Welcome to Forex-TSD!, one of the largest Forex forums worldwide, where you will be able to find the most complete and reliable Forex information imaginable.
From the list below, select the forum that you want to visit and register to post, as many times you want. It’s absolutely free. Click here for registering on Forex-TSD.
Exclusive Forum
The Exclusive Forum is the only paid section. Once you subscribe, you will get free access to real cutting-edge Trading Systems (automated and not), Indicators, Signals, Articles, etc., that will help and guide you, in ways that you could only imagine, with your Forex trading.
Elite Section
Get access to private discussions, specialized support, indicators and trading systems reported every week.
Advanced Elite Section
For professional traders, trading system developers and any other member who may need to use and/or convert, the most cutting-edge exclusive indicators and trading systems for MT4 and MT5.
My friend SignalsBG make some research in Better system results and conclusions are published here^ .May be this will be usefull for you.
I parste SignalsBG‘s posts here for us discuss...just for common Target...
SignalsBG:
Many people believe that this system is based on Neural Networks, but i don't think so.The neural networks are nothing more than simple optimization.There is nothing mysterious about them.The chance of such system working good is the same as one simple system with 10 parameters which are optimized for the past.So, to create neural network with such a performance, you need good rules, and if you have such rules, you don't need neural network.
There are several things that we know about that system.It is easy to see, that there are three independent systems.They are with different Id , and slight change in their parameters.So let's take the first system.It's id is 854.
You can visualize the deals of that subsystem on M1 chart , using the script in the attachment.
It's easy to see that there is a simple rule what trade is next.
So if we have buy, the next must be sell.If we have sell the next deal must be buy.There is also fixed stop and limit of 60 points.
If have a closer look, we will see that all the deals are at local extremums.So we are adding Stochastic oscilator to the chart(M1).We will use standard parameters 5 3 3.
So, all the deals are when the oscillator is oversold.This is for both buy and sell.After that, there is some time without position.(between the two yellow lines).And after that he is starting to use only the overbought levels of the indicator for both buy and sell.
So there is a filter, which levels(overbought oversold) to use for the next signal, and a filter to choose the right signal. Such filter can be something like MACD, or simple moving average.
barnix, what is all this? Image recognition?
Please, if is possible add to posts source code.
The IRIS plants database is one of the best known database used in pattern recognition studies. The original method was proposed by a guy named R.A Fisher back in 1936 google for his paper "The use of multiple measurements in taxonomic problems"
There's some MQL code for solving these types of problems earlier in this thread
//+------------------------------------------------------------------+
//| C - is the number of classes, N - is the number of examples, |
//| Nk - are from class k |
//| d - is the dimensionality of the training examples, |
//| sigma - is the smoothing factor |
//| test_example[d] - is the example to be classified |
//| Examples[N][d] - are the training examples |
//+------------------------------------------------------------------+
int PNN(int C, int N, int Nk, int d, double sigma, double test_example[d], double Examples[N][d])
{
int classify = -1;
double largest = 0;
double sum[];
ArrayResize(sum,C);
// The OUTPUT layer which computes the probability density function for each class C
for ( int k=0; k<C; k++ )
{
sum[ k ] = 0;
// The SUMMATION layer which accumulates the probability density function
// for each example from the particular class k
for ( int i=0; i<Nk; i++ )
{
double product = 0;
// The PATTERN layer that multiplies the test example by the weights
for ( int j=0; j<d; j++ ) product += test_example[j] * Examples[i][j];
//-----
product = (product-1)/(sigma*sigma);
product = MathExp(product);
sum[k] += product;
}
sum[k]/=Nk;
}
//----
for ( k=0; k<C; k++ )
if ( sum[ k ] > largest )
{
largest = sum[ k ];
classify = k;
}
//----
return (classify);
}
//+------------------------------------------------------------------+
Quote:
Originally Posted by Dimicr
barnix, what is all this? Image recognition?
Please, if is possible add to posts source code.