Henny Indriyawati

RESEARCH INTERESTS

System Cerdas, Artificial Intelegent, Data Mining

Scopus Publications

Web-based document certification system with advanced encryption standard digital signature
Henny Indriyawati, Titin Winarti, and Vensy Vydia
Institute of Advanced Engineering and Science
<span>Web-based degree document certification system with a digital signature in Semarang University has a purpose to support academic to do online document certification through a system. The main problem which occurs in academic administration is a long document certification process that causes an ineffective and inefficient certification process. To solve the problem, a system that can encrypt a document for better security is required. This system is built with the advanced encryption standard algorithm with a 128-bit sized key to encrypt confidential information inside the document. During the encryption process, this algorithm operates using 4x4 bit array blocks and passing many encryption processes for at least 10 (ten) times. The application is analyzed with object-oriented analysis and modeled with Unified modeling language. The result of this research is a system which can secure document with AES algorithm with a 256-bit sized key. The security element in this algorithm will make easier to identify the owner of the document. The secured document is easily accessible through PHP-based web or available QR code. When decrypting the document, the application will activate the camera function and decrypt the information document.</span>


Performance comparison between naive bayes and k-nearest neighbor algorithm for the classification of indonesian language articles
Titin Winarti, Henny Indriyawati, Vensy Vydia, and Febrian Wahyu Christanto
Institute of Advanced Engineering and Science
<span id="docs-internal-guid-210930a7-7fff-b7fb-428b-3176d3549972"><span>The match between the contents of the article and the article theme is the main factor whether or not an article is accepted. Many people are still confused to determine the theme of the article appropriate to the article they have. For that reason, we need a document classification algorithm that can group the articles automatically and accurately. Many classification algorithms can be used. The algorithm used in this study is naive bayes and the k-nearest neighbor algorithm is used as the baseline. The naive bayes algorithm was chosen because it can produce maximum accuracy with little training data. While the k-nearest neighbor algorithm was chosen because the algorithm is robust against data noise. The performance of the two algorithms will be compared, so it can be seen which algorithm is better in classifying documents. The comes about obtained show that the naive bayes algorithm has way better execution with an accuracy rate of 88%, while the k-nearest neighbor algorithm has a fairly low accuracy rate of 60%.</span></span>