Detection of vital responses against to life in space by changes in the vocal cord & Detection of diseases caused by low gravity using sound frequencies.

Ainalyze was developed by converting phonation, cough, and breath sounds from more than 300 thousand patients into spectrogram graphics in png format by substracting Mel Frequency Cepstral Coefficients (MFCC). The sounds converted to image format are classified using Convolutional Neural Networks (CNN), one of the deep learning artificial intelligence algorithms. Again, each received sound was classified by Convolutional Neural Networks (CNN) , one of the deep learning algorithms of artificail intelligence, in a certain frequency range. By deterining the mathematical overlap ratios of the two data, we ensured that the correct result was obtained. Our goal is to use artificial intelligence assisted biosensors as a new, easy to use testing method in general clinical and lung cancer diagnosis, to manufacture devices using this logic, and accelerate the treatment process by facilitating the diagnosis of lung cancer. Ainalyze will be able to immediately create a specific scoring for lung cancer by analyzing the defined data with artificial intelligence. In this way, the control physician will be able to diagnose the disease both earlier and in a shorter time. To fulfill the purposes described above, the frequency differences are evaluated in the alveolar air using the numerical response method included in the software. The mathematical data obtained in this way are converted into reference data for arterial blood gas values using the confirmatory artificial intelligence software embedded in our server. The basis of the mathematical formula for these values is the Henderson Hasselbach equation and the equation: [(LDH) X (pCO2)] / [(HCO3) X (pO2)] << (Hgb). In addition to diagnosing 71 types of diseases, we can analyze blood values such as oxygen saturation, LDH, and glucose with 91% accuracy.

The goal is to use the hardware containing our artificial intelligence software to collect and analyze the audio data obtained before leaving the ground for our astronaut participating in the space mission to be realized and the audio data obtained at regular intervals after 24 hours in the working environment of the International Space Station. We believe that the data obtained will be important for understanding noise data and disease symptoms in the space environment. In this way, we believe that a telemedicine application can be developed that can be used in space missions and space tourism.