Skip to search formSkip to main contentSkip to account menu

kingroup: a program for pedigree relationship reconstruction and kin group assignments using genetic markers

Kingroup implements a new method for reconstructing groups of kin that share a common relationship by estimating an overall likelihood for alternative partitions by implementing a maximum likelihood approach to pedigree relationships reconstruction and kin group assignment.
View via Publisher (opens in a new tab)

DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning

This paper presents a baseline for classification performance on the dataset using the benchmark deep learning models, Inception-v3 and ResNet-50, and achieves an average classification accuracy of 95.1% and 95.7%, respectively.
View on Springer (opens in a new tab)

A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis

This work presents DeepFish as a benchmark suite with a large-scale dataset to train and test methods for several computer vision tasks, and collects point-level and segmentation labels to have a more comprehensive fish analysis benchmark.
View on Springer (opens in a new tab)

Modified SIMPSON O(n3) algorithm for the full sibship reconstruction problem

A modified version of the SIMPSON (MS) algorithm that behaves as O(n(3)) and achieves the same or better accuracy when compared with the original algorithm, which has been shown that, in theory, theSIMPSON algorithm runs in non-polynomial time, significantly limiting its usefulness.
View on PubMed (opens in a new tab)

Benchmarking of QSAR Models for Blood-Brain Barrier Permeation

Using the largest available database of 328 blood-brain distribution (logBB) values, a quantitative benchmark was proposed to allow for a consistent comparison of the predictive accuracy of current…
View on PubMed (opens in a new tab)

Partition-distance via the assignment problem

An algorithm is presented that very efficiently reduces the partition-distance calculation to the classic assignment problem of weighted bipartite graphs that has known polynomial-time solutions.
View on PubMed (opens in a new tab)

Robust Cross-Validation of Linear Regression QSAR Models

It was found that (1) a robust version of MLR should always be preferred over the ordinary-least-squares MLR, regardless of the degree of outlier contamination and that (2) the model's predictive power should only be assessed via robust statistics.
View on PubMed (opens in a new tab)

Underwater Fish Detection with Weak Multi-Domain Supervision

This work presents a labelling-efficient method of training a CNN-based fish-detector on relatively small numbers (4,000) of project-domain underwater fish/no-fish images from 20 different habitats, using the Xception CNN as the base.
View on IEEE (opens in a new tab)

Bird call recognition using deep convolutional neural network, ResNet-50

This paper uses ResNet-50, a deep convolutional neural network architecture for automated bird call recognition in acoustic recordings, and uses a publicly available dataset consisting of calls from 46 different bird species to achieve 60%-72% accuracy of birdcall recognition.

Propolis Research in Russia

The objective was to establish an experimental procedure and show direct AFM measurements that unequivocally can be assigned as a type of ‘spatially aggregating agent’ and show high AFM levels in mice.
View PDF (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)