Imperfect Data Research Articles

Enhanced robustness in machine learning: Application of an adaptive robust loss function

In the field of machine learning, the selection of a loss function plays a pivotal role in determining the training dynamics and generalization capability of models. Traditional loss functions such as mean square error (MSE) and cross-entropy are often not equipped to handle noisy and anomalous data effectively, which can result in models that perform poorly in practical scenarios. To address these shortcomings, this study introduces a novel adaptive robust loss function, enhanced by a tunable parameter , which allows for flexibility in adjusting the robustness of the function according to the nature of the data being processed. Our research demonstrates that this new loss function significantly improves the performance of linear regression and multilayer perceptron models, particularly in environments laden with noisy and anomalous data. By adapting the parameter , the function can cater to varying levels of data irregularities, thus enhancing the models accuracy and reliability across diverse and complex data environments. This adaptive mechanism not only offers a substantial theoretical contribution to the understanding of robust loss functions but also provides a practical tool for machine learning practitioners to develop models that are resilient to data imperfections. The implications of this research are profound, suggesting a shift towards more adaptive and robust approaches in machine learning model development.

Deep Reinforcement Learning for personalized diagnostic decision pathways using Electronic Health Records: A comparative study on anemia and Systemic Lupus Erythematosus

Background:Clinical diagnoses are typically made by following a series of steps recommended by guidelines that are authored by colleges of experts. Accordingly, guidelines play a crucial role in rationalizing clinical decisions. However, they suffer from limitations, as they are designed to cover the majority of the population and often fail to account for patients with uncommon conditions. Moreover, their updates are long and expensive, making them unsuitable for emerging diseases and new medical practices. Methods:Inspired by guidelines, we formulate the task of diagnosis as a sequential decision-making problem and study the use of Deep Reinforcement Learning (DRL) algorithms to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from Electronic Health Records (EHRs), which we name a diagnostic decision pathway. We apply DRL to synthetic yet realistic EHRs and develop two clinical use cases: Anemia diagnosis, where the decision pathways follow a decision tree schema, and Systemic Lupus Erythematosus (SLE) diagnosis, which follows a weighted criteria score. We particularly evaluate the robustness of our approaches to noise and missing data, as these frequently occur in EHRs. Results:In both use cases, even with imperfect data, our best DRL algorithms exhibit competitive performance compared to traditional classifiers, with the added advantage of progressively generating a pathway to the suggested diagnosis, which can both guide and explain the decision-making process. Conclusion:DRL offers the opportunity to learn personalized decision pathways for diagnosis. Our two use cases illustrate the advantages of this approach: they generate step-by-step pathways that are explainable, and their performance is competitive when compared to state-of-the-art methods.

Research on Flexible Data Model of MES System based on Time-series Database

In the process of advancing towards digitization and intelligence in manufacturing, Manufacturing Execution Systems (MES) have gradually become the core of production processes. The design of the data model is crucial as it affects the scalability, maintainability, and stability of the system. This study focuses on addressing issues in MES systems such as high investment costs, imperfect data models, lack of flexibility, and inefficient data flow. It proposes a novel flexible data model based on time-series databases.This paper introduces the definition and characteristics of time-series databases, analyzes the shortcomings of existing MES system data models, and proposes a novel flexible MES data model based on time-series databases. Finally, the practicality and efficiency of the new data model are validated through experiments.

Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning

Oral squamous cell carcinoma recognition presents a challenge due to late diagnosis and costly data acquisition. A cost-efficient, computerized screening system is crucial for early disease detection, minimizing the need for expert intervention and expensive analysis. Besides, transparency is essential to align these systems with critical sector applications. Explainable Artificial Intelligence (XAI) provides techniques for understanding models. However, current XAI is mostly data-driven and focused on addressing developers’ requirements of improving models rather than clinical users’ demands for expressing relevant insights. Among different XAI strategies, we propose a solution composed of Case-Based Reasoning paradigm to provide visual output explanations and Informed Deep Learning (IDL) to integrate medical knowledge within the system. A key aspect of our solution lies in its capability to handle data imperfections, including labeling inaccuracies and artifacts, thanks to an ensemble architecture on top of the deep learning (DL) workflow. We conducted several experimental benchmarks on a dataset collected in collaboration with medical centers. Our findings reveal that employing the IDL approach yields an accuracy of 85%, surpassing the 77% accuracy achieved by DL alone. Furthermore, we measured the human-centered explainability of the two approaches and IDL generates explanations more congruent with the clinical user demands.

Neural networks for quantum state tomography with constrained measurements

Quantum state tomography (QST) aiming at reconstructing the density matrix of a quantum state plays an important role in various emerging quantum technologies. Recognizing the challenges posed by imperfect measurement data, we develop a unified neural network (NN)-based approach for QST under constrained measurement scenarios, including limited measurement copies, incomplete measurements, and noisy measurements. Through comprehensive comparison with other estimation methods, we demonstrate that our method improves the estimation accuracy in scenarios with limited measurement resources, showcasing notable robustness in noisy measurement settings. These findings highlight the capability of NNs to enhance QST with constrained measurements.

Pathways to Enhancing the Quality of Agricultural Statistical Services in the Context of Rural Revitalization

In the strategic context of rural revitalization, optimizing the quality of agricultural statistical services is a crucial element for advancing agricultural modernization and sustainable rural economic development. This paper focuses on the significance of enhancing agricultural statistical service quality under the backdrop of rural revitalization. It addresses current issues such as inadequate implementation of agricultural statistical survey systems, an imperfect data quality control system, and a shortage of statistical service personnel. Proposals are made to improve the statistical survey system, enhance the data quality control framework, and strengthen personnel training. These pathways offer references for elevating the quality of agricultural statistical services and implementing the rural revitalization strategy in the new era.

Predicting Patient No-Shows: Situated Machine Learning with Imperfect Data.

Patients who do not show up for scheduled appointments are a considerable cost and concern in healthcare. In this study, we predict patient no-shows for outpatient surgery at the endoscopy ward of a hospital in Denmark. The predictions are made by training machine leaning (ML) models on available data, which have been recorded for purposes other than ML, and by doing situated work in the hospital setting to understand local data practices and fine-tune the models. The best performing model (XGBoost with oversampling) predicts no-shows at sensitivity = 0.97, specificity = 0.66, and accuracy = 0.95. Importantly, the situated work engaged local hospital staff in the design process and led to substantial quantitative improvements in the performance of the models. We consider the results promising but acknowledge that they are from a single ward. To transfer the no-show models to other wards and hospitals, the situated work must be redone.

Particle filter data assimilation for ubiquitous unstable trajectories of two-dimensional three-state cellular automata

Estimating the states of error-growing (sensitive to initial state) cellular automata (CA) based on noisy imperfect data is challenging due to the discreteness of the dynamical system. This paper proposes particle filter (PF)–based data assimilation (DA) for three-state error-growing CA and demonstrates that the PF-based DA can predict the present and future state even with noisy and sparse observations. The error-growing CA used in the present study comprised a competitive system of land, grass, and sheep. To the best of the authors’ knowledge, this is the first application of DA to such CA. The performance of DA for different observation sets was evaluated in terms of observational error, density, and frequency, and a series of sensitivity tests of the internal parameters in the DA was conducted. The inflation and localization parameters were tuned according to the sensitivity tests.

A robust operators’ cognitive workload recognition method based on denoising masked autoencoder

Identifying the cognitive workload of operators is crucial in complex human-automation collaboration systems. An excessive workload can lead to fatigue or accidents, while an insufficient workload may diminish situational awareness and efficiency. However, existing supervised learning-based methods for workload recognition are ineffective when dealing with imperfect input data, such as missing or noisy data, which is not practical in real applications. This study introduces a robust Electroencephalogram (EEG)-enabled cognitive workload recognition model using self-supervised learning. The proposed method, DMAEEG, combines the training strategies of denoising autoencoders and masked autoencoders, demonstrating strong robustness against noisy and incomplete data. More specifically, we adopt the temporal convolutional network and multi-head self-attention mechanisms as the backbone, effectively capturing both the temporal and spatial features from EEG. Extensive experiments are conducted to verify the effectiveness and robustness of the proposed method on an open dataset and a self-collected dataset. The results indicate that DMAEEG performs superior to other state-of-the-art across various evaluation metrics. Moreover, DMAEEG maintains high accuracy in workload inference even when EEG signals are corrupted with a high masking ratio or strong noises. This signifies its superiority in capturing robust intrinsic patterns from imperfect EEG data. The proposed method significantly contributes to decoding EEG signals for workload recognition in real-world applications, thereby enhancing the safety and reliability of human-automation interactions.

Robust online active learning with cluster-based local drift detection for unbalanced imperfect data

With the rapid development of data-driven technologies, a massive amount of actual data emerges from industrial systems, forming data stream. Their data distribution may change over time and outliers may be generated as unbalanced imperfect data due to time-varying working condition, aging equipment, etc. Previous methods struggle with the dual challenges of concept drift and unbalance, however, fail to efficiently distinguishing outliers from a drift under the limited labeling budget, causing the performance degradation. To address the issue, robust online active learning with cluster-based local drift detection is proposed to classify unbalanced imperfect data stream with the above characteristics. The cluster-based local drift detection is first designed to capture a new concept and recognize the corresponding drifted regions. Following that, an improved active learning mechanism is presented to distinguish outliers from a drift, and select most valuable instances for labeling and updating ensemble classifier. Experimental results for eight synthetic and four real-world data streams show that the proposed method outperforms seven comparative methods on classification accuracy and robustness.

Understanding world models through multi-step pruning policy via reinforcement learning

In model-based reinforcement learning, the conventional approach to addressing world model bias is to use gradient optimization methods. However, using a singular policy from gradient optimization methods in response to a world model bias inevitably results in an inherently biased policy. This is because of constraints on the imperfect and dynamic data of state-action pairs. The gap between the world model and the real environment can never be completely eliminated. This article introduces a novel approach that explores a variety of policies instead of focusing on either world model bias or singular policy bias. Specifically, we introduce the Multi-Step Pruning Policy (MSPP), which aims to reduce redundant actions and compress the action and state spaces. This approach encourages a different perspective within the same world model. To achieve this, we use multiple pruning policies in parallel and integrate their outputs using the cross-entropy method. Additionally, we provide a convergence analysis of the pruning policy theory in tabular form and an updated parameter theoretical framework. In the experimental section, the newly proposed MSPP method demonstrates a comprehensive understanding of the world model and outperforms existing state-of-the-art model-based reinforcement learning baseline techniques.

The Materiality of Data: Practices of Coping with Imperfect Data for Machine Learning Development

The Materiality of Data: Practices of Coping with Imperfect Data for Machine Learning Development

Spatio-temporal ecological models via physics-informed neural networks for studying chronic wasting disease

To mitigate the negative effects of emerging wildlife diseases in biodiversity and public health it is critical to accurately forecast pathogen dissemination while incorporating relevant spatio-temporal covariates. Forecasting spatio-temporal processes can often be improved by incorporating scientific knowledge about the dynamics of the process using physical models. Ecological diffusion equations are often used to model epidemiological processes of wildlife diseases where environmental factors play a role in disease spread. Physics-informed neural networks (PINNs) are deep learning algorithms that constrain neural network predictions based on physical laws and therefore are powerful forecasting models useful even in cases of limited and imperfect training data. In this paper, we develop a novel ecological modeling tool using PINNs, which fits a feedforward neural network and simultaneously performs parameter identification in a partial differential equation (PDE) with varying coefficients. We demonstrate the applicability of our model by comparing it with the commonly used Bayesian stochastic partial differential equation method and traditional machine learning approaches, showing that our proposed model exhibits superior prediction and forecasting performance when modeling chronic wasting disease in deer in Wisconsin. Furthermore, our model provides the opportunity to obtain scientific insights into spatio-temporal covariates affecting spread and growth of diseases. This work contributes to future machine learning and statistical methodology development by studying spatio-temporal processes enhanced by prior physical knowledge.

A Heat Method for Generalized Signed Distance

We introduce a method for approximating the signed distance function (SDF) of geometry corrupted by holes, noise, or self-intersections. The method implicitly defines a completed version of the shape, rather than explicitly repairing the given input. Our starting point is a modified version of the heat method for geodesic distance, which diffuses normal vectors rather than a scalar distribution. This formulation provides robustness akin to generalized winding numbers (GWN) , but provides distance function rather than just an inside/outside classification. Our formulation also offers several features not common to classic distance algorithms, such as the ability to simultaneously fit multiple level sets, a notion of distance for geometry that does not topologically bound any region, and the ability to mix and match signed and unsigned distance. The method can be applied in any dimension and to any spatial discretization, including triangle meshes, tet meshes, point clouds, polygonal meshes, voxelized surfaces, and regular grids. We evaluate the method on several challenging examples, implementing normal offsets and other morphological operations directly on imperfect curve and surface data. In many cases we also obtain an inside/outside classification dramatically more robust than the one obtained provided by GWN.

PCDMD: Physics-constrained dynamic mode decomposition for accurate and robust forecasting of dynamical systems with imperfect data and physics

The dynamic mode decomposition (DMD) method has attracted widespread attention as a representative modal-decomposition method and can build a predictive model. However, DMD may give predicted results that deviate from physical reality in some scenarios, such as dealing with translation problems or noisy data. Here, we propose a physics-constrained DMD (PCDMD) method to address this issue. The proposed PCDMD method first employs a data-driven model using DMD, then calculates the residual of the physical equations, and finally corrects the predicted results using Kalman filter and gain coefficients. In this way, the PCDMD method can integrate the physics-informed equations with the data-driven model generated by DMD. Numerical experiments are conducted using PCDMD, including the Allen–Cahn, advection-diffusion, Burgers' equations and lid-driven cavity flow. The results demonstrate that the proposed PCDMD method can reduce the reconstruction and prediction errors by 1%-10% by incorporating physical constraints. Regarding noisy datasets and imperfect physical constraints, PCDMD can still ensure that the predicted results satisfy the physical constraints, thereby reducing errors. Program summaryProgram title: PCDMDDataset link:https://github.com/YinYuhuiTJU/PCDMDLicensing provisions: MITProgramming language: Python

How to Be Certain: Using Known Relations and Trust Discount to Determine Confidence About the Degree of Uncertainty

Ensuring certainty in the rapidly evolving digital twin environments amidst inherent uncertainty is paramount in decision-making for critical engineering systems. This paper presents a novel approach for quantifying and tracking confidence levels within a network of sensors and structural models, specifically addressing uncertainty arising from faulty sensors. By leveraging known relations and implementing a trust discount mechanism, our methodology offers a fundamental framework for navigating in the presence of uncertainties. A quasi-real-time case study on a cantilever beam model is simulated to demonstrate the efficacy of the proposed approach. We showcase the ability of our method to accurately assess and adapt to varying levels of uncertainty introduced by faulty sensors. Our findings highlight the importance of incorporating trust dynamics and established relationships within digital twin environments to achieve improved certainty despite imperfect data. This research contributes to the theoretical underpinnings of digital twin technology and offers practical insights for its application across diverse domains.

Physics-Informed Particle-Based Reinforcement Learning for Autonomy in Signalized Intersections

In this paper, we develop a framework to enhance the control of autonomous vehicles within signalized intersections by integrating system dynamics with imperfect sensor data. Although sensor data for autonomous vehicles is often partial, noisy, or missing, its alignment with underlying physics has the potential to significantly improve prediction accuracy. Our methodology involves a physics-based representation of system dynamics, accounting for stochastic elements originating from differences between real-world scenarios and model-based representations, using a Markov decision process (MDP) model that embraces system physics while accommodating uncertainties. Leveraging partial sensor data, we aim to diminish uncertainty associated with segments of the system model reflected in the data and better estimate the other physical variables that are not measurable through data. This framework develops particle-based reinforcement learning action policies, seamlessly integrating data and physics for controlling autonomous vehicles approaching signalized intersections. Numerical experiments showcase the effectiveness of these policies in ensuring safe control and decision-making in different scenarios of missing state variables and varying levels of data sparsity.

U-Net Convolutional Neural Network for Mapping Natural Vegetation and Forest Types from Landsat Imagery in Southeastern Australia.

Accurate and comparable annual mapping is critical to understanding changing vegetation distribution and informing land use planning and management. A U-Net convolutional neural network (CNN) model was used to map natural vegetation and forest types based on annual Landsat geomedian reflectance composite images for a 500 km × 500 km study area in southeastern Australia. The CNN was developed using 2018 imagery. Label data were a ten-class natural vegetation and forest classification (i.e., Acacia, Callitris, Casuarina, Eucalyptus, Grassland, Mangrove, Melaleuca, Plantation, Rainforest and Non-Forest) derived by combining current best-available regional-scale maps of Australian forest types, natural vegetation and land use. The best CNN generated using six Landsat geomedian bands as input produced better results than a pixel-based random forest algorithm, with higher overall accuracy (OA) and weighted mean F1 score for all vegetation classes (93 vs. 87% in both cases) and a higher Kappa score (86 vs. 74%). The trained CNN was used to generate annual vegetation maps for 2000-2019 and evaluated for an independent test area of 100 km × 100 km using statistics describing accuracy regarding the label data and temporal stability. Seventy-six percent of pixels did not change over the 20 years (2000-2019), and year-on-year results were highly correlated (94-97% OA). The accuracy of the CNN model was further verified for the study area using 3456 independent vegetation survey plots where the species of interest had ≥ 50% crown cover. The CNN showed an 81% OA compared with the plot data. The model accuracy was also higher than the label data (76%), which suggests that imperfect training data may not be a major obstacle to CNN-based mapping. Applying the CNN to other regions would help to test the spatial transferability of these techniques and whether they can support the automated production of accurate and comparable annual maps of natural vegetation and forest types required for national reporting.

Face recognition with occluded face using improve intersection over union of region proposal network on Mask region convolutional neural network

Face recognition entails detecting and identifying facial attributes. Mask region convolutional neural network (R-CNN) method is a prominent approach, while prior research predominantly delved into refining loss functions and perfecting object and face detection, recognizing, and identifying faces using imperfect data remained relatively unexplored. This study focuses on an occluded dataset comprising Indonesian faces, wherein 'occluded' denotes facial data that lacks complete visibility-encompassing instances where objects obscure faces or are partially cropped. This investigation involves a deliberate experiment that tailors the intersection over union (IoU) of the region proposal network (RPN) to suit the nuances of occluded Indonesian faces, thereby augmenting accuracy in recognition and segmentation tasks. The innovation IoU in the strategic utilization of Anchors, which involves the exclusion of anchors falling beyond the image borders to optimize computational efficiency. The outcomes of this research are striking; it showcases a remarkable 14.75%, 10.9%, and 12.97% surge based on mean average precision (mAP), mean average recall (mAR), and F1-Scores compared to the conventional Mask R-CNN approach. Notably, our proposed model elevates the average accuracy by 10% to 15% and decreases running time by 21%, a noteworthy enhancement compared to the preceding model. This progress is substantiated by validation utilizing 300 instances dataset, reinforcing the robustness of our approach.

A Sequential and Asynchronous Federated Learning Framework for Railway Point Machine Fault Diagnosis With Imperfect Data Transmission

A Sequential and Asynchronous Federated Learning Framework for Railway Point Machine Fault Diagnosis With Imperfect Data Transmission