Machine learning‐based behaviour classification using acceleration data is a powerful tool in bio‐logging research. Deep learning architectures such as convolutional neural networks (CNN), long short‐term memory (LSTM) and self‐attention mechanisms as well as related training techniques have been extensively studied in human activity recognition. However, they have rarely been used in wild animal studies. The main challenges of acceleration‐based wild animal behaviour classification include data shortages, class imbalance problems, various types of noise in data due to differences in individual behaviour and where the loggers were attached and complexity in data due to complex animal‐specific behaviours, which may have limited the application of deep learning techniques in this area. To overcome these challenges, we explored the effectiveness of techniques for efficient model training: data augmentation, manifold mixup and pre‐training of deep learning models with unlabelled data, using datasets from two species of wild seabirds and state‐of‐the‐art deep learning model architectures. Data augmentation improved the overall model performance when one of the various techniques (none, scaling, jittering, permutation, time‐warping and rotation) was randomly applied to each data during mini‐batch training. Manifold mixup also improved model performance, but not as much as random data augmentation. Pre‐training with unlabelled data did not improve model performance. The state‐of‐the‐art deep learning models, including a model consisting of four CNN layers, an LSTM layer and a multi‐head attention layer, as well as its modified version with shortcut connection, showed better performance among other comparative models. Using only raw acceleration data as inputs, these models outperformed classic machine learning approaches that used 119 handcrafted features. Our experiments showed that deep learning techniques are promising for acceleration‐based behaviour classification of wild animals and highlighted some challenges (e.g. effective use of unlabelled data). There is scope for greater exploration of deep learning techniques in wild animal studies (e.g. advanced data augmentation, multimodal sensor data use, transfer learning and self‐supervised learning). We hope that this study will stimulate the development of deep learning techniques for wild animal behaviour classification using time‐series sensor data.

This abstract is cited from the original article "Exploring deep learning techniques for wild animal behaviour classification using animal-borne accelerometers" in Methods in Ecology and Evolution (Otsuka et al., 2024).Please see README for the details of the datasets.

If you use this dataset, please cite this paper: Puertas, E.; De-Las-Heras, G.; Sánchez-Soriano, J.; Fernández-Andrés, J. Dataset: Variable Message Signal Annotated Images for Object Detection. Data 2022, 7, 41. https://doi.org/10.3390/data7040041

This dataset consists of Spanish road images taken from inside a vehicle, as well as annotations in XML files in PASCAL VOC format that indicate the location of Variable Message Signals within them. Also, a CSV file is attached with information regarding the geographic position, the folder where the image is located, and the text in Spanish. This can be used to train supervised learning computer vision algorithms, such as convolutional neural networks. Throughout this work, the process followed to obtain the dataset, image acquisition, and labeling, and its specifications are detailed. The dataset is constituted of 1216 instances, 888 positives, and 328 negatives, in 1152 jpg images with a resolution of 1280x720 pixels. These are divided into 576 real images and 576 images created from the data-augmentation technique. The purpose of this dataset is to help in road computer vision research since there is not one specifically for VMSs.

The folder structure of the dataset is as follows:

• vms_dataset/
  • data.csv
  • real_images/
    • imgs/
    • annotations/
  • data-augmentation/
    • imgs/
    • annotations/

In which:

• data.csv: Each row contains the following information separated by commas (,): image_name, x_min, y_min, x_max, y_max, class_name, lat, long, folder, text.
• real_images: Images extracted directly from the videos.
• data-augmentation: Images created using data-augmentation
• imgs: Image files in .jpg format.
• annotations: Annotation files in .xml format.

The goal of this work is to generate large statistically representative datasets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student-t process regression. We apply Student-t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via coloring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics, and classic machine learning clustering algorithms.

Comparative results for pattern mixing-based data augmentation methods.

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for vision.

Comparative results for time domain transformation-based data augmentation methods.

Comparative results for magnitude domain transformation-based data augmentation methods.

Paired-Embedding (PE) method for effective and reliable data augmentation, Act2Act network learns from augmented data

Medical image analysis is critical to biological studies, health research, computer- aided diagnoses, and clinical applications. Recently, deep learning (DL) techniques have achieved remarkable successes in medical image analysis applications. However, these techniques typically require large amounts of annotations to achieve satisfactory performance. Therefore, in this dissertation, we seek to address this critical problem: How can we develop efficient and effective DL algorithms for medical image analysis while reducing annotation efforts? To address this problem, we have outlined two specific aims: (A1) Utilize existing annotations effectively from advanced models; (A2) extract generic knowledge directly from unannotated images.

To achieve the aim (A1): First, we introduce a new data representation called TopoImages, which encodes the local topology of all the image pixels. TopoImages can be complemented with the original images to improve medical image analysis tasks. Second, we propose a new augmentation method, SAMAug-C, that lever- ages the Segment Anything Model (SAM) to augment raw image input and enhance medical image classification. Third, we propose two advanced DL architectures, kCBAC-Net and ConvFormer, to enhance the performance of 2D and 3D medical image segmentation. We also present a gate-regularized network training (GrNT) approach to improve multi-scale fusion in medical image segmentation. To achieve the aim (A2), we propose a novel extension of known Masked Autoencoders (MAEs) for self pre-training, i.e., models pre-trained on the same target dataset, specifically for 3D medical image segmentation.

Scientific visualization is a powerful approach for understanding and analyzing various physical or natural phenomena, such as climate change or chemical reactions. However, the cost of scientific simulations is high when factors like time, ensemble, and multivariate analyses are involved. Additionally, scientists can only afford to sparsely store the simulation outputs (e.g., scalar field data) or visual representations (e.g., streamlines) or visualization images due to limited I/O bandwidths and storage space. Therefore, in this dissertation, we seek to address this critical problem: How can we develop efficient and effective DL algorithms for scientific data generation and compression while reducing simulation and storage costs?

To tackle this problem: First, we propose a DL framework that generates un- steady vector fields data from a set of streamlines. Based on this method, domain scientists only need to store representative streamlines at simulation time and recon- struct vector fields during post-processing. Second, we design a novel DL method that translates scalar fields to vector fields. Using this approach, domain scientists only need to store scalar field data at simulation time and generate vector fields from their scalar field counterparts afterward. Third, we present a new DL approach that compresses a large collection of visualization images generated from time-varying data for communicating volume visualization results.

Data Augmentation Tools Market Outlook

According to our latest research, the global Data Augmentation Tools market size reached USD 1.62 billion in 2024, with a robust year-on-year growth trajectory. The market is poised for accelerated expansion, projected to achieve a CAGR of 26.4% from 2025 to 2033. By the end of 2033, the market is forecasted to reach approximately USD 12.34 billion. This dynamic growth is primarily driven by the rising demand for artificial intelligence (AI) and machine learning (ML) applications across diverse industry verticals, which necessitate vast quantities of high-quality training data. The proliferation of data-centric AI models and the increasing complexity of real-world datasets are compelling enterprises to invest in advanced data augmentation tools to enhance data diversity and model robustness, as per the latest research insights.

One of the principal growth factors fueling the Data Augmentation Tools market is the intensifying adoption of AI-driven solutions across industries such as healthcare, automotive, retail, and finance. Organizations are increasingly leveraging data augmentation to overcome the challenges posed by limited or imbalanced datasets, which are often a bottleneck in developing accurate and reliable AI models. By synthetically expanding training datasets through augmentation techniques, enterprises can significantly improve the generalization capabilities of their models, leading to enhanced performance and reduced risk of overfitting. Furthermore, the surge in computer vision, natural language processing, and speech recognition applications is creating a fertile environment for the adoption of specialized augmentation tools tailored to image, text, and audio data.

Another significant factor contributing to market growth is the rapid evolution of augmentation technologies themselves. Innovations such as Generative Adversarial Networks (GANs), automated data labeling, and domain-specific augmentation pipelines are making it easier for organizations to deploy and scale data augmentation strategies. These advancements are not only reducing the manual effort and expertise required but also enabling the generation of highly realistic synthetic data that closely mimics real-world scenarios. As a result, businesses across sectors are able to accelerate their AI/ML development cycles, reduce costs associated with data collection and labeling, and maintain compliance with stringent data privacy regulations by minimizing the need to use sensitive real-world data.

The growing integration of data augmentation tools within cloud-based AI development platforms is also acting as a major catalyst for market expansion. Cloud deployment offers unparalleled scalability, accessibility, and collaboration capabilities, allowing organizations of all sizes to harness the power of data augmentation without significant upfront infrastructure investments. This democratization of advanced data engineering tools is especially beneficial for small and medium enterprises (SMEs) and academic research institutes, which often face resource constraints. The proliferation of cloud-native augmentation solutions is further supported by strategic partnerships between technology vendors and cloud service providers, driving broader market penetration and innovation.

From a regional perspective, North America continues to dominate the Data Augmentation Tools market, driven by the presence of leading AI technology companies, a mature digital infrastructure, and substantial investments in research and development. However, the Asia Pacific region is emerging as the fastest-growing market, fueled by rapid digital transformation initiatives, a burgeoning startup ecosystem, and increasing government support for AI innovation. Europe also holds a significant share, underpinned by strong regulatory frameworks and a focus on ethical AI development. Meanwhile, Latin America and the Middle East & Africa are witnessing steady adoption, particularly in sectors such as BFSI and healthcare, where data-driven insights are becoming increasingly critical.

Component Analysis

The Data Augmentation Tools market by component is bifurcated into Software and Services. The software segment currently accounts for the largest share of the market, owing to the widespread deployment of standalone and integrated augmentation solutions across enterprises and research institutions. These software plat

This repository contains the data and associated results of all experiments conducted in our work "Phenotype Driven Data Augmentation Methods for Transcriptomic Data". In this work, we introduce two classes of phenotype driven data augmentation approaches – signature-dependent and signature-independent. The signature-dependent methods assume the existence of distinct gene signatures describing some phenotype and are simple, non-parametric, and novel data augmentation methods. The signature-independent methods are a modification of the established Gamma-Poisson and Poisson sampling methods for gene expression data. We benchmark our proposed methods against random oversampling, SMOTE, unmodified versions of Gamma-Poisson and Poisson sampling, and unaugmented data.

This repository contains data used for all our experiments. This includes the original data based off which augmentation was performed, the cross validation split indices as a json file, the training and validation data augmented by the various augmentation methods mentioned in our study, a test set (containing only real samples) and an external test set standardised accordingly with respect to each augmentation method and training data per CV split.

The compressed files 5x5stratified_{x}percent.zip contains data that were augmented on x% of the available real data. brca_public.zip contains data used for the breast cancer experiments. distribution_size_effect.zip contains data used for hyperparameter tuning the reference set size for the modified Poisson and Gamma-Poisson methods.

The compressed file results.zip contains all the results from all the experiments. This includes the parameter files used to train the various models, the metrics (balanced accuracy and auc-roc) computed including p-values, as well as the latent space of train, validation and test (for the (N)VAE) for all 25 (5x5) CV splits.

PLEASE NOTE: If any part of this repository is used in any form for your work, please attribute the following, in addition to attributing the original data source - TCGA, CPTAC, GSE20713 and METABRIC, accordingly:

@article{janakarajan2023signature, title={Phenotype Driven Data Augmentation Methods for Transcriptomic Data}, author={Janakarajan, Nikita and Graziani, Mara and Martinez, Maria Rodriguez}, journal={bioRxiv}, pages={2023--10}, year={2023}, publisher={Cold Spring Harbor Laboratory} }

🩺 Dataset Description

This dataset is an augmented version of an ECG image dataset created to balance and enrich the original classes for deep learning–based cardiovascular disease classification.

The original dataset consisted of unbalanced image counts per class in the training set: - ABH: 233 images - MI: 239 images - HMI: 172 images - NORM: 284 images

To improve class balance and model generalization, each class in the training set was expanded to 500 images using a combination of morphological, noise-based, and geometric data augmentation techniques. Additionally, the test set includes 112 images per class.

⚖️ Final Dataset Composition

• Training set: 4 classes × 500 images each → 2,000 images total
• Test set: 4 classes × 112 images each → 448 images total

🔬 Data Augmentation Techniques

1. Morphological Alterations - Erosion - Dilation - None (original preserved)

2. Noise Introduction - augment_noise_black_rain — simulates black streaks - augment_noise_pixel_dropout_black — random black pixel dropout - augment_noise_white_rain — simulates white streaks - augment_noise_pixel_dropout_white — random white pixel dropout

3. Geometric Transformations - Shift — small translations in all directions - Scale — random zoom-in/zoom-out between 0.9× and 1.1× - Rotate — small random rotation between -5° and +5°

These transformations were applied with balanced proportions to ensure diversity and realism while preserving diagnostic features of ECG signals.

💡 Intended Use

This dataset is designed for: - Training and evaluating deep learning models (CNNs, ViTs) for ECG image classification - Research in medical image augmentation, imbalanced data learning, and cardiovascular disease prediction

📘 License

This dataset is released under the CC0 1.0 License, allowing free use and distribution for research and educational purposes.

Data augmentation recommendations for data type and model type.

This dataset contains synthetic video samples generated from a 10-class subset of Tiny ImageNet using Stable Video Diffusion (SVD). It is designed to evaluate the impact of generative temporal augmentation on image classification performance.

Each training and validation video corresponds to a single image augmented into a sequence of frames.

Videos are stored in .mp4 format and labeled via train.csv and val.csv.

Sources:

Tiny ImageNet: Stanford CS231n

SVD model: Stable Video Diffusion

License: Creative Commons Attribution 4.0 International (CC BY 4.0)

Driving scenes are extremely diverse and complicated that it is impossible to collect all cases with human effort alone. While data augmentation is an effective technique to enrich the training data, existing methods for camera data in autonomous driving applications are confined to the 2D image plane, which may not optimally increase data diver-sity in 3D real-world scenarios.

This is a companion dataset for the paper titled "Class-specific data augmentation for plant stress classification" by Nasla Saleem, Aditya Balu, Talukder Zaki Jubery, Arti Singh, Asheesh K. Singh, Soumik Sarkar, and Baskar Ganapathysubramanian published in The Plant Phenome Journal, https://doi.org/10.1002/ppj2.20112


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.

Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency.

This repository contains the Wallhack1.8k dataset for WiFi-based long-range activity recognition in Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS)/Through-Wall scenarios, as proposed in [1,2], as well as the CAD models (of 3D-printable parts) of the WiFi systems proposed in [2].

PyTroch Dataloader

A minimal PyTorch dataloader for the Wallhack1.8k dataset is provided at: https://github.com/StrohmayerJ/wallhack1.8k

Dataset Description

The Wallhack1.8k dataset comprises 1,806 CSI amplitude spectrograms (and raw WiFi packet time series) corresponding to three activity classes: "no presence," "walking," and "walking + arm-waving." WiFi packets were transmitted at a frequency of 100 Hz, and each spectrogram captures a temporal context of approximately 4 seconds (400 WiFi packets).

To assess cross-scenario and cross-system generalization, WiFi packet sequences were collected in LoS and through-wall (NLoS) scenarios, utilizing two different WiFi systems (BQ: biquad antenna and PIFA: printed inverted-F antenna). The dataset is structured accordingly:

LOS/BQ/ <- WiFi packets collected in the LoS scenario using the BQ system

LOS/PIFA/ <- WiFi packets collected in the LoS scenario using the PIFA system

NLOS/BQ/ <- WiFi packets collected in the NLoS scenario using the BQ system

NLOS/PIFA/ <- WiFi packets collected in the NLoS scenario using the PIFA system

These directories contain the raw WiFi packet time series (see Table 1). Each row represents a single WiFi packet with the complex CSI vector H being stored in the "data" field and the class label being stored in the "class" field. H is of the form [I, R, I, R, ..., I, R], where two consecutive entries represent imaginary and real parts of complex numbers (the Channel Frequency Responses of subcarriers). Taking the absolute value of H (e.g., via numpy.abs(H)) yields the subcarrier amplitudes A.

To extract the 52 L-LTF subcarriers used in [1], the following indices of A are to be selected:

52 L-LTF subcarriers

csi_valid_subcarrier_index = [] csi_valid_subcarrier_index += [i for i in range(6, 32)] csi_valid_subcarrier_index += [i for i in range(33, 59)]

Additional 56 HT-LTF subcarriers can be selected via:

56 HT-LTF subcarriers

csi_valid_subcarrier_index += [i for i in range(66, 94)]
csi_valid_subcarrier_index += [i for i in range(95, 123)]

For more details on subcarrier selection, see ESP-IDF (Section Wi-Fi Channel State Information) and esp-csi.

Extracted amplitude spectrograms with the corresponding label files of the train/validation/test split: "trainLabels.csv," "validationLabels.csv," and "testLabels.csv," can be found in the spectrograms/ directory.

The columns in the label files correspond to the following: [Spectrogram index, Class label, Room label]

Spectrogram index: [0, ..., n]

Class label: [0,1,2], where 0 = "no presence", 1 = "walking", and 2 = "walking + arm-waving."

Room label: [0,1,2,3,4,5], where labels 1-5 correspond to the room number in the NLoS scenario (see Fig. 3 in [1]). The label 0 corresponds to no room and is used for the "no presence" class.

Dataset Overview:

Table 1: Raw WiFi packet sequences.

Scenario System "no presence" / label 0 "walking" / label 1 "walking + arm-waving" / label 2 Total

LoS BQ b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

LoS PIFA b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

NLoS BQ b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

NLoS PIFA b1.csv w1.csv, w2.csv, w3.csv, w4.csv and w5.csv ww1.csv, ww2.csv, ww3.csv, ww4.csv and ww5.csv

4 20 20 44

Table 2: Sample/Spectrogram distribution across activity classes in Wallhack1.8k.

Scenario System

"no presence" / label 0

"walking" / label 1

"walking + arm-waving" / label 2 Total

LoS BQ 149 154 155

LoS PIFA 149 160 152

NLoS BQ 148 150 152

NLoS PIFA 143 147 147

589 611 606 1,806

Download and UseThis data may be used for non-commercial research purposes only. If you publish material based on this data, we request that you include a reference to one of our papers [1,2].

[1] Strohmayer, Julian, and Martin Kampel. (2024). “Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition”, In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 42-56). Cham: Springer Nature Switzerland, doi: https://doi.org/10.1007/978-3-031-63211-2_4.

[2] Strohmayer, Julian, and Martin Kampel., “Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition,” 2024 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2024, pp. 3594-3599, doi: https://doi.org/10.1109/ICIP51287.2024.10647666.

BibTeX citations:

@inproceedings{strohmayer2024data, title={Data Augmentation Techniques for Cross-Domain WiFi CSI-Based Human Activity Recognition}, author={Strohmayer, Julian and Kampel, Martin}, booktitle={IFIP International Conference on Artificial Intelligence Applications and Innovations}, pages={42--56}, year={2024}, organization={Springer}}@INPROCEEDINGS{10647666, author={Strohmayer, Julian and Kampel, Martin}, booktitle={2024 IEEE International Conference on Image Processing (ICIP)}, title={Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition}, year={2024}, volume={}, number={}, pages={3594-3599}, keywords={Visualization;Accuracy;System performance;Directional antennas;Directive antennas;Reflector antennas;Sensors;Human Activity Recognition;WiFi;Channel State Information;Through-Wall Sensing;ESP32}, doi={10.1109/ICIP51287.2024.10647666}}

K. Scott Mader created the original dataset of 204 hand-drawn images for Parkinson’s disease diagnosis, consisting of two classes: Healthy and Parkinson. The dataset includes spiral and wave drawings. For my thesis, the original 204 images were expanded to 3,264 across the same two classes. This increase was achieved through data augmentation techniques, including rotations of 90°, 180°, and 270°, vertical flipping at 180°, and conversion to color images. The augmented data gives the model more opportunities to generalize, enhancing training and testing processes.

Cognata’s highway driving dataset provides a valuable resource for validating perception models in ADAS and autonomous vehicle (AV) systems. The first version of the dataset includes the original video recorded under clear and sunny conditions, along with augmented versions that simulate challenging scenarios such as fog, rain, and erased lane markings. This allows for comprehensive testing of models across various environmental conditions without the need for additional real-world data collection.

The second version introduces updates to the dataset, including a new augmentation for low sun and a version with class segmentation. This expands the dataset’s utility by enabling even more diverse and precise testing scenarios. Additionally, the dataset license has been updated, ensuring developers have access to the most current terms for usage.

By leveraging this dataset, developers can assess how well their object detection and segmentation models perform under varied conditions, identifying strengths and weaknesses in the models’ ability to handle real-world challenges. The augmentation, powered by DriveMatriX, maintains consistency between the original and augmented videos, enabling seamless transitions between conditions for validation purposes. This ensures perception models can be effectively evaluated in terms of precision, recall, and coverage, providing detailed insights into how well they generalize across different scenarios.

This dataset is particularly suited for validating the robustness of perception algorithms, offering a controlled environment to test how models react to adverse weather conditions. By utilizing this resource, developers can focus on improving model performance based on real-world conditions that typically require extensive and costly data collection efforts.

Please see a blog post on how website on how to use the DriveMatriX Highway Dataset: https://www.cognata.com/enhancing-object-detection-performance-with-data-augmentation-dataset/