$GTCH their joint venture, started Phase I in the
Post# of 43922
(Total Views: 142)
Posted On: 12/01/2020 1:05:37 PM
$GTCH their joint venture, started Phase I in the Kirlian Electrophotography imaging technique, potentially aimed for inclusion within its qTerm device. Kirlian photography is a series of techniques that are based on the phenomenon known as electrical coronal discharge. Images that are taken using these techniques present a colorful so-called aura, which can be interpreted in a variety of ways.
The open research is focused on the efforts combining Kirlian imaging with the use of machine learning technology to possibly detect early disease symptoms. GBT/Tokenize is conducting experiments with a few advanced algorithms, one of them is a private derivative of the Genetic algorithm. The genetic algorithm is a method for solving both constrained and unconstrained optimization problems that are based on natural selection, the process that drives biological evolution. The algorithm is planned to find pattern similarities in Kirlian images in living tissues in order to categorize potential health related issues. Kirlian imaging produces typical features such as graphical protuberances, halos, and discharge patterns, which can be analyzed by an AI computer program as unique patterns, and categorized as possible criteria for early symptoms identification. GBT/Tokenize is conducting experiments with advanced algorithms and methods to analyze energy fields generated by living organs at set periods. These image's auras will be graphically analyzed to determine patterns that are associated with possible health related symptoms. GBT/Tokenize plans to develop neural network based pattern recognition technology to detect-and-associate unique patterns with related, possible health issues. The research is planned to be conducted over a period of one year and based on its results the company will evaluate the feasibility of implementation of such techniques within its qTerm human vitals product in order to provide further health information for the user's benefit.
"We are going to look deeper into Kirilian electrophotography science, trying to identify the possibility of detecting early disease symptoms. Kirlian images of a living tissue during various intervals may exhibit some similarities. If we could graphically analyze these images using machine learning technology, reaching some consistent conclusions, then we may find a way to find possible early health issue identification" stated Danny Rittman, GBT’s CTO. "We intend to analyze and measure Kirilian images to find unique patterns that may be associated with early symptoms. We will look for full and partial similarities, repetitions, or atypical auras patterns. We will be using AI computing power to detect dynamic images changes as each image will be digitized using high resolution scanning. Here the power of huge data analysis will be extremely beneficial. We plan to implement interactive algorithms to analyze on-the-fly out-of-boundaries patterns to get a comparative representation between the images. The challenging part will be to associate the human body's various radiations graphical representation, with health related issues. For this purpose, we plan to use our AI, vast data analysis capabilities, trying to assemble a reliable algorithm to create an associative table that will relate patterns to a possible onset disease. Upon reaching conclusions we will evaluate the potential implementation of this technology within our qTerm device to further advice users about their health” continued Dr. Rittman.
The open research is focused on the efforts combining Kirlian imaging with the use of machine learning technology to possibly detect early disease symptoms. GBT/Tokenize is conducting experiments with a few advanced algorithms, one of them is a private derivative of the Genetic algorithm. The genetic algorithm is a method for solving both constrained and unconstrained optimization problems that are based on natural selection, the process that drives biological evolution. The algorithm is planned to find pattern similarities in Kirlian images in living tissues in order to categorize potential health related issues. Kirlian imaging produces typical features such as graphical protuberances, halos, and discharge patterns, which can be analyzed by an AI computer program as unique patterns, and categorized as possible criteria for early symptoms identification. GBT/Tokenize is conducting experiments with advanced algorithms and methods to analyze energy fields generated by living organs at set periods. These image's auras will be graphically analyzed to determine patterns that are associated with possible health related symptoms. GBT/Tokenize plans to develop neural network based pattern recognition technology to detect-and-associate unique patterns with related, possible health issues. The research is planned to be conducted over a period of one year and based on its results the company will evaluate the feasibility of implementation of such techniques within its qTerm human vitals product in order to provide further health information for the user's benefit.
"We are going to look deeper into Kirilian electrophotography science, trying to identify the possibility of detecting early disease symptoms. Kirlian images of a living tissue during various intervals may exhibit some similarities. If we could graphically analyze these images using machine learning technology, reaching some consistent conclusions, then we may find a way to find possible early health issue identification" stated Danny Rittman, GBT’s CTO. "We intend to analyze and measure Kirilian images to find unique patterns that may be associated with early symptoms. We will look for full and partial similarities, repetitions, or atypical auras patterns. We will be using AI computing power to detect dynamic images changes as each image will be digitized using high resolution scanning. Here the power of huge data analysis will be extremely beneficial. We plan to implement interactive algorithms to analyze on-the-fly out-of-boundaries patterns to get a comparative representation between the images. The challenging part will be to associate the human body's various radiations graphical representation, with health related issues. For this purpose, we plan to use our AI, vast data analysis capabilities, trying to assemble a reliable algorithm to create an associative table that will relate patterns to a possible onset disease. Upon reaching conclusions we will evaluate the potential implementation of this technology within our qTerm device to further advice users about their health” continued Dr. Rittman.
(0)
(0)