Simmakers Ltd. company

Artificial Intelligence Programming

Artificial intlligence software development projects

Artificial intelligence applications

Artificial intelligence is a branch of computer science focused on computer simulation of intelligent behavior.

Typical issues for artificial intelligence methods:

Pattern recognition

We offer next pattern recognition services:

  • Optical character recognition
  • Handwriting recognition
  • Face recognition and face detection
  • Motion detection and recognition
Image processing

Our image processing offers:

  • Image retrieval
  • Object recognition
  • Measurement of pattern
  • Image sharpening and restoration
Data mining

Data mining is primarily used today by financial, communication, retail and marketing companies. We provide data mining services that enable these organizations to determine relationships among «internal» factors such as price, staff skills or product positioning, and «external» factors such as economic indicators, competition, and customer demographics. Our solutions enable companies to determine the impact on customer satisfaction, sales, and corporate profits.

Following are the aspects in which Simmakers data mining services can contribute for your business:

Financial Data Mining

Financial Data

  • Data warehouse design & construction, based on benefits of financial data mining
  • Trading strategy development and trading rule discovery using genetic algorithms
  • Market and credit risks calculation
  • Visualization tools for financial data analysis
Telecomunication Data Mining

Telecommunication Industry

  • Data warehouse design & construction, based on benefits of telecommunication data mining
  • Multidimensional analysis of telecommunication data
  • Telecommunication data processing for marketing purposes
  • Telecommunication fraud detection
  • Telecommunication network fault isolation and prediction
  • Visualization tools for telecommunication data analysis
Retail Data Mining

Retail Industry

  • Data warehouse design & construction, based on benefits of retail data mining
  • Analysis of effectiveness of sales campaigns
  • Multidimensional analysis of customers, products, sales, region, time, etc
  • Product recommendation and items cross-referencing
  • Visualization tools for retail data analysis

Organizations Simmakers partners with

Why Clients Choose Simmakers

With Simmakers, you get a competent solution created by highly qualified specialists in  data mining, artificial inteligence, software engineering and applied mathematics.

Tasks, performed by Simmakers specialists:

We have several advantages that allow us to solve problems successfully:

  • Partnership with NVIDIA. Being partners with NVIDIA , the world’s largest producer of graphics cards and GPUs, we apply the corporation’s latest achievements in the development of IT-solutions in computer graphics, data visualization and parallelization of computations.
  • Extensive experience. Cooperating with customers from North America, Western Europe, Russia for more than a decade, our specialists have completed more than 30 complex projects on data visualization and computer simulation of physical and technological processes for various industries, including construction engineering, oil and gas extraction, metallurgy, film industry, healthcare, arts, etc.
  • Profound technological expertise. Simmakers specialists have won high recognition and international awards in various fields and are professionals in applied mathematics, IT and software development. We actively collaborate with the leading international research and development centers, such as the Massachusetts Institute of Technology (MIT), the University of California (UCLA) and the Skolkovo Institute of Science and Technology.
  • Custom-tailored service. In the development of IT solutions, we make the demands and needs of each customer as our highest priority. This approach allows us to develop trusting and mutually beneficial relations with customers resulting in beneficial effect on the efficiency of project implementation.
Case studies

Listed below are some of our featured projects.

Deformable Registration
Deformable Registration
Elementary Car Emulator
Emotion recognizer

See Full Portfolio


We apply various techniques:

Artificial neural networks

Artificial neural networks

  • Perceptrons
  • Multi-layer perceptrons
  • Radial basis networks
  • Cognitron, neocognitron
  • Hopfield networks
Artificial neural networks training algorithms

ANN training algorithms

  • Inverse propagation by gradient descent
  • Levenberg–Marquardt algorithm
  • The resilient propagation (RPROP)
  • Broyden-Fletcher-Goldfarb-Shanno method
  • МConjugate Gradient (CG)
Genetic algorithms

Genetic algorithms

  • Genetic programming
  • Evolutionary programming
  • Evolution strategy
Fuzzy logic

Fuzzy logic

  • Propositional
  • Predicate
  • Highest-order
Expert systems, hybrid intelligence systems

Expert systems, hybrid intelligence systems

  • Hybridization algorithms
  • Hybrid expert systems
  • Hybrid neurons and neural networks
  • Hybrid ANN training algorithms
Frequently Asked Questions (FAQ)

Q: What is Artificial Intelligence?

A: Artificial intelligence (AI) is the intelligence exhibited by machines or software. Also it is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable.

Q: How does Artificial Intelligence work?

A: There are many different approaches to Artificial Intelligence, none of which are either completely right or wrong. Some are obviously more suited than others in some cases, but any working alternative can be defended. Over the years, trends have emerged based on the state of mind of influencial researchers, funding opportunities as well as available computer hardware.

Over the past five decades, AI research has mostly been focusing on solving specific problems. Numerous solutions have been devised and improved to do so efficiently and reliably. This explains why the field of Artificial Intelligence is split into many branches, ranging from Pattern Recognition to Artificial Life, including Evolutionary Computation and Planning.

Q: What are the applications of AI?

A: Here are some examples.

expert systems

A «knowledge engineer» interviews experts in a certain domain and tries to embody their knowledge in a computer program for carrying out some task. How well this works depends on whether the intellectual mechanisms required for the task are within the present state of AI. When this turned out not to be so, there were many disappointing results. One of the first expert systems was MYCIN in 1974, which diagnosed bacterial infections of the blood and suggested treatments. It did better than medical students or practicing doctors, provided its limitations were observed. Namely, its ontology included bacteria, symptoms, and treatments and did not include patients, doctors, hospitals, death, recovery, and events occurring in time. Its interactions depended on a single patient being considered. Since the experts consulted by the knowledge engineers knew about patients, doctors, death, recovery, etc., it is clear that the knowledge engineers forced what the experts told them into a predetermined framework. In the present state of AI, this has to be true. The usefulness of current expert systems depends on their users having common sense.

heuristic classification

One of the most feasible kinds of expert system given the present knowledge of AI is to put some information in one of a fixed set of categories using several sources of information. An example is advising whether to accept a proposed credit card purchase. Information is available about the owner of the credit card, his record of payment and also about the item he is buying and about the establishment from which he is buying it (e.g., about whether there have been previous credit card frauds at this establishment).

speech recognition

In the 1990s, computer speech recognition reached a practical level for limited purposes. Thus United Airlines has replaced its keyboard tree for flight information by a system using speech recognition of flight numbers and city names. It is quite convenient. On the the other hand, while it is possible to instruct some computers using speech, most users have gone back to the keyboard and the mouse as still more convenient.

understanding natural language

Just getting a sequence of words into a computer is not enough. Parsing sentences is not enough either. The computer has to be provided with an understanding of the domain the text is about, and this is presently possible only for very limited domains.

computer vision

The world is composed of three-dimensional objects, but the inputs to the human eye and computers’ TV cameras are two dimensional. Some useful programs can work solely in two dimensions, but full computer vision requires partial three-dimensional information that is not just a set of two-dimensional views. At present there are only limited ways of representing three-dimensional information directly, and they are not as good as what humans evidently use.

game playing

You can buy machines that can play master level chess for a few hundred dollars. There is some AI in them, but they play well against people mainly through brute force computation—looking at hundreds of thousands of positions. To beat a world champion by brute force and known reliable heuristics requires being able to look at 200 million positions per second.

Contact our Manager for Custom Artificial Intelligence Development

Please describe your task:

Simmakers has provided competent data analysis services with a good level of service in communication, responsiveness and timeliness, in addition to the technical work and delivery.

Richard Jamieson

CEO and Co-Founder

Enelytics LLC. USA


Read other testimonials

To learn more about our Artificial Intelligence Software Development services,
please call us at +375 17 286 33 16 or use the contact form.

Project name: The development of software-studio for image processing using custom graphics filters.

Project implementation:2012.

Technologies: C#, WPF 3.5, OpenDiagram, GLSL.

Client: Spectral Lights.

Project description:

Software-studio for image processing using custom graphics filters

The project was aimed at creating image processing software using graphics shaders. A sequence of GLSL shaders was created, each with a special graphic effect, such as digital noise or image blur, on an image. This shader structure was arranged in a special “visual node” network, which permitted. Such organization enabled the construction on a tree of effects for image processing; the interactive alteration of the parameters of each effect; the visualization of the application of a built tree of effects and the respective parameter settings.

The result was the creation of GLSL code conforming to the built tree of effects. This code allows the same effect to be processed on a video card for any other image, significantly reducing the processing time and relieving the CPU while allowing for the creation of professional series of effects for the film industry, amongst other things. The user interface was implemented with WPF technology for the Windows XP OS.

Project name:Acceleration of processed images in the Spectral Studio software.

Project implementation:2010-2011.

Technologies: C#, С++, CUDA API (SDK).

Client: Spectral Lights.

Project description:

Acceleration of processed images in the Spectral Studio software


The main aim of the project was to accelerate the process of image rendering in the Spectral Studio © software, aimed at creating photorealistic images of objects from 3d models.


To facilitate this, a GPU-version of the “Aurora Renderer” module was created, including a new CUDA implementation of ray-tracer, using a specially created structure called BVH (Bounding Volume Hierarchy) to optimize and accelerate operation.

Once all the stages of the “Aurora Renderer” module were implemented, a tenfold acceleration of image creation on video cards was achieved.

Project name:Software for virtual human anatomy

Project implementation: 2010-2012.

Technologies: C++, OpenGL, C#, WPF 3.5, COM, TAO Framework, GLSL.

Client:QuintSysteme GmbH (Austria).

Project description:

Software for virtual human anatomy


The main aim of the project was to create special software to visualize inner parts of a human body; the lymphatic, blood-vascular, and excitatory systems; other anatomic components.


The software, developed with COM-technology, was interfaced with the software which controlled the medical equipment, to display both the current state of a patient and operational status of the equipment. The project included the development of special animation modes to simulate the operation of measuring equipment, to display electromagnetic field dynamics as well as the simulation of the moving parts of the equipment.

Highlighting, flashing and geometry and texture alterations were implemented to assist the diagnostic visualization of organs, with the help of shader graphics applications.

Project name: Deformable Registration Algorithm Implementation

Project implementation: 2010.

Tags: deformable registration, MATLAB, image deform, grid, mesh.

Technologies: MATLAB.

Client: Tomographix IP Ltd. (Canada)


Medical image matching – registration algorithms that deforms one image in a non-rigid [non-linear, elastic] manner to another. Assistance with the implementation of a particular algorithm from the theory in a specific academic – scientific paper.

Project name: Thermosim

Project implementation: 2003-2006

Technologies: C++, C#, .NET Framework: WinForms, Windows Presentation Foundation; Managed DirectX, OpenCascade, FORTRAN, XML, MS SQL.

Sector: Manufacturing


Software package supports 3D graphics for visualization physical fields in point of time. There are also many possibilities for creating of various diagrams that allow to carry out process analysis and optimization.


Technical features:

• 3D-modeling of temperature, hardness, stress and deformation fields

• Taking into account phase changes and stress relaxations

• Prediction of cracks forming

• Integrated database of steel properties

• Ability to use experimental data for training of neural networks

Project name: Ecoview

Project implementation: 2007-2010

Technologies: C++, C#, FORTRAN, .NET Framework: WinForms, Windows Presentation Foundation, Managed DirectX, OpenGL, CUDA, XML, ADO .Net.
Sector: Environment


EcoView software will provide tools for every phase of contaminants transport simulations, pollution impact assessment and pollution risk analyzing. In addition, EcoView will consider the modeling of heat, water transport in the soil etc., runoff processes, contaminants transport in groundwater and to surface water systems (rivers, lakes, bays).

Project name: Elementary Car Emulator

Project implementation: 2009

Technologies: C++, OpenGL

Client: University of East Anglia (UK)

Sector: Education


The user should be provided with the scene consisting of simple roads and buildings. User controls car movement – speed and direction. Several camera positions should exist: car driver’s view, behind car, above car and other user controlled positions. Scene should consists several bot-cars with analytical logic – collision control, traffic rules control, championship control.

Project name: Emotion recognizer

Project implementation: 2010.

Tags: face recognition, image processing, emotion detection.

Technologies: MATLAB

Client: University of East Anglia (UK)


In the program implemented:

  • Graphical data reading, image processing, face detection on the complex background
  • Principal component analysis
  • Emotion recognition using classifier based on Fisher linear discriminant analysis