Projects included with the Samples:
Simulating a Network with Excel     Stuart Moffatt
A Test Excel Simulation     Marco Broccoli
Classifying Components from images     Department of Mechanical Engineering,  Loughborough University
Predicting Soccer Results     Harry Molloy
Other Projects:
Maximising retail profit.
This project was based on the "Grocer.tvq" sample that is supplied with EasyNN-plus.  The main difference is that the network was trained to identify the "special offers" that resulted in the most shoppers visiting the store and the subsequent profit.  It was noted that there was no simple, direct relationship between the number of visitors and the profit. 
Estimating property prices.
This is another project that started with one of the samples.  The "House prices.tvq" sample is based on house prices around Stockport in England.  It was modified using commercial property prices in an area of New York.  Other than being trained with different measures it is the same network as the sample.  Most of the room counts were replaced with floor space sizes.
Food product grading.
A producer of "traditional" oat biscuits wanted a method that could determine the best biscuits in batches of thousands.  The best biscuits were those that looked to be homemade.  The network used the images of freshly baked biscuits.  Three states were determined by manual inspection.  These were "regular", "homemade" and "irregular".  The network took over a day to train and validate because the images were very complex.  It could then identify biscuits that had the homemade look.  The next stage in the project is to incorporate the network into a machine that will sort the biscuits into different grades for different markets.  Regular biscuits go into cylindrical packs.  Homemade biscuits go into flat packs and attract a higher price.  Irregular biscuits are broken up and used for other products.
Electricity supply load. 
Predicting the load for an electricity supply and generating company.  The project was to find the time, day and conditions that resulted in high loads on an electricity supply.  A neural network was trained using the load data for the previous six years sampled once every hour.  This period included extremes of temperature, humidity, wind speed and sky cover.  The neural network could then accurately predict the load for different weather conditions at any time. 
Planning journeys.
Yet another project that started with a supplied sample, "Hometime.tvq".  It is to find the route that a salesman should take to arrive at the most convenient time for the client and result in the most sales.  The sales workload was also planned using a similar technique.  Long journeys that resulted in few sales were given low priorities or avoided completely by referring the client to different ordering methods.
Plant growth.
This network was developed by a student in a horticultural college to find out which factors were most important to growth rate of a type of pine tree used in timber production.  The factors involved were mainly related to rainfall and temperature but also included the different techniques used to encourage rapid growth.
Horse race winners.
This project included a neural network for every race meeting where a group of horse, jockey and trainer were expected to compete during a season.  The networks were then combined to produce an imaginary race meeting in which the winners would be predictable.  Future real meetings were then carefully examined to look for similarities with the model meeting.  If a meeting were identified with any of the horse, jockey and trainer combinations involved in the race, a bet would be placed on that horse. 
Soccer game results.
The results of Soccer matches are extremely difficult to predict but a neural network can do a little better than just guessing.  A neural network was trained using the scores in hundreds of games, the current team positions and historical league positions.
Identifying images of cars.
A neural network was trained to identify cars on a series of photographs of a busy road and validated using a different set of photographs.  After the validating results peaked the network was tested using a third set of photographs.  All cars that were presented with a side elevation which did not overlap other vehicles were identified. 
Wound healing treatments.
A medical physicist developed a network that was trained using the treatment and medical history of hundreds of patients to determine which treatments produced the optimum healing time. 
R.J.Taylor et al: Using an artificial neural network to predict healing times and risk factors for venous leg ulcers
Journal of Wound Care Vol.1,No.3 2002
Stroke rehabilitation progress.
This network was developed by a stroke rehabilitation specialist to help find the combination of therapies that produced the best results.
Marc van Gestel
Drug interactions.
The side effects reported by patients involved in a stage of drug testing were used to train a network.  The reported symptoms and the dosage of all the drugs being taken were used in the training.  The trained network could then indicate possible drug interactions that would need further investigation.
Multiple sclerosis symptoms and treatments.
This project uses a network that establishes which MS symptoms are related to treatments.  The inputs to the network are the treatments and the outputs are the symptom scores over the following eight days.  A second network uses a much longer period.  In both networks, the importance of the treatments is determined after training.  Querying is used to investigate if the importance is due to a positive or a negative change in symptoms.
Identifying liver cancer.
The distinction of hepatocellular carcinoma (HCC) from chronic liver disease (CLD) is a significant clinical problem.  In this project a network has been used to help identify tumor-specific proteomic features, and to estimate the values of the tumor-specific proteomic features in the diagnosis of HCC.
Poon et al.: Comprehensive Proteomic Profiling and HCC Detection
Clinical Chemistry 49, No.  5, 2003
Who wrote this?
A neural network was trained with hundreds of lines of text extracted from ten novels.  The words per sentence, average syllables per word, average letters per word and the actual text were used for inputs.  The ten authors were the outputs.  After training the neural network could identify the most likely author of any given text.  The long term aim of the project is to classify fictional writing styles. 
Germination rate.
Fifty seed trays were used in which 25 seeds of a common food grain were planted.  The germination rate was measured and used as the output of a neural network.  The inputs were the drill depth, spacing, soil temperature, surface temperature and soil moisture by conductivity. 
Chemical analysis.
An application in gas chromatography which predicts retention indices (the position when a chemical compound appears in a chromatogram/plot compared to other components) on the base of topological descriptors, which describe the structure and/or properties of a chemical.
Chronic Nephropathies.
Dimitrov BD, Ruggenenti P, Stefanov R, Perna A, Remuzzi G.  Chronic Nephropathies:
Individual Risk for Progression to End-Stage Renal Failure as Predicted by an Integrated
Probabilistic Model.  Nephron Clin Pract 2003;95:c47-c59.
Reproductive intentions.
Stefanov R.  Reproductive intentions of the newlywed Bulgarian families -
artificial neural network approach. 
Folia Med (Plovdiv) 2002;44(4):28-34

Created with help of DrExplain