The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The background of this paper is the learners' expression recognition in E-learning. In the paper, the method of the face detection based on the adaboost algorithm and a set of haar wavelet like features. To improve the performance of the detectors, the face-contour is combined with the adaboost. The experimental results demonstrate that it can find the position of the detected faces of learners in...
Aiming at the problem of different learning emotions in the integrated emotion model of the emotion recognition interactive E-learning system, this paper proposed an improved SVM classification algorithm to classify the learning emotions, optimized the parameters of the SVM classifier with Genetic Algorithm, and applied it to the emotion classification of E-learning system. It has achieved good results...
This paper is based on the background of learners' expression recognition in emotion recognition interactive E-Learning. This paper aims at time-consuming of training samples and weights degradation two problems of traditional AdaBoost algorithm, proposes a decile eigenvalue AdaBoost algorithm and joins FPR (False Positive Rate) in this algorithm. The experiments use improved AdaBoost algorithm in...
Case-based reasoning is applied to teaching process in order to make students learn well on the basis of previous teaching experience. Through the detailed introduction of implementation details of case-based reasoning: Similar case definition and search, case adjustment and the addition of new cases, this paper introduces a way that cannot only carry out uncertainty information reasoning, but also...
In order to accurately build the learner's learning style in E-Learning, according to the needs and preferences to provide personalized learning materials and harmonious human-computer interaction environment. This paper combines Felder-Silverman learning style with support vector machine technology, and use machine learning technologies for learners to build dynamic learning style. Through the analysis...
This paper presents a new method of the Emotion Recognition Model using the BP Neural Network, in order that E-Learning system simulates the real teaching situation better. As result of the experiment, the model shows a high rate of recognition and better real-time performance.
It is an important direction increasing emotional recognition in the network system. This paper uses the improved Adaboost algorithm based on front-end color optimization to detect face and locate eye and mouth positions, adopts the deformable template matching method to extract eye spacing and uses the method based on lip color model to extract mouth radian. These methods have good test results....
The shortages of missing the emotion and the affective communication in online psychological counseling are analyzed. The agent as the core in the new system can recognize the visitor's emotion and make a dynamic treat. The intelligent psychological counseling system can obtain the information of visitor's emotion and treating effect which is got by the intelligent agent, and then it can propose the...
The traditional E-learning System is to achieve self-learning function of distance. But in the learning process, the learner's emotional information can not be extracted effectively use that the study results is not ideal. Teaching system in the network to increase emotional recognition, it is a personalized Web-based Education is an important direction for the development. This paper using Adaboost...
In order to build the intelligent tutoring system, according to the basic theory of emotional psychology, the emotion mathematical model and the personality-moods-emotions multilayer model are used in this paper. By analyzing facial emotions, body emotions of the learner and the difficulty level of knowledge, we use the advantage of Credal networks to deal with uncertainty and ambiguity of data and...
The traditional teaching of intelligent network system does not have the function of emotion teaching, so the paper has put forward an idea to obtain the chief facial features to analyze learners' emotion. This paper bases the color front-optimized improved Adaboost face detection algorithm to detect human face, uses the best segmentation threshold value to obtain the eyelid spacing and the difference...
Against the defects of the traditional intelligent network tutoring system in the emotion of teaching, the paper presents a new intelligent tutoring system structure which based on emotional cognition model, and solved the uncertainty reasoning problems within the process of emotional teaching effectively through the inference engine which based on Bayesian network. The simulation results show that...
The traditional intelligence network tutoring system can not be implemented affective tutoring. This paper proposed that it can obtain the chief facial features to analyze learners' emotion, through the face detection and location under the web environment. It is based on the skin module to locate a human face to obtain the area of the face and it is based on the apriori knowledge and the best segmentation...
In the "current" statistical model, the maximum acceleration of a maneuvering target is usually assumed to be a constant, which will result in a big estimation error for target state if the target maneuvering happens. To solve this problem, an improved algorithm of maneuvering target tracking is proposed in the paper by using the adaptive relationship between maneuvering acceleration and...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.