Data-driven Problem Research Articles

Beyond Blame: Fostering an Accountability Culture Through Shared Leadership

This article discusses how organizations can move beyond a toxic "blame culture" and instead foster an "accountability culture" where teams share responsibility for both successes and failures. It explains how attribution biases and a lack of psychological safety enable defensive behaviors in blame cultures. Strategies are provided for leaders to establish accountability, including distributing leadership through cross-functional teams, facilitating regular feedback sessions, promoting data-driven problem solving, framing failures in terms of customer impact, and role modeling transparency. Case studies of Toyota, IDEO product design, and patient safety initiatives demonstrate how accountability cultures prioritize continual learning and collaboration over fault-finding. When teams focus on understanding root causes and preventing future mistakes rather than assigning blame, organizations can sustain high performance through innovation and resilience.

Hot Spots of Gun Violence in the Era of Focused Deterrence: A Space-Time Analysis of Shootings in South Philadelphia

Gun and street group violence remains a serious problem in cities across the United States and the focused deterrence strategy has been a widely applied law enforcement intervention to reduce it. Although two meta-analytical studies concluded that the intervention had a significant effect on violence, questions remain about how violence changes across space and time during and after the intervention. This study applies novel geospatial analyses to assess spatiotemporal changes in gun violence before, during, and after the implementation of Philadelphia Focused Deterrence. Emerging hot spot analysis employing Space-Time cubes of ten annual time bins (2009–2018) at the Thiessen polygon level was used to detect and categorize patterns. The analyses revealed a non-significant decreasing trend across the ten-year period. Furthermore, there were ninety-three statistically significant hot spots categorized into four hot spot patterns: fourteen new hot spots; twenty-three consecutive; one persistent; and fifty-three sporadic. There was no evidence showing statistically significant hot spots for the “diminishing” pattern. Knowledge of these patterns that emerge across micro-locations can be used by law enforcement practitioners to complement data-driven problem solving and fine tune these strategies and other place-based programming. Policymakers can use findings to prioritize resources when developing complementary prevention and intervention efforts by tailoring those efforts to the different emergent patterns.

Automatically detect crosswalks from satellite view images – A deep learning approach with ground truth verification

Like roadway information is to motor vehicle safety, pedestrian facility information (e.g., sidewalk presence) is crucial towards improving the safety of these vulnerable road users. Yet unlike widely accessible roadway data, pedestrian facility data is unavailable for most state agencies. Without this information, data-driven problem identification, countermeasure analysis, project evaluation, and performance management will be heavily impeded. Thus, urgent need for this data was recognized by state departments of transportation (DOTs). To address this need, we developed an automated approach to automatically detect crosswalks from satellite view images. The most advanced deep learning methodology, transfer learning with a Convolutional Neural Network (CNN) was used to handle real-world images. During the prediction process, a satellite image of a roadway pavement was analyzed by the satellite view model to predict the presence of a crosswalk. Then, the street view image of the same target was detected by the integrated street view model as a ground truth check. A total of 18,361 images from Bing Maps in satellite view and street view were used to train and test the deep learning model. As a result, the satellite view model itself achieved 98.43% accuracy using testing data from the same region. When dealing with data from another region, using the satellite view detection with ground truth checking increased the accuracy by 49%. It is obvious that by integrating the ground truth checking model into the satellite view crosswalk detection, we can obtain a more robust model which can handle highly occluded, low quality satellite images.

Core Components and Implementation Determinants of Multilevel Service Delivery Frameworks Across Child Mental Health Service Settings.

Multilevel service delivery frameworks are approaches to structuring and organizing a spectrum of evidence-based services and supports, focused on assessment, prevention, and intervention designed for the local context. Exemplar frameworks in child mental health include positive behavioral interventions and supports in education, collaborative care in primary care, and systems of care in community mental health settings. Yet, their high-quality implementation has lagged. This work proposes a conceptual foundation for multilevel service delivery frameworks spanning diverse mental health service settings that can inform development of strategic implementation supports. We draw upon the existing literature for three exemplar multilevel service delivery frameworks in different child mental health service settings to (1) identify core components common to each framework, and (2) to highlight prominent implementation determinants that interface with each core component. Six interrelated components of multilevel service delivery frameworks were identified, including, (1) a systems-level approach, (2) data-driven problem solving and decision-making, (3) multiple levels of service intensity using evidence-based practices, (4) cross-linking service sectors, (5) multiple providers working together, including in teams, and (6) built-in implementation strategies that facilitate delivery of the overall model. Implementation determinants that interface with core components were identified at each contextual level. The conceptual foundation provided in this paper has the potential to facilitate cross-sector knowledge sharing, promote generalization across service settings, and provide direction for researchers, system leaders, and implementation intermediaries/practitioners working to strategically support the high-quality implementation of these frameworks.

Physics-guided recurrent neural network trained with approximate Bayesian computation: A case study on structural response prognostics

A new physics-guided Bayesian recurrent neural network is proposed in this manuscript. This hybrid algorithm benefits from the knowledge in physics-based models, the capability of recurrent neural networks to handle sequential data, and the flexibility of Bayesian methods to quantify the uncertainty. The introduction of physics in the forward pass of the neural network significantly improves the results in multistep-ahead forecasting, and the gradient-free nature of the Bayesian learning engine provides great flexibility to adapt to the observed data. The proposed algorithm has been applied to a data-driven problem about fatigue in composites, and a case study about accelerations in concrete buildings, where a comparison against the state-of-the-art algorithms is also provided. The results revealed: (1) the accuracy of the proposals, comparable to the state-of-the-art recurrent neural networks; (2) its stability during multiple runs of the algorithm, proving that it is a more reliable option; (3) its precise quantification of the uncertainty, which provides useful information for the subsequent decision-making process. As potential future applications to real world scenarios, the proposed Bayesian recurrent neural network could be used in on-board PHM systems in the aerospace industry, or as an on-site prediction tool in buildings for seismic events and/or aftershocks.

Leveraging neural differential equations and adaptive delayed feedback to detect unstable periodic orbits based on irregularly sampled time series.

Detecting unstable periodic orbits (UPOs) based solely on time series is an essential data-driven problem, attracting a great deal of attention and arousing numerous efforts, in nonlinear sciences. Previous efforts and their developed algorithms, though falling into a category of model-free methodology, dealt with the time series mostly with a regular sampling rate. Here, we develop a data-driven and model-free framework for detecting UPOs in chaotic systems using the irregularly sampled time series. This framework articulates the neural differential equations (NDEs), a recently developed and powerful machine learning technique, with the adaptive delayed feedback (ADF) technique. Since the NDEs own the exceptional capability of accurate reconstruction of chaotic systems based on the observational time series with irregular sampling rates, UPOs detection in this scenario could be enhanced by an integration of the NDEs and the ADF technique. We demonstrate the effectiveness of the articulated framework on representative examples.

Addressing Fragmentation of Health Services through Data-Driven Knowledge Co-Production within a Boundary Organization

Behavioral healthcare services involve multiple disconnected sectors and providers serving the same populations. Efforts to identify and address service delivery problems are hampered by fragmentation of datasets. We conducted an engaged research project in which we formed a boundary organization and developed a knowledge co-production process centered on collaborative data sharing and visualization. Multisector participants in [location] worked to access and share data and to collectively interpret the resulting integrated data through visualizations using four knowledge co-production practices: collective interaction with data, perspective taking, reflection & debrief, and iteration of visualizations. The knowledge co-production process was evaluated using qualitative methods. This research extends sociotechnical research on knowledge co-production by proffering collaborative data sharing and visualization as a knowledge co-production process that can extend across disconnected and disparate social groups and contributes to community informatics by highlighting the role boundary organizations can play in facilitating data sharing and data-driven problem solving between fragmented sectors.

Artificial Intelligence in the Management of Rotator Cuff Tears

Technological innovation is a key component of orthopedic surgery. Artificial intelligence (AI), which describes the ability of computers to process massive data and "learn" from it to produce outputs that mirror human cognition and problem solving, may become an important tool for orthopedic surgeons in the future. AI may be able to improve decision making, both clinically and surgically, via integrating additional data-driven problem solving into practice. The aim of this article will be to review the current applications of AI in the management of rotator cuff tears. The article will discuss various stages of the clinical course: predictive models and prognosis, diagnosis, intraoperative applications, and postoperative care and rehabilitation. Throughout the article, which is a review in terms of study design, we will introduce the concept of AI in rotator cuff tears and provide examples of how these tools can impact clinical practice and patient care. Though many advancements in AI have been made regarding evaluating rotator cuff tears-particularly in the realm of diagnostic imaging-further advancements are required before they become a regular facet of daily clinical practice.

κ-statistics approach to optimal transport waveform inversion.

Extracting physical parameters that cannot be directly measured from an observed data set remains a great challenge in several fields of science and physics. In many of these problems, the construction of a physical model from waveforms is hampered by the phase ambiguity of the recorded wave fronts. In this work, we present an approach for mitigating the effect of phase ambiguity in waveform-driven issues. Our proposal combines the optimal transport theory with the κ-statistical thermodynamics approach. We construct an energy function from the most probable state of a system described by a finite-variance κ-Gaussian distribution to introduce an optimal transport metric. We demonstrate that our proposal outperforms the classical frameworks by considering a nonlinear geophysical data-driven problem based on a wave equationnumerical solution. The κ-generalized optimal transport metric is easily adapted to various inverse problems, from estimating power-law exponents to machine learning approaches in quantum mechanics.

Data-driven finite element computation of open-cell foam structures

This paper presents a model-free data-driven strategy for linear and non-linear finite element computations of open-cell foam. Employing sets of material data, the data-driven problem is formulated as the minimization of a distance function subjected to the physical constraints from the kinematics and the balance laws of the mechanical problem.The material data sets of the foam are deduced here from representative microscopic material volumes. These volume elements capture the stochastic characteristics of the open-cell microstructure and the properties of the polyurethane material. Their computation provides the required stress–strain data used in the macroscopic finite element computations without postulating a specific constitutive model. The paper shows how to derive suitable material data sets for the different cases of (non-)linear and (an-)isotropic material behavior efficiently.Exemplarily, we compare data-driven finite element computations with linearized and finite deformations and show that in a data-driven computation the linear kinematic is sufficiently accurate to capture the material’s non-linearity up to 50% of straining. The numerical example of a rubber sealing illustrates possible areas of application, the expenditure, and the proposed strategy’s versatility.

Offline Pricing and Demand Learning with Censored Data

We study a single product pricing problem with demand censoring in an offline data-driven setting. In this problem, a retailer has a finite amount of inventory and faces a random demand that is price sensitive in a linear fashion with unknown price sensitivity and base demand distribution. Any unsatisfied demand that exceeds the inventory level is lost and unobservable. We assume that the retailer has access to an offline data set consisting of triples of historical price, inventory level, and potentially censored sales quantity. The retailer’s objective is to use the offline data set to find an optimal price, maximizing his or her expected revenue with finite inventories. Because of demand censoring in the offline data, we show that the existence of near-optimal algorithms in a data-driven problem—which we call problem identifiability—is not always guaranteed. We develop a necessary and sufficient condition for problem identifiability by comparing the solutions to two distributionally robust optimization problems. We propose a novel data-driven algorithm that hedges against the distributional uncertainty arising from censored data, with provable finite-sample performance guarantees regardless of problem identifiability and offline data quality. Specifically, we prove that, for identifiable problems, the proposed algorithm is near-optimal and, for unidentifiable problems, its worst-case revenue loss approaches the best-achievable minimax revenue loss that any data-driven algorithm must incur. Numerical experiments demonstrate that our proposed algorithm is highly effective and significantly improves both the expected and worst-case revenues compared with three regression-based algorithms. This paper was accepted by J. George Shanthikumar, big data analytics. Funding: This work was supported by the MIT Data Science Laboratory. J. Bu was partially supported by a Hong Kong Polytechnic University Start-up Fund for New Recruits [Project ID P0039585]. Supplemental Material: Data and the online appendices are available at https://doi.org/10.1287/mnsc.2022.4382 .

Artificial Neural Network Modelling for Optimizing the Optical Parameters of Plasmonic Paired Nanostructures

The Artificial Neural Network (ANN) has become an attractive approach in Machine Learning (ML) to analyze a complex data-driven problem. Due to its time efficient findings, it has became popular in many scientific fields such as physics, optics, and material science. This paper presents a new approach to design and optimize the electromagnetic plasmonic nanostructures using a computationally efficient method based on the ANN. In this work, the nanostructures have been simulated by using a Finite Element Method (FEM), then Artificial Intelligence (AI) is used for making predictions of associated sensitivity (S), Full Width Half Maximum (FWHM), Figure of Merit (FOM), and Plasmonic Wavelength (PW) for different paired nanostructures. At first, the computational model is developed by using a Finite Element Method (FEM) to prepare the dataset. The input parameters were considered as the Major axis, a, the Minor axis, b, and the separation gap, g, which have been used to calculate the corresponding sensitivity (nm/RIU), FWHM (nm), FOM, and plasmonic wavelength (nm) to prepare the dataset. Secondly, the neural network has been designed where the number of hidden layers and neurons were optimized as part of a comprehensive analysis to improve the efficiency of ML model. After successfully optimizing the neural network, this model is used to make predictions for specific inputs and its corresponding outputs. This article also compares the error between the predicted and simulated results. This approach outperforms the direct numerical simulation methods for predicting output for various input device parameters.

Three-dimensional data-driven magnetostatic field computation using real-world measurement data

PurposeThe purpose of this paper is to present the applicability of data-driven solvers to computationally demanding three-dimensional problems and their practical usability when using real-world measurement data.Design/methodology/approachInstead of using a hard-coded phenomenological material model within the solver, the data-driven computing approach reformulates the boundary value problem such that the field solution is directly computed on raw measurement data. The data-driven formulation results in a double minimization problem based on Lagrange multipliers, where the sought solution must conform to Maxwell’s equations while at the same time being as close as possible to the available measurement data. The data-driven solver is applied to a three-dimensional model of a direct current electromagnet.FindingsNumerical results for data sets of increasing cardinality verify that the data-driven solver recovers the conventional solution. Additionally, the practical usability of the solver is shown by using real-world measurement data. This work concludes that the data-driven magnetostatic finite element solver is applicable to computationally demanding three-dimensional problems, as well as in cases where a prescribed material model is not available.Originality/valueAlthough the mathematical derivation of the data-driven problem is well presented in the referenced papers, the application to computationally demanding real-world problems, including real measurement data and its rigorous discussion, is missing. The presented work closes this gap and shows the applicability of data-driven solvers to challenging, real-world test cases.

The FEWSION for Community Resilience (F4R) Process: Building Local Technical and Social Capacity for Critical Supply Chain Resilience

Local business leaders, policy makers, elected officials, city planners, emergency managers, and private citizens are responsible for, and deeply affected by, the performance of critical supply chains and related infrastructures. At the center of critical supply chains is the food-energy-water nexus (FEW); a nexus that is key to a community’s wellbeing, resilience, and sustainability. In the 21st century, managing a local FEW nexus requires accurate data describing the function and structure of a community’s supply chains. However, data is not enough; we need data-informed conversation and technical and social capacity building among local stakeholders to utilize the data effectively. There are some resources available at the mesoscale and for food, energy, or water, but many communities lack the data and tools needed to understand connections and bridge the gaps between these scales and systems. As a result, we currently lack the capacity to manage these systems in small and medium sized communities where the vast majority of people, decisions, and problems reside. This study develops and validates a participatory citizen science process for FEW nexus capacity building and data-driven problem solving in small communities at the grassroots level. The FEWSION for Community Resilience (F4R) process applies a Public Participation in Scientific Research (PPSR) framework to map supply chain data for a community’s FEW nexus, to identify the social network that manages the nexus, and then to generate a data-informed conversation among stakeholders. F4R was piloted and co-developed with participants over a 2-year study, using a design-based research process to make evidence-based adjustments as needed. Results show that the F4R model was successful at improving volunteers’ awareness about nexus and supply chain issues, at creating a network of connections and communication with stakeholders across state, regional, and local organizations, and in facilitating data-informed discussion about improvements to the system. In this paper we describe the design and implementation of F4R and discuss four recommendations for the successful application of the F4R model in other communities: 1) embed opportunities for co-created PPSR, 2) build social capital, 3) integrate active learning strategies with user-friendly digital tools, and 4) adopt existing materials and structure.

A Visual Analytics Framework for Reviewing Multivariate Time-Series Data with Dimensionality Reduction.

Data-driven problem solving in many real-world applications involves analysis of time-dependent multivariate data, for which dimensionality reduction (DR) methods are often used to uncover the intrinsic structure and features of the data. However, DR is usually applied to a subset of data that is either single-time-point multivariate or univariate time-series, resulting in the need to manually examine and correlate the DR results out of different data subsets. When the number of dimensions is large either in terms of the number of time points or attributes, this manual task becomes too tedious and infeasible. In this paper, we present MulTiDR, a new DR framework that enables processing of time-dependent multivariate data as a whole to provide a comprehensive overview of the data. With the framework, we employ DR in two steps. When treating the instances, time points, and attributes of the data as a 3D array, the first DR step reduces the three axes of the array to two, and the second DR step visualizes the data in a lower-dimensional space. In addition, by coupling with a contrastive learning method and interactive visualizations, our framework enhances analysts' ability to interpret DR results. We demonstrate the effectiveness of our framework with four case studies using real-world datasets.

Optimized Design of Mechanical Chain Drive Based on a Wireless Sensor Network Data Algorithm

In this paper, we use a wireless sensor network data algorithm to optimize the design of mechanical chain drive by conducting an in‐depth study of the mechanical chain drive optimization. We utilize the crowdsourcing feature of the swarm‐wise sensing network for assisted wireless sensor networking to achieve crowdsourcing‐assisted localization. We consider a framework for crowdsourcing‐assisted GPS localization of wireless sensor networks and propose two recruitment participant optimization objectives, namely, minimum participants and time efficiency, respectively. A model and theoretical basis are provided for the subsequent trusted data‐driven participant selection problem in swarm‐wise sensing networks. The sprocket‐chain engagement frequency has the greatest influence on the horizontal bending‐vertical bending composite in different terrain conditions. The dynamic characteristics under working conditions are most influenced, while the scraping of the scraper and the central groove significantly influenced horizontal bending and vertical bending. Under load conditions, the amplitude of the scraper and central groove scraping increases significantly, which harm the dynamics of the scraper conveyor. By monitoring the speed difference between the head and tail sprockets and the overhang of the scraper, the tensioning status of the scraper conveyor chain can be effectively monitored to avoid chain jamming and chain breakage caused by the loose chain, thus improving the reliability and stability of the scraper conveyor.

Unsupervised damage clustering in complex aeronautical composite structures monitored by Lamb waves: An inductive approach

Structural Health Monitoring (SHM), i.e. the action of monitoring structures in real-time and in an automated manner, is a major challenge in several industrial fields such as aeronautic. SHM is by nature a very high dimensional data-driven problem that possesses several specificities when addressed as a machine learning problem. First of all data in damaged cases are rare and very costly as the generation of damaged data is not always possible and simulations are not reliable especially when dealing with complex structures. SHM is thus by nature an unsupervised problem. Furthermore, any incoming sample should be instantaneously clustered and handcrafted damage indexes are commonly used as a first dimension reduction step due to large datasets to be processed. As a consequence, unsupervised dimensionality reduction (DR) techniques that project very high dimensional data into a two or three-dimensional space (such as t-SNE or UMAP) are very appealing in such a context. However, these methods suffer from one major drawback which is that they are unable to cluster any unknown incoming sample. To solve this we propose to add inductive abilities to these well know methods by associating their projection bases with Deep Neural Networks (DNNs). The resulting DNNs are then able to cluster any incoming unknown samples. Based on those tools, a SHM methodology allowing for unsupervised damage clustering with dimensionality reduction is presented here. To demonstrate the effectiveness of the method, results of damage classification on large experimental data sets coming from complex aeronautical composite structures monitored through Lamb waves are shown. Furthermore, several DR techniques have been benchmarked and recommendations are derived. It is demonstrated that the use of raw Lamb wave signals instead of the associated damage indexes is more effective. This non-intuitive result helps to reduce the gap between laboratory research and the actual start-up of SHM activities in industrial applications.

Data-driven problem based learning: enhancing problem based learning with learning analytics

Problem based learning (PBL) supports the development of transversal skills and could underpin the training of a workforce competent to withstand the constant generation of new information. However, the application of PBL is still facing challenges, as educators are usually unsure how to structure student-centred courses, how to monitor students’ progress and when to provide guidance. Recently, the analysis of educational data, namely learning analytics (LA), has brought forth new perspectives towards informative course monitoring and design. However, existing research shows that limited studies have combined PBL with LA to explore their potential in offering data-driven, student-centred courses. This paper presents a framework, termed PBL_LA, that aims to address this gap by combining PBL with LA. The framework is populated from the literature and discussions with PBL and LA experts. The paper also presents results from redesigning, delivering and assessing ten courses in different disciplines and countries using the proposed framework. Results showed positive feedback on all different testing settings, exhibiting reliability of the framework and potential across countries, disciplines and sectors.

Performance evaluation for distributionally robust optimization with binary entries

We consider the data-driven stochastic programming problem with binary entries where the probability of existence of each entry is not known, instead realization of data is provided. We applied the distributionally robust optimization technique to minimize the worst-case expected cost taken over the ambiguity set based on the Kullback-Leibler divergence. We investigate the out-of-sample performance of the resulting optimal decision and analyze its dependence on the sparsity of the problem.

Offline Pricing and Demand Learning with Censored Data

We study a single product pricing problem with demand censoring in an offline data-driven setting. In this problem, a retailer is given a finite amount of inventory, and faces a random demand that is price sensitive in a linear fashion with unknown price sensitivity and base demand distribution. Any unsatisfied demand that exceeds the inventory level is lost and unobservable. We assume that the retailer has access to an offline data set consisting of triples of historical price, inventory level and potentially censored sales quantity. The retailer's objective is to use the offline data set to find an optimal price, maximizing her expected revenue with finite inventories. Due to demand censoring in the offline data, we show that the existence of near-optimal algorithms in a data-driven problem -- which we call problem identifiability -- is not always guaranteed. We develop a necessary and sufficient condition for problem identifiability, and show that it is directly related to some quality metrics of the censored data. We propose a novel data-driven algorithm that hedges against the distribution uncertainty arising from censored data, and admits provable finite-sample performance guarantees regardless of problem identifiability and offline data quality. Specifically, we prove that, for identifiable problems, the proposed algorithm is near-optimal, and, for unidentifiable problems, its worst-case revenue loss approaches the best-achievable performance guarantee among all data-driven algorithms. The numerical experiments demonstrate that our algorithm is highly effective and significantly improves both the expected revenue and worst-case revenue compared with three baseline algorithms.