Jurnal ULTIMATICS
Jurnal ULTIMATICS merupakan Jurnal Program Studi Teknik Informatika Universitas Multimedia Nusantara yang menyajikan artikel-artikel penelitian ilmiah dalam bidang analisis dan desain sistem, programming, algoritma, rekayasa perangkat lunak, serta isu-isu teoritis dan praktis yang terkini, mencakup komputasi, kecerdasan buatan, pemrograman sistem mobile, serta topik lainnya di bidang Teknik Informatika. Jurnal ULTIMATICS terbit secara berkala dua kali dalam setahun (Juni dan Desember) dan dikelola oleh Program Studi Teknik Informatika Universitas Multimedia Nusantara bekerjasama dengan UMN Press.
Articles
10 Documents
Search results for
, issue
"Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika"
:
10 Documents
clear
<![CDATA[Pembangunan Dashboard Beasiswa dan Pinjaman Program Studi Informatika UKDW ]]>
<![CDATA[Agustinus Rendi Walewowan]]>;
<![CDATA[Willy Sudiarto Raharjo]]>;
<![CDATA[Gloria Virginia]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1253.601 KB)
|
DOI: 10.31937/ti.v12i1.1414
<![CDATA[Ketua program studi (kaprodi) memiliki banyak tugas dan tanggung jawab yang harus dilaksanakan dalam kegiatan akademik. Salah satu tugas dari seorang kaprodi adalah melaporkan seluruh pelaksanaan kegiatan di suatu prodi. Untuk itu, diperlukan suatu sistem yang dapatdigunakan untuk memantau kegiatan operasional sehari-hari dan memberikan laporan. Dashboard adalah sebuah tampilan panel informasi yang digunakan dalam suatu organisasi untuk mengevaluasi suatu masalah sehingga memudahkan seseorang untuk mengambil keputusan. Penelitian ini bertujuan melakukan perancangan sebuah dashboard beasiswa dan pinjaman dengan menggunakan metode prototyping. Prototyping adalah metode pengembangan perangkat lunak, yang berupa model fisik kerja sistem dan berfungsi sebagai versi awal dari sistem. [1]. Hasil rata-rata pengujian task success pada kedua iterasi, yaitu 96,66 sehingga sistem yang dibangun dapat dikatakan cukup efektif dalam menampilkan informasi beasiswa dan pinjaman serta mudah untuk dipelajari. Evaluasi desain antarmuka yang dilakukan menggunakan System Usability Scale (SUS) kepada 5 orang responden pada masing-masing iterasi dan menghasilkan skor SUS 75,2 pada iterasi I dan 76,6 pada iterasi II. Berdasarkan hasil tersebut diperoleh rata-rata skor SUS untuk kedua iterasi, yaitu 75,9. Dengan demikian, antarmuka sistem dinyatakan baik dengan grade scale bernilai C, adjective rating bernilai Good, dan acceptability ranges dapat diterima (acceptable).]]>
<![CDATA[The Decision Tree C5.0 Classification Algorithm for Predicting Student Academic Performance ]]>
<![CDATA[Natanael Benediktus]]>;
<![CDATA[Raymond Sunardi Oetama]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (563.761 KB)
|
DOI: 10.31937/ti.v12i1.1506
<![CDATA[Student’s performance is often used as a benchmark and a student’s activeness is frequently used as a criteria of how well a student academically perform at school. Where in this study would try to find out whether the activeness of a student can predict their academic performance. The data used is an educational dataset is collected using a learning management system (LMS), which is a learner activity tracker tool that is connected by the internet. This data has numerical and categorical variables, so it is needed to have the right algorithm to classify data accurately and ensure data validity. In this study, the C.50 algorithm is used to test the data, where the data is divided into training data by 75% and testing data by 25%. And the result from the tested data, an accuracy of 71.667% is obtained.]]>
<![CDATA[Gray Level Co-ocurence Matrix untuk Pengekstrasian Ciri Topeng Cirebon ]]>
<![CDATA[Felix Indra Kurniadi]]>;
<![CDATA[Vinnia Kemala Putri]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (358.663 KB)
|
DOI: 10.31937/ti.v12i1.1507
<![CDATA[Cirebon mask is one of the intangible cultural heritage in Indonesia. It is one of the prominent cultural assets from Cirebon and becoming one of the identity Cirebon culture. However, the current condition people tend to forget the cultural asset and lack of help from the government makes the Cirebon mask become the third-rate assets. Our concern lays on the extinction of this Mask. We want to implement digitation and automatic identification using image processing techniques. In this paper, we applied the Gray Level Co-occurrence Matrix for extracting the features. K-Nearest Neighbour as the classifier. The best accuracy of this research is 40,67%]]>
<![CDATA[Visualisasi Algoritma sebagai Sarana Pembelajaran K-Means Clustering ]]>
<![CDATA[Alethea Suryadibrata]]>;
<![CDATA[Julio Christian Young]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (553.166 KB)
|
DOI: 10.31937/ti.v12i1.1523
<![CDATA[Algorithm Visualization (AV) is often used in computer science to represents how an algorithm works. Educators believe that visualization can help students to learn difficult algorithms. In this paper, we put our interest in visualizing one of Machine Learning (ML) algorithms. ML algorithms are used in various fields. Some of the algorithms are used to classify, predict, or cluster data. Unfortunately, many students find that ML algorithms are hard to learn since some of these algorithms include complicated mathematical equations. We hope this research can help computer science students to understand K-Means Clustering in an easier way.]]>
<![CDATA[Pengenalan Wajah Bebas Ekspresi Menggunakan Metode Nearest Feature Line dengan Representasi Ciri dalam Ruang Eigen ]]>
<![CDATA[Is Mardianto]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (508.757 KB)
|
DOI: 10.31937/ti.v12i1.1562
<![CDATA[Facial recognition with different expressions is one part of the pattern recognition problem which is quite complex when compared to pattern recognition on a normal profile. The expression-free face recognition method using the Nearest Feature Line (NFL) technique works by finding the closest projection distance between feature vectors, assuming that the closer the projection distance of a feature vector (face) to another feature vector (face), the more similar the properties will be physical feature vector (face) which are close together. The NFL distance calculation is performed on the eigen dimensional space with the aim that the calculated feature vector (face) dimension has a much smaller dimension in order to increase the level of recognition accuracy and speed up computational time. The test results obtained indicate the NFL method provides a fairly good level of recognition accuracy in the average value of 76.7% with the advantage of low computational time needed when compared with other intelligent methods such as artificial neural network systems.]]>
<![CDATA[Komparasi Metode Multilayer Perceptron (MLP) dan Long Short Term Memory (LSTM) dalam Peramalan Harga Beras ]]>
<![CDATA[Steven Sen]]>;
<![CDATA[Dedy Sugiarto]]>;
<![CDATA[Abdul Rochman]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (621.82 KB)
|
DOI: 10.31937/ti.v12i1.1572
<![CDATA[Rice is one of the main commodities in Indonesian society. The main problem with rice nationally is inflation of rice prices. Therefore, this research predicts the price of rice using Multilayer Perceptron (MLP) artificial neural network architecture and deep learning: Long Short Term Memory (LSTM) to anticipate these problems. The data used in this study are real data on rice prices during 2016 - 2019 obtained from PT. Food Station. The total dataset is 1307 with the distribution of 1123 as data train and 184 as test data. The final results obtained in this study are LSTM superior to MLP, with the value of Root Mean Square Error (RMSE) training data: 0.49 RMSE loss value of test data is 0.27. The most optimal LSTM model from 3 tests was carried out, namely the number of hidden layers = 16 and epochs = 150 times.]]>
<![CDATA[Peramalan Utilisasi Perangkat Jaringan dan Bandwidth Dengan Metode Holt-Winters dan Multi Layer Perceptron ]]>
<![CDATA[Muhammad Taufiq]]>;
<![CDATA[Dedy Sugiarto]]>;
<![CDATA[Abdul Rochman]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1059.464 KB)
|
DOI: 10.31937/ti.v12i1.1575
<![CDATA[Network devices become an important medium for transferring data from one node to another node in the form of switches, routers or network security devices. The reliability of network devices must be maintained both in terms of device resources and bandwidth. The study was conducted by applying the Holt-Winters and Multi Layer Perceptron (MLP) method to network device and bandwidth data utilization. The two methods are compared to assess which accuracy is better when applied to network device and bandwidth utilization data by calculating Root Mean Squared Error (RMSE) and Mean Absolute Percentage (MAPE). The results of the measurement of accuracy in the network device testing data, MLP produces a value of RMSE of 5,67 and MAPE of 2.34, and Holt-Winters produces a value of RMSE of 14.56 and MAPE of 2.95. For the results of the measurement of accuracy in the bandwidth testing data with MLP produces a value of RMSE of 0.13 and MAPE of 7.27, and Holt-Winters produces RMSE values of 2.59 and MAPE of 134.31. Based on the results of these measurements it is concluded that the MLP method has a smaller error value compared to the Holt-Winters method applied to network device and bandwidth utilization data with a span of 3 years historical data.]]>
<![CDATA[Analisis Perbandingan Efisiensi Algoritma Brute Force dan Divide and Conquer dalam Proses Pengurutan Angka ]]>
<![CDATA[Fenina Adline Twince Tobing]]>;
<![CDATA[James Ronald Tambunan]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1071.13 KB)
|
DOI: 10.31937/ti.v12i1.1585
<![CDATA[Abstrak— Perbandingan algoritma dibutuhkan untuk mengetahui tingkat efisiensi suatu algoritma. Penelitian ini membandingkan efisiensi dari dua strategi algoritma sort yang sudah ada yaitu brute force dan divide and conquer. Algoritma brute force yang akan diuji adalah bubble sort dan selection sort. Algoritma divide and conquer yang akan diuji adalah quick sort dan merge sort. Cara yang dilakuakn dalam penelitian ini adalah melakukan tes dengan data sebanyak 50 sampai 100000 untuk setiap algoritma. Tes dilakukan dengan menggunakan bahasa pemrograman JavaScript. Hasil dari penelitian ini adalah algoritma quick sort dengan strategi divide and conquer memiliki efisiensi yang baik serta running time yang cepat dan algoritma bubble sort dengan strategi brute force memiliki efisiensi yang buruk serta running time yang lama. Kata Kunci – Efisiensi, algoritma, brute force, divide and conquer, bubble sort, selection sort, quick sort, merge sort]]>
<![CDATA[Kombinasi Backpropagation dan Hopfield Modifikasi untuk Persamaan Polynomial ]]>
<![CDATA[Rina Pramitasari]]>;
<![CDATA[Imam Rofiki]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (824.002 KB)
|
DOI: 10.31937/ti.v12i1.1627
<![CDATA[Tujuan artikel ini mencari akar untuk menyelesaikan persamaan polynomial. Dimana tingkat keamanan dari system kriptografi kunci public adalah pada permasalahan matematika yang sulit dipecahkan. Sehingga Salah satunya adalah kriptografi kunci public multivariat. Untuk mengkriptanalisis tersebut adalah menyelesaikan sistem persamaan polynomial multivariat atas lapangan hingga. Penelitian ini dilakukan dengan kombinasi metode backpropagarian dan Hopfield modifikasi. Hasil penelitian menunjukkan lebih baik dari pada metode Hopfield Modifikasi saja. Karena menjamin nilai awal yang diberikan metode Hopfield modifikasi dimana selalu dekat dengan nilai optimal. Pendekatan ini memberikan solusi yang akurat.]]>
<![CDATA[Implementasi Algoritma Apriori untuk Rekomendasi Kombinasi Produk Penjualan ]]>
<![CDATA[Andre Setiawan]]>;
<![CDATA[Farica Perdana Putri]]>
<![CDATA[ Ultimatics : Jurnal Teknik Informatika Vol 12 No 1 (2020): Ultimatics : Jurnal Teknik Informatika ]]>
Publisher : <![CDATA[Faculty of Engineering and Informatics, Universitas Multimedia Nusantara ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (709.773 KB)
|
DOI: 10.31937/ti.v12i1.1644
<![CDATA[Analyzing and systematically extracting essential information from recording transactions is important for a business, including online stores. Sometimes, some online stores offer a product package that is not suitable for the customer. It happens because they did not process the data transaction to observe the association between products on a package. A web-based recommendation system was build using the CodeIgniter framework with PHP programming language. The system developed using Market Basket analysis that can determine the combination of products. Apriori algorithm used as a technique to analyze the relationship between products based on the data transaction. The lift ratio value generated from the rule is 1.18, which means that the rule has the power of relationships between items. We evaluate the system using USE questionnaire with usefulness results is 90.83%, ease of use 89.09%, ease of learning 95%, and satisfaction 90.94%, which strongly agree in every aspect.]]>
