GBT Tokenize is Developing Advanced Computational Geometry Methods

SAN DIEGO, Jan. 05, 2021 (GLOBE NEWSWIRE) -- GBT Technologies Inc. (OTC PINK: GTCH) ("GBT”, or the “Company”), announced that GBT Tokenize (“GBT/Tokenize) is developing new methods for health analysis based on its Kirlian Electrophotography research. GBT/Toeknize is developing a set of methods and algorithms to analyze imaging made by Kirlian Electrophotography.

Kirlian photography introduces a series of techniques that are based on the phenomenon known as electrical coronal discharge. Images that are produced using these techniques present a colorful so-called aura. Although not scientifically proven, some believe that these images can be interpreted to analyze health conditions. GBT/Tokenize reiterates that the claim that a medical conclusion can be reached based on analysis of the image (whether through AI or in person) has not been scientifically established. GBT/Tokenize is performing open research from a technological point of view, which cannot be considered medical research or portrayed to be as such.

It is believed by some that the Kirlian imaging process is made by placing an object on a photographic plate that is connected to a source of high-voltage current. A more modern way is using low voltage hand and head sensors to produce visual, interactive data that may represent health energy information. Kirlian imaging can produce organs energetic visualization such as graphical protuberances, halos, and discharge patterns, which can be analyzed by computer program to identify unique patterns. GBT is now developing a set of computational geometry algorithms targeted to be the base for a further AI analysis. Computational geometry is a mathematical field that involves the design, analysis and implementation of efficient algorithms for solving geometric problems. Advanced applications that typically use computational geometry methods are pattern recognition, computer vision, animation and graphics, (CAD) computer-aided design, robotics, and similar especially when require real-time speeds. We are developing a private, derived set of algorithms in order to classify the combinatorial and numerical computational geometry of Kirlian images. Each set is designed to identify, analyze and categorize images according to its parametric surfaces and curves, for example, spline curves and Bezier curves. This information will be fed to a machine learning program. Our algorithms are identifying and evaluating the image's surfaces and parts of surfaces from particular viewing angles in order to categorize and classify anomalies.