CURRENT RESEARCH IN MACHINE LEARNING

by

CURRENT RESEARCH IN MACHINE LEARNING FROM BEO-GRAMS

Zrimec T., Kononenko I., Prihavec B.

University of Ljubljana, Faculty of Computer and Information Science

Extended Abstract

 

We present the ongoing studies with the computer recording and visualisation of the Biological Emission and Optical Radiation using the Gas Discharge Visualisation (GDV) technique. BEO GDV technology provides possibly useful information about the biophysical or psychical state of an object or a patient in a form of BEO- grams. The problem is how to interpret these BEO-grams (processed GDV images) and reveal the detected information in order to make use of it. We try to alleviate this problem by using machine learning technology which can transform training data into knowledge. Machine learning has shown to be successful on classification and prediction tasks in many real domains. Machine learning technology enables induction of general descriptions of set of preclassified examples and applying that descriptions to new data. In our research we are experimenting with different machine learning algorithms: Assistant-R, Assistant-I, (Cestnik et al., 1987), the naive Bayesian classifier and C5, that is an improved version of C4.5 (Quinlan, 1986).

Current studies with the Crown-TV

In our study we have developed, for practical reasons (performing experiments on different machines), a new piece of software that enables use of the Crown-TV with built-in video-input. With this program we have speeded up and improved the process of image acquisition.

Image analysis requires to formulate and describe visual information, such as what type of image features we can extract from the images, what properties those features are expected to have, and how they are related to each other. We use the GDV Analysis software developed by Korotkov’s team and provided together with the Crown-TV equipment to analyse BEO-grams.

Currently we are performing several studies with the Crown-TV:

  • Diagnosis: We are trying to discover the relation between the human BEO-grams and the diagnosis determined by an extrasense therapist. The patient’s GDV images were recorded on his/her first visit to the physician specialist. The set of data from different patients with obtained image features and the diagnoses were used as input to the machine learning algorithm. Automatically derived diagnostic rules will be verified on separate ‘test’ cases.
  • Magic bowls: We are measuring the effect of glass bowls, coded with a certain information by Vili Poznik from Celje, Slovenia, on the human aura and on the water. We are performing the experiment in a group of 30 people. Current results show the significant effect of holding the bowl in a hand for few minutes.
  • Color T-shirts: We are measuring the effect of color T-Shirts, developed by dr. Tom Chalko from Melbourne, on the human aura. Current results show the significant effect of wearing the shirt for only few minutes.
  • Pyramids: We are measuring the effect of pyramids on the human aura and on the water. Current results show the significant effect of the pyramid that is positioned near the person.
  • Water drops: We are trying to distinguish different kinds of water: ordinary tap water, water from various springs, water charged by a healer and water charged with various vibrations.
  • Natural energy source: We are measuring the effect of a natural energy source in Tunjice village near Kamnik in Slovenia on the human aura. Current results show the significant effect of walking near the natural energy sources for half an hour.
  • Double coronas: We already recorded several persons that have on at least one finger obvious double corona and the recordings were repeatable. Besides, by recording coronas of some hundreds of persons we noticed that occasionally there appears a slight tendency of double corona (which however could be ignored as noise). There is no physical explanation for this phenomenon. We talked to one expert in gas discharge, and besides being confused he said that there should be some carrier of the charge on that destination from the finger. Our current hypothesis is that the Kirlian camera is able to record only the first-level eteric body while the others are too subtle. Only in special cases, when a person have a special state of mind with emphasis on mental or emotional body, the camera is able to record this. Indeed, from our experience as well as from the experience of some other researchers from Russia, Finland, and Canada, it seems that this effect shows one of the following. The person:
  • is under stress,
  • has some psychic problems,
  • took drugs or drunk alcohol or even inhaled bensin,
  • has very disordered health state,
  • is in some other way in disharmony (such as very mentaly oriented person),
  • is spiritualy developed and is able to amplify other etheric levels.

One of our colleagues always had normal (single) coronas. Once he recorded double coronas on his fingers after one short treatment with color essences. After an hour the double corona disappeared and additional treatments with essences didn’t show this effect anymore.

  • Recording coronas of apples: We are trying to determine, whether Kirlian camera can record any useful information by recording coronas of apples. We decided to record the coronas of peels that were cut off from apples in a standardized way (four circular peels with diameter of 18mm, cut off from equatorial part of the apple skin and all equally oriented). We used four sorts of apples of two different ages (one year difference). The central parts of coronas were manuallly deleted in order to adapt the records for the available GDV Analysis software. We tried to solve three different problems: classification of apples according to sort (four classes, 40 training examples of each class), according to age (two classes, 40 examples of each class), and according to the sun/shadow part of apple (two classes, 32 examples of each class). The training data was used with different learning algorithms. The average information score shows that parameters contain useful information for the first two problems while for the problem of separating sun/shadow sides of the apple there is practically no useful information. Among the three classifiers the naive Bayesian classifier achieves the best results.

Results

  • The preliminary results show that machine learning algorithms can be used to detect whether the GDV records, the BEO-grams, described with a set of parameters, contain any useful information or it is only noise. In the case of apples it was clearly demonstrated, that for the two problems (determining the sort and the age of apples) the parameters that describe coronas of apple peels contain useful information while for the sun/shadow problem the parameters are not better than noise.

2000 from IUMAB Archive

Leave a Comment