Attentive learning is an important feature of the learning process. It provides a beneficial learning experience and plays a key role in generating positive learning outcomes. Most studies widely applied electroencephalogram (EEG) to measure human attention level. Although most studies use EEG handcrafted features and statistical methods to classify attention level, a more effective feature learning technique is still needed. In this paper, we aim to analyze participants' EEG signals through a deep learning model and classify those signals as showing either attentive or inattentive behaviors. To carry out this research, we initially conducted a background study on attention and its detection in EEG. After that, we design a Troxler's fading experiment and use an EEG device to collect data on participants' attentive and inattentive behaviors during the test. The collected EEG data will be analyzed using a Convolution Attention Memory Neural Network (CAMNN) model to classify participants' attention level. The proposed CAMNN model is optimized with Vector-to-Vector (Vec2Vec) modeling, where the model can be learned through deep neural networks in an end-to-end approach. The result shows that our model can achieve 92% accuracy and 0.92 F1 score which outperforms several existing neural network models such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN), Deep Learning with Convolutional Neural Networks (deep ConvNets), and Compact Convolutional Network for EEG-based BCIs (EEGNet). This research can be useful for those who are interested in developing attention level monitoring or biofeedback system in areas such as educational classroom learning, medical research, and industrial operator.

This project concerns on the development of applications using sensors for the rehabilitation of stroke patients. Thus, the leap motion sensor is employed for the finger motor rehabilitation training while the Microsoft Kinect sensor is utilized for the upper limb motor rehabilitation. Two applications which are named ‘Pick and Place’ and ‘Stone Breaker’ are developed. For the first application, the patient is required to pick up the virtual blocks and stack it up. The ‘Stone Breaker’ game requires the patient to move the upper limb in controlling the paddle movement in the game. At the end of the project, it is able to achieve the dominant objective of the project when the tested patient shows significant improvement in both the application

No abstract

No abstract

Latex gloves are seen as an indispensable item in the healthcare field because it offers superior protection for both the medical staff and patient against harmful substances. However, latex gloves with high protein concentration have a high possibility to induce latex allergy which in the worst case can lead to a life-threatening condition. To minimize the occurrence of an allergy reaction, the computerized Biocompatibility Morphological Mean (BMM) test for protein detection is proposed. This test initially goes through the chemical process to determine the protein that resides in the glove sample. After that, the sample is electronically converted into a digital image. Finally, the image undergoes color image processing for calculating the color difference values. These values are then plotted on a standard curve. A high correlation coefficient (R2>0.97) of the standard curve gives better accuracies. The proposed method only takes about 40 minutes to complete the test, while existing methods need at least 6 hours.