Data-driven Approach Research Articles

Data-driven approach for air pollutant concentrations forecasting: A window-based multi-output GBRT approach

Air pollutant concentrations forecasting is essential for detrimental public exposure prevention, air quality enhancement, and effective environmental policy shaping. Recently, air pollutant concentrations forecasting based on machine learning has been considerably advanced with the development of data-driven approaches. However, multi-source data constraints and architectural complexity in machine learning approaches limit the use of machine learning in actual scenarios. Herein we present a window-based multi-output gradient boosting regression tree (WM-GBRT) approach to predict air pollutant concentrations for the next 48 h at each monitoring station, considering air pollutant monitoring data, meteorological monitoring data, NECP-GFS data, and GEOS-CF data. The key innovation of our approach lies in the flexible input window configuration and the implementation of an multi-step independent strategy. The experiments were conducted in China and compared to existing data-driven baselines, we show that our approach achieved the superior performance in forecasting concentrations of six air pollutants, with a considerable improvement of 6.94 % (PM2.5), 12.3 % (PM10), 3.84 % (O3), 30.6 % (SO2), 9.84 % (NO2), and 93.9 % (CO) when compared to the second-best baselines. This simple yet efficient approach can be easily applied, providing a reliable technical method for predicting air pollutant concentrations.

Data-Driven Heuristic Optimization for Complex Large-Scale Crude Oil Operation Scheduling

This paper addresses the challenging scheduling of crude oil operations (SCOO) problem, characterized by the intricate sequencing of activities involving discrete events and continuous variables. Given the NP-Hard nature of scheduling problems due to their combinatorial complexity, this study employs a data-driven optimization approach. Initially, historical operational data relevant to the SCOO are scrutinized; however, due to data limitations, small-scale instances are solved using a mathematical programming model to generate data. Subsequently, operational solution data are processed using the Apriori algorithm, a renowned data mining technique. The insights gained are translated into heuristic rules, laying the groundwork for a novel data-driven heuristic algorithm tailored for the SCOO problem. This algorithm is then applied to a 45-day scheduling scenario, demonstrating the efficacy of the proposed approach.

Unsupervised Characterization of Prediction Error Markers in Unisensory and Multisensory Streams Reveal the Spatiotemporal Hierarchy of Cortical Information Processing.

Elicited upon violation of regularity in stimulus presentation, mismatch negativity (MMN) reflects the brain's ability to perform automatic comparisons between consecutive stimuli and provides an electrophysiological index of sensory error detection whereas P300 is associated with cognitive processes such as updating of the working memory. To date, there has been extensive research on the roles of MMN and P300 individually, because of their potential to be used as clinical markers of consciousness and attention, respectively. Here, we intend to explore with an unsupervised and rigorous source estimation approach, the underlying cortical generators of MMN and P300, in the context of prediction error propagation along the hierarchies of brain information processing in healthy human participants. The existing methods of characterizing the two ERPs involve only approximate estimations of their amplitudes and latencies based on specific sensors of interest. Our objective is twofold: first, we introduce a novel data-driven unsupervised approach to compute latencies and amplitude of ERP components accurately on an individual-subject basis and reconfirm earlier findings. Second, we demonstrate that in multisensory environments, MMN generators seem to reflect a significant overlap of "modality-specific" and "modality-independent" information processing while P300 generators mark a shift toward completely "modality-independent" processing. Advancing earlier understanding that multisensory contexts speed up early sensory processing, our study reveals that temporal facilitation extends to even the later components of prediction error processing, using EEG experiments. Such knowledge can be of value to clinical research for characterizing the key developmental stages of lifespan aging, schizophrenia, and depression.

Datasets in design research: needs and challenges and the role of AI and GPT in filling the gaps

AbstractDespite the recognized importance of datasets in data-driven design approaches, their extensive study remains limited. We review the current landscape of design datasets and highlight the ongoing need for larger and more comprehensive datasets. Three categories of challenges in dataset development are identified. Analyses show critical dataset gaps in design process where future studies can be directed. Synthetic and end-to-end datasets are suggested as two less explored avenues. The recent application of Generative Pretrained Transformers (GPT) shows their potential in addressing these needs.

Three-dimensional Spinal Canal Morphometric Analysis and Relevant Spinal Cord Occupational Ratios in Congenital Cervical Spinal Stenosis: A classification algorithm of the stenosis phenotypes and data driven decompression approach.

Three-dimensional Spinal Canal Morphometric Analysis and Relevant Spinal Cord Occupational Ratios in Congenital Cervical Spinal Stenosis: A classification algorithm of the stenosis phenotypes and data driven decompression approach.

Physics-Constraint Variational Neural Network for Wear State Assessment of External Gear Pump.

Most current data-driven prognosis approaches suffer from their uncontrollable and unexplainable properties. To address this issue, this article proposes a physics-constraint variational neural network (PCVNN) for wear state assessment of the external gear pump. First, a response model of the pressure pulsation of the gear pump is constructed via a spectral method, and a compound neural network is utilized to extract features from the pressure pulsation signal. Then, the response model is formulated into an objective function to softly constrain the learning process of the neural network, forcing the learned features to have explicit physics meaning. Meanwhile, to characterize the system uncertainty, the variational inference is utilized to extend a Kullback-Leibler (KL) divergence into the objective function. Finally, the wear state is evaluated based on the distance of learned physics features. Experimental results on an external gear pump validate the merits of the proposed method in explainable representation learning and system uncertainty estimation. It also offers a controllable and explainable perspective to understand the dynamic behavior of the system.

Predicting the Curie temperature of Sm-Co-based alloys via data-driven strategy

Calculating the Curie temperature of rare-earth permanent magnetic materials has remained a big theoretical challenge. In this study, based on a home-built Sm-Co-based alloys database, a data-driven machine learning approach was developed to predict the Curie temperature of Sm-Co-based alloys. High-throughput predictions of Curie temperature were achieved using a genetic program based symbolic regression model. A classification model based on logistic regression was established to quantify the effect of doping on the Curie temperature of Sm-Co-based alloys. The key physical descriptor affecting Curie temperature was extracted from the established machine learning models, and the Curie temperature sensitivity coefficient was defined. It was discovered that the doping elements with large electrical conductivity and similar heat of fusion to that of Sm are likely to increase the Curie temperature of Sm-Co-based alloys. The model predictions were verified quantitatively by the experimental results of a series of prepared Sm-Co-based samples. This work provides a high-efficiency method for developing Sm-Co-based permanent magnets with high Curie temperatures.

Explainable Intelligent Fault Diagnosis for Nonlinear Dynamic Systems: From Unsupervised to Supervised Learning.

The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD approaches for nonlinear dynamic systems. More specifically, we parameterize nonlinear systems through a generalized kernel representation for system modeling and the associated fault diagnosis. An important result obtained is a unified form of kernel representations, applicable to both unsupervised and supervised learning. More importantly, through a rigorous theoretical analysis, we discover the existence of a bridge (i.e., a bijective mapping) between some supervised and unsupervised learning-based entities. Notably, the designed IFD approaches achieve the same performance with the use of this bridge. In order to have a better understanding of the results obtained, both unsupervised and supervised neural networks are chosen as the learning tools to identify the generalized kernel representations and design the IFD schemes; an invertible neural network is then employed to build the bridge between them. This article is a perspective article, whose contribution lies in proposing and formalizing the fundamental concepts for explainable intelligent learning methods, contributing to system modeling and data-driven IFD designs for nonlinear dynamic systems.

Data-driven support for CAD parts modelling based on automated estimated production planning – approach and user research

AbstractWe present a data-driven approach to support decision-making in CAD modelling and to improve design for manufacturing. Based on automated estimated production planning, information is provided on possible design actions and their impact. A study was conducted on perspectives on and visualizations in CAD modelling. Requirements for a user interface of the described support system were identified. The results serve as basis for further research and development on the interaction of engineering designers with data-driven decision-making support in CAD modelling.

Scenario Generation by Physical Model-Free Approaches for Multiple Renewables

The augmentation of renewable energy sources within the global energy portfolio is imperative for mitigating the impacts of climate change. Nonetheless, the inherent variability, intermittency, and unpredictability associated with certain forms of renewable energy present significant challenges. Effective integration of these energy sources into existing grids is contingent upon accurate predictions and robust scenario planning. To address this, we introduce a novel data-driven framework that facilitates the generation of energy scenarios without relying on intricate physical models or extensive assumptions. This framework is underpinned by an innovative combination of a grey neural network, which is fine-tuned using a genetic algorithm, and a Gaussian Copula to enhance the prediction accuracy. Extensive experimental analyses validate the effectiveness and advanced capabilities of our proposed model. Moreover, the adaptable nature of this data-driven approach allows for its potential application across various sectors within the sustainable industry, further underscoring its versatility and utility.

Impact of practical challenges on the implementation of data-driven services for building operation: Insights from a real-life case study

– Data-driven applications in buildings using AI and machine learning have generated a lot of interest, but scaling these applications is challenging due to the uniqueness of each building. During the process of implementing a data-driven predictive heating control in a full-scale real-life office building in Norway, 24 practical challenges were encountered. In this work, those practical challenges are presented, discussed and attributed to four main categories: i) physical limitations, ii) data acquisition and communication, iii) data and model definition and iv) building occupants. Detailed examples for the challenges are provided and more than 15 lessons-learned with regards to developing and implementing data-driven services for building operation are presented. Furthermore, this work discusses how the practical challenges impact the choice of a data-driven approach to control the operation of an office building heating system in a predictive manner and how the practical challenges influence the creation of variation in the measurement data needed to identify a model during normal building operation. Finally, it is shown that a substantial number of practical challenges that were encountered during the operational phase are rooted in the design and construction phase of a building project or from rehabilitation during the operational phase. This highlights the fact that the possible use of data-driven services for building operation should be considered during the tendering and design phase to minimize the number of challenges regarding the widespread implementation of data-driven services for building operation, especially regarding predictive control.

121. Data-Driven Approaches to Modeling the Temporal Relationship Between Circadian Functioning and Mood Instability in Bipolar Disorder

121. Data-Driven Approaches to Modeling the Temporal Relationship Between Circadian Functioning and Mood Instability in Bipolar Disorder

Cerebrospinal fluid reference proteins increase accuracy and interpretability of biomarkers for brain diseases.

Cerebrospinal fluid (CSF) biomarkers reflect brain pathophysiology and are used extensively in translational research as well as in clinical practice for diagnosis of neurological diseases, e.g., Alzheimer's disease (AD). However, CSF biomarker concentrations may be influenced by non-disease related inter-individual variability. Here we use a data-driven approach to demonstrate the existence of inter-individual variability in mean standardized CSF protein levels. We show that these non-disease related differences cause many commonly reported CSF biomarkers to be highly correlated, thereby producing misleading results if not accounted for. To adjust for this inter-individual variability, we identified and evaluated high-performing reference proteins which improved the diagnostic accuracy of key CSF AD biomarkers. Our reference protein method attenuates the risk for false positive findings, and improves the sensitivity and specificity of CSF biomarkers, with broad implications for both research and clinical practice.

Effective tribological performance-oriented concentration optimization of lubricant additives based on a machine learning approach

The tribological performance of lubricant is significantly affected by additive concentration. To realize optimization of additive concentrations, an eXtreme Gradient Boosting machine learning method was proposed to predict the tribological performance of a lubricant, reflected by wear volume, with data collected from four-ball friction experiments. The Shapley Additive exPlanation tool was used to explain the predictions of the model. Particle swarm optimization was used to optimize additive concentration proportions. The tribological properties of grease additives were verified through validation experiment. The chemical components of wear scars include MXenes, carbon films, iron oxides, and iron phosphides, which facilitate direct contact between friction surfaces. This study provides a novel data-driven approach for optimization of additive concentrations with effective and predictable tribological performance.

Application of the full consistency method (FUCOM) - Cosine similarity framework in 5G infrastructure investment planning: An approach for telecommunication quality improvements

In the rapidly evolving telecommunications landscape, the shift towards advanced communication technologies marks a critical milestone. This transition promises to revolutionize connectivity by enabling seamless data downloads, high-quality video streaming, and instant access to applications. However, adapting to these advanced technologies poses significant challenges for infrastructure expansion, requiring innovative investment and deployment strategies. These strategies aim not only to enhance service quality but also to ensure extensive network coverage. To address the need for systematic planning in infrastructure investment, this paper presents a novel methodology that combines the Full Consistency Method (FUCOM) with cosine similarity analysis. This integrated approach effectively prioritizes service areas for the deployment of 5G technology, emphasizing the importance of detailed planning in mobile strategy development. By leveraging FUCOM to determine the weights of various criteria and employing cosine similarity analysis to rank service areas, the methodology facilitates efficient resource allocation and service quality enhancements. Empirical validation using real data from a Turkish telecommunications company confirmed the effectiveness of the proposed algorithm. The results indicate that this integrated approach can significantly advance the telecommunications industry by providing essential insights for companies seeking to improve service quality amidst the transition to 5G and beyond. The successful implementation of the proposed algorithm demonstrates its effectiveness in addressing the challenges faced by telecommunications companies and underscores the importance of a data-driven approach in strategic decision-making and resource allocation. Furthermore, the findings suggest that the integrated FUCOM and cosine similarity analysis approach can offer a valuable tool for telecommunications companies worldwide, offering a systematic method for prioritizing infrastructure investments and enhancing network performance.

Hydrodynamic characterization of bubble column using Dynamical High Order Decomposition approach

Bubble columns play a crucial role in a wide range of industries, including chemical and biochemical processes, petrochemicals, and environmental engineering. Understanding the dynamics of bubble columns is essential for optimizing their performance in various applications. This study proposes a data-driven approach for analyzing the dynamics of a two-dimensional bubble column system. We conducted simulations with varying superficial velocities and generated a comprehensive training dataset encompassing the entire velocity and pressure fields to achieve this. We then compared the performance of two approaches, the Fast Fourier Transformation (FFT) and the High-Order Dynamic Mode Decomposition (HODMD), in representing the system’s dynamics. Our findings demonstrate that the conventional FFT approach fails to adequately capture the complex dynamics of the dispersed multiphase flow system. This limitation arises due to the distribution of frequencies along the domain. Conversely, our work highlights the success of the HODMD method in accurately representing the system’s dynamics using only a few arbitrary sampling points within the domain. The implications of this study are significant, as it sheds light on the potential benefits of employing HODMD for analyzing bubble column dynamics. By utilizing this approach, industrial processes can be optimized more effectively across various applications.

Stress Detection in IT Employees using Machine Learning

In today's fast-paced technology landscape, stress management is becoming increasingly important, especially among IT professionals. The work environment in the IT industry is often characterized by long hours, tight deadlines, and high expectations, which can lead to elevated stress levels. Unchecked stress not only impacts the health and well-being of professionals but also affects productivity and job satisfaction. This study aims to predict the stress levels of IT professionals using machine learning techniques, thereby aiding in proactive stress management. We utilize a range of features indicative of work stress, including Heart Rate, Skin Conductivity, Hours Worked, Number of Emails Sent, and Meetings Attended. These features provide a comprehensive view of both the physiological and work-related factors that contribute to stress. The application of machine learning in this context serves as an innovative approach to an increasingly pertinent issue. By leveraging the power of data analytics, this model aims to provide actionable insights for both individuals and organizations. Individuals can use these predictions for self-monitoring and early intervention, while organizations can utilize them to identify high-stress environments or roles, thereby allocating resources or interventions more effectively. Our preliminary results indicate a strong correlation between the chosen features and stress levels, demonstrating the viability of using machine learning for stress prediction in IT professionals. This study stands as a crucial step towards a more data-driven approach to mental health and well-being in the workplace Key Words: Random Forest , AdaBoost Classifier, Extra Tree Classifier, Decision Tree, Stacking etc.

A two-step post-optimality approach for a multi-objective railway maintenance planning problem

Maintenance planning for railway networks is an exacting task, impacting numerous stakeholders with diverse objectives. While a multi-objective optimization model addresses the problem, it often results in numerous solutions on a Pareto front. Past researchers have introduced various Pareto pruning methods to autonomously create a shortlist of promising solutions. Nonetheless, solely relying on data-driven approaches to finalize solutions can lead to undesirable outcomes for the decision maker (DM). To strike a balance between a human-involved and a data-centric decision, this article proposes a two-step approach. In the first step, Latent Profile Analysis (LPA) is utilized to group similar solutions on the Pareto front together, and a representative solution from each group is presented to the DM. After the DM identifies a focus region, Data Envelopment Analysis (DEA), including CCR and BCC models, is employed in the second step to rank the solutions in a selected group by their relative efficiency. Applying the proposed approach to a real-world case study demonstrates its capability in the railway asset management context. Key advantages of LPA lie in its ability to provide the appropriate number of solutions in the pruned set and its flexibility in grouping solutions. DEA enhances decision-making by ranking solutions within the focus region. Ultimately, by integrating automated algorithms with human insight, the two-step approach successfully identifies an efficient solution and mitigates the risk of obtaining undesirable outcomes on the Pareto front.

Striatal functional alterations link to distinct symptomatology across mood states in bipolar disorder

BackgroundAs a central hub in cognitive and emotional brain circuits, the striatum is considered likely to be integrally involved in the psychopathology of bipolar disorder (BD). However, it remains unclear how alterations in striatal function contribute to distinct symptomatology of BD during different mood states. MethodsBehavioral assessment (i.e., emotional symptoms and cognitive performance) and neuroimaging data were collected from 125 participants comprising 31 (hypo)manic, 31 depressive and 31 euthymic patients with BD, and 32 healthy controls. We compared the functional connectivity (FC) of striatal subregions across BD mood states with healthy controls and then used a multivariate data-driven approach to explore dimensional associations between striatal connectivity and behavioral performance. Finally, we compared the FC and behavioral composite scores, which reflect the individual weighted representation of the associations, among different mood states. ResultsPatients in all mood states exhibited increased FC between the bilateral ventral rostral putamen (VRP) and ventrolateral thalamus. Bipolar (hypo)mania uniquely exhibited increased VRP connectivity and superior ventral striatum connectivity. One latent component was identified, whereby increased FCs of striatal subregions were associated with distinct psychopathological symptomatology (more manic symptoms, elevated positive mood, less depressive symptoms and worse cognitive performance). Bipolar (hypo)manic patients had the highest FC and behavioral composite scores while bipolar depressive patients had the lowest. ConclusionsOur data demonstrated both trait features of BD and state features specific to bipolar (hypo) mania. The findings underscored the fundamental role of the striatum in the pathophysiological processes underlying specific symptomatology across all mood states.

A Survey and Study of Signal and Data-Driven Approaches for Pipeline Leak Detection and Localization

A Survey and Study of Signal and Data-Driven Approaches for Pipeline Leak Detection and Localization