Learning system that effectively and efficiently into the output (output) is desired by each of the components involved in the education world. One of the learning system developed at this time is a distance learning or commonly referred to as e-learning. The system of distance learning or e-learning has been developed by academics, but what is desired for the educational system can be run more effectively and efficiently without reducing the quality of that output is still very far from what is expected. The methods and ways that run on this research uses analysis tool of the results of a survey of systems developed. Results were analyzed to see kecndrungan of a system if it serves the user, for this reason, this research will develop the processing of data on patterns of development of knowledge through online learning systems.

Research on the Vanet system always has its own challenges and obstacles. The communication system between nodes is certainly the main problem that is always faced. The communication model and concept in the routing protocol process is a very decisive choice to get good communication quality. Four categories in vanet system topology, namely position based routing protocols, broadcast based routing protocols, cluster based routing protocols and multicast/geocast routing protocols, have fundamental differences, especially in the concept of sending data and information between nodes. For this reason, in this study, the selection of standardization and integration of data delivery between nodes is of particular concern and is certainly an interesting thing to study more deeply. The ability to send data properly in busy and fast traffic conditions has its own challenges. For this, there are many variables that must be considered, so that communication between nodes will be better Povzetek: .

State universities have a library as a facility to support students’ education and science, which contains various books, journals, and final assignments. An intelligent system for classifying documents is needed to ease library visitors in higher education as a form of service to students. The documents that are in the library are generally the result of research. Various complaints related to the imbalance of data texts and categories based on irrelevant document titles and words that have the ambiguity of meaning when searching for documents are the main reasons for the need for a classification system. This research uses k-Nearest Neighbor (k-NN) to categorize documents based on study interests with information gain features selection to handle unbalanced data and cosine similarity to measure the distance between test and training data. Based on the results of tests conducted with 276 training data, the highest results using the information gain selection feature using 80% training data and 20% test data produce an accuracy of 87.5% with a parameter value of k=5. The highest accuracy results of 92.9% are achieved without information gain feature selection, with the proportion of training data of 90% and 10% test data and parameters k=5, 7, and 9. This paper concludes that without information gain feature selection, the system has better accuracy than using the feature selection because every word in the document title is considered to have an essential role in forming the classification.

Database course is the main courses in the department of informatics and computer science. This course aims to provide knowledge to students to build and manage data on Database Management Systems (DBMS) like MySQL. Therefore, the implementation of database processing practices in one of the DBMS such as MySQL is very important as basic skills in the field of informatics. With the growing number of informatics students, lectures cannot correct the results of student exercises quickly. For that, we need a system that can help lecturers to make corrections of query exercise on MySQL automatically, which is called Online Judge MySQL. This application was developed using NodeJS to execute queries that users input and ReactJS to build its interfaces. Testing is done by using this application for the online exam in several classes simultaneously. The results show that this application can correct the test results quickly and lightly.

The backpropagation algorithm has many training and activation functions that can be used to influence or maximize prediction results, all of which have their respective advantages and disadvantages. The purpose of this paper is to analyze one of the training functions of the backpropagation algorithm which can be used as a reference for use in data prediction problems in the form of models and best performance. The training function is the Bayesian Regularization method. This method is able to train the network by optimizing the Levenberg-Marquardt by updating the bias and weights. The research dataset used to analyze the data in this paper is Formal Education Participation in Indonesia 2015-2020 which consists of the School Participation Rate, the Gross Enrollment Rate, and the Pure Enrollment Rate. The 2015-2016 dataset is used as training data with a 2017 target, while the 2018-2019 dataset is the test data with a 2020 target. The models used are 2-10-1, 2-15-1, and 2-20-1. Based on the analysis and calculation process, the results of the 2-15-1 model are the best with an epoch of 217 iterations and an MSE of 0.00002945, this is because the epoch is not too large and has the smallest MSE compared to the other 2 models.