Showing results for: [ Knowledge Representation and Machine Learning ]
Active learning for surface binding
Machine Learning Group Operating Cost - - Published 22 Jan 2021
The dataset includes measurements from two different sensor types on the quadruped robot DyRET. A 3-axis force sensor is mounted on the end of each of the four legs (Optoforce OMD-20-SH-80N), referred... more to as 'raw' in the dataset. The robot also has an Inertial Measurement Unit (IMU) mounted (Xsens MTI-30). It contains a 3-axis gyroscope providing rotational velocities, a 3-axis accelerometer providing linear accelerations, and a 3-axis magnetometer providing absolute orientation in reference to the Earth's magnetic field. The data is labeled 'imu' in the dataset. The robot walks forward on 6 different surfaces, available in the 'surface' column (0: Concrete, 1: Grass, 2: Gravel, 3: Mulch, 4: Dirt, 5: Sand). It does so at 6 different speeds, available in the 'speed' column (0-1: frequency 0.125 Hz; 1-2: frequency 0.1875 Hz; 3-4: frequency 0.25 Hz; 0,2,4: step length 80 mm; 1,3,5: step length 120 mm). There are 10 trials in each file (available in the 'eval_id' column) with 8 steps for each trial. This gives a total of 6*10*6*8 = 2880 steps in total. The jupyter notebook source code used for processing the force sensor data and IMU data is provided.
Legacy data - - Published 21 Dec 2020
Underwater images of seagrasses in Moreton Bay, Queensland, Australia. Images are labelled by the seagrass superclass: Strap-like, Fern-like and Rounded. Additionally, a class of images without seag... morerass present was collected. Only images containing dense seagrass cover are included in this dataset. This dataset also includes additional images for the 5 class case, in which the background is divided into substrate and water column. Each image (4624 x 2600 pixels) has been divided into patches of 578 x 520 pixels for training.less
AIM FSP_TB07_WP02: Physiological sensing for marine species - - Published 18 Dec 2020
VariantSpark is a scalable toolkit for genome-wide association studies optimized for GWAS like datasets.
TBioinf TRL increase for software products - - Published 17 Dec 2020
Python software for Exploratory Lithology Analysis
This package combines features to:
* perform natural language processing on lithology descriptions in the logs, to detect primary and secondary li... morethologies
* apply supervised machine learning to interpolate lithologies across a 3D grid
* visualise interactively the 3D data
Legacy data - - Published 22 Oct 2020
1. Multi-spectral super-resolution dataset (extension to PIRM2018 multi-spectral super-resolution challenge dataset).
The dataset includes
- 272 training stereo registered multi-spectral RGB image pai... morers including the original RGB mosaic images.
- 970 raw multi-spectral images. These need to be downsampled (x2 or x3 etc.) to create low-resolution images for training a CNN for the task of super-resolution.
- 50 test images.
2. Dataset for simultaneous colour-prediction and super-resolution.
This dataset includes:
- 250 registered stereo multi-spectral/RGB image pairs for training
- 25 registered stereo multi-spectral/RGB image pairs for validation
- 21 registered stereo multi-spectral/RGB image pairs for testing.less
AIM FSP_TB07_WP05: Optical sensing for marine environments - - Published 10 Jan 2020
Example code for the protein droplet processing algorithms
Legacy data - - Published 01 Mar 2018
Classification pipeline for images produced at the Collaborative Crystallisation Centre
Multi-Stage LSTM (MS-LSTM) is a deep sequence learning architecture that leverage two types of descriptors, i.e., action-aware and context-aware features to determine the action label. To do it at ear... morely stages, MS-LSTM is trained with a novel loss function that encourages correct prediction as early as possible.less
Legacy data - - Published 22 Feb 2018
A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation with stochastic gradient variational Bayes inference.
License: Apache 2.0
Legacy data - Data61 Engineering and Design - Published 02 Oct 2017
These models are the product of research undertaken under the 2017 APS Data Fellowship program. This collection included trained MITIE NER models that are ready for use with a standard MITIE library c... morelassifier. A summary Precision, Recall and F1 performance statistics table is included for future reference.less
Legacy data - NER model training - Published 02 Jun 2017