Penerapan Algoritma C5.0 Untuk Prediksi Kelulusan Pembelajaran Mahasiswa Pada Matakuliah Arsitektur Sistem Komputer

Computer system architecture is one of the subjects that must be taken in the informatics engineering study program. In the study program the graduation of each student in the course is one of the important aspects that must be evaluated every semester. Graduation for each student / I in the course is an illustration that the learning process delivered is going well and also the material presented by the lecturer in charge of the course can be digested by students. Graduation of each student in the course can be predicted based on the habit pattern of the students. Data mining is an alternative process that can be done to find out habit patterns based on the data that has been collected. Data mining itself is an extraction process on a collection of data that produces valuable information for companies, agencies or organizations that can be used in the decision-making process. Prediction of graduation with data mining can be solved by classifying the data set. The C5.0 algorithm is an improvement algorithm from the C4.5 algorithm where the process is almost the same, only the C5.0 algorithm has advantages over the previous algorithm. The results of the C5.0 algorithm are in the form of a decision tree or a rule that is formed based on the entropy or gain value. The prediction process is carried out based on the classification of the C5.0 algorithm by using the attributes of Attendance Value, Assignment Value, UTS Value and UAS Value. The final result of the C5.0 algorithm classification process is a decision tree with rules in it. The performance of the C5.0 algorithm gets a high accuracy rate of 93.33%

Design of Electric Linear Load Simulator based on LabVIEW+PXI

In order to realize the hardware-in-the-loop (HIL) experiments of a certain type of electric linear actuator in the laboratory, an electric linear load simulator (ELLS) based on LabVIEW+PXI platform was developed to simulate the external force of the actuator under actual working conditions. In structural design, the ball screw is used to convert the PMSM torque into linear force. In hardware design, the system is built using the upper-lower computer system architecture based on PXI bus. In software design, the program is written in LabVIEW, which mainly includes the data processing and display program in the upper computer and the data acquisition program, the loading motor control program and the actuator control program in the lower computer (PXI), in order to ensure the loading accuracy of ELLS, control methods such as force closed-loop PID controller, position feedforward compensation and input feedforward compensation are also introduced in the loading motor program. Finally, the ELLS was built and the signal tracking tests were carried out. The experimental results shows that the loading accuracy can reach 93.5% and 90.3% when ELLS tracks 1000N-2 Hz and 1000N-5 Hz respectively, which proved that the accuracy of ELLS satisfies the “Double Ten Index”.

Research of Adaptive Control Algorithm Based on the Cached Playing of Streaming Media

Aimed at the quality issues of current network streaming media playing, it manages by introducing a streaming media caching mechanism to help improve the playing effect. But the cached playing also has its own deficiencies, so here combines the adaptive control algorithm with the caching mechanism to solve this problem. It firstly introduces the streaming media service, and analyzes the transmission process of streaming media and adaptive media playing in detail; secondly analyzes the adaptive control algorithm of streaming media caching from the principle and design of reserving cache algorithm and the balance frame dropping algorithm; and finally gives the core code of the algorithm. This paper has a certain reference value to the video website developers and computer system architecture researchers.