Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurtik STMIK Bandung

ANALISIS TINGKAT KEPUASAN PENGGUNA SISTEM INFORMASI UJIAN AKHIR SEMESTER MENGGUNAKAN METODE END USER COMPUTING SATISFACTION (EUCS) Nanny Raras Setyoningrum; Prihandoko Prihandoko
JURTIK:Jurnal Penelitian dan Pengembangan Teknologi Informasi dan Komunikasi Vol 7 No 2 (2018): JURTIK : Jurnal Teknologi Informasi dan Komunikasi
Publisher : LPPM STMIK BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (297.468 KB)

Abstract

The use of information technology in the world of education has developed a lot, especially in universities. As an example of the application of college-level information technology is the delivery of information presented through the official website of the Higher Education. One of the web-based systems owned by the Sekolah Tinggi Teknologi Indonesia Tanjungpinang is the Final Semester Examination Information System (SIUAS). With this technology, the final semester exam no longer uses the manual method with answer sheets but students can answer directly on a computer or laptop. Satisfaction level analysis is important to know the extent of expectations and realities of system users in an effort to achieve the perfection of an information system and can meet user expectations. One method in analyzing user satisfaction is end user computing satisfaction (EUCS). Dimensions contained in EUCS consist of content, accuracy, format, ease of use and timeliness. This type of research is descriptive research that is intended to describe the phenomena that exist, which take place now or in the past. Data collection methods include observation, interviews and questionnaires with a sample of 47 respondents who are active users of SIUAS. The results of the analysis of the level of satisfaction of SIUAS users of the Tanjungpinang Indonesian Institute of Technology used the EUCS method of 87.01% with a gap of 12.99% meaning that the user is in a very satisfied category range. Of the five dimensions, the variable easy of use has the smallest gap, namely 9.9% while the biggest gap is in the variable timeliness, which is 17.52%.
PERBANDINGAN KINERJA ALGORITMA C4.5, NAÏVE BAYES, K-NEAREST NEIGHBOR, LOGISTIC REGRESSION, DAN SUPPORT VECTOR MACHINES UNTUK MENDETEKSI PENYAKIT KANKER PAYUDARA Taghfirul Azhima Yoga Siswa; Prihandoko Prihandoko
JURTIK:Jurnal Penelitian dan Pengembangan Teknologi Informasi dan Komunikasi Vol 7 No 2 (2018): JURTIK : Jurnal Teknologi Informasi dan Komunikasi
Publisher : LPPM STMIK BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (792.339 KB) | DOI: 10.58761/jurtikstmikbandung.v7i2.105

Abstract

Evaluate the best performance comparison of C4.5, Naïve Bayes, K-Nearest Neighbor, Logistic Regression, and Support Vector Machines classification methods for detecting breast cancer using a 10 fold Cross Validation test by comparing the values of accuracy, precision, and recall using confusion matrix . The breast cancer dataset used was 699 records with 11 indicator parameters consisting of Code Number, Clump Thickness, Uniformity of Cell Size, Uniformity of Cell Shape, Marginal Adhesion, Single Epithelial Cell Size, Bare Nuclei, Bland Chromatin, Normal Nucleoli, Mitoses, and Classes obtained from http://archive.ics.uci.edu. The data was processed using Rapid Miner Version 9 software. The results of this study found that the percentage of performance of each classification algorithm analyzed, that is C4.5 Algorithm (accuracy 93.70%, precision 94.26%, recall 87.86%), Naïve Bayes Algorithm (accuracy 96.19 %, precision 92.25%, recall 97.50%), K-Nearest Neighbor Algorithm (95.61% accuracy, precision 94.99%, recall of 92.43%), Logistic Regression Algorithm (accuracy 96.77%, precision 95.93%, recall 94.98%), and Support Vector Machines algorithm (accuracy 96.78%, precision 94.83%, recall 96.20%). The best performance results tested using T-Test found that the Logistic Regression and Support Vector Machines algorithm has the same highest accuracy value that is equal to 0.968.