Indonesia is a tropical country that has various skin diseases. Tinea versicolor, ringworm, and scabies are the most common types of skin diseases suffered by the people of Indonesia. The classification of the three skin diseases can be automatically completed by artificial intelligence and deep learning technology because the classification process using an expert will require a lot of money and time. The challenge in classifying skin diseases is in the process of collecting data. Because health data cannot be obtained freely, there must be approval from the patient or hospital. Therefore, to overcome the limited amount of data, Pre-Trained CNN is used. The Pre-Trained CNN model has many patterns from thousands of images, so we do not need many images to train the model. In this study, a comparison of five pre-trained CNN models was conducted, namely VGGNet16, MobileNetV2, InceptionResNetV2, ResNet152V2, and DenseNet201. The aim is to find out which CNN model can produce the best performance in classifying skin diseases with a limited amount of image data. The test results show that the ResNet152V2 model has the best classification ability with the highest accuracy, precision, recall, and F1 score values, namely 95.84%, 0.963, 0.96, and 0.956. As for the training execution time, the ResNet152V2 model has the fastest time to achieve 95% accuracy. That's happened because the addition of the dropout parameter is 20%.
In daily life, people with visual impairment have difficulty in their activities, especially at home activities. People with visual impairment as of 2017 reached 1.5 percent or around 3.75 million people from the population of Indonesia and more than 253 million people worldwide. The number of blind people who are not small need help to get a good quality of life and independent. Friendly home design for the blind is not yet available specifically. It is a particular difficulty for blind people to access the latest electronic goods or information (news). Then this becomes the basis of this research on how to provide easy access for blind people. This research provides a solution that is designing a prototype of a house that is visually impaired in addition to the use of electronic equipment. This system starts from the microphone as a sensor in charge of picking up sound and then the results are processed by Android and then connected to NodeMCU via Wi-Fi. The microphone used is the default microphone of the Android smart phone. By using the speech recognition method, the command is enough to say the keywords, Android will manage the sound into a code that will be sent to the microcontroller to perform the task. There are several categories of commands that can be handled, including (a) Turning on / off electronic devices, (b) Providing news information from popular news web portals, (c) Entertainment by playing streaming radio and (d) General information on hours and dates. All planned functions are running properly, there are some features that might be developed further. Adding sensitivity to starting voice commands and adding the ability to read long stories can be further research.
Integrating logical and analytical thinking activities to support 21st century learning ability, into a learning activity at elementary and junior high school level becomes a challenge. One of them is less interesting learning media. One of the technologies that can be used to support exciting learning is block programming Alice and Scratch. This article aims to develop online training materials Logic and Algorithm utilize block programming scratch for level five elementary school and block programming Alice for level eight junior high school as eLearning content. The development of this research is carried out by Analysis-Design-Development-Implementation-Evaluation (ADDIE) development model. Initial products were reviewed and advised by 2 primary school teachers, 2 junior high school teachers. Product quality assessment is done based on content feasibility aspect, feasibility of presentation, language feasibility using Likert scale. The results data are then analyzed using the ideal scoring criteria to determine product quality. The results of the overall training content quality assessment show an average grade of 89.8 with good.
<p><em>Light Monitoring Dimmed Lights and Curtain Control Windows Node-based MCU is a system designed to turn on and off lights using android controls. In addition the system is also equipped with features open and close the window curtain automatically. This feature and traffic use the LDR sensor to detect light and make it up to 300 then the servo motor will move and open the window. In addition to control android applications, this is in accordance with the function of this system is to control whether the lights are in a state of light or </em><em>not</em><em>. You can use remote lights in accordance with the conditions desired by the home owner</em><em> on android device</em><em>. This system is used to explore issues related to energy and home</em><em> safety</em><em>.</em></p>
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.