An official website of the United States government
Abstract The biodiversity crisis necessitates spatially extensive methods to monitor multiple taxonomic groups for evidence of change in response to evolving environmental conditions. Programs that combine passive acoustic monitoring and machine learning are increasingly used to meet this need. These methods require large, annotated datasets, which are time‐consuming and expensive to produce, creating potential barriers to adoption in data‐ and funding‐poor regions. Recently released pre‐trained avian acoustic classification models provide opportunities to reduce the need for manual labelling and accelerate the development of new acoustic classification algorithms through transfer learning. Transfer learning is a strategy for developing algorithms under data scarcity that uses pre‐trained models from related tasks to adapt to new tasks.Our primary objective was to develop a transfer learning strategy using the feature embeddings of a pre‐trained avian classification model to train custom acoustic classification models in data‐scarce contexts. We used three annotated avian acoustic datasets to test whether transfer learning and soundscape simulation‐based data augmentation could substantially reduce the annotated training data necessary to develop performant custom acoustic classifiers. We also conducted a sensitivity analysis for hyperparameter choice and model architecture. We then assessed the generalizability of our strategy to increasingly novel non‐avian classification tasks.With as few as two training examples per class, our soundscape simulation data augmentation approach consistently yielded new classifiers with improved performance relative to the pre‐trained classification model and transfer learning classifiers trained with other augmentation approaches. Performance increases were evident for three avian test datasets, including single‐class and multi‐label contexts. We observed that the relative performance among our data augmentation approaches varied for the avian datasets and nearly converged for one dataset when we included more training examples.We demonstrate an efficient approach to developing new acoustic classifiers leveraging open‐source sound repositories and pre‐trained networks to reduce manual labelling. With very few examples, our soundscape simulation approach to data augmentation yielded classifiers with performance equivalent to those trained with many more examples, showing it is possible to reduce manual labelling while still achieving high‐performance classifiers and, in turn, expanding the potential for passive acoustic monitoring to address rising biodiversity monitoring needs.
more »
« less
Class‐specific data augmentation for plant stress classification
Abstract Data augmentation is a powerful tool for improving deep learning‐based image classifiers for plant stress identification and classification. However, selecting an effective set of augmentations from a large pool of candidates remains a key challenge, particularly in imbalanced and confounding datasets. We propose an approach for automated class‐specific data augmentation using a genetic algorithm. We demonstrate the utility of our approach on soybean [Glycine max (L.) Merr] stress classification where symptoms are observed on leaves; a particularly challenging problem due to confounding classes in the dataset. Our approach yields substantial performance, achieving a mean‐per‐class accuracy of 97.61% and an overall accuracy of 98% on the soybean leaf stress dataset. Our method significantly improves the accuracy of the most challenging classes, with notable enhancements from 83.01% to 88.89% and from 85.71% to 94.05%, respectively. A key observation we make in this study is that high‐performing augmentation strategies can be identified in a computationally efficient manner. We fine‐tune only the linear layer of the baseline model with different augmentations, thereby reducing the computational burden associated with training classifiers from scratch for each augmentation policy while achieving exceptional performance. This research represents an advancement in automated data augmentation strategies for plant stress classification, particularly in the context of confounding datasets. Our findings contribute to the growing body of research in tailored augmentation techniques and their potential impact on disease management strategies, crop yields, and global food security. The proposed approach holds the potential to enhance the accuracy and efficiency of deep learning‐based tools for managing plant stresses in agriculture.
more »
« less
- Award ID(s):
- 1954556
- PAR ID:
- 10579886
- Publisher / Repository:
- The Plant Phenome Journal
- Date Published:
- Journal Name:
- The Plant Phenome Journal
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2578-2703
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This research presents a hybrid intrusion detection approach that integrates Generative Adversarial Networks (GANs) for synthetic data generation with Random Forest (RF) as the primary classifier. The study aims to improve detection performance in cybersecurity applications by enhancing dataset diversity and addressing challenges in traditional models, particularly in detecting minority attack classes often underrepresented in real-world datasets. The proposed method employs GANs to generate synthetic attack samples that mimic real-world intrusions, which are then combined with real data from the UNSW-NB15 dataset to create a more balanced training set. By leveraging synthetic data augmentation, our approach mitigates issues related to class imbalance and enhances the generalization capability of the classifier. Extensive experiments demonstrate that RF trained on the combined dataset of real and synthetic data achieves superior detection performance compared to models trained exclusively on real data. Specifically, RF trained solely on the original dataset achieves an accuracy of 97.58%, whereas integrating GAN-generated synthetic data improves accuracy to 98.27%. The proposed methodology is further evaluated through comparative analysis against alternative classifiers, including Support Vector Machine (SVM), XGBoost, Gated Recurrent Unit (GRU), and related studies in the field. Our findings indicate that GAN-augmented training significantly enhances detection rates, particularly for rare attack types, while maintaining computational efficiency. Furthermore, RF outperforms other classifiers, including deep learning models, demonstrating its effectiveness as a lightweight yet robust classification method. Integrating GANs with RF offers a scalable and adaptable framework for intrusion detection, ensuring improved resilience against evolving cyber threats.more » « less
-
Automated canopy stress classification for field crops has traditionally relied on single-perspective, two-dimensional (2D) photographs, usually obtained through top-view imaging using unmanned aerial vehicles (UAVs). However, this approach may fail to capture the full extent of plant stress symptoms, which can manifest throughout the canopy. Recent advancements in LiDAR technologies have enabled the acquisition of high-resolution 3D point cloud data for the entire canopy, offering new possibilities for more accurate plant stress identification and rating. This study explores the potential of leveraging 3D point cloud data for improved plant stress assessment. We utilized a dataset of RGB 3D point clouds of 700 soybean plants from a diversity panel exposed to iron deficiency chlorosis (IDC) stress. From this unique set of 700 canopies exhibiting varying levels of IDC, we extracted several representations, including (a) handcrafted IDC symptom-specific features, (b) canopy fingerprints, and (c) latent feature-based features. Subsequently, we trained several classification models to predict plant stress severity using these representations. We exhaustively investigated several stress representations and model combinations for the 3-D data. We also compared the performance of these classification models against similar models that are only trained using the associated top-view 2D RGB image for each plant. Among the feature-model combinations tested, the 3D canopy fingerprint features trained with a support vector machine yielded the best performance, achieving higher classification accuracy than the best-performing model based on 2D data built using convolutional neural networks. Our findings demonstrate the utility of color canopy fingerprinting and underscore the importance of considering 3D data to assess plant stress in agricultural applications.more » « less
-
Abstract Metagenomic read classification is a fundamental task in computational biology, yet it remains challenging due to the scale, diversity, and complexity of sequencing datasets. We propose a novel, run-length compressed index based on the move structure that enables efficient multi-class metagenomic classification inO(r) space, whereris the number of character runs in the BWT of the reference text. Our method identifies all super-maximal exact matches (SMEMs) of length at leastLbetween a read and the reference dataset and associates each SMEM with one class identifier using a sampled tag array. A consensus algorithm then compacts these SMEMs with their class identifier into a single classification per read. We are the first to perform run-length compressed read classification based on full SMEMs instead of semi-SMEMs. We evaluate our approach on both long and short reads in two conceptually distinct datasets: a large bacterial pan-genome with few metagenomic classes and a smaller 16S rRNA gene database spanning thousands of genera or classes. Our method consistently outperforms SPUMONI 2 in accuracy and runtime while maintaining the same asymptotic memory complexity ofO(r). Compared to Cliffy, we demonstrate better memory efficiency while achieving superior accuracy on the simpler dataset and comparable performance on the more complex one. Overall, our implementation carefully balances accuracy, runtime, and memory usage, offering a versatile solution for metagenomic classification across diverse datasets. The open-source C++11 implementation is available athttps://github.com/biointec/taggerunder the AGPL-3.0 license.more » « less
-
Data augmentation is a common practice to help generalization in the procedure of deep model training. In the context of physiological time series classification, previous research has primarily focused on label-invariant data augmentation methods. However, another class of augmentation techniques (i.e., Mixup) that emerged in the computer vision field has yet to be fully explored in the time series domain. In this study, we systematically review the mix-based augmentations, including mixup, cutmix, and manifold mixup, on six physio- logical datasets, evaluating their performance across different sensory data and classification tasks. Our results demonstrate that the three mix-based augmentations can consistently improve the performance on the six datasets. More importantly, the improvement does not rely on expert knowledge or extensive parameter tuning. Lastly, we provide an overview of the unique properties of the mix-based augmentation methods and highlight the potential benefits of using the mix-based augmentation in physiological time series data. Our code and results are available at https://github.com/comp-well-org/ Mix-Augmentation-for-Physiological-Time-Series-Classification.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1002/ppj2.20112
