Thierry Jean (20691795), Rose Guay Hottin (20691798), Pierre Orban (62056) · Figshare · 2025
Each row is associated with a mental state and each outer column with a forecast horizon. For each of the 30 conditions, heatmaps show XGBoost and LSTM test predictions. The cell indicates the number of predictions with x-axis being the true class and the y-axis the predicted class. The color scale is normalized per column, indicating the per-class recall value on the diagonal. This figure adds context to the <a href="/article/info:doi/10.1371/journal.pdig.0000734#pdig.0000734.g004" target="_blank">Fig 4</a> and provides raw values to allow any metrics to be computed. (TIF)
Cited by 0Open access
Lei Jia (303610), Ramya Yarlagadda (794457), Charles C. Reed (794458) · Figshare · 2015
Cited by 0Open access
Kitchin, John, Tilton, Robert, Chilkunda, Chetan · Figshare · 2025
This data supports a manuscript titled "A Classification-based Methodology for the Estimation of Binary Surfactant Critical Micelle Concentrations" submitted to Digital Discovery. It contains data files and a Jupyter notebook that illustrates how to use the data to perform the analysis in the paper.
Cited by 0Open access
Fabien Raphel (9421987), Tessa De Korte (9421990), Damiano Lombardi (4352779) et al. · Figshare · 2020
<p>Plain (resp. dotted) lines correspond to the average confidence of the LDA classifier for well classified (resp. misclassified) compound (well classification is according to <a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1008203#pcbi.1008203.t001" target="_blank">Table 1</a>). The black values on the lines correspond to the proportion of well classified observations for each compound.</p>
Cited by 0Open access
A. J. Larner · 2024
Cited by 0
Dr. Amrinder Kaur · Zenodo (CERN European Organization for Nuclear Research) · 2026
No description provided.
Cited by 0Open access
Thierry Jean (20691795), Rose Guay Hottin (20691798), Pierre Orban (62056) · Figshare · 2025
Each row is associated with a mental state and each outer column with a forecast horizon. For each of the 30 conditions, bar plots show XGBoost and LSTM test predictions. The bar height corresponds to the number of examples with each bar indicating the true class and colors reflecting the predicted classes. The BAcc for these XGBoost and LSTM model predictions are shown against the BAcc significance threshold (Bonferroni corrected <i>P</i> < .05) and the corresponding Monte Carlo baseline distribution. n.s., non-significant.
Cited by 0Open access
P Isiri, Deshpande Nikhil, Sampada K S · SSRN Electronic Journal · 2025
Cited by 0Open access
Mohammed Tawfik (19287598) · Figshare · 2024
<div><p>The proliferation of Internet of Things (IoT) devices and fog computing architectures has introduced major security and cyber threats. Intrusion detection systems have become effective in monitoring network traffic and activities to identify anomalies that are indicative of attacks. However, constraints such as limited computing resources at fog nodes render conventional intrusion detection techniques impractical. This paper proposes a novel framework that integrates stacked autoencoders, CatBoost, and an optimised transformer-CNN-LSTM ensemble tailored for intrusion detection in fog and IoT networks. Autoencoders extract robust features from high-dimensional traffic data while reducing the dimensionality of the efficiency at fog nodes. CatBoost refines features through predictive selection. The ensemble model combines self-attention, convolutions, and recurrence for comprehensive traffic analysis in the cloud. Evaluations of the NSL-KDD, UNSW-NB15, and AWID benchmarks demonstrate an accuracy of over 99% in detecting threats across traditional, hybrid enterprises and wireless environments. Integrated edge preprocessing and cloud-based ensemble learning pipelines enable efficient and accurate anomaly detection. The results highlight the viability of securing real-world fog and the IoT infrastructure against continuously evolving cyber-attacks.</p></div>
Cited by 0Open access
Xiaoou Tang, Feng Lin, Scott Samson et al. · IEEE Journal of Oceanic Engineering · 2006
In marine biology study, it is important to investigate the distribution of plankton organisms. Because of the overwhelming data size, automatic processing of the large amount of image data collected by underwater image recorders becomes inevitable. However, due to the fragmentation and the large within-class variations of binary plankton images, it is difficult to extract reliable shape features. In this paper, we propose several new shape descriptors and use a normalized multilevel dominant eigenvector estimation method to select a best feature set for binary plankton image classification. We achieve more than 91% classification accuracy in experiments on more than 3000 images
Cited by 39
Mohammed Tawfik (19287598) · Figshare · 2024
<div><p>The proliferation of Internet of Things (IoT) devices and fog computing architectures has introduced major security and cyber threats. Intrusion detection systems have become effective in monitoring network traffic and activities to identify anomalies that are indicative of attacks. However, constraints such as limited computing resources at fog nodes render conventional intrusion detection techniques impractical. This paper proposes a novel framework that integrates stacked autoencoders, CatBoost, and an optimised transformer-CNN-LSTM ensemble tailored for intrusion detection in fog and IoT networks. Autoencoders extract robust features from high-dimensional traffic data while reducing the dimensionality of the efficiency at fog nodes. CatBoost refines features through predictive selection. The ensemble model combines self-attention, convolutions, and recurrence for comprehensive traffic analysis in the cloud. Evaluations of the NSL-KDD, UNSW-NB15, and AWID benchmarks demonstrate an accuracy of over 99% in detecting threats across traditional, hybrid enterprises and wireless environments. Integrated edge preprocessing and cloud-based ensemble learning pipelines enable efficient and accurate anomaly detection. The results highlight the viability of securing real-world fog and the IoT infrastructure against continuously evolving cyber-attacks.</p></div>
Cited by 0Open access
Towers, David, Ericsson, Linus, McGough, Andrew Stephen et al. · Newcastle University · 2024
The Myofibre dataset is a constructed dataset derived from the NCL_SM dataset (doi.org/10.25405/data.ncl.24125391), which contains high-quality images of human tissue. This dataset is one of the three hidden datasets used by the 2024 NAS Unseen-Data Challenge. The images include around 50,000 manually segmented muscle fibres (myofibres). These myofibres have been split into four categories: Analysable Myofibre, Non-Transverse Myofibre, Freezing Artefact Myofibre, and Folded Region. We took each of the cells that the original authors manually labelled, rescaled them to a uniform (3, 128, 128) data shape, and used these images to create a binary-classification task. We converted the task into a binary classification task due to the imbalance between the four original labels, there are 30,794 AM Myofibres, but only 18,102 NTMs, 1,538 FAMs, and 405 FRs. While there is still an imbalance, the balance is not as drastic and since this was created from real-world data, we hope that it is representative of that fact. The data is in a channels-first format with a shape of (n, 3, 128, 128) where n is the number of samples in the corresponding set (39,497 for training, 4,937 for validation, and 4,937 for testing). As this is a binary classification task, there are two classes in the dataset, with aproximately 30,000 AM images and 20,000 NAM images, randomly distributed between each of the three sets. The two classes and corresponding numerical label are as follows:<br> Analysable Myofibre (AM): 0,<br> Not Analysable Myofibre (NAM): 1 NumPy (.npy) files can be opened through the NumPy Python library, using the `numpy.load()` function by inputting the path to the file into the function as a parameter. The metadata file contains some basic information about the datasets, and can be opened in many text editors such as vim, nano, notepad++, notepad, etc <br>
Cited by 0Open access
Towers, David, Ericsson, Linus, McGough, Andrew Stephen et al. · Figshare · 2024
The Myofibre dataset is a constructed dataset derived from the NCL_SM dataset (doi.org/10.25405/data.ncl.24125391), which contains high-quality images of human tissue. This dataset is one of the three hidden datasets used by the 2024 NAS Unseen-Data Challenge. The images include around 50,000 manually segmented muscle fibres (myofibres). These myofibres have been split into four categories: Analysable Myofibre, Non-Transverse Myofibre, Freezing Artefact Myofibre, and Folded Region. We took each of the cells that the original authors manually labelled, rescaled them to a uniform (3, 128, 128) data shape, and used these images to create a binary-classification task. We converted the task into a binary classification task due to the imbalance between the four original labels, there are 30,794 AM Myofibres, but only 18,102 NTMs, 1,538 FAMs, and 405 FRs. While there is still an imbalance, the balance is not as drastic and since this was created from real-world data, we hope that it is representative of that fact. The data is in a channels-first format with a shape of (n, 3, 128, 128) where n is the number of samples in the corresponding set (39,497 for training, 4,937 for validation, and 4,937 for testing). As this is a binary classification task, there are two classes in the dataset, with aproximately 30,000 AM images and 20,000 NAM images, randomly distributed between each of the three sets. The two classes and corresponding numerical label are as follows:<br> Analysable Myofibre (AM): 0,<br> Not Analysable Myofibre (NAM): 1 NumPy (.npy) files can be opened through the NumPy Python library, using the `numpy.load()` function by inputting the path to the file into the function as a parameter. The metadata file contains some basic information about the datasets, and can be opened in many text editors such as vim, nano, notepad++, notepad, etc <br>
Cited by 0Open access
Raoul Heese (12960179), Jochen Schmid (3445184), Michał Walczak (14439244) et al. · Figshare · 2023
<p>An exemplary binary classification problem with one-dimensional feature space and class labels <i>y</i> ∈ {−1, +1}. We compare a GPC (using a radial-basis-function kernel and expectation propagation (EP) with the implementation from [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0279876#pone.0279876.ref019" target="_blank">19</a>]) and our CASIMAC (based on a GPR with Matérn kernel as the underlying regression model), both trained on the same <i>D</i> = 25 training datapoints. The top plot shows the expectation values , and the standard deviations of the latent space distributions , for both approaches (on two different scales), whereas the bottom plot contains the class probability predictions and for both approaches. The gray and white areas indicate the true regions of the class + 1 and −1, respectively. All datapoints are sampled without noise from these regions. Finally, the dotted horizontal lines (⋅⋅⋅⋅⋅⋅⋅⋅⋅⋅⋅⋅⋅) represent the decision boundaries. The corresponding cone segments for CASIMAC, and , are shown in the top plot.</p>
Cited by 0Open access
Wael hasan · Kaggle · 2025
Cited by 0Open access
Linus Ericsson, David Towers, McGough Andrew Stephen et al. · Newcastle University · 2026
The Myofibre dataset is a constructed dataset derived from the NCL_SM dataset (doi.org/10.25405/data.ncl.24125391), which contains high-quality images of human tissue. This dataset is one of the three hidden datasets used by the 2024 NAS Unseen-Data Challenge. The images include around 50,000 manually segmented muscle fibres (myofibres). These myofibres have been split into four categories: Analysable Myofibre, Non-Transverse Myofibre, Freezing Artefact Myofibre, and Folded Region. We took each of the cells that the original authors manually labelled, rescaled them to a uniform (3, 128, 128) data shape, and used these images to create a binary-classification task. We converted the task into a binary classification task due to the imbalance between the four original labels, there are 30,794 AM Myofibres, but only 18,102 NTMs, 1,538 FAMs, and 405 FRs. While there is still an imbalance, the balance is not as drastic and since this was created from real-world data, we hope that it is representative of that fact. The data is in a channels-first format with a shape of (n, 3, 128, 128) where n is the number of samples in the corresponding set (39,497 for training, 4,937 for validation, and 4,937 for testing). As this is a binary classification task, there are two classes in the dataset, with aproximately 30,000 AM images and 20,000 NAM images, randomly distributed between each of the three sets. The two classes and corresponding numerical label are as follows:<br> Analysable Myofibre (AM): 0,<br> Not Analysable Myofibre (NAM): 1 NumPy (.npy) files can be opened through the NumPy Python library, using the `numpy.load()` function by inputting the path to the file into the function as a parameter. The metadata file contains some basic information about the datasets, and can be opened in many text editors such as vim, nano, notepad++, notepad, etc <br>
Cited by 0Open access
Gerard J. P. van Westen (195154), Anna Gaulton (547084), John P. Overington (188498) · Figshare · 2015
<p>Recall values are calculated over the rows and precision values over the columns.</p>
Cited by 0Open access
Lisnichenko, Marina O. · TIB Data Manager · 2024
Cited by 0Open access
Judith Somekh (109861), Nir Lotan (12225562), Ehud Sussman (12225565) et al. · Figshare · 2022
Cited by 0Open access
Kounadis, Gerasimos · Zenodo (CERN European Organization for Nuclear Research) · 2024
Cited by 0Open access