Science topic

# Genetic Algorithm - Science topic

Genetic Algorithm are solving problems in maths by optimization technique using GA
Questions related to Genetic Algorithm
Question
Hi,
How can we prove the results of the GA that are optimised, in other words, are there criteria or measures to determine the best results (optimize results).
regards
Thank you for all your replies.
Regards
Question
I have running GA optimization using "gamultiobj" in Matlab. The upper bound and lower bound of my design variables are like [10 30 175 1] and [30 60 225 3]. But after convergence, I see the design variables (like all of them) near 20,47,175 and 1. I am not getting a Pareto Front. What could be the possible reasons for that?
Question
how genetic algorithm fittness function calculated for botnet attack detection?
A Decision Tree-Aware Genetic Algorithm for Botnet Detection
Question
I already saw some examples of GA (genetic algorithm) applications to tune PID parameters, but I (until now) don't know a way to define the bounds. The bounds are always presented in manuscripts, but they appear without great explanations. I suspect that they are obtained in empirical methods.
Could Anyone recommend me research?
Dear Italo,
In general, the bounds selection is made empirically because the "suitable range" of a PID controller is problem-dependent. The way I use to select the bounds is: 1. I tune a PID controller that produces a stable response to the closed-loop system. Then, 2. I choose a range around this "nominal" value large enough such that the GA has still some degree of freedom to search in the optimization space. Finally, 3. if the GA converges, I start decreasing/increasing this range till I got a more or less good behavior of the GA, i.e., the GA doesn't stick in a sub-optimal minimum or so.
If you want to use a more rigorous approach, I would suggest computing the set of all stabilizing PID controllers for the particular system. Then, I would establish the bounds for the GA search space to be the this computed set. In that way, you would search for the optimal controller only within those producing a stable closed-loop response.
Best,
Jorge
Question
I have modelled a system using ANN predicting the extraction yield corresponding to four input parameters. Now I want to use this model as objective function in GA to determine individual optimum parameters and optimum overall yield. How can I do that? How to frame and call the objective function in GA Toolbox? I have tried several times and it is showing undefined function for input arguments of the type 'double'
My pleasure. The toolbox of Matlab is not for advanced uses. You need to find a GA code( the .m file).
There you have complete control over the GA.
after your ANN training is finished, there is a structure named "net."
You can use it as follows:
suppose you have five inputs (x1 to x5) you should use this command :
net(x1,x2,x3,x4,x5) returns Ann's output corresponding to those inputs.
You can try to put your trained ANN(the net structure) inside a new function that could be used by the handle and check if it is acceptable in the Toolbox or not.
Overall, I suggest that you try the GA codes instead of Toolbox.
Question
Assuming, I have a number of vectors where each item in the vector is a real number. I was to generate some vectors from those initials ones and add them to the collection of initial vectors. This was I can have a initial population of increased size. What are some ways to do this?
Question
Dear all,
according to , QGA are more efficient than GA (genetic algorithms), and according to  PSO is better than GA. Do you know if there are papers that do the comparison between PSO and QGA ?
Thank you
 - Z.Laboudi (2012) - Comparison of Genetic Algorithm and Quantum Genetic Algorithm
 - F D Wihartiko (2017) - Performance comparison of genetic algorithms and particle swarm optimization for model integer programming bus
time tabling problem
Best regards
Question
How does one optimize a set of data which is comprised of 3 input variables and 1 output variable (numerical variables) using a Genetic Algorithm? and also how can I create a fitness function? How is a population selected in this form of data? What will the GA result look like, will it be in a form of 3 inputs and 1 output?
I do understand how the GA works, however, I am confused about how to execute it with the form of data that I have.
My data is structured as follows, just for better understanding:
3 columns of Input data, and the fourth column of Output Data. (4 Columns and 31 rows) data. The 3 input variables are used to predict the fourth variable. I want to use GA to improve the prediction results.
Lastly, Can I use decimal numbers (E.g. 0.23 or 24.45); or I should always use whole numbers for chromosomes.
GOOD LUCK
Question
How can I optimize ANFIS using Genetic Algorithm; and also with Aquila Optimizer in MATLAB? Any available code I can use?
Question
Dear Members
I had recently gone through a sample program code (in MATLAB) corresponding to Pareto GA in Appendix II (Program 4, Page: 219) of the book PRACTICAL GENETIC ALGORITHMS by Haupt. However, I failed to understand the Niching strategy employed in the program code. Also, kindly explain the Pareto dominance tournaments that have been employed or used for mate selection in the example provided in the book. The flow diagram for Pareto GA delineated in Figure 5.2 of the book, mentions an increase in the cost of closely located chromosomes. But the code apparently contains no such steps. Kindly explain the anomaly.
If there is no layout available, nexttile creates one. Create a Pareto chart by passing the axes to the pareto function as the first argument. Call the nexttile function to add a second axes object to the layout. Then create a second Pareto chart.
Question
hello!
how i can use the Neural network fitness function i.e., after simulation the value we get basically in terms of MSE(mean squared error). so can you tell me how we this MSE as fitness function in Genetic Algorithm in order to minimize the MSE for better neural netwrok model.
Regards,
Shafagat
Question
hello!
can anyone tell me how i can integrate the neural network and genetic algorithm. i have a simple real coded genetic algorith where i need to use the neural network. please help me on thia. my code is in matlab. if some one provide me the code
Regards,
Shafagat
Question
Hii,
I have implemented genetic algorithm with partially mapped crossover for solving tsp. Here I'm using different random.seed vlaues(24,42,72,112). When I run the algorithm , can I get the same graph with different seed values without changing the parameters but city co-ordinates are randomly generated.
best regards
Annapareddy
Well, I still don't understand the point of your experiment.
I don't understand why you use "random cities" since the TSP requires "all" cities to be visited, BUT regardless, I understand that you have a problem with generating pseudo random numbers.
Please, tell me, what language are you using for develop your experiment ?
Have you developed your own genetic algorithm?
Question
How can I get a MATLAB code for solving multi objective transportation problem and traveling sales man problem?
Question
Here, I have implemented my genetic algorithm with combining two crossover operators i.e..(PMX,OX). After running the algorithm I am getting same fitness values as output from staring generation to ending generation. There is no change Is it correct.? please can anyone answer
Best regards
Anna
Nabil Boumedine I used initially ordered crossover of genetic algorithm for solving tsp problem
after generating new offspring (a,b) with ordered crossover.  After that I used a,b as new parents for partially mapped crossover to produce another new offspring i.e(c,d).
So here c, d acts as another parent to apply uniform crossover to produce another new offspring. This will be done on one algorithm
def crossovers(self, p1, p2, r_cross):
off1 = self.ordered_crossover(p1, p2, r_cross)
off2 = self.ordered_crossover(p2, p1, r_cross)
#print(off1, off2)
Off1 = self.partially_mapped(off1, off2,r_cross)
Off2 = self.partially_mapped(off2, off1,r_cross)
#print(Off1,Off2)
off3 = self.uniform(Off1, Off1,1)
off4 = self.unifrom(Off2, Off2,1)
return [off3, off4]
couuld you tell for above theory , is this code is correct
Question
Hello all, I am new to image processing.... I want to detect edges from an image. When I searched on detecting edges in images I came across about edge detection using genetic algorithms. Where I find the chromosomes and find fitness function for crossover and mutation process. Also, they say that chromosomes are binary array. I am finding it difficult to understand how can we find binary arrays from an image and picking that as a chromosomes or do we have any methods to find chromosomes from an image. Please help me...any help is appreciated.
1.Taking gray levels of histogram of an image in an array u can create a chromosome.
2. Taking coordinate (i, j) and amplitude of pixels in an array u can do it.
Generate an expression including statistical parameters and features of image as the fitness function.
Question
Hii,
I have implemented genetic algorithm with partially mapped and ordered crossover for solving tsp.
In partially mapped crossover, I have taken 100 generations, when I run the algorithm the best solution is getting of 20th generation. from 20th generations onwards the solution is constant until last generation( 100). may I know the error . Please acn anyone suggest the error.?
Thank you
I need help for this code. How can add getters and setters for this class city method : please
import math
class City:
def __init__(self, x, y):#initializing the cities
self.x = x
self.y = y
def dist(self, city):#calculate distance betwwen 2 cities
dx = abs(self.x - city.x)#mising getter and setters methods cant access
dy = abs(self.y - city.y)
return math.sqrt(dx ** 2 + dy ** 2)
def __repr__(self):#
return 'City : x:' + str(self.x) + ', y:' + str(self.y)
Question
Define attributes suitable for comparison of both algorithms?
Genetic algorithm with tabu search OR Genetic algorithm with simulated annealing ?
Mahnoor Iftekhar In my opinion, you must examine both algorithms in your problems, then select which one is the best.
Question
I am studying on global optimization algorithm now, it seems that there are many different versions of each kind of algorithm. Only for particle swarm optimization (PSO) algorithm, there are many versions like APSO, CPSO, PSOPC, FAPSO, ARPSO, DGHPSOGS (see Han and Liu, 2014, Neurocomputing). In addition, the class of genetic algorithm (GA), differential evolution (ED), ant colony optimization (ACO), simulated annealing (SA) and so on, can also be used to solve the problem. When we develop a new global algorithm, it is worthwhile comparing the performance of these different methods on some benchmark functions (like Resenbrock function and Rastrigin function) in a fair way. For example, I would say the average number of evaluations of cost functions, the success rate, and the average time-consuming is good as measurements for comparison.
So my question is "is there any source code (Matlab) has been developed for comparing different kinds of global optimization (GO) methods?". The code should be easy to use, convenient to fairly compare enough advanced GO methods, and should also have provided enough benchmark functions (given gradient of each function would be better, so that we can compare some gradient-based global optimization algorithm).
Best wishes,
Bin She.
Dear Bin She,
I share my thoughts (I'm not an expert), perhaps it might help you in something:
If you want to compare performance between optimizers, you shouldn't limit yourself by the programming language.
I think that a good way to go forward is to consider each author's code regardless the language (as is pointed out by Luis Gerardo de la Fraga) and instead try an asymptotic analyzes (Big O), because as you said each strategy is quite different and comparing by time might happen that even being the same language (matlab) a strategy is efficiently implemented (e.g. vectorization) but the remaining methods are naively compared, which is also unfair.
Note that some contests (like CEC contests as is pointed out by Stephen Oladipo) considers a measurement of time regardless the language, which is understandable in a contest environment, which I think is not you case.
Fortunately, there are a lot of frameworks that integrates some populations meta heuristics and newton-based methods, and perhaps this list might help you in your research (I've used some of them in my short experience testing):
1) PlatEMO (MATLAB): https://github.com/BIMK/PlatEMO is matlab and I've read several papers that take into account this framework which is nice.
4)Pymo (python): https://pymoo.org/
5)Shark (CPP): I like this because is extremely fast and is ready to be tested in parallel as well.
6)MOEA framework (java) : http://moeaframework.org/
7)Also you might try to look at the code of some contest, check Ponnuthurai Nagaratnam Sugantham github: https://github.com/P-N-Suganthan
As Abubakar Bala said you might look for the code in github, the disadvantage is that the source code might be wrong.
I suggest you to compare them in both quality and complexity,
Good look! :)
Question
I am using an evolutionary-based GA optimisation tool that divides the space of possibilities into subsets to perform hypercube sampling within each subset, and thereafter generates multiple generation of results, the best of which will form the Pareto front and through each iteration move closer to the global optimum. However is it possible that through the process of hypercube sampling (and hence disregarding some options) , this tool might miss a true global optimum?
this is a natural thing in mathematics there is no perfect solution especially the no linear problem, and most metaH utilized in the no linear problem, so you need always to expect and accept that fact, and keep improving the study of the metaH
Question
While working in both the software, after loading the training and validation data for the prediction of a single output using several input variables (say 10), it skips some of the inputs and delivered an explicit mathematical equation for future prediction of the specific parameter but it skips some of the input variables (say 2 or 3 or maybe greater). What criteria are these software uses in the back for picking the most influential parameters while providing a mathematical predictive model?
First of all, was the fitness (error) zero (0) at the end of the evolution?
If yes, it means that the skipped variables are not important for the data being analyzed.
If not, it can either mean that some variables are not important or that the evolution is stuck in a local optimum.
Note, that for real-world data, it is unlikely to obtain fitness 0 because of noise or other imperfections (in data collection or measurement).
regards,
Mihai
Question
Hello everyone,
Could you recommend papers, books or websites about mathematical foundations of artificial intelligence?
Thank you for your attention and valuable support.
Regards,
Cecilia-Irene Loeza-Mejía
Mathematics helps AI scientists to solve challenging deep abstract problems using traditional methods and techniques known for hundreds of years. Math is needed for AI because computers see the world differently from humans. Where humans see an image, a computer will see a 2D- or 3D-matrix. With the help of mathematics, we can input these dimensions into a computer, and linear algebra is about processing new data sets.
Here you can find good sources for this:
Question
Both genetic algorithms and metaheuristic algorithms are optimization algorithms. Is one category of these two is included under the other?
Evolutionary algorithms, physics-based algorithms, swarm-based algorithms, and human-based algorithms are the four primary types of meta-heuristic algorithms. These algorithms are based on human or animal behavior, as well as some physical behaviors of molecules, and so forth.
Genetic algorithms, partial swarm optimization, grey wolff optimization, ant colony optimization, and Social-Based Algorithm are some example.
Question
I am working on RCSR. I need genetic algorithm for 1-bit coding Metasurface so that i can arrange my unit cells.
Dear Hamza,
May you please describe a little about the technical details of this GA? I am able to modify the GA code based on your goal if I know the details.
Question
I am coding a multi-objective genetic algorithm, it can predict the pareto fronts accurately for convex pareto front of multi-objective functions. But, for non-convex pareto fronts, it is not accurate and the predicted pareto points are clustered on the ends of the pareto front obtained from MATLAB genetic algorithm. can anybody provide some techniques to solve this problem. Thanks in advance.
The attached pdf file shows the results from different problems
Your question provoked me to write an preprint
NON-CONVEX FUNCTIONS: A GENERALIZATION OF JENSEN'S INEQUALITY
I posted it recently at ResearchGate
If all goes well, I want to write another preprint on a similar theme
Question
in his name is the judge
hi
I wrot a sub code on opensees for active tlcd or tuned liqiud gass damper (tlcgd) and assign it to some structures, it seems worked correctly.
In next step i want to optimize tlcgds location on each story with some objects like max dislacement or torsion ratio and ... so i have to use multi objective optimization (which may NSGAII algorithm is the best choice) code or toolbox on matlab and simulink. For this purpose i want to run NSGAII algorithm in matlab, then algorithm Calling my code in opensees (tcl) and run it, after that NSGAII algorithm modify damper location (in opensees code) after each timehistory analysis In order to improve objectives and then analysis my code again and again until find best location for dampers.
Note that I actually want to changing dampers location be part of the NSGAII algorithm and the algorithm itself automatically relocation the dampers to get the best answer.
one best solution may use openseespy but i think it's not free access and i can't get it from iran, So i think realyhead Over heels in this case.
Any help is greatly appreciated.
Take refuge in the right.
I think that's the best answer
Question
I am working on a hybrid wind turbine system and pumped storage system to meet the load of Morocco. the objective is to optimize the gain to resume as much as possible from #pload. optimization #PSO #genetic #algorithm #using #python.
the objective function to be maximized :
Question
I wanna optimize 2 complex functions (that have an imaginary part and a real part) using MOGA in Matlab, Are there any other methods for this type or there is no change even if the objective functions are complex?
NB: variables are all scalars
Optimize complex objectives in what sense? For example, a complex objective value z1= a1 + ib1 can be better than z2= a2 + ib2 if say the magnitude is larger, i.e. (a12 + b12 ) > (a22 + b22 ). In this sense, you basically have a real-valued objective that is a function of the real and imaginary parts of the complex outcome. Alternatively, you may be interested in real and imaginary parts individually. Say, for instance, you want to maximize the real part and minimize the imaginary part, well then you basically have two individual real-valued objectives for the real and imaginary parts separately. In this sense, if you have 2 complex functions you may treat this as an optimization problem with 4 real-valued objectives.
Question
I am presently working on the application of the genetic algorithm for solving multi-objective optimisation of machining parameters.
I need assistance in this area. especially as it has to do with genetic Algorithms.
Multi-Objective optimization problem involves more than one objective function to find one or more solutions.
The best reference that can help you understand multi-objective optimization (MOO) is the book by K. DEB "multi-objective optimization using evolutionary algorithms (GA)". the book includes a section about using GA for MOO:
1-Binary GA
2-Real parameters GA
3- Constraint-handling in GA
moreover, it discusses different evolution strategies.
It also discusses Linear and Nonlinear MOO, convex and nonconvex MOO, Pareto optimal solution.
Question
Hi,
Can anyone be kind to help me with optimizing PID controller gains using genetic algorithm for a MIMO system (Twin Rotor MIMO System (TRMS)). I have been stuck with this problem for quite a very long time now. I have uploaded the code and simulink model for the TRMS with the decoupler that i used.
Whenever i call and run the optimtool for the ga program in MATLAB, the tool does not optimize the system. Instead the system fails to decay and settle on the step input, but both the pitch and yaw signals become unstable and uncontrollable (go into infinity along the y-axis).
I believe the code i am using is wrong and maybe the configured simulink model. Somethings are wrong.
Please I need help Sirs. Thank you
You can try to get initial PID gain values from Ziegler Nicola's method for closed loop decoupled transfer functions of pich and yaw rotors. Then you can use GA MATLAB tool box setting the range of gains nearby the values you got from ZN method.
This paper might be useful to you.
Question
I have a multi-objective optimization with the following properties:
Objective function: thee minimization objective functions) two non-linear functions and one linear function
Decision variable: two real variables (Bounded)
Constraint: three linear constraint (two bounding constraint and one relationship constraint)
Problem type: non-convex
Solution required: Global optimum
I have used two heuristic algorithms to solve the problem NSGA-II and NSGA-III.
I have performed NSGA-II and NSGA-III for the following instances (population size, number of generations, maximum number of functional evaluations(i.e. pop size x no. of gen)): (100,10,1000), (100,50,5000),(100,100,10000), (500, 10, 1000), (500, 50, 25000), and (500,100,50000).
My observations:
Hypervolume increases with increase in number of functional evaluations. However, for a given population size, as the number of generation increases the hypervolume reduces. Which I think should rather increase. Why am I getting such an answer?
Greetings to you all.
Please how can I find MATLAB code for Accelerated Particle Swarm Optimization algorithm for tuning PID controller.
Question
I want to optimize an objective function (power plant problem) in MATLAB, connecting with EES. The function file in MATLAB runs without issues, but when the genetic algorithm file is run, I keep getting the error statement and the operation terminates.
Your function probably returns a vector or an array. To check if it returns a scalar value, follow what is displayed in the output window after calling the function. It should be a single numeric value.
Question
I need the recent resources( videos and websites) and reseach papers in term of multi processor scheduling using ant colony with genetic algorithm with python code description
These papers might be useful, have a look:
And the codes:
Kind Regards
Qamar Ul Islam
Question
I have developed an algorithm for event detection in a time series data. I have 3 parameters to adjust. Can I use meta-heuristics or other genetic algorithm to optimize this problem?
As it mentioned that before if you could define a fitness function, implementing an optimisation framework is not challenging, and I would be happy to help in this way.
Question
Dear All,
I have successfully applied NSGA-II on a multi-objective optimization problem.
While I was observing the results during the optimization process, I have noticed that some variables (genes) have reached very good values that matches my objectives, while others haven't. However during the optimization, the good genes are being frequently changed and swapped to undesired results (due to genetic operations; mutation and crossover) until the algorithm reaches a good local optima, or hits a condition.
My question is this:
Can I exclude some genes from the optimization process since they have already reached my condition sand finally combine them with the remained genes in the final chromosome?
All the genes play an important rolein in the optimization process, The likely good genes contribute information for improving the qulity of new ones and the likely bad genes could help to avoid non factible solutions and to re-direct the search to new areas of the domain. So, I think that all the genes must to participate in the solution search process.
Question
Hello
I have to run an optimization using the genetic algorithm GA with a defined initial population.
The same problem is optimized using PSO as well, and this is the option command for the GA
options = optimoptions(@ga,'Generations',Max_iteration,'OutputFcns',@outputfunction,'PopulationSize',50,'InitialPopulationMatrix',initialX,'TolFun',1e-10);
where initialX is my initial population.
The issue is that I am not getting the same value of the first run for both algorithms.
Any one can help me with this?
Hi Djedoui,
If I understand your question correctly, I'm assuming you have a fixed/non-randomized initial population for both the GA and PSO optimizer and that by "run" you mean "iteration." If that it the case, then you shouldn't be surprised if your first iteration produces different objective function values. Remember, for most metahueristic algorithms, the value of the first iteration is estimated only after the position of the search agents are updated. To simplify, the algorithm first creates the initial population (in your case, fixed for both GA and PSO) and then the search agents go through the first iterational loop whereby positions and therefore objective value functions are updated. The best optimized value is selected and then reported for "Iteration 1." Since both GA and PSO employ randomized operators, you will definitely get different results.
Question
using genetic algorithm in schedule of rivers and canals also calculating capacity and yield of dams by optimal solution (optimization )
A typical irrigation scheduling problem is one of preparing a schedule to service a group of outlets that may be serviced simultaneously. This problem has an analogy with the classical multimachine earliness/tardiness scheduling problem in operations research (OR). In previously published work, integer programming was used to solve irrigation scheduling problems; however, such scheduling problems belong to a class of combinatorial optimization problems known to be computationally demanding. This is widely reported in OR literature. Hence integer programs (IPs) can be used only to solve relatively small problems typically in a research environment where considerable computational resources and time can be allocated to solve a single schedule. For practical applications, metaheuristics such as genetic algorithms, simulated annealing, or tabu search methods need to be used.
Question
As i am a fresher so I wanna know how genetic algorithm and LSTM will work together?
Question
there are various bioinformatics tools that show the patients' mortality rate related to gene expression such as prognoscan! if you know other bioinformatics platforms or approaches please let me know!!!
regards
Dear Dr Mohammed,
I also suggest you to read these recent articles:
Best regards,
Pr Hambaba
Question
New optimization algorithms are developed by researchers every year and then they begin to solve the same kinds of problems previously solved by their classical counterparts such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), etc., taking their inspiration into account NFL (No Free Lunch). Can you have your expert opinions on what are other new meta-heuristic application zones?
Question
I need this community assistance on implementation code of this study "Efficient clustering in collaborative filtering recommender
system: Hybrid method based on genetic algorithm and gravitational emulation local
search algorithm" By Mohammadpour, T., et al.(2019) for my research as a benchmark algorithm
Question
My dataset is having few categorical features (binary) and few ordinal features (multiple classes), the dependent feature is also binary.
Please suggest how I can do feature selection using Genetic algorithms by defining fitness function.
Question
Hi
I have a project in the field of optimizing the groundwater monitoring network through coding in MATLAB software (with NSGA2 algorithm), I have read the complete research background and I am completely familiar with the subject in theory, but I have no background to start coding. Does anyone have a related or educational code file in this subject?
Question
Can you recommend any good books for learning artificial neural networks and genetic algorithms (basic level). Especially the books with easy examples, case studies and tasks are welcomed.
Dear Colleagues
Thank you very much for all your suggestions. They are very helpful!
Best regards for all of YOU!
Question
I have a model of depression which I am attempting to convert into a functional simulation in the form of a recurrent neural network or genetic algorithm, whichever would suit it better. (The model is attached)
Some of my questions on how this may work include:
1. How ought one optimise the initial parameters of the system?
2. How best to deal with positive feedback-loop induced instability?
3. How to go about choosing between activation functions
Any suggestions on how to go about coding an initial loop and then expanding it would be very helpful. Also, any suggestions on where to code this, I was thinking Jupyter.
Question
I used uniform crossover to solve eight queens problem. It is taking more than 3hrs to get the output. Is there any way to reduce the running time or better crossover to solve eight queens problem? Any answer regarding this will be appreciated.
Thank you
These links might be useful, have a look:
Kind Regards
Qamar Ul Islam
Question
Hello everyone,
I am looking to build genetic algorithms for production scheduling using python.
I found out that there are a few libraries like DEAP and PyEvolve and GeneAI and pyGAD , which support wide variety of genetic algorithms.
Alternatively, one can also try to code the algorithm up by themselves.
I'd like to know which approach is better?
Considerations include:
Continued code support for the program's usage lifetime, which is longer than the project duration
Flexibility and the ability to explore a wide range of crossover and mutation functions
Easiness of implementation ( avoiding premature convergence)
Code maintenance,
Looking forward to hearing from you all,
With warm regards,
Akhil Ramesh
I suggest you first try to build you own codes from scratch that way you get to learn a lot like. And once you learn and understand how GA works then you can use library and stuff to optimize any problems.
Also writing GA from scratch is no that hard.. you can complete coding in like an hour or so but you need have clear idea on how GA works. May be the following vide on YouTube might be help full to start from scratch. check it out
Question
Have you met a usage of blockchain in combination with genetic algorithms?
In distributed computing, there is a problem with the calculated results reliability. Some distributed computing projects are using parallel implementation of genetic algorithms. I am thinking, is it possible for blockchain technology to be used for distributed computing results approval?
In distributed computing, computers are not under the control of the person who is doing the project. The owners of the computers can manipulate calculations and results.
I personally think there's no need to add a genetic algorithm in contrast to the blockchain as both have different use cases. Plus there are services like Oscar Medina mentioned which can work for your scenario.
Question
In many genetic programming software products, I can see there is always a function named automatically defined function. This idea is interesting because it can generate some sub-functions, which alleviates the burden of traditional genetic programming algorithms. However, in most recent papers published in evolutionary algorithm journals and conferences, it seems that this method has always been ignored. So why don't most researchers give up such a good idea?
Kind Regards
Qamar Ul Islam
Question
I am working in a project to assist an experimental team in optimizing reaction conditions. The problem involves a large number of dimensions, i.e. 30+ reactants which we are trying out different concentrations to achieve the highest yield of a certain product.
I am familiar with stochastic optimization methods such as simulated annealing, genetic algorithms, which seemed like a good approach to this problem. The experimental team proposes using design of experiments (DoE), which I'm not too familiar with.
So my question is, what are the advantages/disadvantages of DoE (namely fractional factorial I believe) versus stochastic optimization methods, and are there use cases where one is preferred over the other?
When there are 30+ reactants, I first would make a network, with the input of the experimenters, of the relations between the reactants: you really have to understand parts of the chemical reactions . Modeling, without understanding the basics of what you are trying to model, is never a good idea. And, given my knowledge of chemistry, I fail to see the use of stochastic optimization in this context. Maybe systems and control theory could give you insights as well. Maybe you can view the whole as a system, with inputs and outputs.
Question
Hi,
Can someone recommend some documents to me on genetic algorithms optimization?
Thank you Mr Barry Fox it's very interesting fiels
Question
who can help me Genetic Algorithm - MATLAB code for Multiobjective algorithm?
Question
Hi, i want to simulate Genetic algorithm for load balancing in cloud, but i don't know from where to begin?
As Jordan Pollard said you need to clarify the question.
First, a clear definition of what cloud platform are you going to tackle (not all cloud environments are equal). This has an effect on what you are going to model. It is a completely different issue when you are modeling a SaaS vs. a PaaS vs a IaaS. There are various sub questions that need to be addressed depending on the selected cloud environment (e.g. closed environment such as private cloud for multiple data source storage or open to the public).
Once you have this clear then the second step would be that based on your data and the problem you need to answer the question on how you are going to create the optimisation strategy. That is is it going to be static optimisation or does it change with time (e.g. during the day the platform will be subject to different kinds of loads at different times).
Getting these issues answers will then allow you to move to the specifics of the genetic algorithm.
Regards
Question
We are trying to breed some parameter configurations controlling the search of a deduction system. Some parameters are integers, some are reals, some are boolean, and the most complex one is a variable length list of different elements, where each of the elements has its own (smallish) sub-set of parameters. Since we have Python competence and Python is already used in the project, that looks like a good fit. I've found DEAP and PyEvolve as already existing frameworks for genetic algorithms. Does anybody have experience with these and can tell me about the strengths and weaknesses of the two (or any other appropriate) systems?
If it helps: In our application, determining the fitness of the individual is likely the most expensive part - it will certainly be minutes per generation, and if we are not careful and/or rich (to buy compute clusters), could be hours per individual. So time taken by the rest of the GA is probably not a major factor - think "several generations per day", not "several generations per second".
It is an open-source library for general-purpose optimization using the genetic algorithm. It is very easy to learn.
Question
How to use optimization techniques like Genetic Algorithm and Particle Swarm Optimization in reliability analysis? Please give an idea about it
Your research approach is problematic. Before you ask a research question or ponder the answer to a problem, you are starting with a method and trying to fit the method to a field, not even to a specific problem. You should first ask a research question, formulate the problem, build the model and then find a suitable optimization method to solve it.
Question
Dear all,
I am working on the optimization of the activity chain (set of locations) using a Genetic Algorithm (GA). My fitness function consists of (10) variables [y=x1+x2+x3 .......x10]. Some of the variables should be calling in a dynamic way while others work with an offline database.
Is it right to divide the optimization into two phases, firstly, optimization based on dynamic data using an algorithm (A)? Then, work on an algorithm (B) to optimize the activity chain based on the offline database?
Hello Ali,
I hope you are doing well.
Yes, it is possible.
Based on your questions A and B, the first thing to come to my mind is to attempt to develop a methodology based on bi-level optimization principles (since you are working with two groups/types of variables). Essentially, you would need to optimize the first group of variables in A and then optimize variables in group B(based on the solutions/values that you have for group A).
Also, an interesting concept to include in your bi-level or dynamic approach is repair heuristics. By applying some repair heuristic rules, you can turn a feasible solution from subproblem A to a feasible solution for subproblem B.
/Dimitris
Question
I hope you all are doing well.
The Genetic algorithm updates the population in every iteration, so what if we have a specific population and we want to choose the best among them. how we can optimize such a problem?
I want to design a pipeline. Since companies produce pipes in a few sizes I'm wondering how can I find the optimal diameter ???
I would be grateful if you respond to my question.
I have written (with PhD students of mine) a basic book on modelling, theory (especially on what "optimum" is, and how to check that it is an optimum), and basic procedures in mathematical optimisation:
An Introduction to Continuous Optimization, authors Andréasson et al [as I like to use alphabetical ordering], publisher Dover Publications.
I hope you can find it. Let me know if you find useful!
Cheers! /Michael
Question
Genetic algorithm can be implemented using ga tool in matlab Plz suggest any tool to implement the evolutionary algorithm or nature inspired algorithm.
You can find a lot of ready algorithms from this website.
Question
Hi,
Does anyone know any source (journal paper, conference paper, slides, etc.) that shows how to improve runtime of Genetic Algorithms (or any Evolutionary Algorithm)? I am hoping to find a way to increase the speed of GA to match or get as close as possible to the equivalent mathematical programming problem. I am looking for both algorithmic tweaks (e.g. giving the GA a good starting population) and implementation/technical tricks (e.g. using Cython if the GA code is written in Python).
Many thanks,
Majed
I hope you find the below publications useful :
two papers from Professor Deb (father of modern multi-objective evolutionary algorithms),
and one paper plus its code from professor Doerr .
Question
Various metaheuristic optimization algorithms with different inspiration sources have been proposed in recent past decades. Unlike mathematical methods, metaheuristics do not require any gradient information and are not dependent on the starting point. Furthermore, they are suitable for complex, nonlinear, and non-convex search spaces, especially when near-global optimum solutions are sought after using limited computational effort. However, some of these metaheuristics are trapped in a local optimum and are not able to escape out, for example. For this purpose, numerous researchers focus on adding efficient mechanisms for enhancing the performance of the standard version of the metaheuristics. Some of them are addressed in the following references:
I will be grateful If anyone can help me to find other efficient mechanisms.
I recommend you to check also the CCSA algorithm implemented by a Conscious Neighborhood-based approach which is an effective mechanism to improve other metaheuristic algorithms as well. The CCSA and its full source code are available here:
Question
I am trying to solve a MINLP problem using genetic algorithm (from MATLAB's global optimization toolbox).
My number of decision variables is 168.
• 96 of these decision variables are binary [0 1]
• The remaining 72 variables can take the integer values of [1 2 3].
The problem is accurately formulated and there is no doubt about it.
Following are my doubts:
1. What is the appropriate population size to be used? I am trying: 2*168, 3*168, and 4*168. But the size seems to be large. Since all the decision variables are integers, what do you suggest about the population size?
2. For different initial guesses, I get different optimized solutions. I am using 20,50 and 60 % of the population size as the initial population matrix. Of course, I know that we cannot guarantee global optimum with GA; but still, what can you suggest to get global optimum? Trying multiple times and getting the lowest fval doesn't sound good to me.
3. The mutants are taken as 10% of the total population. Can you suggest an appropriate size for it ?
Finally, when the initial population matrix is not defined at all, I do not get the linear constraints (inequality) satisfied. But with some initial population size, I get ( but i think the optimum values are local and not global.
1. Other than genetic algorithm, are there other optimizers for such problems? (I do not like to think surrogate-optimization is a good idea ), which are free and can handle such large MINLP problem?
2. Are there other toolboxes (apart from the global optimization toolbox), which are free but can be used to handle large MINLP?
Thanks
Theodor: Perhaps the objective function has been decided by someone else - for example the company that you work for. Then you simply have to use what is given.
Personally I would not use a metaheuristic - as it is not even devised to find an optimum - something that everyone should know.
Question
Hi,
I was practicing Isight optimisation tool with Abacus.
Features used
1. optimization genetic algorithm
2. calculator component
3. NSGA-II - Nondominated Sorting Genetic Algorithm
I had imported the CAE file of ansys and followed the procedure available in the internet.
But I get a error which I do not understand. But I am sure that the error do not say and missing parameter in the input.
After I run the file, I get following Error for one step. And 7 such step is executed, which all contain same error message.
The message is
1. Component "Optimiyation1.Abaqus" failed execution
1.1 There was an error preparing the run. Please see abaqus_rpy output file parameter(abaqus_rpy output file parameter) for more information.
1.1.1 com.engineous.sdk.runtime.RtException: There was an error preparing the run, Please see abaqus.rpy (abaqus_rpy output file parameter) for more information.
1.1.2 at com.engineous.component.abaqus.AbaqusExecutor.execCae (AbaqusExecutor.java:1668)
1.1.3 at com.engineous.component.abaqus.AbaqusExecutor.execCae (AbaqusExecutor.java:205)
If any one has faced any such issue, please share your experience.
Hi every body
I need to export composite material unit cell from Abaqs to Isight (Motne carlo) , however the the imported output file (ODB) show only von Misses stress , and I need the output to be composite properties (E1 , E2 , E3 ---- so on), how can I solve this problem? , how I make ODB file includes material properties to be read by Isight.
thanks you
Question
I have some equations attached as a file to the question.
I want to find the variables S, delta ,V ,Vc ,Te and beta_c resulting in the smallest overall error in the equations using genetic algorithm.
The problem is I don't know what do I have to do now?!
Does it mean that I must find the minimum or maximum of these equation? How should the fitness function be defined? as a first effort I have taken all the terms to one side of the equation and put a zero in the other side. after that add the three equations together and define them as a single fitness function...
but I'm not sure about the correctness.
Hi Neda,
It would look something like this if you use the l2 norm:
min (T_inf + 8*a*S3/(3*pi*k) - Tc)^2 + ... (write here the rest)
Be aware that you can get stuck in a local minimum (a point that is the best in its neighborhood but still doesn't satisfy your equations).
Best,
Charlie
Question
If yes, could anyone provide me with some references/resources on how to compute the theoretical performance guarantee (i.e. approximation ratio) for a population-based differential evolutionary algorithm?
Yes there are, but most of them focus on the very simple optimisation problems.
such as
Question
firstly my fuzzy system is based on 5 image features dental x-ray images, consisting of 120 preapical images. features are described as below:
1-Entropy, Edge-Value, and Intensity: [30:55]
2-Local Binary Patterns - LBP: [140:160]
3-Red-Green-Blue - RGB: [82:140]
5-Patch Level Feature: [0.01:0.33]
output range: [1:5]
based on the article:
I achieved the membership function parameters of my fuzzy system (the number of my parameters to optimize were 48).
then created a cost function to optimize the values in order to minimize the Errors. but it gained a poor accuracy (about 13%) and a great number of MAE and MSE (MAE=1.27 and MSE= 2.22).
Is there a better.
Do you know a better way to optimize my system?
my programming software: MATLAB2019
Regards,
Shafagat
Question
For my research purpose and to compare the results with the results of swarm algorithm I need an evolutionary algorithm. And I consider GA as one of them.
Also, if you prefer using predefined functions in Matlab, check this link:
Question
I have to do an optimization using genetic algorithm. In this optimization "In every population, parents are chosen among the 30% individuals resulting in the smallest overall error in the fitness function." we have different selection functions in genetic algorithm such as Roulette wheel, Stochastic universal sampling, Rank-based selection and Tournament selection but it seems none of them are suitable for this case, can anyone help me with this problem?
Dear Charlie Vanaret in this optimization problem I have a fitness function and 6 variables, an individual must be a Bit string with 48 bits. it means every variable is a Bit string with eight bits. In every generation, 50 population has been used. for the initial population I have used random strings of bits, although here I have a problem too, one of the variables is dependent on the other variable in its range, I mean for instance the variable Vc range is [0,V] and I don't know how to insert this constraint to my code, and actually the main problem is what I asked before according to the sentence in the quotation mark, what kind of selection method I have to choose to select the parents for the next generation?
sincerely
Neda
Question
I have a range [0,10] that must be converted to binary representation and this range have to divide into 256 parts. and some crossover and mutation function must be applied on it, I need some guidance to find the genetic operator functions code in MATLAB or write them by myself? actually the point is that first I must learn to convert the real values in binary and vice versa
For the genetic algorithm processing, I recommend that you develop your own code by first choosing a type of crossover (number of points of crossing), taking parts of the parents vectors and merge them to generate the offspring. Once you are finished crossing all parents, add some random elements with a low percentage for mutation.
Bood luck
Question
Can we add algorithm in optimization toolbox, manually?
Like wind driven optimization algorithm or any other?