Claim Missing Document
Check
Articles

Found 17 Documents
Search

Optimization Of Determination Against K-Means Cluster Algorithm Using Elbow Creation Melda Pita Uli Sitompul; Opim Salim Sitompul; Zakarias Situmorang
Jurnal Teknik Informatika C.I.T Medicom Vol 14 No 1 (2022): March: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/cit.Vol14.2022.176.pp1-9

Abstract

Clustering is a data mining method for grouping data that have similar or different characters in each section. One of the methods is using K-Means by measuring the distance between clusters using the shortest distance or Euclidean Distance. K-means entails weakness, which is the determination of clusters in k-means clustering, resulting in the different data grouping and affecting the results of the data cluster distribution. To overcome this issue, the elbow creation method is employed to determine the similarity level in the cluster by observing the comparison between Root Means Square and R Square to measure the homogeneity and heterogeneity of the cluster where this method is applied by considering the changes in the comparison between the RMSSTD (Root Means Square Standard Deviation) and RS (R Squared) values which have the intersection of the RMSSTD and RSquared values. The difference between RMSSTD cluster 1 and RMSSTD cluster 2 was 0.066 and RS cluster 1 and RS cluster 2 was -0.304. Based on those figures, the highest difference was found in cluster 2. All considered, tourist destinations in East Asia frequently visited or interested to visitors are grouped into cluster 2, comprising criteria 6, 7, 8, and 10, or in other words, resort destination, picnic area, beaches, and religious institutions
Penentuan Kelayakan Pemberian Bantuan BBM pada Nelayan menggunakan Metode Vikor : (Studi Kasus : Dinas Perikanan dan Kelautan Kabupaten Langkat) Anisa Putri Pratiwi; Relita Buaton; Melda Pita Uli Sitompul
Jurnal Penelitian Teknologi Informasi dan Sains Vol. 2 No. 3 (2024): SEPTEMBER : JURNAL PENELITIAN TEKNOLOGI INFORMASI DAN SAINS
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jptis.v2i3.2349

Abstract

Fishermen is a term for people whose daily work is catching fish or other biota that live on the bottom or surface of the water. Fishermen can also discuss and share experiences in overcoming problems in the fisheries and marine sector to meet the needs of fishermen. The government of the Fisheries and Marine Service is required to support the need for subsidized fuel for fishermen. The increase in fuel oil (BBM) has an impact on the operational costs of fishermen, because BBM is one of the main components in the daily activities of fishermen, with the high price of BBM, fishermen will face an increase in operational costs that they must spend to carry out fishing activities. This can reduce the income earned by fishermen, because higher costs will affect the profits that fishermen get from the sale of fish. So the Fisheries and Marine Service of Langkat Regency Provides Assistance for Fishermen in Langkat Regency, from the many assistance that have been distributed in this thesis I took a sample of the Fishermen of Secanggang Village. Based on the research conducted, the results obtained were that the first alternative that was a priority to receive subsidized fuel assistance for fishermen in Langkat Regency with a Q value = 0 and was entitled to be recommended. And the next priority was the second alternative with a Q value = 0.492.
Pengelompokan Penanganan Resiko Pada Kegiatan Panen Berdasarkan Alat Pelindung Diri Yang digunakan : (Studi Kasus: PT. Langkat Nusantara Kepong Kebun Padang Brahrang) Nur Fariza Khairani; Relita Buaton; Melda Pita Uli Sitompul
Modem : Jurnal Informatika dan Sains Teknologi. Vol. 2 No. 4 (2024): Oktober : Modem : Jurnal Informatika dan Sains Teknologi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/modem.v2i4.232

Abstract

Personal Protective Equipment (PPE) is essential for worker safety, especially in oil palm harvesting activities. PT Langkat Nusantara Kepong faces major challenges related to work safety, with analysis showing that work accidents still occur frequently in the Padang Brahrang Plantation. This indicates the need for an in-depth evaluation of the use of Personal Protective Equipment (PPE) to reduce the risk of work accidents. By using the clustering method to group data based on the type of Personal Protective Equipment (PPE) used and aims to provide recommendations for optimizing the use of personal protective equipment based on risk management and reducing the incidence of work accidents. From testing the results of cluster 3, cluster 4 and cluster 5 it can be concluded that clustering with 5 clusters provides the most efficient and precise results, followed by 4 clusters, while 3 clusters provide greater variation within clusters, indicating that clustering with fewer clusters is less able to capture subtle differences in the data.
Application of the Apriori Algorithm to Analyze the Correlation of Underage Marriage Factors Rizki Tri Ipanda; A M H Pardede; Melda Pita Uli Sitompul
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 1 (2024): October 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i1.632

Abstract

This study aims to analyze the correlation between various factors contributing to underage marriage in Kota Binjai. The primary variables influencing underage marriage include economic, social, cultural, parental, and educational factors. These five variables are considered significant in the prevalence of underage marriage within the Kota Binjai community. The methodology employed involves data mining techniques using the Apriori algorithm to identify the most frequently occurring data correlations. The analysis reveals that the best rule with 2 itemsets has a support of 42.7% and a confidence of 69.6%, while the best rule with 3 itemsets has a support of 26.7% and a confidence of 71.4%. For 4 itemsets, the support is 12% with a confidence of 50%. These findings indicate that economic factors are the most frequently appearing and consistently influential in the decision of Kota Binjai residents to engage in underage marriage, both independently and in combination with social, cultural, and parental influence factors
Digital Image Security Analysis using Hill Cipher and AES Algorithm Ranti, Dwi; Achmad Fauzi; Sitompul, Melda Pita Uli
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 1 (2024): October 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i1.665

Abstract

In today's digital era, digital image exchange has become very common in various industries, but this also increases security risks such as counterfeiting, image manipulation, and information theft. To protect the confidentiality of information in digital images, encryption is a fairly effective method. Hill Cipher, as a classic cryptographic method, offers matrix-based encryption, while Advanced Encryption Standard (AES) is known for its high level of security and efficiency. By combining Hill Cipher and AES, encryption systems can leverage the strengths of classic and modern cryptography together, providing an additional layer of protection that strengthens the security of digital data and reduces vulnerabilities that may exist in each method separately. This approach provides a more comprehensive solution for maintaining the confidentiality of digital images in the context of evolving security threats.
Penggunaan Metode Logika Fuzzy Mamdani untuk Menentukan Potensi Bakat dan Keterampilan Siswa Br Sitepu, Kristina; Sitompul, Melda Pita Uli
JUKI : Jurnal Komputer dan Informatika Vol. 6 No. 2 (2024): JUKI : Jurnal Komputer dan Informatika, Edisi Nopember 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Educational management in the implementation of the educational process in high schools wants its graduates to get jobs or continue their studies later according to their abilities. But in reality it is not as beautiful as expected, some alumni students who continue their studies to college drop out of their studies because the majors they take at college do not match the interests and talents of the students or do not match the abilities of the students, so that it is very important to find out the intelligence, interests and talents of the students early so as not to be late in recognizing and developing the potential of the students based on the intelligence, interests and talents of each student. This study aims to identify talents that are more dominant than the skills possessed by students by calculating the Fuzzy Logic method which can help students determine majors related to their talents after graduating from school, so that it can reduce cases of wrong majors faced by students after determining their majors at college. The problem solving used in this study uses the Fuzzy Logic method with the aim of determining the most dominant skill value of a student against the criteria of Sports, Language, Communication, Writing, and Singing based on alternative skills of Physical Fitness, Music, Social, Art, and Leadership. This research will produce the best rule that is expected to be used as a Decision Support System in determining talent based on student skills that can be used as a recommendation to determine the major to be chosen in college. The results obtained in this study are to determine the most appropriate rule and 5 rules are obtained for the application of Fuzzy Logic to determine the most dominant talent from student skills.
Rancang Bangun Pengembangan Robot Pembersih Sampah Berbasis Internet of Thing (IOT) Untuk Pemantauan dan Pengontrolan Jarak Jauh. MHD Micho Januar Prananta; Akim Manaor Hara Pardede; Melda Pita Uli Sitompul
Repeater : Publikasi Teknik Informatika dan Jaringan Vol. 3 No. 2 (2025): April: Repeater : Publikasi Teknik Informatika dan Jaringan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/repeater.v3i2.407

Abstract

The increasing waste problem requires innovative solutions that are efficient and sustainable. This study aims to design and build an Internet of Things (IoT) based garbage cleaning robot that can be monitored and controlled remotely. This system is designed by utilizing a microcontroller as the main brain, sensors to detect the presence of garbage, and an IoT-based communication module that allows monitoring and control of the robot via mobile devices or the web. Based on the results of the analysis and testing carried out, this study shows that the use of ESP8266 in the RC Trans Robot motor control with the Blynk application has succeeded in significantly increasing system efficiency. The system successfully responds to user input via a mobile application and can control the movement of the robot in real-time. The performance of the robot system controlled via a WiFi network shows good stability in various test scenarios. The robot can operate effectively within a distance that matches the range of the WiFi network, with fast control response and reliable communication.
OPTIMASI PENJADWALAN MATA KULIAH DENGAN MENGGUNAKAN PSO Simanjuntak, Magdalena; Sitompul, Melda Pita Uli; Juliana Naftali Sitompul; Kahfi Lanang; Rahimah Faizah
Jurnal Mahajana Informasi Vol 10 No 1 (2025): JURNAL MAHAJANA INFORMASI
Publisher : Universitas Sari Mutiara Indonesia Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51544/jurnalmi.v10i1.6062

Abstract

Penjadwalan mata kuliah merupakan masalah kompleks yang sering dihadapi oleh institusi pendidikan tinggi. Ketidakefisienan dalam penjadwalan dapat mengakibatkan konflik jadwal, pemanfaatan ruang yang tidak optimal, serta ketidakpuasan dosen dan mahasiswa. Oleh karena itu, diperlukan metode optimasi yang efektif untuk menghasilkan jadwal yang optimal dan efisien. Penelitian ini bertujuan untuk mengembangkan dan mengimplementasikan algoritma Particle Swarm Optimization (PSO) untuk mengoptimalkan penjadwalan mata kuliah. PSO dipilih karena kemampuannya dalam menangani masalah optimasi dengan ruang solusi yang besar dan kompleks. Algoritma ini diharapkan dapat menghasilkan jadwal yang meminimalkan konflik, mengoptimalkan penggunaan ruang kelas, serta memperhitungkan preferensi dosen dan mahasiswa. Penelitian ini menggunakan algoritma PSO untuk mencari solusi optimal dalam penjadwalan mata kuliah. Langkah-langkah dalam optimasi penjadwalan meliputi: Membentuk populasi partikel yang mewakili solusi potensial, Menetapkan jumlah partikel, kecepatan awal, koefisien kecepatan (c1, c2), dan faktor inersia, Mengembangkan fungsi tujuan yang mengevaluasi kualitas setiap solusi berdasarkan kriteria minimisasi konflik, optimalisasi penggunaan ruang, dan preferensi dosen serta mahasiswa, Memperbarui posisi dan kecepatan partikel berdasarkan rumus PSO, Mengevaluasi solusi baru, memperbarui pbest dan gbest berdasarkan hasil evaluasi, Menentukan kriteria konvergensi untuk mengakhiri iterasi algoritma. Dengan hasil penelitian ini, diharapkan dapat memberikan solusi yang praktis dan efektif bagi institusi pendidikan tinggi dalam mengelola penjadwalan mata kuliah, sehingga meningkatkan kualitas proses belajar mengajar.
Analisis Kerusakan pada Beton dengan Citra Digital Menggunakan Metode Edge Canny Detection M. Naufal Syahputra; Achmad Fauzi; Melda Pita Uli Sitompul
Neptunus: Jurnal Ilmu Komputer Dan Teknologi Informasi Vol. 3 No. 3 (2025): Agustus : Neptunus : Jurnal Ilmu Komputer Dan Teknologi Informasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/neptunus.v3i3.1047

Abstract

This study aims to design and implement a damage analysis system for concrete surfaces by utilizing digital image processing based on the Canny edge detection method. The developed system allows users to upload images of concrete surfaces, which are then processed through several stages: conversion to grayscale, transformation to binary images, and crack edge detection using the Canny operator. This process aims to automatically detect crack patterns on the concrete surface. The detection results, represented as edge lines, are used to calculate the percentage of the damaged area. Based on this percentage value, the system automatically classifies the damage level into light, moderate, or severe categories. System testing shows that the Canny method can accurately identify crack patterns, with sufficient detection levels to be used in monitoring the condition of concrete surfaces. The analysis results are then presented in both visual and numerical forms, providing valuable information for assessing the structural condition of concrete. Thus, this system can serve as an efficient and effective tool for early detection of structural damage in concrete infrastructure, ultimately supporting better maintenance and repair efforts.
Penerapan Sistem Pendukung Keputusan Dengan Metode Fuzzy AHP Untuk Penentuan Kriteria Prioritas Pelayanan Dikementrian Agama Kota Binjai Diana Lestari Simamora; Akim Manaor Hara Pardede; Melda Pita Uli Sitompul
Indonesian Journal of Science, Technology and Humanities Vol. 3 No. 2 (2025): IJSTECH - October 2025
Publisher : PT. INOVASI TEKNOLOGI KOMPUTER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60076/ijstech.v3i2.1555

Abstract

Penelitian ini bertujuan untuk menerapkan Sistem Pendukung Keputusan (SPK) dengan metode Fuzzy Analytical Hierarchy Process (F-AHP) untuk menentukan prioritas pelayanan di Kementerian Agama Kota Binjai. Metode F-AHP digunakan untuk mengatasi ketidakpastian dan subjektivitas dalam pengambilan keputusan multi-kriteria. Kriteria yang digunakan meliputi: Tingkat Kebutuhan Masyarakat, Dampak Sosial, Aksesibilitas Pelayanan, Kesiapan Sumber Daya, dan Dukungan Kebijakan/Regulasi. Hasil penelitian menunjukkan bahwa Tingkat Kebutuhan Masyarakat merupakan kriteria paling dominan dengan bobot 1,0. Dari sepuluh alternatif pelayanan, Fasilitasi Perayaan Hari Besar Agama Non-Muslim dan Penyusunan Kurikulum Pendidikan Agama Non-Muslim di Sekolah memperoleh skor tertinggi (5,0), sedangkan Pengadaan Buku & Media Ajar Agama Non-Muslim memiliki skor terendah (1,0). Sistem yang dibangun menggunakan PHP dan MySQL mampu menghasilkan perangkingan yang objektif dan terstruktur, sehingga dapat mendukung pengambilan keputusan yang lebih akurat dan konsisten