Since the introduction of image pattern recognition and computer vision processing, the classification of cancer tissues has been a challenge at pixel-level, slide-level, and patient-level. Conventional machine learning techniques have given way to Deep Learning (DL), a contemporary, state-of-the-art approach to texture classification and localization of cancer tissues. Colorectal Cancer (CRC) is the third ranked cause of death from cancer worldwide. This paper proposes image-level texture classification of a CRC dataset by deep convolutional neural networks (CNN). Simple DL techniques consisting of transfer learning and fine-tuning were exploited. VGG-16, a Keras pre-trained model with initial weights by ImageNet, was applied. The transfer learning architecture and methods responding to VGG-16 are proposed. The training, validation, and testing sets included 5000 images of 150 × 150 pixels. The application set for detection and localization contained 10 large original images of 5000 × 5000 pixels. The model achieved F1-score and accuracy of 0.96 and 0.99, respectively, and produced a false positive rate of 0.01. AUC-based evaluation was also measured. The model classified ten large previously unseen images from the application set represented in false color maps. The reported results show the satisfactory performance of the model. The simplicity of the architecture, configuration, and implementation also contributes to the outcome this work.

No abstract

Sleepwalking is a type of sleep disorder which originates during deep sleep and results in walking state and performing series of complex behaviors or actions while sleeping. In some cases, sleepwalking patients can injure themselves from their actions such as driving a car or climbing out of a window. In addition, to wake up the sleepwalkers can be difficult. The suddenly waking up and can cause them to be confused or even attack the person who wakes them. Therefore, detecting the sleepwalking incident in an early state can help the caretaker or family members to stop the patients before they harm themselves from any strange, inappropriate, or violent behaviors. In this research, we present a prototype system of sleepwalking detection algorithm and notification system using smart device which work coordinating with wearable device. There are two main groups of users; patients and caretakers. User Activity Sensor (UAS) in the wearable device is utilized for detecting User Activity Data (UAD) which is unusual activities of inducing a sleepwalking patient provided by the Remote Sensor SDK. The system returns the patient UAD states consisting of standing, walking, and running. The smart device accepts the UAD states from the wearable device, performs sleepwalking detection algorithms then, alarms caretakers when the sleepwalking state has already invoked. The system is implemented, built, tested and deployed. The threefold experimental measurement of physical user activites have been performed to validate our proposed sleepwalking detection algorithms. The system correctly detects the sleepwalking states and notifies the caretaker.

No abstract

This paper proposes an architectural design of a prototype for handwriting practice application for pre-primary school students, 4 to 6 years old, on Android tablet computer. The application provides mechanisms for alphabets validation and score calculation. The application also provides handwriting tutorial animation for motivating the students.