Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi Cyberku
Vincent Suhartono
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
PENERAPAN ALGORITMA C4.5 BERBASIS ADABOOST UNTUK PREDIKSI PENYAKIT JANTUNG Abdul Rohman; Vincent Suhartono; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 13 No 1 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (202.065 KB)

Abstract

Heart disease is the occurrence of partial or total blockage of a blood vessel over, as a result of the self peyumbatan deep chemical energy supply to the heart muscle is reduced, resulting in impaired balance between supply and needs .Research in predicting heart disease have been carried out by several previous investigators. In this study will be done for heart disease prediction algorithm using C4.5 and improved the performance of C4.5 algorithm using Adaboost method is implemented on the data of heart disease patients. From the test results by measuring method using a C4.5-based Adaboost, confusion matrix, and the ROC curve, it is known that C4.5 algorithms yield accuracy values 86,59%, AUC values obtained after 0.957 and optimized by using the method to be 92,24% Adaboost, the AUC to 0.982. by looking at the accuracy and AUC values after the optimizations, the algorithmbased C4.5 classification Adaboost into the category of groups is very good, because AUC values between 0.90 – 1.00
PENENTUAN TINGKAT KELULUSAN TEPAT WAKTU MAHASISWA STMIK SUBANG MENGGUNAKAN ALGORITMA C4.5 Hermansyah Nur Ahmad; Vincent Suhartono; Ika Novita Dewi
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 13 No 1 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (306.758 KB)

Abstract

Timely graduatuion rates in college could not be consideres easy and trivial. Many cases found that the share of the number of students who did not get in and who have completed their studies so that the build up of high numbers of students in every period. I need to know the factors cause students not graduating on time. Classification data mining techniques can be used to predict student graduation rates. The algorithm used is algoritmic C 4.5 with data as much as 200 students study computer engineering programs STMIK Subang. The result of the classification process is evaluated by using the confusion matrix, ROC Curve, Recall. Based on experimental results and evluation is done then it can be inferred that the algorithm C 4.5 accurately applied to determine the level of students graduation. After testing the prediction accuracy resulting from trials reached 95,00% of the classification result generate information in the from of graph in the form of the curve results from the decision tree that is useful for institutions of higher education in taking policy.
DETEKSI API MENGGUNAKAN BACKGROUND SUBSTRACTION DAN ARTIFICIAL NEURAL NETWORK UNTUK REAL TIME MONITORING Andi Kamaruddin; Vincent Suhartono; Ricardus Anggi Pramunendar
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (410.01 KB)

Abstract

The most important initial step in the detection and localization of the fire is to detect fire quickly and reliably. Video-based surveillance is one of the most promising solutions for automatic fire detection with the ability to monitor a large area and ease of reading an alarm to the operator through the monitorSupervision, unfortunately, the main drawback of video-based fire monitoring system that uses optic is a false alarm caused by an Error detection (Error detection), for it is then in this study using the feature extraction GLCM (Gray level Coocurance Matrix) as input spectral classification of Neural network to detect fire, the approach can reduce the Average Error detection with Error detection rate Average is 7%
MODEL MULTI-CLASS SVM MENGGUNAKAN STRATEGI 1V1 UNTUK KLASIFIKASI WALL-FOLLOWING ROBOT NAVIGATION DATA Azminuddin I. S. Azis; Vincent Suhartono; Heribertus Himawan
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 13 No 2 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1006.645 KB)

Abstract

Manusia memiliki keterbatasan dalam mengerjakan hal-hal yang berat, rumit, cepat, berbahaya, berulang-ulang secara langsung baik itu di kalangan rumah tangga, industri, militer, penelitian, hiburan, dsb. Robot merupakan mesin yang dapat mempermudah pekerjaan dan mengatasi keterbatasan manusia, sedangkan AI dapat membuat robot semakin cerdas. Berbagai macam metode AI telah diusulkan untuk mengatasi salah satu teknik navigasi robot, yaitu wall-following robot navigation, namun masih belum optimal. State of the art dalam klasifikasi wall-following robot navigation data adalah MLP dengan akurasi sebesar 97.59%. Namun akhir-akhir ini, state of the art dalam klasifikasi pattern recognition adalah SVM. Wall- following robot navigation data melibatkan multi-class, non-linear, dan high dimensional problem. 1V1 merupakan strategi terbaik yang dapat diterapkan pada SVM untuk mengatasi multi class problem yang selanjutnya dapat disebut multi-class SVM. Sedangkan untuk mengatasi non-linear dan high dimensional problem, SVM sendiri sudah dimodifikasi dengan memasukkan fungsi Kernel. Dengan demikian, akurasi sebesar 97.59% yang dihasilkan oleh MLP untuk klasifikasi wall-following robot navigation data masih dianggap rendah. Namun model multi-class SVM menggunakan strategi 1V1 untuk klasifikasi wall-following robot navigation data yang diperoleh dengan solusi yang global optimal dan tanpa perlu adanya dimensionality reduction (by PCA/SVD) dalam tingkat akurasi fair classification, yaitu 91.10% < 97.59% yang dihasilkan penelitian sebelumnya menggunakan MLP. Namun secara teoritis, multi-class SVM menggunakan strategi 1V1 lebih cepat dengan waktu proses yang dihasilkan = 10.7505 detik. Dengan demikian, model tersebut dapat mempelajari navigasi robot pengikut dinding tanpa tabrakan (menjaga jarak terhadap dinding dengan baik).
FEATURE RECOGNITION BERBASIS CORNER DETECTION DENGAN METODE FAST, SURF, DAN FLANN TREE UNTUK IDENTIFIKASI LOGO PADA AUGMENTED REALITY MOBILE SYSTEM Rastri Prathivi; Vincent Suhartono; Guruh Fajar Shidik
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (360.371 KB)

Abstract

Logo is a graphical symbol that is the identity of an organization, institution, or company. Logo isgenerally used to introduce to the public the existence of an organization, institution, or company.Through the existence of an agency logo can be seen by the public. Feature recognition is one of theprocesses that exist within an augmented reality system. One of uses augmented reality is able torecognize the identity of the logo through a camera. The first step to make a process of feature recognitionis through the corner detection. Incorporation of several method such as FAST, SURF, and FLANN TREEfor the feature detection process based corner detection feature matching up process, will have the betterability to detect the presence of a logo. Additionally when running the feature extraction process there areseveral issues that arise as scale invariant feature and rotation invariant feature. In this study theresearch object in the form of logo to the priority to make the process of feature recognition. FAST, SURF,and FLANN TREE method will detection logo with scale invariant feature and rotation invariant featureconditions. Obtained from this study will demonstration the accuracy from FAST, SURF, and FLANNTREE methods to solve the scale invariant and rotation invariant feature problems
PENENTUAN THRESHOLD MENGGUNAKAN ALGORITMA SELF ORGANIZING MAPS (SOM) UNTUK SEGMENTASI REGION KARAKTER PADA PLAT NOMOR KENDARAAN Apriyanto Alhamad; Vincent Suhartono; Ricardus Anggi Pramunendar
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (784.538 KB)

Abstract

At this time the era of information technology , the use of automation and intelligent systems are becomingmore and more widespread. Transfortasi Intelligent Systems has received so much attention that manysystems are being developed and applied throughout the world. In a vehicle license plate recognitionsystem consists of several stages , namely pre-processing , license plate detection, the segmentation ofcharacters and the vehicle license plate character recognition . In previous studies determining thethreshold value using Otsu local method by dividing two variants of black and white . In a study usinglocal methods otsu susceptible to interference in the picture . In the study proposes a method of self -organizing map in determining the threshold value . Then from the results of the threshold determinationfollowed by segmenting the characters using the function bouding Box . From the experimental results ofthreshold determination method of self - organizing maps can increase the threshold value of 0.5241 andthe experimental test of character segmentation as measured using the function Means Square Error of6.93E +03 pixels , smaller than the test results of the local segmentation character Otsu method
PREDIKSI PENYAKIT KANKER PAYUDARA MENGGUNAKAN ARTIFICIAL NEURAL NETWORK Supriyadi Supriyadi; Vincent Suhartono; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 1 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (615.246 KB)

Abstract

Breast cancer is a malignant tumor that begins in the cells of the breast. A malignant tumor is a group of cancer cells that can grow and invade surrounding tissues or spread (metastasize) to distant areas of the body. This disease occurs almost entirely in women, but men can also get it. The hypothesis of this study is the method of Artificial Neural Network which is expected to increase the accuracy in the prediction of breast cancer patients. Results of testing to be performed by measuring method and compared with the Artificial Neural Network algorithm C.45. The dataset taken from UCI with a total number of 699 and it is found benign tumors or as many as 458 (65.5%) whereas malignant cancer or 241 (34.5%), with 699 data and 10 attributes which are processed are the thickness of breast cancer, cell size, cell shape, adhesion Margina, single epi cell size, cell nuclei, bland chromatin, normal nucleoli, myth, and the class of breast cancer benign and malignant breast cancer. From various experiments conducted with the Artificial Neural Network algorithm best results are with 500 Cycle Training and Learning Rate 0.5 to obtain an accuracy value of 95.57%, 93.00% presicion, recall 94.62% and AUC 0.986 with time 38s. So based on grouping by comparing the accuracy and AUC values of experiments shows that the algorithm has a classification Artificial Neural Network with a very good, and when compared with the C4.5 algorithm with the result 0.963 is better than Artificial Neural Network algorithm. To be able to increase the level of accuracy of previous studies that only 93.00% to 95.57% gain research or an increase of 2.57%. For computing the level of accuracy with 94.42% and the standard reached by using computational experiments that change the value of Learning Rate it generated 95.57%, an increase of 1.42%.
Co-Authors ABDUL ROHMAN Andi Kamaruddin Apriyanto Alhamad Azminuddin I. S. Azis Catur Supriyanto Guruh Fajar Shidik Heribertus Himawan Hermansyah Nur Ahmad Ika Novita Dewi Rastri Prathivi Ricardus Anggi Pramunendar Supriyadi Supriyadi