Journal Information System Development
Jurnal Information System Development (ISD) hadir sebagai wadah bagi para Akademisi, Developer, Peneliti, dan Ilmuwan yang hendak menyumbangkan karya ilmiahnya bagi dunia ilmu pengetahuan di bidang Sistem Informasi. Jurnal yang diterbitkan oleh Prodi Sistem Informasi Universitas Pelita Harapan ini menerima publikasi hasil pengembangan atau penelitian terbaru di bidang Sistem Informasi. Topik-topik meliputi pengembangan software desktop, web, mobile, database system, artificial intelligence, data warehouse, data mining, UI/UX programming, IT infrastructure, Internet of Things, Game Development, Cyber Security, dan topik-topik lainnya. Setiap tahunnya, Jurnal ISD terbit dalam dua (2) periode yaitu pada Bulan Januari dan Juli
Articles
227 Documents
<![CDATA[IMPLEMENTASI ANT-BASED ROUTING ALGORITHM PADA MOBILE AD HOC NETWORK (MANET) ]]>
<![CDATA[Rahmadani, Safriadi]]>
<![CDATA[ Journal Information System Development (ISD) Vol 2, No 1 (2017): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[MANET is a network model cordless (wireless) from mobile devices that can be setup dynamically from anywhere and at anytime without using a fixed network infrastructure. Ease of use and it is without a fixed infrastructure (less infrastructure) makes this model very suitable for use in critical situations, such as in the aftermath of disaster, isolated areas and areas with minimal communications network resources. To maximize the utilization and use of MANET network system, especially on the determination and selection of the best route to a node can connect and transmit the packet from the source node to the destination node to be optimized. This study was done to improve the performance of packet delivery by creating a node that functioned as a gateway and client using routing protocols Ant-Based Routing Algorithm (ABRA) so as to reduce the processing time (overhead) that often occurs in MANET network. Testing is done with a number of different nodes of 10, 20, and 30 nodes, with a bandwidth of 5 Mbps, 5 Mbps and the packet area of 10x10 m. The test results demonstrate the value of performance metrics on throughput and delay have optimal performance and low overhead so that the process of communication in the area of MANET network can take place with the stable.Keywords: Manet, ant-based routing algorithm, networking]]>
<![CDATA[ENSEMBLE LEARNING DENGAN METODE SMOTEBAGGING PADA KLASIFIKASI DATA TIDAK SEIMBANG ]]>
<![CDATA[Siringoringo, Rimbun]]>;
<![CDATA[Jaya, Indra Kelana]]>
<![CDATA[ Journal Information System Development (ISD) Vol 3, No 2 (2018): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Unbalanced data classification is a crucial problem in the field of machine learning and data mining. Data imbalances have a poor impact on classification results where minority classes are often misclassified as a majority class. Conventional machine learning algorithms are not equipped with the ability to work on unbalanced data, so the performance of conventional algorithms is always not optimal. In this study, ensemble learning using SMOTEBagging method was applied to classify 11 unbalanced datasets. SMOTEBagging performance is also compared with three types of conventional classification algorithms namely SVM, k-NN, and C4.5. By applying the 5 cross-validation scheme, the AUC value generated by SMOTEBagging is higher at 10 datasets. The mean values of the lowest to highest AUC were obtained by SVM, k-NN, C4.5 and SMOTEBagging algorithms with values 0.638, 0.742, 0.770 and 0.895. By applying Friedman test it was found that the performance of AUC SMOTEBagging differed significantly with the other three conventional methods SVM, k-NN and C4.5ENSEMBLE LEARNING DENGANÂ METODEÂ SMOTEBagging PADA KLASIFIKASI DATA TIDAK SEIMBANG]]>
<![CDATA[PERAN MEDIA PEMBELAJARAN DALAM PENINGKATAN PEMAHAMAN SISWA SEKOLAH DASAR PADA MATAPELAJARAN MATEMATIKA ]]>
<![CDATA[NIT, Nita Syahputri]]>;
<![CDATA[Indriani, Ulfah]]>
<![CDATA[ Journal Information System Development (ISD) Vol 3, No 1 (2018): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Mathematics is one of the subjects that tend to be less favored by students, especially the students of grade 1 primary school. The students prefer to draw or other mathematics that are visual compared to mathematics. Therefore, in this research try to combine the mathematical material in the form of visual which is animation and also use the character of drawing which is liked by the children, so that the student is more interested in the learning process of mathematics. Selection of programming in writing this research using macromedia flash application. With the help of information technology and programming languages, especially animation, there will be many benefits that can be obtained. In this case the teacher is easier in delivering the material and students more easily in absorbing the material delivered so that the learning process can run more effectively and efficiently. And with the role of this learning media can overcome the problem of lack of interest in learning students of mathematics subject matter and of course increase the value of students in exercises or exams conducted in schools. Keywords: Role; Media; Learning; Math]]>
<![CDATA[PENYUSUNAN ALFABET MEMBENTUK KATA MENGGUNAKAN ALGORITMA GENETIKA ]]>
<![CDATA[Saragih, Rijois Iboy Erwin]]>
<![CDATA[ Journal Information System Development (ISD) Vol 2, No 1 (2017): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Genetic algorithm is heuristic searching algorithm which based on nature selection of mechanism and nature genetic. The basic concept that inspires the genetic algorithm is that evolution theory. The word is consisted of the alphabet. Alphabet is a set of letters or other characters with which one or more languages are written especially if arranged in a customary order. In this research will use genetic algorithm to form a word based on the typing word. The final result of this research is that showing the exact word that is typed.]]>
<![CDATA[DATA MINING PENGELOMPOKKAN PEMAKAIAN LISTRIK TERBOROS MENGGUNAKAN METODE CLUSTERING (STUDI KASUS PLN AREA BINJAI) ]]>
<![CDATA[Manik, Ediman]]>
<![CDATA[ Journal Information System Development (ISD) Vol 3, No 2 (2018): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[-- Clustering is a method used to classify a set of objects into classes consisting of the same objects. In other words clustering is the process of grouping objects based on the similarity of characteristics among the objects. In this thesis will be discussed about the clustering method by using K-Means algorithm that is used to determine the value of the electricity usage group as well as grouping it based on the level of power usage and the hours of the flame so that it can be grouped and known which ones are lost. The K-Means algorithm is one of the clustering methods that researchers will use to solve the problem of grouping. Starting from the determination of the grouping boundaries to the determination of each cluster so that the groups formed the data of electricity consumption adjusted with the level of usage. The result of this thesis is the value of data grouped by level of electricity usage grouping. And with the support of GUI programming MATLAB expected this program can be used easily. With this application can be seen the results of 200 data for cluster 1 as much as 44 with the Group of use of electricity in the group at the address is Binjai Timur and for Power group 450 and Jam on> 1100 and Cluster 2 as many as 60 Users of the listik peloros at the address group is Binjai Kota and for Power 450 and 901-1100 Clock 3 and 96 for cluster 3 groups with License usage groups in the Address group are North Binjai and for Daya Power 450 and Jam 700-900.Keywords: Clustering, Electricity Usage]]>
<![CDATA[MODIFIKASI ALGORITMA ROUND ROBIN DENGAN DYNAMIC QUANTUM TIME DAN PENGURUTAN PROSES SECARA ASCENDING ]]>
<![CDATA[Pangaribuan, Gortap]]>
<![CDATA[ Journal Information System Development (ISD) Vol 1, No 2 (2016): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[ABSTRAKAlgoritma Round Robin merupakan salah satu algoritma penjadwalan proses yang digunakan secara luas didalam penjadwalan CPU. Algoritma Round Robin menggunakan sistem time sharing dengan static quantum time untuk setiap proses yang akan dieksekusi CPU. Algoritma ini tergantung pada ukuran quantum time yang diberikan. Jika quantum time terlalu besar, maka respons time untuk proses-proses terlalu tinggi. Sebaliknya, jika quantum time terlalu kecil, maka dapat mengakibatkan overhead pada CPU dimana context switching dari proses menjadi lebih besar. Pada penelitian ini, untuk meningkatkan performa CPU dengan memperkecil waiting time dan turnaround time dilakukan modifikasi terhadap algoritma Round Robin dengan menggunakan dynamic quantum time serta sorting proses secara ascending. Dilakukan pengujian terhadap antrian proses dan hasilnya dengan menggunakan algoritma Round Robin yang dimodifikasi ini didapat average waiting time dan average turnaround time yang lebih kecil dibandingkan menggunakan algoritma Round Robin Klasik. Kata kunci: Quantum Time, Static Quantum Time, Dynamic Quantum Time, Ascending,     Average Waiting Time, Average Turnaround Time]]>
<![CDATA[KLASIFIKASI DATA TIDAK SEIMBANG MENGGUNAKAN ALGORITMA SMOTE DAN k-NEAREST NEIGHBOR ]]>
<![CDATA[Siringoringo, Rimbun]]>
<![CDATA[ Journal Information System Development (ISD) Vol 3, No 1 (2018): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Unbalanced data classification is a crucial problem in the field of machine learning and data mining. Data imbalances have a poor impact on classification results where minority classes are often misclassified as a majority class. k-Nearest Neighbor is one of the most popular and simple classification methods but it is not equipped with the ability to work on unbalanced datasets. In this study, the Synthetic Minority Over-Sampling Technique (SMOTE) was applied to solve the class imbalance problem on the Credit Card Fraud dataset. By applying the 10-cross-validation evaluation scheme, it was found that SMOTE increases the mean of G-Mean by 53.4% to 81.0% and the mean of F-Measure by 38.7 to 81.8%Keywords: Class imbalance, Synthetic Minority Over-sampling Technique, k-Nearest Neighbor]]>
<![CDATA[STUDI TENTANG MASALAH PENEMPATAN FASILITAS BERKAPASITAS SATU SUMBER DUA ESELON ]]>
<![CDATA[Sinambela, Lamtiur]]>
<![CDATA[ Journal Information System Development (ISD) Vol 2, No 2 (2017): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Facility location problem is an important part of integer programming problems, with application in the field of telecommunications, and transportation industry. This study discussed the facility location problem with two echelon. Each second echelon facilities have limited capacity and can only be supplied by a facility on second echelon. Each customer is served only by a single facility in second echelon. The number and location of the second echelon of custumers to facilities determined echelon two simltaneous. This study addresses the questions of decision-making in designing cargo distribution system where there is a two echelon distribution system the two level structure, components and issues related decisions. The purpose of the model in the study is to determine the location of facilities at each echelon which is a distribution facility and cargo capacity at the facility so that can minimize the total cost of the minimum as the optimal solution of the modeling. Keywords: CFLP, integer programming, optimization, two echelon ]]>
<![CDATA[Optimasi Algoritma Fuzzy Clustering dengan Menggunakan Algoritma Forest Optimization ]]>
<![CDATA[Kurniawan, Robert]]>;
<![CDATA[Prabowo, Edhi]]>
<![CDATA[ Journal Information System Development (ISD) Vol 4, No 1 (2019): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (419.364 KB)
<![CDATA[Fuzzy C-Means (FCM) adalah salah satu teknik clustering yang sering digunakan, tetapi memiliki kelemahan yaitu sensitif terhadap local optima dan sensitif terhadap pusat cluster awal. Forest Optimization Algortihm mampu mengatasi kelemahan dari FCM. FOFCM dibangun dengan 2 jenis jarak yaitu Euclidean dan Mahalanobis. FOFCM memiliki performa yang lebih baik dari FCM, karena sebagian besar iterasi FOFCM lebih sedikit dari FCM. FOFCM Mahalanobis menghasilkan nilai fungsi objektif paling kecil pada sebaran data hyperspherical dibandingkan dengan FOFCM Euclidean maupun FCM. Oleh karena itu, dapat disimpulkan bahwa FOFCM Mahalanobis cocok untuk data hyperspherical.]]>
<![CDATA[OPTIMALISASI DETEKSI TEPI DENGAN METODE SEGMENTASI CITRA ]]>
<![CDATA[Pangaribuan, Hotma]]>
<![CDATA[ Journal Information System Development (ISD) Vol 4, No 1 (2019): Journal Information System Development (ISD) ]]>
Publisher : <![CDATA[UNIVERSITAS PELITA HARAPAN ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (706.844 KB)
<![CDATA[Segmentasi citra sebagai bagian dari proses pengolahan citra, adalah kegiatan untuk membagi citra menjadi beberapa bagian atau region, yang bertujuan untuk mengisolasi atau menemukan suatu obyek di dalam citra. Beberapa pertumbuhan kemajuan teknologi baru membuka peluang bagi pengembangan lebih lanjut dalam bidang ini. Saat ini pengolahan citra mempunyai peranan yang sangat penting dalam berbagai bidang kehidupan. Segmentasi adalah proses pemisahan objek dengan latar belakangnya. Saat ini telah banyak dilakukan penelitian tentang segmentasi.Deteksi tepi merupakan suatu proses pencarian informasi tepi dari sebuah gambar. Deteksi tepi memiliki tujuan antara lain digunakan untuk menandai bagian yang menjadi detail dari sebuah gambar Ada banyak metode dalam melakukan segmentasi salah satunya adalah level-set menggunakan metode roberts, prewit sobel dan frei chan. Histogram citra digunakan untuk mengetahui intensitas dan kontras suatu citra, timing run digunakan untuk mengetahui lamanya suatu proses citra, dan SNR (Signal to Noise Ratio) yang digunakan untuk mengetahui kualitas citra. Pengujian dilakukan dengan melakukan uji coba terhadap Objek citra dan selanjutnya dilakukan analisis citra.Metode Sobel dan Prewitt memiliki proses komputasi yang lebih lebih sedikit jika dibandingkan. Secara umum algoritma segmentasi citra didasarkan pada satu dari dua property nilai intensitas yaitu mendeteksi diskontinuitas atau mendeteksi similaritas. Dari hasil penelitian ini didapat kesimpulan sebagai berikut:metode segmentasi yang paling tajam hasilnya yaitu menggunakan Operator Freichen, karena dari sudut pandang horizontal dan sudut pandang Vertikal sama sama menghasilkan hasil yang bagus, Dari hasil pembahasan untuk jenis operator yang paling baik adalah operator Robert, Hasil deteksi pada operator sobel lebih bagus atau tegas dibandingkan dengan operator Robert dan prewitt. Operator Sobel lebih sensitif terhadap tepi diagonal daripada tepi vertikal dan horizontal Hal ini berbeda dengan operator Prewitt, yang lebih sensitif terhadap tepi vertikal dan horizontal.]]>
