Indonesia is part of a tropical climate with high rainfall intensity. High rainfall intensity can potentially cause flooding. To minimize this, accurate weather predictions are needed to be able to anticipate beforehand. This research was conducted with the aim of classifying based on the rain category with the dichotomy of heavy rain and very heavy rain using data mining techniques with the CRISP-DM methodology. The algorithm used in the classification technique is CART (Classification And Regression Tree) with Confusion Matrix test parameters. Based on the results of the model evaluation, it shows that the CART algorithm has a fairly good performance in classifying with an accuracy value of 89.4%.
Presence is an important thing in educational world especially higher education. One of students’ success keys is in their presence because it has correlation to the learning quantity carried out by a college student. Some colleges whose learning conducted face to face still use conventional way by using attendant list sheet until this system is felt less effective in the middle of digitalization development marked by the increase of technology usage. Face recognition attendance technology is a technology which can be adapted from one of artificial intelligence science namely machine learning. Machine learning with deep learning branch becomes the solution which eases human’s work. In its process, face recognition requires certain accurate face detection with certain algorithm. In this research, the method used was You Only Look Once (YOLO) algorithm where to follow some research which had been conducted previously it has high accuracy in face prediction. The test results obtained an average accuracy of 0.9793 by paying attention to parameters such as lighting and real-time sending to the website. Through this research, it is hoped that the attendance process will be more effective and can be monitored by lecturers.
Automatic Dependent Surveillance Broadcast (ADS -B) is a surveillance technology that provides information on aircraft in the air in the form of 24 bit ICAO aircraft address, ident or squawk, massage, altitude, nationality, speed, longitude, track and heading. The problem faced now is that surveillance can only be done with a web and android-based application on FlightRadar24 so that if the user wants to display more aircraft information, the user is required to pay a subscription. To overcome this problem, hardware is needed that can receive ADS-B signals with a frequency of 1090 MHz and can translate them into information signals. RTL-SDR is hardware that can receive signals with a frequency range from 25 MHz -1700 MHz, by applying the Raspberry Pi it is used to configure RTL-SDR as a receiver capable of receiving information from ADS-B signals. To get the maximum reception, an omnidirectional antenna is needed that can receive signals from all directions. With this system, it is expected to make it easier to monitor aircraft in real time and processing ADS-B signal data is determined by the strength and weakness of the signal that can be received by RTL-SDR.
— Video Conference is a communication service that can be used to bring together two users (client) or more. Video conferencing can be used for a variety of activities that require communication in real-time without having to come face to face directly. One open-source that can be utilized as a means of communicating is OpenMeetings. OpenMeetings uses IP and in the same network as a means of conducting video conferencing between clients. But if a client is not in the same network, it can utilize the Virtual Private Network (VPN) technology. The VPN can be remote by using a MikroTik router. The Video conferencing service requires fairly high and stable connectivity. Quality of Service (QoS) can be used whether the network is eligible for video conferencing. The QoS parameters used are throughput and packet loss. The QoS test can be done using Wireshark.
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.