D
David J. Livingstone
Researcher at University of Portsmouth
Publications - 75
Citations - 4515
David J. Livingstone is an academic researcher from University of Portsmouth. The author has contributed to research in topics: Artificial neural network & Quantitative structure–activity relationship. The author has an hindex of 28, co-authored 75 publications receiving 4234 citations. Previous affiliations of David J. Livingstone include University of Hertfordshire & The Hertz Corporation.
Papers
More filters
Journal ArticleDOI
Virtual computational chemistry laboratory - design and description
Igor V. Tetko,Johann Gasteiger,Roberto Todeschini,Andrea Mauri,David J. Livingstone,Peter Ertl,Vladimir A. Palyulin,Eugene V. Radchenko,Nikolai S. Zefirov,Alexander S. Makarenko,Vsevolod Yu. Tanchuk,Volodymyr V. Prokopenko +11 more
TL;DR: The main features and statistics of the developed system, Virtual Computational Chemistry Laboratory, allowing the computational chemist to perform a comprehensive series of molecular indices/properties calculations and data analysis are reviewed.
Journal ArticleDOI
Neural network studies. 1. Comparison of overfitting and overtraining
TL;DR: Application of ANN ensembles has allowed the avoidance of chance correlations and satisfactory predictions of new data have been obtained for a wide range of numbers of neurons in the hidden layer.
Reference BookDOI
Predicting Chemical Toxicity and Fate
TL;DR: The use of Quantitative Structure-Activity Relationships and Expert Systems to Predict Toxicity by Governmental Regulatory Agencies and a Framework for Promoting the Acceptance and Regulatory Use of (Quantitative) Structure- activity Relationships are outlined.
Journal ArticleDOI
Unsupervised Forward Selection: A Method for Eliminating Redundant Variables
TL;DR: An unsupervised learning method is proposed for variable selection and its performance assessed using three typical QSAR data sets, showing it to produce simple, robust, and easily interpreted models for the chosen data sets.
Journal ArticleDOI
Data modelling with neural networks: Advantages and limitations
TL;DR: Four problems in the use of neural networks in data modelling are discussed, namely overfitting, chance effects, overtraining and interpretation, and examples are given of the means by which the first three of these may be avoided.