Intelligent Learning Systems

Intelligent (machine) learning is a subfield of artificial intelligence and it originates from the researches in the pattern recognition, the computational learning theory, and the use of statistics for the purpose of learning - based on previously available data.Extremely important is to make a distinction between machine learning and artificial intelligence - in order to understand their operation: while artificial intelligence aims not only to mimic human behavior through learning, and also some sort of abstract thinking, knowledge representation and reasoning, machine learning is only directed to create software that can learn from past experiences.Machine learning is much closer to the data mining and statistical analysis. Many even believe that it have prevailed over the classical statistics, because it relies on the accuracy of the prediction, as opposed to a pure data modeling.The machine learning techniques have gained large popularity nowadays, since many companies apply some type of data mining in order to understand the clients’ behaviour and to predict the future market trends. This edition covers different topics from machine learning, and application of pattern recognition solutions in the industry, economy, engineering etc. Also, the intelligent tutoring systems will be covered in the last section, since they will re-shape the future of the current e-learning and distance learning systems.Section 1 focuses on machine learning basics, providing machine learning overview, types of machine learning algorithms, and methods for pattern classification.Section 2 focuses on intelligent learning methods and approaches, describing evolutionary learning of concepts, neural machine learning approaches: Q-learning and complexity estimation, training with input selection and testing (TWIST) algorithm, hybrid neural network architecture for on-line learning, and resampling methods for unsupervised learning from sample data.Section 3 focuses on intelligent learning applications, describing application of machine-learning based prediction techniques in wireless networks, application of extreme learning machine in fault classification of power transformer, prediction of solar irradiation using quantum support vector machine learning algorithm, data mining in electronic commerce: benefits and challenges, and data mining with time series data in short-term stocks prediction.Section 4 focuses on human learning assisted by intelligent systems, describing application of data-mining technology on e-learning material recommendation, intelligent interaction support for e-learning, data mining for instructional design, learning and assessment, students’ access patterns in e-learning including Web 2.0 resources, and advances in artificial intelligence in modeling of student-centered VLEs.

Dr. Zoran Gacovski has earned his PhD degree at Faculty of Electrical engineering, Skopje. His research interests include Intelligent systems and Software engineering, fuzzy systems, graphical models (Petri, Neural and Bayesian networks), and IT security. He has published over 50 journal and conference papers, and he has been reviewer of renowned Journals. In his career he was awarded by Fulbright postdoctoral fellowship (2002) for research stay at Rutgers University, USA. He has also earned best-paper award at the Baltic Olympiad for Automation control (2002), US NSF grant for conducting a specific research in the field of human-computer interaction at Rutgers University, USA (2003), and DAAD grant for research stay at University of Bremen, Germany (2008). Currently, he is a professor in Computer Engineering at European University, Skopje, Macedonia.