No abstract

No abstract

When students are performing bad in their academics or sports activities, there are underlying causes as to why they are unable to concentrate during class and training. This paper describes the method used to obtain, identify and classify emotions from EEG signals captured from students. As the focus on this paper is on military cadets’ performance, the signals are acquired during classes and military training. The acquired signals are pre-processed using artifact removal techniques before sent for feature extraction and finally signals classification based on the valence-arousal emotion model system. The output of the classification will be able to determine if the students are having positive or negative emotions during class thus effecting their concentration level. This paper analyses the current available methods on artifact removals, feature extractions and the training model for the signal classification. Each method is analyzed in accordance to their accuracy, adaptability and the method that results in the least amount of lost data.

Over the past years, finger vein identification has gaining increasing attention in biometrics. It has many advantages as compared to other biometrics such as living-body identification, difficult to counterfeit because it resides underneath the finger skin and noninvasiveness. Finger vein feature extraction plays an important role in finger vein identification. The performance of finger vein identification is highly depending on the meaningful extracted features from feature extraction process. However, most of the works focus on how to extract the individual features and not presenting the individual characteristic of finger vein patterns with systematic representation. This paper proposed an improved scheme of finger vein feature extraction method by adopting discretization method. The extracted features will be represented systematically way in order to make classification task easier and increase the identification accuracy rate. The experimental result shows that the accuracy rate of identification of the proposed framework using Discretization is above 98.0%.

No abstract