Search NASA⌕ Search

SEARCH · Search NASA

Results for “imbalanced classification”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

32 records · Page 2

Improving Text Classification with Large Language Model-Based Data Augmentation

Large Language Models (LLMs) such as ChatGPT possess advanced capabilities in understanding and generating text. These capabilities enable ChatGPT to create text based on specific instructions, which can serve as augmented data for text classification tasks. Previous studies have approached data augmentation (DA) by either rewriting the existing dataset with ChatGPT or generating entirely new data from scratch. However, it is unclear which method is better without comparing their effectiveness. This study investigates the application of both methods to two datasets: a general-topic dataset (Reuters news data) and a domain-specific dataset (Mitigation dataset). Our findings indicate that: 1. ChatGPT generated new data consistently enhanced model’s classification results for both datasets. 2. Generating new data generally outperforms rewriting existing data, though crafting the prompts carefully is crucial to extract the most valuable information from ChatGPT, particularly for domain-specific data. 3. The augmentation data size affects the effectiveness of DA; however, we observed a plateau after incorporating 10 samples. 4. Combining the rewritten sample with new generated sample can potentially further improve the model’s performance.

97 MATHEMATICS AND COMPUTING↗

A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.

99 - GENERAL AND MISCELLANEOUS↗

Results of the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC)

Abstract Next-generation surveys like the Legacy Survey of Space and Time (LSST) on the Vera C. Rubin Observatory (Rubin) will generate orders of magnitude more discoveries of transients and variable stars than previous surveys. To prepare for this data deluge, we developed the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC), a competition that aimed to catalyze the development of robust classifiers under LSST-like conditions of a nonrepresentative training set for a large photometric test set of imbalanced classes. Over 1000 teams participated in PLAsTiCC, which was hosted in the Kaggle data science competition platform between 2018 September 28 and 2018 December 17, ultimately identifying three winners in 2019 February. Participants produced classifiers employing a diverse set of machine-learning techniques including hybrid combinations and ensemble averages of a range of approaches, among them boosted decision trees, neural networks, and multilayer perceptrons. The strong performance of the top three classifiers on Type Ia supernovae and kilonovae represent a major improvement over the current state of the art within astronomy. This paper summarizes the most promising methods and evaluates their results in detail, highlighting future directions both for classifier development and simulation needs for a next-generation PLAsTiCC data set.

79 ASTRONOMY AND ASTROPHYSICS↗

Training a Quantum Annealing Based Restricted Boltzmann Machine on Cybersecurity Data

A restricted Boltzmann machine (RBM) is a generative model that could be used in effectively balancing a cybersecurity dataset because the synthetic data a RBM generates follows the probability distribution of the training data. RBM training can be performed using contrastive divergence (CD) and quantum annealing (QA). QA-based RBM training is fundamentally different from CD and requires samples from a quantum computer. We present a real-world application that uses a quantum computer. Specifically, we train a RBM using QA for cybersecurity applications. The D-Wave 2000Q has been used to implement QA. RBMs are trained on the ISCX data, which is a benchmark dataset for cybersecurity. For comparison, RBMs are also trained using CD. CD is a commonly used method for RBM training. Our analysis of the ISCX data shows that the dataset is imbalanced. We present two different schemes to balance the training dataset before feeding it to a classifier. The first scheme is based on the undersampling of benign instances. The imbalanced training dataset is divided into five sub-datasets that are trained separately. A majority voting is then performed to get the result. Our results show the majority vote increases the classification accuracy up from 90.24% to 95.68%, in the case of CD. For the case of QA, the classification accuracy increases from 74.14% to 80.04%. In the second scheme, a RBM is used to generate synthetic data to balance the training dataset. We show that both QA and CD-trained RBM can be used to generate useful synthetic data. Balanced training data is used to evaluate several classifiers. Among the classifiers investigated, K-Nearest Neighbor (KNN) and Neural Network (NN) perform better than other classifiers. They both show an accuracy of 93%. Our results show a proof-of-concept that a QA-based RBM can be trained on a 64-bit binary dataset. The illustrative example suggests the possibility to migrate many practical classification problems to QA-based techniques. Further, we show that synthetic data generated from a RBM can be used to balance the original dataset.

97 MATHEMATICS AND COMPUTING↗

Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types

In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.

60 APPLIED LIFE SCIENCES↗

Decoding crystallography from high-resolution electron imaging and diffraction datasets with deep learning

While machine learning has been making enormous strides in many technical areas, it is still massively underused in transmission electron microscopy. To address this, a convolutional neural network model was developed for reliable classification of crystal structures from small numbers of electron images and diffraction patterns with no preferred orientation. Diffraction data containing 571,340 individual crystals divided among seven families, 32 genera, and 230 space groups were used to train the network. Despite the highly imbalanced dataset, the network narrows down the space groups to the top two with over 70% confidence in the worst case and up to 95% in the common cases. As examples, we benchmarked against alloys to two-dimensional materials to cross-validate our deep-learning model against high-resolution transmission electron images and diffraction patterns. We present this result both as a research tool and deep-learning application for diffraction analysis.

97 MATHEMATICS AND COMPUTING↗

Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension

Convolutional Neural Networks (CNN) have recently demonstrated effective performance in many Natural Language Processing tasks. In this study, we explore a novel approach for pruning a CNN's convolution filters using our new data-driven utility score. We have applied this technique to an information extraction task of classifying a dataset of cancer pathology reports by cancer type, a highly imbalanced dataset. Compared to standard CNN training, our new algorithm resulted in a nearly .07 increase in the micro-averaged F1-score and a strong .22 increase in the macro-averaged F1-score using a model with nearly a third fewer network weights. We show how directly utilizing a network's interpretation of data can result in strong performance gains, particularly with severely imbalanced datasets.

Yoon, Hong-Jun↗

Image-driven discriminative and generative machine learning algorithms for establishing microstructure–processing relationships

We investigate methods of microstructure representation for the purpose of predicting processing condition from microstructure image data. A binary alloy that is currently under development as a nuclear fuel was studied for the purpose of developing an improved machine learning approach to image recognition, characterization, and building predictive capabilities linking microstructure to processing conditions. Here, we test different microstructure representations and evaluate model performance based on classification accuracy. A classification accuracy of 95.8% was achieved fordistinguishing between micrographs corresponding to ten different thermo-mechanical material processing conditions.We find that our newly developed microstructure representation describes image data well, and the traditional approachof utilizing area fractions of different phases is insufficient for distinguishing between multiple classes using a relativelysmall, imbalanced original data set of 272 images. To explore the applicability of generative methods for supplementing such limited data sets, generative adversarial networks were trained to generate artificial microstructure images. Two different generative networks were trained and tested to assess performance. Challenges and best practices associated with applying machine learning to limited microstructure image data sets is also discussed. Our work has implications for quantitative microstructure analysis, and development of microstructure-processing relationships in limited data sets typical of metallurgical process design studies.

36 MATERIALS SCIENCE↗

Classification of animal sounds in a hyperdiverse rainforest using convolutional neural networks with data augmentation

To protect tropical forest biodiversity, we need to be able to detect it reliably, cheaply, and at scale. Automated detection of sound producing animals from passively recorded soundscapes via machine-learning approaches is a promising technique towards this goal, but it is constrained by the necessity of large training data sets. Using soundscapes from a tropical forest in Borneo and a Convolutional Neural Network model (CNN), we investigate i) the minimum viable training data set size for accurate prediction of call types (‘sonotypes’), and ii) the extent to which data augmentation and transfer learning can overcome the issue of small and imbalanced training data sets. We found that even relatively high sample sizes (>80 per sonotype) lead to mediocre accuracy, which however improved significantly with data augmentation and transfer learning, including at extremely small sample sizes (3 per sonotype), regardless of taxonomic group or call characteristics. Neither transfer learning nor data augmentation alone achieved high accuracy. Our results suggest that transfer learning and data augmentation could make the use of CNNs to classify species’ vocalizations feasible even for small soundscape-based projects with many rare species. Retraining our open-source model requires only basic programming skills which makes it possible for individual conservation initiatives to match their local context, in order to enable more evidence-informed management of biodiversity.

54 ENVIRONMENTAL SCIENCES↗

Combining Spike Time Dependent Plasticity (STDP) and Backpropagation (BP) for Robust and Data Efficient Spiking Neural Networks (SNN)

National security applications require artificial neural networks (ANNs) that consume less power, are fast and dynamic online learners, are fault tolerant, and can learn from unlabeled and imbalanced data. We explore whether two fundamentally different, traditional learning algorithms from artificial intelligence and the biological brain can be merged. We tackle this problem from two directions. First, we start from a theoretical point of view and show that the spike time dependent plasticity (STDP) learning curve observed in biological networks can be derived using the mathematical framework of backpropagation through time. Second, we show that transmission delays, as observed in biological networks, improve the ability of spiking networks to perform classification when trained using a backpropagation of error (BP) method. These results provide evidence that STDP could be compatible with a BP learning rule. Combining these learning algorithms will likely lead to networks more capable of meeting our national security missions.

97 MATHEMATICS AND COMPUTING↗

Sparse coding of pathology slides compared to transfer learning with deep neural networks

Background Histopathology images of tumor biopsies present unique challenges for applying machine learning to the diagnosis and treatment of cancer. The pathology slides are high resolution, often exceeding 1GB, have non-uniform dimensions, and often contain multiple tissue slices of varying sizes surrounded by large empty regions. The locations of abnormal or cancerous cells, which may constitute a small portion of any given tissue sample, are not annotated. Cancer image datasets are also extremely imbalanced, with most slides being associated with relatively common cancers. Since deep representations trained on natural photographs are unlikely to be optimal for classifying pathology slide images, which have different spectral ranges and spatial structure, we here describe an approach for learning features and inferring representations of cancer pathology slides based on sparse coding. Results We show that conventional transfer learning using a state-of-the-art deep learning architecture pre-trained on ImageNet (RESNET) and fine tuned for a binary tumor/no-tumor classification task achieved between 85% and 86% accuracy. However, when all layers up to the last convolutional layer in RESNET are replaced with a single feature map inferred via a sparse coding using a dictionary optimized for sparse reconstruction of unlabeled pathology slides, classification performance improves to over 93%, corresponding to a 54% error reduction. Conclusions We conclude that a feature dictionary optimized for biomedical imagery may in general support better classification performance than does conventional transfer learning using a dictionary pre-trained on natural images.

59 BASIC BIOLOGICAL SCIENCES↗

TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks

Background: With cancer as one of the leading causes of death worldwide, accurate primary tumor type prediction is critical in identifying genetic factors that can inhibit or slow tumor progression. There have been efforts to categorize primary tumor types with gene expression data using machine learning, and more recently with deep learning, in the last several years. Methods In this paper, we developed four 1-dimensional (1D) Convolutional Neural Network (CNN) models to classify RNA-seq count data as one of 17 highly represented primary tumor types or 32 primary tumor types regardless of imbalanced representation. Additionally, we adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). Unlike previous work, we avoided selection bias by not filtering genes based on expression values. RNA-seq count data expressed as FPKM-UQ of 9,025 and 10,940 samples from The Cancer Genome Atlas (TCGA) were downloaded from the Genomic Data Commons (GDC) corresponding to 17 and 32 primary tumor types respectively for training and validating the models. Results: All 4 1D-CNN models had an overall accuracy of 94.7% to 97.6% on the test dataset. Further evaluation indicates that the models with protein coding genes only as features performed with better accuracy compared to the models with all Ensembl genes for both 17 and 32 primary tumor types. For all models, the accuracy by primary tumor type was above 80% for most primary tumor types. Conclusions: We packaged all 4 models as a Python-based deep learning classification tool called TULIP (TUmor CLassIfication Predictor) for performing quality control on primary tumor samples and characterizing cancer samples of unknown tumor type. Further optimization of the models is needed to improve the accuracy of certain primary tumor types.

Jones, Sara↗

Light-Duty Vehicle Trip Classification Using One-Class Novelty Detection and Exhaustive Feature Extraction

Travel mode classification within travel survey data sets, especially light-duty vehicle (LDV) trips, is foundational, though nontrivial, to emerging mobility systems, travel behavior analysis, and fuel consumption estimation. Current travel mode detection approaches require well-sampled and balanced data sets with ground truth travel mode labels. The detection approaches are rarely applied and validated on large-scale, real-world data sets, which may not satisfy the dataset requirements. This work proposes an LDV trip detection model as a supplement to current travel mode detection methods, for the case when the training set is highly (and/or completely) unbalanced, to the extent that classical machine-learning approaches become difficult or impossible to deploy. The proposed model uses a novelty detection technique - one-class support vector machines (OCSVMs) - and a novel exhaustive feature extraction (EFE) technique on continuous time series data (i.e., Global Positioning System [GPS] speed profiles) for single-mode trip trajectories. Training and validation of the model are conducted on a large-scale, real-world data set. The proposed method accurately identifies LDV trips from a broad set of multimodal trips by leveraging a wealth of preexisting in-vehicle GPS travel data. Additional sensitivity analysis sheds light on the optimal training size and feature selection, which will benefit applications limited by highly imbalanced data. The paper also discusses performance comparison with regular machine-learning approaches, the model's robustness, and the potential to extend the proposed model to multi-modal trip prediction.

33 ADVANCED PROPULSION SYSTEMS↗

Harnessing Machine Learning and Data Fusion for Accurate Undocumented Well Identification in Satellite Images

This study utilizes satellite data to detect undocumented oil and gas wells, which pose significant environmental concerns, including greenhouse gas emissions. Three key findings emerge from the study. Firstly, the problem of imbalanced data is addressed by recommending oversampling techniques like Rotation–GaussianBlur–Solarization data augmentation (RGS), the Synthetic Minority Over-Sampling Technique (SMOTE), or ADASYN (an extension of SMOTE) over undersampling techniques. The performance of borderline SMOTE is less effective than that of the rest of the oversampling techniques, as its performance relies heavily on the quality and distribution of data near the decision boundary. Secondly, incorporating pre-trained models trained on large-scale datasets enhances the models’ generalization ability, with models trained on one county’s dataset demonstrating high overall accuracy, recall, and F1 scores that can be extended to other areas. This transferability of models allows for wider application. Lastly, including persistent homology (PH) as an additional input improves performance for in-distribution testing but may affect the model’s generalization for out-of-distribution testing. A careful consideration of PH’s impact on overall performance and generalizability is recommended. Overall, this study provides a robust approach to identifying undocumented oil and gas wells, contributing to the acceleration of a net-zero economy and supporting environmental sustainability efforts.

SMOTE↗