Dr. John Abbot has been a scientific researcher for over 30-years both in academia and industrial settings. Currently, Dr. Abbot is a Professorial Research Fellow at Central Queensland University in Noosa, Australia. The majority of his projects are related to environmental issues including his current project for forecasting medium and long-term monthly rainfall in Australia. Dr.
NeuroDimension Neural Network Applications
A neural network is a powerful data modeling tool that is able to capture and represent complex input/output relationships. Neural network technology performs "intelligent" tasks similar to those performed by the human brain. It acquires knowledge through learning and then stores that knowledge within inter-neuron connection strengths known as synaptic weights.
Neural Networks can be applied to a wide variety of problems, from breast cancer detection to classification of satellite imagery. Below, we've included numerous examples of how NeuroSolutions and other NeuroDimension products can be used to apply neural network technology to real-world applications.
In this quantitative correlational study, simulated data were employed to examine artificial-intelligence techniques or, more specifically, artificial neural networks, as they relate to the location prediction of improvised explosive devices (IEDs). An ANN model was developed using NeuroSolutions to predict IED placement, based upon terrain features and objects related to historical IED detonation events, the associated visual and radio-frequency lines of sight of these features and objects, and the volume of target-vehicle traffic during a 24-hour period.
In the mining industry, most of the underground injuries and fatalities are due to rock falls (i.e. fall of hanging wall/roof). CSIR has developed a device that assists any miner in making an objective decision when determining the integrity of the hanging wall. A trained neural network model is embedded into the device. The device then records the sound emitted when a hanging wall is tapped. The sound is then preprocessed before being input into a trained neural network model and the trained model classifies the hanging wall as either intact or detached.
Gary Howorth has been working in the oil and gas industry for 25-years and has a Degree in Electronic Engineering specializing in digital control theory and a MBA. Mr. Howorth has worked for several key corporations in the industry including BP, Arthur Andersen (Petroleum Services Group), PA Consulting and currently PFC Energy performing quantitative analysis on new and obscure modeling.
Cameron Cooper has been a instructor at Fort Lewis College in Southwestern Colorado for 4-years teaching developmental mathematics and computer science and also serves as an enrollment analyst. Mr. Cooper has an extensive educational background with a Bachelors in Mathematics from Occidental College, a Masters in Information Networking from Carnegie Mellon University, a Masters in Communications from Northwestern University and a Masters in Education from Harvard University. Mr. Cooper is a doctoral candidate in Applied Management & Decision Sciences at Walden University.
Fraser Cook is the Principal Engineer for Artificial Intelligence (AI) at Qualitrol-DMS in the United Kingdom. Qualitrol-DMS supply condition monitoring systems and services for the electrical power transmission and distribution industry. Qualitrol-DMS is the world leader in Partial Discharge (PD) monitoring for Gas Insulated Switchgear (GIS). Mr. Cook studied Artificial Intelligence while receiving his Masters degree in Cognitive Science from Division of Informatics, University of Edinburgh.
Using NeuroSolutions, this study searched through a database of WWW businesses and classified them as “interesting” and “not interesting” for determining future business ventures. With generalized models, the new data sets were classified at 84.75% on average correctly.
This paper reports on oil classification with fluorescence spectroscopy. Using NeuroSolutions, the objective is to classify the oil fluorescence spectra based on a laboratory dataset of fluorescence spectra of several oil classes (sludge, crude and heavy oil). The classification was carried out using the following three methods: channel relationship method (CRM), artificial neural networks (ANNs), and support vector machines (SVMs).
Mr. Honorowski is trading the New Zealand Dollar/U.S. Dollar with a 5x leverage and his four most recent trades alone have yielded 4.46%, 5.31%, 13.28% and 20.60% returns with an overall 77% wins since April '06! *
Mr. Honorowski said he "Absolutely loves the software (TradingSolutions)" and "Would recommend it to anyone and everyone". His favorite features are the Optimal Signal technology along with the neural network modeling. He likes that TradingSolutions was "non-blackbox" with all of the settings and parameters he had control over and said that it was "hard to beat TradingSolutions optimization results".
Mr. Cuni began using TradingSolutions in June '06. He actively traded the Solution Service and models from the Sample Performance section of www.tradingsolutions.com while learning how to create his own profitable models in TradingSolutions. In March '07 he began trading his own models and has earned a 31% annualized return in the past 6 months alone! Mr. Cuni wanted to emphasize four aspects of his model development process that he attributes to his success with TradingSolutions: