Claim Missing Document
Check
Articles

Found 23 Documents
Search

OPTIMASI FUNGSI KEANGGOTAAN FUZZY BERBASIS ALGORITMA MODIFIED PARTICLE SWARM OPTIMIZATION Rimbun Siringoringo; Zakarias Situmorang
Komputa : Jurnal Ilmiah Komputer dan Informatika Vol 3 No 2 (2014): Komputa : Jurnal Ilmiah Komputer dan Informatika
Publisher : Program Studi Teknik Informatika - Universitas Komputer Indonesia (UNIKOM)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (835.074 KB) | DOI: 10.34010/komputa.v3i2.2391

Abstract

Pada penelitian ini optimasi berbasis algoritma Modified Particle Swarm Optimization (MPSO) diterapkan untuk mengoptimasi fungsi keanggotaan fuzzy. Terdapat dua metode MPSO yang diterapkan yaitu metode Linear Decreasing Inertia Weight (LDIW) dan Constriction Factor Method (FCM). Masing-masing metode tersebut diuji dengan 10 kali percobaan pada dua jenis jumlah particle yaitu 50 dan 20 particle. Dari hasil pengujian diperoleh bahwa pada jumlah particle yang sama, CFM memperoleh nilai global best fitness yang lebih optimal daripapa metode LDIW. Pengujian sebanyak 10 kali percobaan dan menerapkan 50 particle, pada percobaan pertama diperoleh nilai global best fitness yaitu 1,4; 1,4; 2,36 dan 3,28 untuk masing-masing variabel produktifitas, keterisolasian, hubungan sosial dan aksesibilitas. Pengujian sebanyak 10 kali percobaan dan menerapkan 20 particle diperoleh nilai global best fitness yaitu 2,34; 2,40; 2,37 dan 3,36 untuk masing-masing variabel. Di sisi lain metode CFM memperoleh hasil konvergensi yang lebih cepat dari pada metode LIDW. Pengujian pada 100 swarm metode LDIW menemukan global best fitness pada swarm 91, 84, 54 dan 38 untuk masing-masing variabel, sementara dengan metode CFM menemukan global best fitness pada swarm 81, 23, 34 dan 23.
Perancangan Sistem Pelayanan Informasi Berbasis Android dengan Algoritma Nazief Andriani (Studi Kasus : Universitas Katolik Santo Thomas) Ita Juwita Saragih; Zakarias Situmorang
JUKI : Jurnal Komputer dan Informatika Vol. 1 No. 2 (2019): JUKI : Jurnal Komputer dan Informatika, Edisi November 2019
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53842/juki.v1i2.19

Abstract

Service is an effort to help prepare what others need. Or it can be interpreted that service is a series of activities or processes that fulfill the needs of others more satisfactorily. To simplify the services available at the Catholic University of Santo Thomas, it is necessary to build an android-based information service system with Nazief Andriani algorithm. This algorithm is able to find the basic words of each input so that it can produce a separate output or in other words the output issued right on target or on purpose. With this system, students no longer need to come to the administrative unit or via chat to get information about activities or complaints that are received or what they want to convey. So that this system is expected to make it easier for users to get accurate, efficient information and does not require a relatively long time, causing slow, limited and unresponsive service in providing answers.
Determining Bullying Text Classification Using Naive Bayes Classification on Social Media Ade Clinton Sitepu; Wanayumini Wanayumini; Zakarias Situmorang
Jurnal Varian Vol 4 No 2 (2021)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v4i2.1086

Abstract

Cyber-bullying includes repeated acts with the aim of scaring, angering, or embarrassing those who are targeted Cyber-bullying is happening along with the rapid development of technology and social media in society. The media and users need to filter out bully comments because they can indirectly affect the mental psychology that reads them especially directly aimed at that person. By utilizing information mining, the system is expected to be able to classify information circulating in the community. One of the classification techniques that can be applied to text-based classification is Naïve Bayes. The algorithm is good at performing the classification process. In this research, the precision of the algorithm's has been carried out on 1000 comment datasets. The data is grouped manually first into the labels "bully" and "not bully" then the data is divided into training data and test data. To test the system's ability, the classified data is analyzed using the confusion matrix method. The results showed that the Naïve Bayes Algorithm got the level of precision at 87%. and the level of area under the curve (AUC) at 88%. In terms of speed of completing the system, the Naïve Bayes Algorithm has a very good rate of speed with completion time of 0.033 seconds.
ANALISIS MODEL KEPUASAN MAHASISWA TERHADAP CARA PENGAJARAN DOSEN MENGGUNAKAN ALGORITMA C4.5 P.P.P.A.N.W. Fikrul Ilmi R.H. Zer; Masri Wahyuni; Aditia Rangga; Zakarias Situmorang
JURNAL INFORMATIKA DAN KOMPUTER Vol 6, No 1 (2022): ReBorn - February 2022
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (397.482 KB) | DOI: 10.26798/jiko.v6i1.520

Abstract

Kesuksesan suatu pembelajaran ditentukan berdasarkan kepuasan mahasiswa dalam belajar, salah satunya tehadap cara pengajaran dosen. Dalan melakukan proses belajar mengajar seorang dosen harus memperhatikan cara dalam menyampaikan materi yang diajarkan. Dosen diharapkan memiliki sikap capability dan loyality, yakni dalam bidang ilmu yang diajarkan seorang dosen harus memiliki kemampuan dalam mengajar yang baik agar memberikan kepuasan kepada mahasiswa dalam proses belajar mengajar. Faktor yang digunakan dalam klasifikasi model kepuasan mahasiswa adalah komunikasi,membangun suasana, penilaian terhadap mahasiswa, dan penyampaian terhadap materi. Tujuan dalan pemelitian ini adalah klasifikasi model kepuasan mahasiswa terhadap cara pengajaran dosen. Metode yang digunakan dalam penelitian ini adalah Algoritma C4.5 dengan data sebanyak 100 sampel di STIKOM Tunas Bangsa Pematangsiantar. Penelitian ini menghasilkan nilai akurasi data sebesar 80,00% dengan variabel Penyampaian Terhadap Materi merupakan node tertinggi dengan kategori Sangat Baik dengan jumlah kepuasan sebanyak 19. Penelitian ini adalah hasil perbandingan dari penelitian sebelumnya dengan hasil akurasi data sebesar 92.00% dengan Algoritma Naïve Bayes. Hasil yang diperoleh penelitian menggunakan ini Algoritma C4.5 memberikan model kepuasan mahasiswa yang tidak lebih dibandingkan daripada Algoritma Naïve Bayes. Dengan hasil penelitian ini dapat memberikan keputusan yang akan diambil oleh pihak perguruan tinggi dalam mengevaluasi kinerja dosen terkhusus terhadap cara pengajaran dosen.
Autoregressive Integrated Moving Average (ARIMA-Box Jenkins) Pada Peramalan Komoditas Cabai Merah di Indonesia Ridha Maya Faza Lubis; Zakarias Situmorang; Rika Rosnelly
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 2 (2021): April 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i2.2927

Abstract

Chili is one of the main staples in making a dish and chili is one of the values in a commodity that has superior value, the price of chili often experiences price fluctuations or what is known as the price which is always changing. data taken from BPS (Central Bureau of Statistics) data nationally from January 2001 to December 2015 data, this study also aims to be able to predict national chili prices which will later be used in research, namely discussing the Autoregressive Integrated Moving Average (ARIMA) method. In this study, the identification of the model was carried out using two tests, namely the stationarity test and the correlation test. The stationarity test is the Augmented Dickey-Fuller (ADF) test, the Philips-Perron (PP) test and the Kwiatkowski-Philips-Schmidt-Shin (KPPS) test using Minitab 9.The chili commodity is a very important commodity in the Indonesian economy, because In terms of consumption, chilies have a very significant market share, which can be seen from data from the Central Statistics Agency (BPS) with an inflation weight value of 0.35%. From the research, it was found that for the selection of the best method, namely ARIMA (3,1,0) because it has the smallest MSE value and the forecasting results for the next 12 periods in January 2016 ranged from Rp. 11,868.2 to Rp. 28,315.5 and so on until December 2016.
Kombinasi Metode Simple Additive Weigthing dan Weigthed Product Untuk Seleksi Proposal Program Kreatifitas Mahasiswa Raden Aris Sugianto; Roslina Roslina; Zakarias Situmorang
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 2 (2021): April 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i2.2929

Abstract

This Research aims to develop a decision support system that can facilitate the proposal selection process and provide an alternative ranking for the selection results of student creativity program proposal selection. This decision support system uses a combination calculation of the Simple Additive Weighting and Weigthted Product methods, hereinafter referred to as Modified SAW. The criteria used in this assessment refer to the 2020 Student Creativity Program Guidebook. The data used in this decision support system uses proposal selection data in the Student Creativity Development Unit of Muhammadiyah University of North Sumatra in 2019 for 2020. This system was developed by determining criteria and weight determination using the Simple Additive Weighting method and then make improvements to the weight and determine the preference value using the Weighted Product method. Each of the SAW and WP methods certainly has advantages and disadvantages. The advantages of SAW with a simple and simple ranking process, can be applied to decision-making cases such as in the recommendation of selecting proposals with various attributes. While the use of Weighted Product (WP) is often used because the weight is calculated based on the level of importance and can evaluate the set of attributes by multiplying all criteria with alternative results as well as the power between weights and alternative multiplication results. This WP method can also be used in assisting in recommendation of proposal selection based on what is needed by the University. By utilizing the advantages and disadvantages of each method, this combination is able to produce an accuracy of 91% for the SAW method, 97% for the accuracy using the WP and 99% for the accuracy value for the combination of the SAW and WP methods. This decision support system using MOD SAW can help facilitate the proposal selection process and provide alternative ranking results. Further research is suggested for the development of a decision support system for proposal selection using a combination of different methods between SAW and other methods.
Analisis Kinerja Support Vector Machine dalam Mengidentifikasi Komentar Perundungan pada Jejaring Sosial Ade Clinton Sitepu; Wanayumini Wanayumini; Zakarias Situmorang
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 2 (2021): April 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i2.2923

Abstract

Cyberbullying is the same as bullying but it is done through media technology. Bullying has often occurred along with the development of social media technology in society. Some technique are needed to filter out bully comments because it will indirectly affect the psychological condition of the reader, morover it is aimed at the person concerned. By using data mining techniques, the system is expected to be able to classify information circulating in the community. This research uses the Support Vector Machine (SVM) classification because the algorithm is good at performing the classification process. Research using about 1000 dataset comments. Data are grouped manually first into the labels "bully" and "not bully" then the data divide into training data and test data. To test the system capability, data is analyzed using confusion matrix. The results showed that the SVM Algorithm was able to classify with an level of accuracy 87.75%, 89% precision and 91% Recal. The SVM algorithm is able to formulate training data with level of accuracy 98.3%
Analisis Ward and Peppard Model Pada Strategi Bisnis dan Perencanaan Strategis Sistem Informasi Daim Azhari Parinduri; Roslina Roslina; Zakarias Situmorang
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 2 (2021): April 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i2.2977

Abstract

Muslim Nusantara Al-Washliyah University is a private university that already has information system technology and information technology as an effort to improve the competitiveness of higher education. However, the existence of the existing information system is still not perfect so that work becomes inefficient. Therefore, this research was conducted to make strategic planning of information systems so as to increase the competitiveness of higher education institutions. The model used in strategic planning in this study is the Ward and Peppard model. The strategic plan is drawn up for a timeframe of 2 phases. The process begins with Internal and External Business Analysis through SWOT Analysis, Value Chain Analysis, PEST Analysis and testing of strategy results using the Profile Matching method which is the choice to provide an assessment of recommended information system applications. There are three aspects in conducting the assessment and evaluation, namely new aspects, develop and continue.
Penerapan Decision Tree Algoritma C4.5 Dalam Penentuan Izin Pembongkaran Muatan Kapal Jaka Kusuma; Abwabul Jinan; Zakarias Situmorang
MEANS (Media Informasi Analisa dan Sistem) Volume 7 Nomor 1
Publisher : LPPM UNIKA Santo Thomas Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (595.022 KB) | DOI: 10.54367/means.v7i1.1632

Abstract

Along with the increasing number of bulk cargoes that are dismantled every year at belawan port and for the creation of services in accordance with expectations, it is necessary to develop services in support of indonesia's logistics improvement readiness, especially in terms of demolition. Utilization of machine learning using the C4.5 algorithm can make it easier to conduct selection and classification of the feasibility of ships that get permission for demolition activities. The use of the C4.5 algorithm will produce a decision tree that can equalize the results of data mining, so that the information obtained from the data will be easier to identify in testing methods using the Orange Data Mining tool. The results obtained by the C4.5 algorithm in the form of a decision tree with an accuracy value of 84%, 90% precision and 84% recall.
REGRESI LINIER BERGANDA UNTUK MEMPREDIKSI JUMLAH NASABAH Agus Fahmi Limas Putra; Junaidi Junaidi; Zakarias Situmorang; Asyahri Hadi Nasyuha
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 5, No 2 (2022): June 2022
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v5i2.915

Abstract

Industri perbankan merupakan sektor penting dalam pembangunan maupun dalam pemodalan  usaha dan dipandang sebagai inti dari sistem perekonomian. Melihat hal ini, pemerintah melonggarkan aturan-aturan bagi perbankan dan non perbankan baik dari sektor pemerintah ataupun swasta untuk memberikan pinjaman atau bantuan kepada para nasabah atau pelaku UMKM. Banyaknya nasabah-nasabah dalam penyaluran kredit atau perbankan juga akan banyak terjadi masalah – masalah dalam pinjaman ataupun pengembalian pinjaman dana, maka dari itu pihak penyaluran kredit harus siap menghadapi resiko kredit yang bermasalah atau biasa disebut dengan kredit macet. Penelitian ini bertujuan untuk menciptakan suatu sistem berbasis komputerisasi, kemudian dengan diterapkannya sistem tersebut maka hasil yang didapatkan akan benar-benar akurat dan cepat. Diharapkan metode regresi linier berganda ini dapat menyelesaikan  permasalahan dalam menangani atau mengatasi nasabah yang bermasalah sehingga dapat membantu pihak perusahaan untuk memprediksi jumlah kredit macet setiap bulannya.