Arwin Datumaya Wahyudi Sumari

Brain-Inspired Knowledge-Growing System: Towards a True Cognitive Agent

Knowledge growing is one of intelligence characteristics possessed by human brain. In this paper we review some fundamental theories that are appropriate for emulating this kind of intelligence in order to develop an intelligent system in Artificial Intelligence (AI) field, called brain-inspired KnowledgeGrowing System (KGS). The development of this system is approached from various fields, namely psychological, mathematical, social, and electrical engineering and informatics fields. Based on the review results, we have built this system along with mechanism for growing the knowledge that consists of a model of Human Inference System (HIS), Sense-InferenceDecide and Act (SIDA) cycle, and the mathematical formulation for growing the knowledge called Observation Multi-time Arwin– Adang–Aciek–Sembiring (OMA3S) information-inferencing fusion method. In conclusion, brain-inspired KGS is a cognitive agent which is equipped with knowledge growing mechanism as its intelligent characteristic. Keywords-Artificial Intelligence;Brain-Inspired KGS;Cognitive Agent;Inferencing;Intelligent System; Knowledge-Growing; OMA3S

Implementation Knowledge Growing System Algorithm using VHDL

Knowledge Growing System (KGS) is novel perspectives in Artificial Intelligence which emulate the way of human brain develop new knowledge from information which obtained from its sensory organs. Information Fusion is a process to combine a set of information from several observation which come from difference sources, to generate single information as a conclusion. In this paper we propose how to design VHDL program to execute KGSs Information Fusion Algorithm. Furthermore, the VHDL Program of Information Fusion will became the basis of designing a chip of processor call Cognitive Processor.

Cogitive Artificial Intelligence: The fusion of Artificial Intelligence and information fusion

Cognitive Artificial Intelligence (CAI) is a new perspective in Artificial Intelligence (AI), which brings a new concept of intelligence that is not only limited in the emulation of behavior and ways of how human thinks but also to explore how humans brain grows its knowledge. The development of CAI was started by devising new method that is able to mimick the humans brain ability to perform Knowledge Growing (KG). Based on our long and thorough observation, the knowledge development in human brain is carried out by fusing the information obtained by human sensory organs from the environment. New knowledge is obtained as the time passes by fusing new information with the knowledge already stored in the brains memory. In this paper we present a method which emulates the mechanism of KG within human brain called A3S (Arwin-Adang-Aciek-Sembiring). The system which uses this method is called as Knowledge Growing System (KGS). We also present an example with real-life data to show the work of A3S in performing KG.

Obtaining Knowledge of Genes’ Behavior in Genetic Regulatory System by Utilizing Multiagent Collaborative Computation

All living organisms are built from millions of cells that work together in a very systematic manner. The trait of each organism is determined by the cells. The function of a living cell is performed by a sequence of well-coordinated activities by a large number of genes. The gene itself is a sequence of Deoxyribonucleic Acid (DNA). The products of a cell are made by the proteins synthesized in accordance with the instructions contained in the DNA (Willett, 2006) since it encodes all the information required for the development and functioning of an organism (Emmert-Streib & Dehmer, 2008). The expression of a gene is a biological process which a DNA sequence is translated to become a protein. The protein is an important molecule for determining the structure, mortality, metabolism, signaling, reproduction, etc. of a cell. Some genes influence how other gene or genes are expressed. Modifying genes may change the affect of other genes. The expression of a gene or genes is regulated by a mechanism called Genetic Regulatory System (GRS). The GRS’ task is to control whether genes are active or inhibit. Of ways for understanding and analyzing the behavior of GRS is by using microarray data. Microarray is sets of miniaturized reaction areas that may also be used to test the binding of DNA fragment (Reece, 2004). and it exploits the preferential binding of complementary nucleic acid sequences to simultaneously measure expression levels of thousands of genes (Dill, Liu, & Grodzinski, 2009). By having knowledge regarding the influence of a gene or genes to the others in microarray data, we can make estimations of the genes behavior in GRS in order to obtain better products in the future. According to (Ewens & Grant, 2005), there are three basic questions that can be answered by using microarray data: a. What genes are expressed in a given sample? b. Which genes are differentially expressed between different samples? c. How can one find different classes, or clusters, of genes which are expressed in a correlated fashion across a set of samples? How can one find different classes of samples based on their gene expression behavior?

A new information-inferencing fusion method for intelligent agents

In this paper we address an approach on how to emulate humans capability in obtaining comprehensive inferencing after observing a phenomenon in its environment. Before making a decision or taking an action regarding a situation that is occurring or probably occurs in the future, human observes the situation dynamics by using his/her sensing organs and communicating with other people. Information collected by the sensing organs is delivered to the brain to be fused to obtain inferencing. Comprehensive inferencing will be obtained after the previous inferencing is fused with new inferencing obtained from other sources. This humans capability will bring a benefit to humankind if it can be emulated and applied to intelligent agents. For this purpose, we propose a new information-inferencing fusion method called A3S (Arwin-Adang-Aciek-Sembiring) as an emulation of human information-inferencing fusion mechanism.

Strategic decision making based on A3S information-inferencing fusion method

Making a strategic decision is one of important matters especially in a military organization such as Indonesian Air Force (IDAF). There are many cases which need an accurate and quick decision in the IDAF such as selecting the most representative weaponry systems to replace the old ones. In this paper we propose the use of A3S information-inferencing fusion method for selecting a new light transport aircraft from four prospective aircraft candidates. The result of the selection will be used by the decision maker to select the best light transport aircraft candidate as the new weaponry system. In this paper we use original data from four aircraft candidates. After computed by using A3S method, we found that aircraft “A” is the most probable candidate to replace the old aircraft “X” with Degree of Certainty (DoC) 27,8%.

The application of knowledge growing system for inferring the behavior of genes interaction

Knowledge Growing System (KGS) is a novel perspective in Artificial Intelligence (AI) which is aimed to emulate how the human brain obtains new knowledge from information delivered by human sensory organs. The new knowledge is then used as the basis for making an estimation in the future of the phenomenon being observed as the basis for the most appropriate decision or action that will be decided or taken. In this paper we address the application of KGS to infer the behavior of genes interaction in Genetic Regulatory System (GRS) in order to estimate their behavior in the subsequent interaction time. For this purpose we model the genes as multi-agent that performs collaborative computations in Multiagent Collaborative Computation (MCC) paradigm. In order to show how KGS works in MCC framework, we use yeast genes-interaction values as the case study.

The performance of intelligent and unintelligent approaches on aircraft identification tasks

This paper is a report of our research progress in the area of pattern recognition in endeavouring finding a novel method for aircraft identification. In this paper we address the performance comparison between intelligent and unintelligent approaches in performing aircraft identification tasks in a generic system called Generic Aircraft Identification System (G-AIS) especially in accessing the knowledge stored in database. For this purpose, we select two types of neural networks namely, Back Propagation Network (BPN) for the supervised exemplar and Adaptive Resonance Theory (ART) for the unsupervised one for intelligent identification approach. For unintelligent approach we select standard approach in database technology namely linked list. As for previous research, we use two kinds of input namely aircraft Radar Cross Section (RCS) and average speed. Their performance will be validated by using already-learnt and never-learnt patterns.