No abstract

Disable persons are facing a lot of problems in daily life activities. They need some help from others to fulfil their needs every day. To avoid this condition modern technology help such persons to overcome the problem in a natural way like bio signal based-human-computer interaction. In this paper, we focused to study the performance of male subjects compared with female subjects to analyze the performance to design Electrooculographgy-based HCI using periodogram and neural network. Five male subjects and five female subjects are involved in this experiment. From the experimental analysis, we identified that male performance was maximum compared to female performance. From this paper, we analyzed that subject S4 from male subjects and subject S10 from female subjects performance was marginally high compared with other subjects performance took part in this experiment. From the classification accuracy, we conclude that male subject performance was encouraged with 93.67 % and 92.28% for female subjects. The offline test was conducted in the indoor environment to identify the tasks to confirm the performance of individual subjects. From the offline analysis, we conclude that subject S4 performance was high compared to other subjects take part in this paper. Subject S4 took less time to perform the task as per the protocol. Through this paper, we confirm that scheming HCI is achievable. INDEX TERMS Electrooculography, periodogram, human-computer interface, probabilistic neural network.

The aim of this article is to design an expert system for medical image diagnosis. We propose a method based on association rule mining combined with classification technique to enhance the diagnosis of medical images. This system classifies the images into two categories namely benign and malignant. In the proposed work, association rules are extracted for the selected features using an algorithm called AprioriTidImage, which is an improved version of Apriori algorithm. Then, a new associative classifier CLASS_Hiconst (CLassifier based on ASSociation rules with High Confidence and Support) is modeled and used to diagnose the medical images. The performance of our approach is compared with two different classifiers Fuzzy-SVM and multilayer back propagation neural network (MLPNN) in terms of classifier efficiency with sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. The experimental result shows 96% accuracy, 97% sensitivity, and 96% specificity and proves that association rule based classifier is a powerful tool in assisting the diagnosing process.

No abstract

No abstract