COVID-19 is a new disease with a very rapid and tremendous spread. The most important thing needed now is a COVID-19 early detection system that is fast, easy to use, portable, and affordable. Various studies on desktop-based detection using Convolutional Neural Networks have been successfully conducted. However, no research has yet applied mobile-based detection, which requires low computational cost. Therefore, this research aims to produce a COVID-19 early detection system based on chest X-ray images using Convolutional Neural Network models to be deployed in mobile applications. It is expected that the proposed Convolutional Neural Network models can detect COVID-19 quickly, economically, and accurately. The used architecture is MobileNet's Single Shot Detection. The advantage of the Single Shot Detection MobileNet models is that they are lightweight to be applied to mobile-based devices. Therefore, these two versions will also be tested, which one is better. Both models have successfully detected COVID-19, normal, and viral pneumonia conditions with an average overall accuracy of 93.24% based on the test results. The Single Shot Detection MobileNet V1 model can detect COVID-19 with an average accuracy of 83.7%, while the Single Shot Detection MobileNet V2 Single Shot Detection model can detect COVID-19 with an average accuracy of 87.5%. Based on the research conducted, it can be concluded that the approach to detecting chest X-rays of COVID-19 can be detected using the MobileNet Single Shot Detection model. Besides, the V2 model shows better performance than the V1. Therefore, this model can be applied to increase the speed and affordability of COVID-19 detection.

Detecting disease is something that can help to determine how to cure it. Potato diseases, namely early blight and late blight, are the problem in agriculture. Both diseases have almost the same characteristics so it is difficult to recognize. The technique used by farmers only utilizes their eyesight. In addition, previous studies have mostly used the biological aspect approach. In this study utilizing Machine Learning to detect an object. The development of this application uses the training configuration used is SSD Mobilenet v1. Application test results obtained an average value of 90% can detect and distinguish the types of diseases in the potato plant.

Emotions have an important role in education. Affective development, attitudes, and emotions in learning are measured using affective assessment. This method is the right way to determine the student’s affective development. However, the process did not run optimally because the teacher found it difficult to collect student’s affective data. This paper describes the development of a system that can assist teachers in carrying out affective assessment. The system was developed using a v-model that aligns the verification phase with the validation. The use of the system is carried out during learning activities. The emotion detection system detects through body gestures using PoseNet to generate emotional data for each student. The detection results are then processed and displayed on an information system in the form of a website for affective assessment. The accuracy of emotion detection got validation values of 84.4% and 80.95% after being tested at school. In addition, the acceptance test with the usability aspect of the system by the teacher got a score of 77.56% and a score of 79.85% by the students. Based on several tests carried out, this developed system can assist the process of implementing affective assessment.