Feature Imputation Research Articles

An MRI multi-sequence feature imputation and fusion mutual-aid model based on sequence deletion for differentiation of high-grade from low-grade glioma

To evaluate the performance of magnetic resonance imaging (MRI) multi-sequence feature imputation and fusion mutual model based on sequence deletion in differentiating high-grade glioma (HGG) from low-grade glioma (LGG). We retrospectively collected multi-sequence MR images from 305 glioma patients, including 189 HGG patients and 116 LGG patients. The region of interest (ROI) of T1-weighted images (T1WI), T2-weighted images (T2WI), T2 fluid attenuated inversion recovery (T2_FLAIR) and post-contrast enhancement T1WI (CE_T1WI) were delineated to extract the radiomics features. A mutual-aid model of MRI multi-sequence feature imputation and fusion based on sequence deletion was used for imputation and fusion of the feature matrix with missing data. The discriminative ability of the model was evaluated using 5-fold cross-validation method and by assessing the accuracy, balanced accuracy, area under the ROC curve (AUC), specificity, and sensitivity. The proposed model was quantitatively compared with other non-holonomic multimodal classification models for discriminating HGG and LGG. Class separability experiments were performed on the latent features learned by the proposed feature imputation and fusion methods to observe the classification effect of the samples in twodimensional plane. Convergence experiments were used to verify the feasibility of the model. For differentiation of HGG from LGG with a missing rate of 10%, the proposed model achieved accuracy, balanced accuracy, AUC, specificity, and sensitivity of 0.777, 0.768, 0.826, 0.754 and 0.780, respectively. The fused latent features showed excellent performance in the class separability experiment, and the algorithm could be iterated to convergence with superior classification performance over other methods at the missing rates of 30% and 50%. The proposed model has excellent performance in classification task of HGG and LGG and outperforms other non-holonomic multimodal classification models, demonstrating its potential for efficient processing of non-holonomic multimodal data.

Towards Better Modeling With Missing Data: A Contrastive Learning-Based Visual Analytics Perspective.

Missing data can pose a challenge for machine learning (ML) modeling. To address this, current approaches are categorized into feature imputation and label prediction and are primarily focused on handling missing data to enhance ML performance. These approaches rely on the observed data to estimate the missing values and therefore encounter three main shortcomings in imputation, including the need for different imputation methods for various missing data mechanisms, heavy dependence on the assumption of data distribution, and potential introduction of bias. This study proposes a Contrastive Learning (CL) framework to model observed data with missing values, where the ML model learns the similarity between an incomplete sample and its complete counterpart and the dissimilarity between other samples. Our proposed approach demonstrates the advantages of CL without requiring any imputation. To enhance interpretability, we introduce CIVis, a visual analytics system that incorporates interpretable techniques to visualize the learning process and diagnose the model status. Users can leverage their domain knowledge through interactive sampling to identify negative and positive pairs in CL. The output of CIVis is an optimized model that takes specified features and predicts downstream tasks. We provide two usage scenarios in regression and classification tasks and conduct quantitative experiments, expert interviews, and a qualitative user study to demonstrate the effectiveness of our approach. In short, this study offers a valuable contribution to addressing the challenges associated with ML modeling in the presence of missing data by providing a practical solution that achieves high predictive accuracy and model interpretability.

Feature Imputation using Neutrosophic Set Theory in Machine Learning Regression Context

The prediction context of machine learning aims to discern the underlying patterns that dictate the characteristics to forecast the output. This prediction lacks precision when the input data is not accurate or precise. This study focuses on feature imputation through the application of the neutrosophic set theory. The primary concept involves substituting feature data, which may have accuracy and correctness issues, with neutrosophic variables considering the degrees of truth, indeterminacy, and falsity to produce more precise and resilient predictions. The proposed method was implemented in a specific case study, and the results are analyzed.

Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering

In recent years, incomplete multi-view clustering (IMVC), which studies the challenging multi-view clustering problem on missing views, has received growing research interests. Previous IMVC methods suffer from the following issues: (1) the inaccurate imputation for missing data, which leads to suboptimal clustering performance, and (2) most existing IMVC models merely consider the explicit presence of graph structure in data, ignoring the fact that latent graphs of different views also provide valuable information for the clustering task. To overcome such challenges, we present a novel method, termed Adaptive feature imputation with latent graph for incomplete multi-view clustering (AGDIMC). Specifically, it captures the embbedded features of each view by incorporating the view-specific deep encoders. Then, we construct partial latent graphs on complete data, which can consolidate the intrinsic relationships within each view while preserving the topological information. With the aim of estimating the missing sample based on the available information, we utilize an adaptive imputation layer to impute the embedded feature of missing data by using cross-view soft cluster assignments and global cluster centroids. As the imputation progresses, the portion of complete data increases, contributing to enhancing the discriminative information contained in global pseudo-labels. Meanwhile, to alleviate the negative impact caused by inferior impute samples and the discrepancy of cluster structures, we further design an adaptive imputation strategy based on the global pseudo-label and the local cluster assignment. Experimental results on multiple real-world datasets demonstrate the effectiveness of our method over existing approaches.

Exploring content-based group recommendation for suggesting restaurants in Havana City

Recommender systems (RSs) are a relevant kind of artificial intelligence-based systems focused on providing users with the information that best fit their preferences and needs in a search space overloaded of possible options. Specifically, group recommender systems (GRSs) are a special type of RS centered on recommending items that are consumed in groups and not individually, being TV program and touristic packages key examples of such items. The current work is focused on proposing a content-based group recommendation approach (CB-GRS) contextualized to the restaurant recommendation domain. In contrast to previous content-based group recommendation models, the proposal incorporates novel stages such as restaurants feature imputation, the generation of a virtual group profile, the use of feature weighting, and the automatic selection of the most appropriate aggregation approach for composing group recommendations. The proposal is evaluated in an original recommendation scenario, related to restaurant from Havana City in Cuba, where several restaurant attributes are identified for applying the proposed CB-GRS approach. The experimental protocol evaluates individually each component of the proposal, evidencing their importance as part of the whole framework. Furthermore, the comparison with previous works has been also developed. The proposed approach can be applied in other recommendation scenarios, and in addition, the developed experimental protocol is generalizable for the evaluation of further content-based individual and group recommendation approaches in the tourism domain.

Sonic Well-Log Imputation Through Machine-Learning-Based Uncertainty Models

Sonic well logs provide critical information to calibrate seismic data and support geomechanical characterization. Advanced subsurface data analytics and machine learning enable new methods and workflows for property estimation, regression, and classification for geoscience and subsurface engineering applications. However, current applications for imputation of well-logging values rely only on model accuracy and low error predictions. T raditional model validation techniques are not enough to validate models and account for the substantial uncertainty in the subsurface. Well-logging imputation estimates and their associated uncertainty models are essential to the field development planning and decision-making workflows, such as reservoir modeling, volumetric resource assessment, predrill prediction with uncertainty, remaining resource mapping, and production allocation. When performing subsurface feature imputation with machine learning, we must expand our machine-learning model training and complexity tuning workflows to check the entire uncertainty model to ensure uncertainty distributions are precise and accurate. We propose a workflow that integrates the goodness metric to calculate accurate and precise uncertainty models of sonic well-log predictions based on ensembles of the machine-learning estimates. Our workflow combines model evaluation and visualization of the estimates and the uncertainty model with respect to measured depth. Our proposed method provides intuitive diagnostics and metrics to evaluate estimation accuracy and uncertainty model goodness.

Handling missing data in well-log curves with a gated graph neural network

Well logging is a common method that is used to obtain the rock properties of a formation. It is relatively frequent, however, that log information is incomplete due to cost limitations or borehole problems. Existing models predict missing well logs from a fixed combination of other available well logs. However, the missing well logs vary from well to well. We have proposed using a gated graph neural network (GNN) to handle the missing values in well-log curves. It takes sequential data, predicting each missing measurement in the data not only using other available variables measured at the same depth but also available measurements of neighboring observations. Meanwhile, the missing well logs and available well logs could be any possible combinations as long as they are mutually exclusive. This approach has two advantages: (1) the gated GNN does not need to build a specific model for each missing measurement or from every possible combination of available measurements and (2) it can be integrated into the training process of the following predictive model to perform classification tasks. We evaluate the gated GNN model along with two other models: the GRAPE model and the multiple imputation by chained equations (MICE)-gated recurrent unit (GRU) model, on a data set from the North Sea to perform a missing feature imputation task and a lithofacies identification task. The GRAPE model also is a graph-based model, and it predicts values for each missing measurement from available variables measured at the same depth. The MICE-GRU model is a combination of the MICE algorithm and GRU, which handles the feature imputation procedure and the lithofacies identification procedure separately. Our experiments find that the gated GNN model outperforms the MICE algorithm and the GRAPE model on the missing feature imputation task. For the lithofacies identification task, the gated GNN model also provides comparable results to the MICE-GRU model, and they both outperform the GRAPE model.

Similarity-based prediction of ejection fraction in heart failure patients

Biomedical research is increasingly employing real world evidence (RWE) to foster discoveries of novel clinical phenotypes and to better characterize long term effect of medical treatments. However, due to limitations inherent in the collection process, RWE often lacks key features of patients, particularly when these features cannot be directly encoded using data standards such as ICD-10. Here, we propose a novel data-driven statistical machine learning approach, named Feature Imputation via Local Likelihood (FILL), designed to infer missing features by exploiting feature similarity between patients. We test our method using a particularly challenging problem: differentiating heart failure patients with reduced versus preserved ejection fraction (HFrEF and HFpEF respectively). The complexity of the task stems from three aspects: the two share many common characteristics and treatments, only part of the relevant diagnoses may have been recorded, and the information on ejection fraction is often missing from RWE datasets. Despite these difficulties, our method is shown to be capable of inferring heart failure patients with HFpEF with a precision above 80% when considering multiple scenarios across two RWE datasets containing 11,950 and 10,051 heart failure patients. This is an improvement when compared to classical approaches such as logistic regression and random forest which were only able to achieve a precision < 73%. Finally, this approach allows us to analyse which features are commonly associated with HFpEF patients. For example, we found that specific diagnostic codes for atrial fibrillation and personal history of long-term use of anticoagulants are often key in identifying HFpEF patients.

VEXAS: VISTA EXtension to Auxiliary Surveys

Context. We present the second public data release of the VISTA EXtension to Auxiliary Surveys (VEXAS), where we classify objects into stars, galaxies, and quasars based on an ensemble of machine learning algorithms. Aims. The aim of VEXAS is to build the widest multi-wavelength catalogue, providing reference magnitudes, colours, and morphological information for a large number of scientific uses. Methods. We applied an ensemble of thirty-two different machine learning models, based on three different algorithms and on different magnitude sets, training samples, and classification problems (two or three classes) on the three VEXAS Data Release 1 (DR1) optical and infrared (IR) tables. The tables were created in DR1 cross-matching VISTA near-infrared data with Wide-field Infrared Survey Explorer far-infrared data and with optical magnitudes from the Dark Energy Survey (VEXAS-DESW), the Sky Mapper Survey (VEXAS-SMW), and the Panoramic Survey Telescope and Rapid Response System Survey (VEXAS-PSW). We assembled a large table of spectroscopically confirmed objects (VEXAS-SPEC-GOOD, 415 628 unique objects), based on the combination of six different spectroscopic surveys that we used for training. We developed feature imputation to also classify objects for which magnitudes in one or more bands are missing. Results. We classify in total ≈90 × 106 objects in the Southern Hemisphere. Among these, ≈62.9 × 106 (≈52.6 × 106) are classified as ‘high confidence’ (‘secure’) stars, ≈920 000 (≈750 000) as ‘high confidence’ (‘secure’) quasars, and ≈34.8 (≈34.1) million as ‘high confidence’ (‘secure’) galaxies, with pclass ≥ 0.7 (pclass ≥ 0.9). The DR2 tables update the DR1 with the addition of imputed magnitudes and membership probabilities to each of the three classes. Conclusions. The density of high-confidence extragalactic objects varies strongly with the survey depth: at pclass &gt; 0.7, there are 11 deg−2 quasars in the VEXAS-DESW footprint and 103 deg−2 in the VEXAS-PSW footprint, while only 10.7 deg−2 in the VEXAS-SM footprint. Improved depth in the mid-infrared and coverage in the optical and near-infrared are needed for the SM footprint that is not already covered by DESW and PSW.

Feature replacement methods enable reliable home video analysis for machine learning detection of autism

Autism Spectrum Disorder is a neuropsychiatric condition affecting 53 million children worldwide and for which early diagnosis is critical to the outcome of behavior therapies. Machine learning applied to features manually extracted from readily accessible videos (e.g., from smartphones) has the potential to scale this diagnostic process. However, nearly unavoidable variability in video quality can lead to missing features that degrade algorithm performance. To manage this uncertainty, we evaluated the impact of missing values and feature imputation methods on two previously published autism detection classifiers, trained on standard-of-care instrument scoresheets and tested on ratings of 140 children videos from YouTube. We compare the baseline method of listwise deletion to classic univariate and multivariate techniques. We also introduce a feature replacement method that, based on a score, selects a feature from an expanded dataset to fill-in the missing value. The replacement feature selected can be identical for all records (general) or automatically adjusted to the record considered (dynamic). Our results show that general and dynamic feature replacement methods achieve a higher performance than classic univariate and multivariate methods, supporting the hypothesis that algorithmic management can maintain the fidelity of video-based diagnostics in the face of missing values and variable video quality.

Combining Partially Overlapping Multi-Omics Data in Databases Using Relationship Matrices.

Private and public breeding programs, as well as companies and universities, have developed different genomics technologies that have resulted in the generation of unprecedented amounts of sequence data, which bring new challenges in terms of data management, query, and analysis. The magnitude and complexity of these datasets bring new challenges but also an opportunity to use the data available as a whole. Detailed phenotype data, combined with increasing amounts of genomic data, have an enormous potential to accelerate the identification of key traits to improve our understanding of quantitative genetics. Data harmonization enables cross-national and international comparative research, facilitating the extraction of new scientific knowledge. In this paper, we address the complex issue of combining high dimensional and unbalanced omics data. More specifically, we propose a covariance-based method for combining partial datasets in the genotype to phenotype spectrum. This method can be used to combine partially overlapping relationship/covariance matrices. Here, we show with applications that our approach might be advantageous to feature imputation based approaches; we demonstrate how this method can be used in genomic prediction using heterogeneous marker data and also how to combine the data from multiple phenotypic experiments to make inferences about previously unobserved trait relationships. Our results demonstrate that it is possible to harmonize datasets to improve available information across gene-banks, data repositories, or other data resources.

Distributed Semi-Supervised Learning With Missing Data.

Data classification is usually challenged by the difficulty and/or high cost in collecting sufficient labeled data, and unavoidability of data missing. Besides, most of the existing algorithms belong to centralized processing, in which all of the training data must be stored and processed at a fusion center. But in many real applications, data are distributed over multiple nodes, and cannot be centralized to one node for processing due to various reasons. Considering this, in this article, we focus on the problem of distributed classification of missing data with a small proportion of labeled data samples, and develop a distributed semi-supervised missing-data classification (dS2MDC) algorithm. The proposed algorithm is a distributed joint subspace/classifier learning, that is, a latent subspace representation for missing feature imputation is learned jointly with the training of nonlinear classifiers modeled by the χ2 kernel using a semi-supervised learning strategy. Theoretical performance analysis and simulations on several datasets clearly validate the effectiveness of the proposed dS2MDC algorithm from different perspectives.

Deep learning of joint myelin and T1w MRI features in normal-appearing brain tissue to distinguish between multiplesclerosispatients and healthy controls.

Myelin imaging is a form of quantitative magnetic resonance imaging (MRI) that measures myelin content and can potentially allow demyelinating diseases such as multiple sclerosis (MS) to be detected earlier. Although focal lesions are the most visible signs of MS pathology on conventional MRI, it has been shown that even tissues that appear normal may exhibit decreased myelin content as revealed by myelin-specific images (i.e., myelin maps). Current methods for analyzing myelin maps typically use global or regional mean myelin measurements to detect abnormalities, but ignore finer spatial patterns that may be characteristic of MS. In this paper, we present a machine learning method to automatically learn, from multimodal MR images, latent spatial features that can potentially improve the detection of MS pathology at early stage. More specifically, 3D image patches are extracted from myelin maps and the corresponding T1-weighted (T1w) MRIs, and are used to learn a latent joint myelin-T1w feature representation via unsupervised deep learning. Using a data set of images from MS patients and healthy controls, a common set of patches are selected via a voxel-wise t-test performed between the two groups. In each MS image, any patches overlapping with focal lesions are excluded, and a feature imputation method is used to fill in the missing values. A feature selection process (LASSO) is then utilized to construct a sparse representation. The resulting normal-appearing features are used to train a random forest classifier. Using the myelin and T1w images of 55 relapse-remitting MS patients and 44 healthy controls in an 11-fold cross-validation experiment, the proposed method achieved an average classification accuracy of 87.9% (SD = 8.4%), which is higher and more consistent across folds than those attained by regional mean myelin (73.7%, SD = 13.7%) and T1w measurements (66.7%, SD = 10.6%), or deep-learned features in either the myelin (83.8%, SD = 11.0%) or T1w (70.1%, SD = 13.6%) images alone, suggesting that the proposed method has strong potential for identifying image features that are more sensitive and specific to MS pathology in normal-appearing brain tissues.

Spectral Reconstruction and Noise Model Estimation Based on a Masking Model for Noise Robust Speech Recognition

An effective way to increase noise robustness in automatic speech recognition (ASR) systems is feature enhancement based on an analytical distortion model that describes the effects of noise on the speech features. One of such distortion models that has been reported to achieve a good trade-off between accuracy and simplicity is the masking model. Under this model, speech distortion caused by environmental noise is seen as a spectral mask and, as a result, noisy speech features can be either reliable (speech is not masked by noise) or unreliable (speech is masked). In this paper, we present a detailed overview of this model and its applications to noise robust ASR. Firstly, using the masking model, we derive a spectral reconstruction technique aimed at enhancing the noisy speech features. Two problems must be solved in order to perform spectral reconstruction using the masking model: (1) mask estimation, i.e. determining the reliability of the noisy features, and (2) feature imputation, i.e. estimating speech for the unreliable features. Unlike missing data imputation techniques where the two problems are considered as independent, our technique jointly addresses them by exploiting a priori knowledge of the speech and noise sources in the form of a statistical model. Secondly, we propose an algorithm for estimating the noise model required by the feature enhancement technique. The proposed algorithm fits a Gaussian mixture model to the noise by iteratively maximising the likelihood of the noisy speech signal so that noise can be estimated even during speech-dominating frames. A comprehensive set of experiments carried out on the Aurora-2 and Aurora-4 databases shows that the proposed method achieves significant improvements over the baseline system and other similar missing data imputation techniques.