainty problems. This study proposed a new method called the robust stochastic DEA (RSDEA) to approach performance efficiency in tackling uncertainty problems (i.e., stochastic and robust optimization). The RSDEA method develops to combine the stochastics DEA (SDEA) formulation method and Robust Optimization. The numerical example demonstrates the performance efficiency of the proposed formulation method, with the results performing confirmed that the efficiency value is 89%.

To effectively deal with the challenge of optimal dispatch caused by uncertainties such as renewable energy in active distribution network, a day-ahead optimal dispatch strategy for active distribution network based on improved deep reinforcement learning is proposed. First, the day-ahead optimal dispatch problem for the active distribution network is modeled as a multistage stochastic programming model. Multistage models attempt to capture the dynamics of unfolding uncertainties over time, so that the interaction between decision making and uncertainty unfolding is represented more accurately and realistically, and the decision can be adjusted dynamically and adaptively. Second, with the help of deep neural network to approximate the power flow model of the active distribution network in a data-driven manner, an improved deep reinforcement learning algorithm is proposed to solve the corresponding multistage stochastic programming problem. The proposed improved deep reinforcement learning algorithm effectively solves the problem that trial-and-error information acquisition methods are difficult to apply to high-cost power systems. Finally, the effectiveness of the proposed day-ahead optimization dispatch strategy for active distribution network based on improved deep reinforcement learning is verified by a modified IEEE33 case.

Like many healthcare organizations, Baylor Scott & White Health (BSWH) is awash with data. Often, this data is used in siloed departments to monitor safety and quality, make local business decisions, and motivate staff to improve processes to achieve sustained excellence and market share. As margins get thinner and competition from various disrupters increases, organizations have tried to improve the patient experience to remain viable as part of a calculated strategy. Nevertheless, these entities have struggled to focus limited resources for sustained improvement in patient experience. This article details how a large Texas-based healthcare system "operationalized" The Beryl Institute's Experience Framework via a multidisciplinary data approach. "Key gaps" that negatively impact the patient experience were identified using 99 data elements from common, readily available sources. Demonstrating the interconnected nature of the data has proven to be essential in engaging leaders to view the patient experience as an essential component to providing quality care. This crucial support from senior leaders drives efforts to safety, quality, and experience. A plan for how this approach can be implemented in any organization is shared, along with a discussion on sustainability, the use of these tools in an organization's improvement journey, and how it can help create higher-performing care teams. Limitations and future opportunities for enhancements to the approach are also provided. Experience Framework This article is associated with the Policy & Measurement lens of The Beryl Institute Experience Framework. (https://www.theberylinstitute.org/ExperienceFramework). Access other PXJ articles related to this lens. Access other resources related to this lens.

Software technical debt (TD) is a relevant software engineering problem. Only if properly managed can TD provide benefits while avoiding risks. Current TD management (TDM) support is limited. Recent advances in software engineering (SE) and data science (DS) promote data-driven TDM. In this paper, we summarize experiences concerning data-driven TDM gained in several research projects with industry. We report challenges and their consequences, propose solutions, and sketch improvement directions.

Detailed chemical studies of Solar-type stars have long been routine in stellar astrophysics, making possible studies in Galactic chemodynamics and exoplanet demographics. However, a similar understanding of the chemistry of M and late-K dwarfs—the most common stars in the Galaxy and most likely to host planets—has been greatly hampered by the complex molecular chemistry of their cool atmospheres. Here we present a new implementation of the Cannon, a data-driven model widely used in stellar astrophysics, developed for low–medium resolution optical (400–700nm) cool dwarf spectra. Our novel four parameter implementation in Teff, log g, [Fe/H], and [Ti/H] models both label uncertainties and missing labels, and is trained on 121 cool dwarf benchmarks—21 of which have literature elemental abundances measured from a warmer binary companion. Under leave-one-out cross-validation, we recover Teff, [Fe/H], and [Ti/H] with precisions of 2%, ±0.12 dex, and ±0.09 dex respectively, a precision which allows insight into the giant planet–[Fe/H] correlation for our sample of 65 TESS candidate planet hosts. Our work highlights the importance of precisely known benchmark systems; the promise of data-driven models for chemical analysis of the rich, but challenging to model, optical spectra of cool stars; and the utility of both in studying exoplanet demographics in the era of TESS and Gaia.

Detailed chemical studies of Solar-type stars have long been routine in stellar astrophysics, making possible studies in Galactic chemodynamics and exoplanet demographics. However, a similar understanding of the chemistry of M and late-K dwarfs—the most common stars in the Galaxy and most likely to host planets—has been greatly hampered by the complex molecular chemistry of their cool atmospheres. Here we present a new implementation of the Cannon, a data-driven model widely used in stellar astrophysics, developed for low–medium resolution optical (400–700nm) cool dwarf spectra. Our novel four parameter implementation in Teff, log g, [Fe/H], and [Ti/H] models both label uncertainties and missing labels, and is trained on 121 cool dwarf benchmarks—21 of which have literature elemental abundances measured from a warmer binary companion. Under leave-one-out cross-validation, we recover Teff, [Fe/H], and [Ti/H] with precisions of 2%, ±0.12 dex, and ±0.09 dex respectively, a precision which allows insight into the giant planet–[Fe/H] correlation for our sample of 65 TESS candidate planet hosts. Our work highlights the importance of precisely known benchmark systems; the promise of data-driven models for chemical analysis of the rich, but challenging to model, optical spectra of cool stars; and the utility of both in studying exoplanet demographics in the era of TESS and Gaia., {"references":["Rains, A. D. et al. (2021), MNRAS, 504, 5788"]}

Policymaking has always revolved around the initiative to solve problems and since the start of more focused research on it, it contained many stages from problem identification and agenda setting to policy formulation, legitimization, implementation and evaluation. As policymaking evolved and societal challenges became more complex, policymakers tried to include more factors into the decision-making process and thus data driven policymaking became an important tool in this field. Data driven policymaking aims to make optimal use of data and extensive analysis in order to create and evaluate policies. The handling of data that is required has raised various legal and ethical issues that are hard to tackle on a case to case basis, without solid guidelines and standards. This need for standardization in data driven policymaking is more crucial due to the heterogeneity of the modern data sources and the interoperability of data. Several standards have been developed around this notion and were examined in the scope of the H2020 Policy Cloud project. In order to cover the project’s needs, a 3-dimensional end-to-end analysis is proposed, which uses a novel Interim Repository to facilitate the ethical and legal analysis on the interoperable data. This approach tries to find the balance between legal/ethical compliance and registrability of analytics, a fine line that most policymaking services need to optimize.

Given the background of electricity market, the electricity consumption optimization can reduce consumers’ energy cost, and also help to reduce the peak load and improve the accommodation level of clean energy. Aiming at solving the problem of consumers’ insufficient management of their own electricity consumption, a multi-objective optimization model of electricity consumption is proposed considering the correlation of equipment electricity consumption. First, the cross-correlation coefficient is adopted to identify the consumption correlation among various electricity equipment based on the historical load data of consumers, and the significance of the consumption correlation is analyzed by silhouette index. Next, a multi-objective optimization model is constructed and the optimal electricity consumption strategy is obtained to maximize the consumer-side economy and comfort benefits. Finally, the results of case studies on a Zhejiang stir-fried tea enterprise in China show that the proposed model is feasible and effective.

The field of fluid simulation is developing rapidly, and data-driven methods provide many frameworks and techniques for fluid simulation. This paper presents a survey of data-driven methods used in fluid simulation in computer graphics in recent years. First, we provide a brief introduction of physicalbased fluid simulation methods based on their spatial discretization, including Lagrangian, Eulerian, and hybrid methods. The characteristics of these underlying structures and their inherent connection with datadriven methodologies are then analyzed. Subsequently, we review studies pertaining to a wide range of applications, including data-driven solvers, detail enhancement, animation synthesis, fluid control, and differentiable simulation. Finally, we discuss some related issues and potential directions in data-driven fluid simulation. We conclude that the fluid simulation combined with data-driven methods has some advantages, such as higher simulation efficiency, rich details and different pattern styles, compared with traditional methods under the same parameters. It can be seen that the data-driven fluid simulation is feasible and has broad prospects.

Progress in data-driven self-driving laboratories for solving materials grand challenges has accelerated with the advent of machine learning, robotics, and automation, but they are usually designed with specific materials and processes in mind. To develop the next generation of materials acceleration platforms (MAPs), we propose a unified framework to enable collaboration between MAPs, leveraging on object-oriented programming principles using research groups around theworldthatwouldbeabletoeffectively evolveexperimentalworkflows.Wedemonstratetheframeworkvia three experimental case studies from disparate fields to illustrate theevolutionof,andseamlessintegrationbetween,workflows,promoting efficient resource utilization and collaboration. Moving forward, we project our framework on three other research areas that would benefit from such an evolving workflow. Through the wide adoption of our framework, we envision a collaborative, connected, global community of MAPs working together to solve scientific grand challenges. Agency for Science, Technology and Research (A*STAR) National Research Foundation (NRF) Submitted/Accepted version We acknowledge funding from Accelerated Materials Development for Manufacturing Program A1898b0043 at A*STAR via the AME Programmatic Fund by the Agency for Science, Technology and Research. K.H. also acknowledges funding from the NRF Fellowship NRF-NRFF13-2021- 0011.

The ever-increasing travel demand has brought great challenges to the organization, operation, and management of the subway system. An accurate estimation of passenger flow distribution can help subway operators design corresponding operation plans and strategies scientifically. Although some literature has studied the problem of passenger flow distribution by analyzing the passengers’ path choice behaviors based on AFC (automated fare collection) data, few studies focus on the passenger flow distribution while considering the passenger–train matching probability, which is the key problem of passenger flow distribution. Specifically, the existing methods have not been applied to practical large-scale subway networks due to the computational complexity. To fill this research gap, this paper analyzes the relationship between passenger travel behavior and train operation in the space and time dimension and formulates the passenger–train matching probability by using multi-source data including AFC, train timetables, and network topology. Then, a reverse derivation method, which can reduce the scale of possible train combinations for passengers, is proposed to improve the computational efficiency. Simultaneously, an estimation method of passenger flow distribution is presented based on the passenger–train matching probability. Finally, two sets of experiments, including an accuracy verification experiment based on synthetic data and a comparison experiment based on real data from the Beijing subway, are conducted to verify the effectiveness of the proposed method. The calculation results show that the proposed method has a good accuracy and computational efficiency for a large-scale subway network.

Scoping review of professional perspectives on the acceptability of data-driven clinical recommendations

International audience; This paper tackles the challenge presented by small-data to the task of Bayesian inference. A novel methodology, based on manifold learning and manifold sampling, is proposed for solving this computational statistics problem under the following assumptions: 1) neither the prior model nor the likelihood function are Gaussian and neither can be approximated by a Gaussian measure; 2) the number of functional input (system parameters) and functional output (quantity of interest) can be large; 3) the number of available realizations of the prior model is small, leading to the small-data challenge typically associated with expensive numerical simulations; the number of experimental realizations is also small; 4) the number of the posterior realizations required for decision is much larger than the available initial dataset. The method and its mathematical aspects are detailed. Three applications are presented for validation: The first two involve mathematical constructions aimed to develop intuition around the method and to explore its performance. The third example aims to demonstrate the operational value of the method using a more complex application related to the statistical inverse identification of the non-Gaussian matrix-valued random elasticity field of a damaged biological tissue (osteoporosis in a cortical bone) using ultrasonic waves.

The fundamental challenge of the origin-destination (OD) matrix estimation problem is that it is severely under-determined. In this paper we propose a new data driven OD estimation method for cases where a supply pattern in the form of speeds and flows is available. We show that with these input data, we do not require an iterative dynamic network loading procedure that results in an equilibrium assignment, nor do we need an assumption on the kind of equilibrium that emerges from this process. The minimal number of ingredients which are needed are (a) a method to estimate / predict production and attraction time series; (b) a method to compute the N shortest paths from each OD zone to the next; and (c) two—possibly OD-specific—assumptions on the magnitude of N; and on the proportionality of path flows between these origins and destinations, respectively. The latter constitutes the most important behavioral assumption in our method, which relates to how we assume travelers have chosen their routes between OD pairs. We choose a proportionality factor that is inversely proportional to realized travel time, where we incorporate a penalty for path overlap. For large networks, these ingredients may be insufficient to solve the resulting system of equations. We show how additional constraints can be derived directly from the data by using principal component analysis, with which we exploit the fact that temporal patterns of production and attraction are similar across the network. Experimental results on a toy network and a large city network (Santander, Spain) show that our OD estimation method works satisfactorily, given a reasonable choice of N, and the use of so-called 3D supply patterns, which provide a compact representation of the supply dynamics over the entire network. Inclusion of topological information makes the method scalable both in terms of network size and for different topologies. Although we use a neural network to predict production and attraction in our experiments (which implies ground-truth OD data were needed), there are straight-forward paths to improve the method using additional data, such as demographic data, household survey data, social media and or movement traces, which could support estimating such ground-truth baseline production and attraction patterns. The proposed framework would fit very nicely in an online traffic modeling and control framework, and we see many paths to further refine and improve the method.

Availability of reliable and extended datasets of recorded power output from renewables is nowadays seen as one of the key drivers to improve the design and control of smart energy systems. In particular, these datasets are needed to train artificial intelligence methods. Very often, however, datasets can be corrupted due to lack of records connected to failures of the acquisition system, maintenance downtime periods, etc. Several recovery (imputation) methods have been used to guess and replace missing data. In this paper, we exploit the matrix completion approach. The available measures of several variables referring to a real onshore wind farm are organized into a matrix in a daily range and the Singular Value Thresholding method is used to carry out the matrix completion process. Numerical results show that matrix completion is a reliable and parameter-free tuning tool to impute missing data in these applications.

Bovine paratuberculosis is an endemic disease caused by Mycobacterium avium subspecies paratuberculosis (Map). Map is mainly transmitted between herds through movement of infected but undetected animals. Our objective was to investigate the effect of observed herd characteristics on Map spread on a national scale in Ireland. Herd characteristics included herd size, number of breeding bulls introduced, number of animals purchased and sold, and number of herds the focal herd purchases from and sells to. We used these characteristics to classify herds in accordance with their probability of becoming infected and of spreading infection to other herds. A stochastic individual-based model was used to represent herd demography and Map infection dynamics of each dairy cattle herd in Ireland. Data on herd size and composition, as well as birth, death, and culling events were used to characterize herd demography. Herds were connected with each other through observed animal trade movements. Data consisted of 13 353 herds, with 4 494 768 dairy female animals, and 72 991 breeding bulls. We showed that the probability of an infected animal being introduced into the herd increases both with an increasing number of animals that enter a herd via trade and number of herds from which animals are sourced. Herds that both buy and sell a lot of animals pose the highest infection risk to other herds and could therefore play an important role in Map spread between herds.

The paper deals with the development of a data-driven simulation model for the process optimization of an automatic electroplating plant in the fashion industry. Starting from the process mapping of the production process using the Business Process Modelling and Notation (BPMN standard), an object-oriented simulation model has been defined using the commercial software AnyLogic®. Finally, the model has been validated and the plant has been optimized.

Network-based epidemic models that account for heterogeneous contact patterns are extensively used to predict and control the diffusion of infectious diseases. We use census and survey data to reconstruct a geo-referenced and age-stratified synthetic urban population connected by stable social relations. We consider two kinds of interactions, distinguishing daily (household) contacts from other frequent contacts. Moreover, we allow any couple of individuals to have rare fortuitous interactions. We simulate the epidemic diffusion on a synthetic urban network for a typical medium-sized Italian city and characterize the outbreak speed, pervasiveness, and predictability in terms of the socio-demographic and geographic features of the host population. Introducing age-structured contact patterns results in faster and more pervasive outbreaks, while assuming that the interaction frequency decays with distance has only negligible effects. Preliminary evidence shows the existence of patterns of hierarchical spatial diffusion in urban areas, with two regimes for epidemic spread in low- and high-density regions.

Cold ironing (CI) is an electrification alternative in the maritime sector used to reduce shipborne emissions by switching from fuel to electricity when a ship docks at a port. During the ship’s berthing mode of operation, accurately estimating the berthing duration could assist the port operator to manage the berth allocation and energy scheduling optimally. However, the involvement of multiple input parameters with a large dataset requires a suitable handling method. Thus, this paper proposed a data-driven approach for ship berthing forecasting of cold ironing with various models such as artificial neural networks, multiple linear regression, random forest, decision tree, and extreme gradient boosting. Meanwhile, RMSE and MAE are two main indicators applied to assess forecasting accuracy. The simulation-based result shows that the artificial neural network outperforms all other models with the lowest error performance of RMSE (3.1343) and MAE (0.2548), suggesting its capability to handle nonlinearities in complex forecasting problems of port activity. The high accuracy of forecasting output in this study, which is berthing duration contributes to close estimation of two info: 1) CI power consumption and 2) departure time of the ship. This information is vital to the port operator to be used in the energy management system (EMS) as well as in the berth allocation problem (BAP).

High cycle fatigue failures of fan blade systems due to vibrational loads are of great concern in the design of aero engines, where energy dissipation by the relative frictional motion in the dovetail joints provides the main damping to mitigate the vibrations. The performance of such a frictional damping can be enhanced by suitable coatings. However, the analysis and design of coated joint roots of gas turbine fan blades are computationally expensive due to strong contact friction nonlinearities and also complex physics involved in the dovetail. In this study, a data driven surrogate model, known as the Nonlinear in Parameter AutoRegressive with eXegenous input (NP-ARX) model, is introduced to circumvent the difficulties in the analysis and design of fan systems. The NP-ARX model is a linear input-output model, where the model coefficients are nonlinear functions of the design parameters of interest, such that the Frequency Response Function (FRF) can be directly obtained and used in the system analysis and design. A simplified fan bladed disc system is considered as the test case. The results show that by using the data driven surrogate model, an efficient and accurate design of aero-engine fan systems can be achieved. The approach is expected to be extended to solve the analysis and design problems of many other complex systems.

The looper tension control system of hot strip mills is a typical multi-agent system, and the coupling effects among the agents are strong. However,it is difficult for us to establish the accurate coupling model for the looper tension control system. In this study, a distributed control strategy is proposed for the looper tension control system. With the subspace identification method, the local measurement of the looper control system and the information of its neighbors are used directly to develop the consensus control protocol without any knowledge of the looper tension system dynamics. The sufficient conditions for the consensus of multi-agent system with the proposed control protocol are proposed. In addition, a consensus control protocol with communication time delay is presented. Finally simulations are performed to verify the effectiveness of the control strategy.

Facing economic pressure and case-based compensation systems, hospitals strive for effectively planning patient hospitalization and making efficient use of their resources. To support this endeavor, this paper proposes a flexible hierarchical mixed-integer linear programming (MILP)-based approach for the day-level scheduling of clinical pathways (CP). CP form sequences of ward stays and treatments to be performed during a patient’s hospitalization under consideration of all relevant resources such as beds, operating rooms and clinical staff. Since in most hospitals CP-related information needed for planning is not readily available, we propose a data-driven approach in which the structure of the CP to be scheduled including all CP-related constraints is automatically extracted from standardized hospital billing data available in every German hospital. The approach uses a flexible multi-criteria objective function considering several patient- and hospital-related aspects which makes our approach applicable in various scenarios. Furthermore, in contrast to other approaches, it considers several practically relevant aspects ensuring the implementability of the scheduling results such as multiple ward stays per hospitalization and gender-separated room assignments. Regarding the treatment resources such as operation rooms and clinical staff, it considers the eligibility of resources for treatments based on information such as special equipment or qualification and represents complex resources individually to avoid disaggregation problems. To allow solving the resulting complex and large-scale scheduling problem for realistically dimensioned problem instances, we propose a hierarchical two-stage MILP approach involving carefully designed anticipation components in the first-stage model. We evaluate our approach in a case study with real-world data from a German university hospital showing that our approach is able to solve instances with a planning horizon of 1 month exhibiting 1088 treatments and 302 ward stays of 286 patients. In addition to comparing our approach to a monolithic MILP approach, we provide a detailed discussion of the scheduling results for two practically motivated scenarios.

This study develops a data-driven, comprehensive evaluation method to improve the science and technology innovative efficiency of industrial enterprises above designated size (hereinafter “industrial enterprises”). Based on an innovation value chain perspective, a two-stage evaluation index system is constructed. Thereafter, the Pearson correlation coefficient method was used to analyze correlations in the constructed index system. A two-stage network data envelopment analysis model with additional intermediate input was constructed to measure and evaluate industrial enterprises’ science and technology innovative efficiency from three aspects—research and development (R&D), commercialization, and comprehensive efficiencies—to reveal the temporal and spatial evolution. The feasibility and effectiveness of the method was verified using the statistical data of industrial enterprises in 16 cities in Anhui Province, China, from 2011 to 2020. The results show that the comprehensive efficiency of the scientific and technological innovation of industrial enterprises in these cities is at a medium level, and the efficiency development of the two stages is uncoordinated; the two-stage efficiency distribution tends to be “high R&D–high commercialization” and “low R&D–low commercialization”, and targeted countermeasures and suggestions are proffered. This study provides a reference for the sustainable development of industrial enterprises in relevant regions.

Social relationships refer to the connections that exist between people and indicate how people interact in society. The effective recognition of social relationships is conducive to further understanding human behavioral patterns and thus can be vital for more complex social intelligent systems, such as interactive robots and health self-management systems. The existing works about social relation recognition (SRR) focus on extracting features on different scales but lack a comprehensive mechanism to orchestrate various features which show different degrees of importance. In this paper, we propose a new SRR framework, namely Multi-level Transformer-Based Social Relation Recognition (MT-SRR), for better orchestrating features on different scales. Specifically, a vision transformer (ViT) is firstly employed as a feature extraction module for its advantage in exploiting global features. An intra-relation transformer (Intra-TRM) is then introduced to dynamically fuse the extracted features to generate more rational social relation representations. Next, an inter-relation transformer (Inter-TRM) is adopted to further enhance the social relation representations by attentionally utilizing the logical constraints among relationships. In addition, a new margin related to inter-class similarity and a sample number are added to alleviate the challenges of a data imbalance. Extensive experiments demonstrate that MT-SRR can better fuse features on different scales as well as ameliorate the bad effect caused by a data imbalance. The results on the benchmark datasets show that our proposed model outperforms the state-of-the-art methods with significant improvement.

Compelling evidence has suggested that the human cerebellum is engaged in a wide range of cognitive tasks besides traditional opinions of motor control, and it is organized into a set of distinct functional subregions. The existing model-driven cerebellum parcellations through resting-state functional MRI (rsfMRI) and task-fMRI are relatively coarse, introducing challenges in resolving the functions of the cerebellum especially when the brain is exposed to naturalistic environments. The current study took the advantages of the naturalistic paradigm (i.e., movie viewing) fMRI (nfMRI) to derive fine parcellations via a data-driven dual-regression-like sparse representation framework. The parcellations were quantitatively evaluated by functional homogeneity, and global and local boundary confidence. In addition, the differences of cerebellum–cerebrum functional connectivities between rsfMRI and nfMRI for some exemplar parcellations were compared to provide qualitatively functional validations. Our experimental results demonstrated that the proposed study successfully identified distinct subregions of the cerebellum. This fine parcellation may serve as a complementary solution to existing cerebellum parcellations, providing an alternative template for exploring neural activities of the cerebellum in naturalistic environments.

The construction of advanced metering infrastructure and the rapid development of deep learning technology make it possible to quickly find the optimal strategy for reactive power optimization by mining historical data and prior knowledge instead of relying on physical models. Therefore, a method for reactive power optimization based on graph convolutional network (GCN) is proposed. Through representing the topology information between nodes in distribution network with the adjacency matrix, the proposed algorithm can effectively mine the correlation between the node loads, mapping the complex nonlinear relationship between the power equipment status and the load data with the deep graph convolutional architecture. The simulation results show that the accuracy and robustness of the GCN are better than that of the existing data-driven methods such as the convolutional neural network, the multi-layer perceptron and the case-based reasoning. Its solution time is much shorter than the traditional heuristic algorithm, which can meet the real-time demand of the reactive power optimization in distribution networks.

In this paper, we propose a data-driven methodology to identify the optimal placement of sensors in a multi-zone building. The proposed methodology is based on statistical tests that study the (in)dependence of measurements from various available sensors. The tests advice on a set of most dissimilar sensors to be retained, as they would convey the maximum information. The method starts with an initial setup that can provide measurements of every building zone to carry out this study; any of these sensors can be removed eventually to decrease costs in normal operation. The method has the advantages of being purely data driven and computationally efficient, as against several methods proposed in the scientific literature, that operate under the premise that detailed building models are available, to evaluate the number/position of the required sensors. This property makes the method scale to different buildings, in an expert free manner. The methodology can help towards better characterization of a building for optimal control and monitoring applications. It is validated against a widely used method - Kalman filtering with Grey-box models, using two different case studies. In both cases, the proposed approach agrees with the results using grey box models, suggesting that the method is reliable, while being quick and efficient. ispartof: ENERGY AND BUILDINGS vol:243 status: published

As the core component of an electric vehicle, the health of the traction battery closely affects the safety performance of the electric vehicle. If the sub-health state cannot be identified and dealt with in time, it may cause traction battery failure, pose a safety hazard, and cause property damage to the driver and passengers. This study used data-driven methods to identify the two typical types of sub-health state. For the first type of sub-health state, the interclass correlation coefficient (ICC) method was used to determine whether there was an inconsistency between the voltage of a single battery and the overall voltage of the battery pack. In order to determine the threshold, the ICC value of each vehicle under different working conditions was analyzed using box plots, and a statistical ICC threshold of 0.805 was used as the standard to determine the first sub-health type. For the second type of sub-health state, the Z-score and the differential area method were combined to determine whether the single cell voltage deviated from the overall battery pack voltage. A battery whose voltage differential area exceeds the range of u ± 3σ is regarded as having a sub-health state. The results show that both methods can accurately judge the sub-health state type of a single battery. Furthermore, combined with the one-month operation data of the vehicle, we could calculate the sub-health state frequency of each single battery and take single batteries with a high frequency as the key object of attention in future vehicle operations.

Data driven approaches are utilized for optimal sensor placement as well as for velocity prediction of wind turbine wakes. In this work, several methods are investigated for suitability in the clustering analysis and for predicting the time history of the flow field. The studies start by applying a proper orthogonal decomposition (POD) technique to extract the dynamics of the flow. This is followed by evaluations of different hyperparameters of the clustering and machine learning algorithms as well as their impacts on the prediction accuracy. Two test cases are considered: (1) the wake of a cylinder and (2) the wake of a rotating wind turbine rotor exposed to complex flow conditions. The training and test data for both cases are obtained from high fidelity CFD approaches. The studies reveal that the combination of a classification-based machine learning algorithm for optimal sensor placement and Bi-LSTM is sufficient for predicting periodic signals, but a more advanced technique is required for the highly complex data of the turbine near wake. This is done by exploiting the dynamics of the wake from the set of POD modes for flow field reconstruction. A satisfactory accuracy is achieved for an appropriately chosen prediction horizon of the Bi-LSTM networks. The obtained results show that data-driven approaches for wind turbine wake prediction can offer an alternative to conventional prediction approaches.

In order to study the multiple restricted factors and parameters of the eddy current loss of generator end structures, both the multi-layer perceptron (MLP) and support vector regression (SVR) are used to study and predict the mechanism of the synergistic effect of metal shield conductivity, relative permeability of clamping plates and structural characteristics of eddy current losses. Based on the eddy current losses of generator end structures under different metal shielding thicknesses and electromagnetic properties, the calculation accuracy of the MLP and SVR is compared. The prediction method gives an effective means for the complex design of the end region of the generator, which reduces the effort of the designers. It also promotes the design efficiency of the electrical generator.

This Special Issue contains a collection of outstanding papers covering several recent advances in optical networks for 5G communications and beyond. Papers are organized into four categories: network resource planning; optical access networks; optical fronthaul solutions; and autonomous and data-driven network management. In this introduction, a brief overview of the field is given, followed by a summary of the seventeen papers of this Special Issue, and a discussion of future directions in the field., �� 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works."

Balancing sustainability and disruption of supply chains requires organizational ambidexterity. Sustainable supply chains prioritize efficiency and economies of scale and may not have sufficient redundancy to withstand disruptive events. There is a developing body of literature that attempts to reconcile these two aspects. This study gives a data-driven literature review of sustainable supply chain management trends toward ambidexterity and disruption. The critical review reveals temporal trends and geographic distribution of literature. A hybrid of data-driven analysis approach based on content and bibliometric analyses, fuzzy Delphi method, entropy weight method, and fuzzy decision-making trial and evaluation laboratory is used on 273 keywords and 22 indicators obtained based on the experts’ evaluation. The most important indicators are identified as supply chain agility, supply chain coordination, supply chain finance, supply chain flexibility, supply chain resilience, and sustainability. The regions show different tendencies compared with others. Asia and Oceania, Latin America and the Caribbean, and Africa are the regions needs improvement, while Europe and North America show distinct apprehensions on supply chain network design. The main contribution of this review is the identification of the knowledge frontier, which then leads to a discussion of prospects for future studies and practical industry implementation., Graphical abstract Image, graphical abstract

Motivated by recent successes on learning 3D feature representations, we present a Siamese network to generate representative 3D descriptors for 3D point matching in point cloud registration. Our system, dubbed HAF-Net, consists of feature extraction module, hierarchical feature reweighting and recalibration module (HRR), as well as feature aggregation and compression module. The HRR module is proposed to adaptively integrate multi-level features through learning, acting as a hierarchical attention fusion mechanism. The learnable feature pooling technique VLAD is extended into our aggregation module, which is further utilized to extract principal components of features and compress them into a low dimensional feature vector. To train our model, we amass a large dataset for 3D point matching. The dataset is composed of matched and unmatched point block pairs, which are automatically searched from existing reconstruction datasets with known poses. The experiments demonstrate that the proposed HAF-Net not only outperforms other state-of-the-art approaches in 3D feature representation but also has a good generalization ability in various tasks and datasets.

With the continuous improvement in user demand and the increasingly obvious complexity characteristics, such as strong coupling and nonlinearity of the system, it has become a new problem faced by the decision making of conceptual design. Decision-making methods in conceptual design such as traditional information axioms and the multi-criteria decision-making (MCDM) framework cannot provide a good solution for systems with strong coupling and nonlinearity. To fill these gaps, this paper proposes a decision-making method of design for a coupling system based on a complexity composite method (DMDCC). DMDCC is composed of a prediction model and a synthetic paradigm. In the early stages of decision making of design, design-centric complexity (DCC) theory is used to preliminarily sort the schemes. Then, driven by the twin data of existing products, the complexity of function units is obtained by using the prediction model. The complexity of different function units is composited by the composite paradigm to obtain the total function realization probability of the design scheme. A more accurate calculation of the total function realization probability of new products can assist designers to judge the scheme from the perspective of function and help to guide the decision making of the design of new systems’ development scientifically and reasonably. The engineering example of the bulk traditional Chinese medicine dispensing device is used to verify the scientific effectiveness of the research.

The push towards Industry 4.0 is constraining the industries to work in integrated supply chains. This implies to be open to the integration their production plants with other plants, and to provide access to their data and processes. In most cases, this also means to give access at data and flows to their customers to perform some synchronizations, permit supervision, and to create integrated control rooms, with synoptics and dashboards. This activity is also facilitated by the introduction of IoT solutions with IoT Devices, IoT Brokers, etc., which have a completely different approach with respect to DCS and SCADA solutions usually adopted in the industry for controlling their local productions. In this paper, Snap4Industry with its IoT development environment and framework for implementing the Control and Supervision of complex plant with multiple DCS and/or chains in the view of Industry 4.0 is presented. In particular, the paper describes the motivations/requirements and the actions performed to extend IoT Snap4City 100% open-source platform to comply with Industry 4.0 requirements. The main additions for creating Snap4Industry solution have been on: (i) industry protocols, (ii) custom widgets and synoptics Dashboards, (iii) new MicroServices for Node-RED for enabling the usage of synoptics as event driven devices, (iv) usage of WebSocket secure for the communication with custom Synoptics and Widgets for dashboards, automatized process for producing synoptics templates according to GDPR, and (v) the possibility of creating integrated workflows from data ingestion to synoptics. The paper also presents the assessment of the solution in terms of volume data and messages exchanged. The research has been founded into SODA R&D project founded by Regional Tuscany Gov.

Though data is largely recognized as a new form of capital in the digital era, little research has been done on how innovations related to finding health professionals and using health services are evolving in smart-city-based, preventive healthcare service delivery networks. How does digital data affect preventive healthcare practices in service delivery networks? Evidence is provided from a smart city service delivery network on how data and ICT usage impact preventive healthcare innovations. The research is based on a case study highlighting the transformations continuously occurring in such a network. The results suggest that using data from different sectors will enable individuals and health professionals to communicate via intelligent personalized services, which will act as agents, guiding and coaching individuals to change their lifestyles to avoid chronic diseases. This study provides new knowledge on how continuously using health data can produce novel routines and innovations in healthcare networks over time.

Human survival depends on the sustainable development of agriculture. This study constructs a data-driven evaluation and optimization method of agricultural sustainable development capacity, aiming to better cope with challenges such as environmental pollution and excessive consumption of resources and energy, as well as improve agricultural economic level. Further, an evaluation index system was constructed based on comprehensive consideration of energy and resources utilization, environmental pollution, and agricultural economy. After simplifying and integrating the data, a data envelopment analysis model was constructed to quantitatively evaluate the capability for agricultural sustainable development and its changing trend. Moreover, its influencing factors were analyzed from the perspective of input, which provides accurate countermeasures for improving agricultural sustainable development ability, resource utilization efficiency, and process optimization. This study shows the realization process of the aforementioned method for the agricultural development of six cities in northern Anhui from 2010 to 2019. Our results suggest that the sustainable development ability of northern Anhui is weak, but overall, has a good development trend. Based on our results, some countermeasures were proposed to control production scale reasonably, reduce environmental load, and improve resource efficiency, which provides a reference for policymakers to guide and standardize the development of regional agriculture.

In this paper, a data-driven controller is synthesised for systems with negative imaginary (NI) properties such as the piezoelectric tube scanner (PTS) of an atomic force microscopy (AFM). The scanning speed of an AFM is limited by the dynamic behaviours of its scanning unit. The controller aims to damp vibrations, increase the closed-loop bandwidth and track reference signals with high accuracy. The measured frequency response of the PTS is used to calculate the controller frequency response at each frequency by minimising a cost function. The data-driven control optimisation problem is constrained by NI properties to guarantee that the controller is stable and identifiable. The designed controller is implemented on the AFM using a dSPACE ds1103 real-time prototyping system. Experimental results show that the controller is able to significantly damp the resonances in the scanner's lateral axes, provide a high-bandwidth closed-loop system and allow reference signal tracking. Refereed/Peer-reviewed

ing turbine states and predicting the transition into failure states ahead of time is important in operation and maintenance of wind turbines. This study presents a method to monitor state transitions of a wind turbine based on the online inference on residuals. In a Bayesian framework, the state transitions are based on a hidden variable relevant for the predictor, namely the information of the current state. Given an underlying predictive model based on a student's t-distribution for the samples and a conditional prior on the state transition, it is shown that state transitions can be abstracted from generated data. Two models are presented: 1) assuming independence and 2) assuming dependence between states. In order to select the right models, machine learning is utilized to update hyperparameters on the conditional probabilities. Comparing fixed to learned hyperparameters points out the impact machine learning concepts have on the predictive performance of the presented models. In conclusion, a study on model residuals is performed to highlight the contribution to wind turbine monitoring. The presented algorithm can consistently detect the state transition under various configurations. Comparing to heuristic interpretations of the residuals, both models can qualitatively inform about the time when a state transition occurs.

Despite the development of novel treatments, improvement in the design of delivery devices, and new technologies for monitoring and improving adherence, the burden of asthma is not decreasing. Predicting an individual patient's response to asthma drugs remains challenging, and the provision of personalized treatment remains elusive. Although biomarkers, such as allergic sensitization and blood eosinophilia, might be important predictors of response to inhaled corticosteroids in preschool children, these relatively cheap and available investigations are seldom used in clinical practice to select patients for corticosteroid prescription. However, for the majority of patients, response to different treatments cannot be accurately predicted. One of the key factors preventing further advances is the reductionist view of asthma as a single disease, which is forcing patients with different asthma subtypes into a single group for empiric treatment. This inevitably results in treatment failures and, for some, an unacceptable risk/benefit ratio. The approach to asthma today is an example of the traditional symptom (diagnosis)–based, one-size-fits-all approach rather than a stratified approach, and our guidelines-driven management based on a unitary diagnosis might not be the optimal way to deliver care. The only way to deliver stratified medicine and find a cure is through the understanding of asthma endotypes. We propose that the way to discover endotypes, biomarkers, and personalized treatments is through the iterative process based on interpretation of big data analytics from birth and patient cohorts, responses to treatments in randomized controlled trials, and in vitro mechanistic studies using human samples and experimental animal models, with technological and methodological advances at its core.

Many complex turbulent flows in nature and engineering can be qualitatively regarded as being constituted of multiple simpler unit flows. The objective of this work is to characterize the coherent structures in such complex flows as a combination of constituent unitary flow structures for the purpose of reduced-order representation. While turbulence is clearly a non-linear phenomenon, we aim to establish the degree to which the optimally weighted superposition of unitary flow structures can represent the complex flow structures. The rationale for investigating such superposition stems from the fact that the large-scale coherent structures are generated by underlying flow instabilities that may be reasonably described using linear analysis. Clearly, the degree of validity of superposition will depend on the flow under consideration. In this work, we take the first step toward establishing a procedure for investigating superposition. Experimental data of single and triple tandem jets in crossflow are used to demonstrate the procedure. A composite triple tandem jet flow field is generated from optimal superposition of single jet data and compared against ‘true’ triple jet data. Direct comparisons between the true and composite fields are made for spatial, temporal, and kinetic energy content. The large-scale features (obtained from proper orthogonal decomposition or POD) of true and composite tandem jet wakes exhibit nearly 70% agreement in terms of modal eigenvector correlation. Corresponding eigenvalues reveal that the kinetic energy of the flow is also emulated with only a slight overprediction. Temporal frequency features are also examined in an effort to completely characterize POD modes. The proposed method serves as a foundation for more rigorous and robust dimensional reduction in complex flows based on unit flow modes.

This work proposes a method for identifying functional dependencies among components of complex technical infrastructures using databases of alarm messages. The developed method is based on the representation of the alarm database by a binary matrix, the use of the Apriori algorithm for mining association rules and a new algorithm for identifying groups of functionally dependent components. The effectiveness of the proposed method is shown by means of its application to an artificial case study and a real large-scale database of alarms generated by different supervision systems of the complex technical infrastructure of CERN (European Organization for Nuclear Research).

Time-series prediction of a river stage during typhoons or storms is essential for flood control or flood disaster prevention. Data-driven models using machine learning (ML) techniques have become an attractive and effective approach to modeling and analyzing river stage dynamics. However, relatively new ML techniques, such as the light gradient boosting machine regression (LGBMR), have rarely been applied to predict the river stage in a tidal river. In this study, data-driven ML models were developed under a multistep-ahead prediction framework and evaluated for river stage modeling. Four ML techniques, namely support vector regression (SVR), random forest regression (RFR), multilayer perceptron regression (MLPR), and LGBMR, were employed to establish data-driven ML models with Bayesian optimization. The models were applied to simulate river stage hydrographs of the tidal reach of the Lan-Yang River Basin in Northeastern Taiwan. Historical measurements of rainfall, river stages, and tidal levels were collected from 2004 to 2017 and used for training and validation of the four models. Four scenarios were used to investigate the effect of the combinations of input variables on river stage predictions. The results indicated that (1) the tidal level at a previous stage significantly affected the prediction results, (2) the LGBMR model achieves more favorable prediction performance than the SVR, RFR, and MLPR models, and (3) the LGBMR model could efficiently and accurately predict the 1–6-h river stage in the tidal river. This study provides an extensive and insightful comparison of four data-driven ML models for river stage forecasting that can be helpful for model selection and flood mitigation.

Effectively transporting drilled cuttings to the surface is a vital part of the well construction process. Usually, mechanistic models are used to estimate the cuttings concentration during drilling. Based on the results from these model, operational parameters are adjusted to mitigate any nonproductive time events such as pack-off or lost circulation. However, these models do not capture the underlying complex physics completely and frequently require updating the input parameters, which is usually performed manually. To address this, in this study, a data-driven modeling approach is taken and evaluated together with widely used mechanistic models. Artificial neural networks are selected after several trials. The experimental data collected at The University of Tulsa–Drilling Research Projects (in the last 40 years) are used to train and validate the model, which includes a wide range of wellbore and pipe sizes, inclinations, rate-of-penetration values, pipe rotation speeds, flow rates, and fluid and cuttings properties. It is observed that, in many cases, the data-driven model significantly outperforms the mechanistic models, which provides a very promising direction for real-time drilling optimization and automation. After the neural network is proven to work effectively, an optimization attempt to estimate flow rate and pipe rotation speed is introduced using a genetic algorithm. The decision is made considering minimizing the required total energy for this process. This approach may be used as a design tool to identify the required flow rate and pipe rotation speed to acquire effective hole cleaning while consuming minimal energy.

International audience; The potential of the diverse chemistries present in natural products (NP) for biotechnology and medicine remains untapped because NP databases are not searchable with raw data and the NP community has no way to share data other than in published papers. Although mass spectrometry (MS) techniques are well-suited to high-throughput characterization of NP, there is a pressing need for an infrastructure to enable sharing and curation of data. We present Global Natural Products Social Molecular Networking (GNPS; http://gnps.ucsd.edu), an open-access knowledge base for community-wide organization and sharing of raw, processed or identified tandem mass (MS/MS) spectrometry data. In GNPS, crowdsourced curation of freely available community-wide reference MS libraries will underpin improved annotations. Data-driven social-networking should facilitate identification of spectra and foster collaborations. We also introduce the concept of 'living data' through continuous reanalysis of deposited data.

The aim of nuclear safeguards is to ensure that special nuclear material is used for peaceful purposes. Historically, nuclear material accounting (NMA) has provided the quantitative basis for monitoring for nuclear material loss or diversion, and process monitoring (PM) data is collected by the operator to monitor the process. PM data typically support NMA in various ways, often by providing a basis to estimate some of the in-process nuclear material inventory. We develop options for combining PM residuals and NMA residuals (residual = measurement − prediction), using a hybrid of period-driven and data-driven hypothesis testing. The modified statistical tests can be used on time series of NMA residuals (the NMA residual is the familiar material balance), or on a combination of PM and NMA residuals. The PM residuals can be generated on a fixed time schedule or as events occur.

How do you transform a traditionally un-data-orientated organisation into being data-driven armed with data science processes and plenty of enthusiasm? With the exponential growth of data, more and more organisations are demanding to become data-driven. Seeking value from their data, big data and data science initiatives; jobs and skill sets have risen up the organisations agenda. The first data scientist at a museum shares her experience and learning on the journey to transform the British Museum to be data-driven by 2018. How is one of the most popular museums in the world, with 6.8 million annual visitors, using data science to achieve a data-driven transition? Valuing of Data Data Science at the British Museum Transformation advice Vision for the future By valuing data and using data science processes, any organisation can become data-driven.

How do you transform a traditionally un-data-orientated organisation into being data-driven armed with data science processes and plenty of enthusiasm? With the exponential growth of data, more and more organisations are demanding to become data-driven. Seeking value from their data, big data and data science initiatives; jobs and skill sets have risen up the organisations agenda. The first data scientist at a museum shares her experience and learning on the journey to transform the British Museum to be data-driven by 2018. How is one of the most popular museums in the world, with 6.8 million annual visitors, using data science to achieve a data-driven transition? Valuing of Data Data Science at the British Museum Transformation advice Vision for the future By valuing data and using data science processes, any organisation can become data-driven.