DNA encrypted in algorithms to expand cognitive abilities | Gdańsk University of Technology

Strengthening human intelligence and expanding human cognitive abilities is a mission that has been carried out for 30 years by Prof. Edward Szczerbicki, a world expert in the field of knowledge engineering and artificial intelligence. The concept of decisional DNA was developed 15 years ago with a team of scientists, i.a. from the Faculty of Management and Economics of Gdańsk University of Technology and the Australian University in Newcastle. The concept and its practical applications have been presented so far in over 300 scientific articles, and we owe its development, among others, to Prof. Cesar Sanin from the University of Newcastle, Prof. Haoxi Zhang from the University of Information Technology in Chengdu (China), Prof. Syed Imran Shafiq of the Muslim University of Aligarh (India) and Dr. Carlos Toro from the Vicomtech Research Institute (Spain).

–  Decisional DNA is a metaphor. It's a bio-inspired way of knowledge management. It is an attempt to recreate in artificial systems what natural DNA does in an amazingly perfect and unattainable way - says Prof. Edward Szczerbicki.

An "artificial" doctor with specialist knowledge

Prof. Szczerbicki focuses primarily on the use of decisional DNA in medicine. Dr. Carlos Toro, associated with the University of the Basque Country and the Spanish research center Vicomtech Research Institute, largely contributed to the conceptual scope and application of this theory in this discipline.

–  Many people with Alzheimer's disease could be effectively helped if they had been diagnosed earlier. In Spain, we conducted a study on a group of 350 patients. It turned out that an algorithm that collects data such as age, lifestyle, medical test results and analyzes them according to the concept of the decisional DNA can detect a disease earlier than a doctor. There are many areas of medicine in which artificial intelligence is more effective than humans - says Prof. Edward Szczerbicki.

Human activity recognition sensors are another example. They help, among others, in the daily observation of the elderly in hospitals and nursing homes. The team of Prof. Szczerbicki proposed a new tool based on the use of experience embedded in convolutional neural networks. Its effectiveness is much greater than that of the existing solutions. The results were published in a scientific article "A novel IoT-perceptive human activity recognition (HAR) approach using multihead convolutional attention" at IEEE Internet of Things Journal.

Matrix, in other words, in 30 years we will be hybrids

In the near future, the development of the Internet of Things and subsequent steps to improve artificial intelligence are to make collecting information by objects and applications not only a common phenomenon, but also will reach an unprecedented scale. This is a challenge to be faced by the decisional DNA. It is all about concentrating this knowledge in the most effective tool possible. This can be compared to the "Matrix" trilogy, in which the protagonist learns martial arts by connecting to a special machine that installs new skills in his brain like programs on a hard disk.

–  We are able to collect knowledge, formalize it into sets and bases, which may consist of the so-called SOEKS - Set of Experience Knowledge Structure, i.e. a set of experiences from a given situation. We proposed a new tool to solve the traveling salesman problem, i.e. a typical logistics problem in the area of operational research. SOEKS absorbs past experiences from all experiments, regardless of whether it is a good or bad experience, says Prof. Edward Szczerbicki.

AI-based decision support can be used in almost every area of life. The aforementioned traveling salesman problem has been described in a scientific article titled "Evolutionary algorithm and decisional DNA for multiple traveling salesman problem” in the pages of the "Neurocomputing” journal, whereas the concept of decisional DNA has been implemented in over 20 research projects around the world. Thanks to the concept, it was possible to indicate the optimal locations for geothermal installations in Australia, the optimal time for servicing cars and machines in Spain, or to facilitate decisions on granting installment and investment loans for the banking sector in Poland.

"Experience is the only source of knowledge"

What is decisional DNA then? It is an algorithm that enables making optimal decisions based on experience. It is drawn from the past as well as from the research and achievements of scientists and experts. Additionally, there are the immeasurable resources of the Internet and data from many sensors that, thanks to the Internet of Things, will record billions of parameters - from the temperature of the water in the ocean, through the heart rate during an interview, to the wear rate of oilfield drills. As Albert Einstein said, "the only source of knowledge is experience," the "only” challenge is  to skillfully use millions of data at our disposal.

–  Natural intelligence is the ability to act appropriately in a new situation. We want to support it through past experiences gathered by other people and things. We can already see the applications of the decisional DNA in many areas, however the possibilities are endless. As the slogan often quoted in the scientific world says: “if the only tool you have is a hammer, you tend to see every problem as a nail" - says Prof. Szczerbicki.

Smart software to make dreams come true

Currently Prof. Szczerbicki and his team are working on an application that helps to achieve one’s goals and dreams. For example, a person who wants to study biochemical engineering in Australia or the United States in three years, while working during their studies and staying there with their family, will receive a personalized action plan proposed by the decisional DNA thanks to the application.

–  The application is based on a questionnaire completed by the user, the life experiences of its community and the changing circumstances of life. It is, in a sense, an interactive intelligent coach that will advise, motivate and help to get closer to the aim, all of that in real time - explains Prof. Szczerbicki.