The educational concepts upholding the theory of brain dominance have been developed for more than 30 years. Some academicians developed a series of syllabus to exploit the brain capability of students by training their weaker hemisphere of the brain. Prior to training the weaker side of the brain with the developed syllabus, the brain dominance of the student shall be determined. All the current methods used to determine brain dominance are questionnaire-based assessments. There is a possibility that questionnaire biases could exist and lead to inaccurate results. In this research, we introduce a deep-learning method to classify brain dominance based on electroencephalogram (EEG) signal that reflects the bio-information of the brain. In this paper, we employ a series of EEG signal processing techniques and a state-of-the-art deep learning neural network namely Metric Learning Based Convolutional Neural Network (MLBCNN) to determine brain dominance. We prove that the brain dominance theory is valid and it can be determined by applying machine learning from the EEG signals. We also present the results that show the MLBCNN system can give the best performance as compared to the other benchmark neural network models of which its classification accuracy is 97.44%. Hence, this proposed method can contribute to the education field by providing a system to discover students' brain dominance and keep track of their brain training progress. In this way, the potential and capability of their brain can be fully unleashed.
Quick Response (QR) code is commonly utilized in this era to serve multiple purposes. In order to uplift the data size of QR code, higher versions of QR code are introduced for greater data size. Nonetheless, the current QR code has met the bottleneck of data size. The latest version of QR code (version 40) now can only encode up to 4 kilobytes of data. Besides, QR code version 40 is unable to be decoded easily due to the high layout density. Hence, this research’s objective is to develop a Multi-color Code which involves multiple colors to uplift the data size. Similar to the QR Code, the Multi-color Code (McC) also consists of the features of auto rotation and error correction. The outcome of the research is the developed McC can achieve up to 10Kb. Besides, McC is capable to encode image file for offline identification. The results shows that the auto rotation feature, Reed-Solomon error correction algorithm, developed Lanczos-8 interpolation method and adaptive piecewise transformed normalization contribute in yielding 100% decoding accuracy.
This paper presents the development of augmented reality (AR) based brain memory training to improve the memorizing capability of the student. The AR visual memory training application is built on top of the mobile phone by utilizing the Unity and Vuforia platform. The developed visual memory test is a flipping card test that can measure a person’s memory capability to retain visual images and spatial perception in the mind. In this study, it is aimed to prove that AR technology is suitable to be employed in the education field. The results are justified based on the visual memory test score and the engaging level of the user computed from the electroencephalogram (EEG) signal. The results are assessed by comparing with the physical mode and computer-based mode. As result, it is shown that the student performed better in the AR-based visual memory test compared to physical and computer-based modes. Besides, the EEG signals also show that students are more engaged and attentive while using AR technology.
This paper presents the implementation of high data capacity code by embedding multiple colors into the code. The main intention of this project is to implement a code that consists at least double the data capacity as compared to the present Quick Response (QR) code. This paper explains the elements that consist in the proposed high data capacity code layout. The high data capacity code utilizes color multiplexing technique to represent data by using 8 kinds of colors. The colors involved are three primary colors, three secondary colors, black and white. Besides, the code is embedded with same error correction algorithm as QR code namely Reed Solomon Error Correction. In this project, a decoder application is developed on personal computer to decode the information from the camera-captured code. The results show that the developed decoder software is capable to perform decoding without any error within the captured range of 7 cm to 15 cm. Since the developed second prototype consist of similar number of module with QR Version 8, the performance is assessed to compare with QR Version 8. As outcome of this project, the developed high data capacity code is to achieve more than doubles the data capacity of QR code Version 8.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.