Human Computer Interaction and Its Impact on e-Learning in Engineering Education

One of the primary aims in human-computer interaction research is to develop an ability to recognize affective state of the user. Such an ability is indispensable to have a more human-like nature in human-computer interaction. However, the researches in this direction are not mature and intensive efforts have only been witnessed recently. For human beings, recognition of affective state of a person is a trivial task, which can be accomplished by computer through integration of methods from tremendously diverse research fields such as image processing, speech processing, artificial intelligence, cognitive science and psychology. This work envisages the possibility of integration of recently developed methods such as artificial neural networks, fuzzy logic, genetic algorithm and artificial intelligence in processing the robust parameters which will be determined from visual and verbal information to achieve an affective human-computer interaction. Such ability of computers will have a great impact in e-learning processes for engineering education. The paper firstly considers how human computer interaction can play a critical role to have more natural e-learning applications in engineering education and then necessary progresses of such a development will be introduced. The anticipated steps of an adaptive and interactive e-learning project and inclusion of humancomputer interaction into a student model will be discussed. 1 e-Learning and biometric signal processing The primary ability of new generation computers in human computer interaction will be to recognize the affective state of users, such as nervousness, fear, happiness, concentration, eager etc., using verbal and nonverbal information [1,2]. This ability is the first step to have a more humanlike interaction between the users and computers. These improvements in human computer interaction will enhance e-learning applications leading to a more natural and hence effective environment. An intelligent educational system constitutes fundamentally five interrelated entities. These are student model, pedagogical model, communication model, information model and expert model [3]. For the accomplishment of more natural human computer interaction and its usage in intelligent educational systems, it is required to include biometric information into the student model as a new mode. The improvement in the pedagogical model will also be achieved, parallel to the student model, in order to approach a more natural interaction. A project with these objectives should cover two related consequent fields. The first is to determine the technical obstacles and necessary measures to have a human computer interaction with a more natural, adaptive and affective human-human-like interaction. The second field of problem is to provide virtual educational environments which enable a dialog between student and computer, as like as traditional teacherstudent dialog does, and technical obstacles and necessary action to deal with to achieve such environments. In this project an attempt to define new and robust biometric parameters will be undertaken. The integration of the proposed parameters will also be investigated in the sense of how to achieve a successful determination of affective state of user. Integration of artificial intelligence methods is investigated to fuse the parameters from two information modes. The possible achievement on these subjects will pave the way to efficient use of human computer interaction in e-learning applications which will be widespread in approaching information society.