Claim Missing Document
Check
Articles

Found 33 Documents
Search

Pengelompokkan Data Pembelian Tinta Dengan Menggunakan Metode K-Means Susliansyah, Susliansyah; Sumarno, Heny; Priyono, Hendro; Hikmah, Noer
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 3, No 2 (2019): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (641.686 KB) | DOI: 10.30645/j-sakti.v3i2.156

Abstract

PT. Mayer Indah Indonesia is engaged in the production of goods, where the most important part to prepare the needs for production needs is the purchasing department, but in the purchasing section it is difficult to determine which items must be bought a lot, are and few in meeting the demand requirements of each part because of the needs goods for production are very unpredictable, eventually causing some goods demand not to be fulfilled because the goods are out of stock. To solve the problems experienced by the purchasing part, datamining using clustering algorithm is k-means method, where the initial stages determine the centroid randomly and do the first iteration calculation and determine the new centroid from the first iteration, then the second iteration calculation is done, because the results of the first and second iterations in the smallest layout of the three groups, the calculation stops. The results obtained by using the ink purchase data seen from the three attributes of incoming goods, items purchased and stock of goods, making it easier and help the purchasing department in classifying items that must be purchased a lot, medium and little.
Perancangan Program Peminjaman Dan Pengembalian Buku Pada Perpustakaan (Studi Kasus Smp Pgri 1 Cibinong) Sarita, Nur; Aria, Ririn Restu; Susliansyah, Susliansyah
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 2 (2017): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (804.303 KB) | DOI: 10.30645/j-sakti.v1i2.45

Abstract

The library is one of absolute means that must be owned by a school because students can get more science and knowledge without having to buy a book of its own. Now an interest read the students also had the higher it should be supported by the school.Library of PGRI 1 Junior High School in Cibinong need once the existence of an application program library that support and provide satisfactory service for the students in the process of borrowing and the return on the book. For that is the writer trying to make final assignment regarding the design of the program and the repayment of loan book at the library of the PGRI 1 Junior High School in Cibinong which is still done manually, starting from the processing of the data members of the data processing, book loaning, transaction processing, transaction processing, and returns to the making of reports, thus allowing the process to take place at the time the error occurred in the logging, less akuratnya the report is made and the delay in the search for the required data. The design of the program is the best solution to solve the problems that exist in the library, as well as with the design of the program can be reached by an activity which is effective and efficient in supporting activities at the library. Then this in the design of the program better than the manual systems to run more effectively and efficiently as well as lending system and return books that are now more conducive than with the previous system.
Aplikasi Monitoring Proses Distribusi Makanan Beku Untuk Informasi Secara Realtime Susliansyah, Susliansyah; Handayanna, Frisma
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 2, No 1 (2018): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v2i1.49

Abstract

The control of frozen food distribution process done by the logistic part in obtaining the data is still manual, using the form and excel, causing the admin difficulty in monitoring and controlling the distribution process or the delivery of frozen food to store or outlet. Problem solving is made an application using data collection method and RAD method, where the model of Rapid Application Development (RAD) has business modeling stage using kebutuah application admin and user, data modeling that explains the use of ERD and LRS from the database side, about usecase diagrams and activity diagrams from the application process side, application generation evolves about programming languages in application creation while testing and turnover describes the use of white box testing. The purpose of the application is made to facilitate the related division in processing the data distribution process, monitor and control the distribution process and obtain information distribution process in realtime.
Penerapan Metode Profile Matching pada Pemilihan Guru Terbaik SMK Madani S, Susliansyah; Wijayanti, Annisa Dwi; Sumarno, Heny; Priyono, Hendro; Maulida, Linda
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 4, No 1 (2020): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v4i1.197

Abstract

Depok Madani Vocational School is a Vocational High School consisting of 2 majors namely Light Vehicle Engineering (TKR) and Computer and Network Engineering (TKJ) with 20 teachers as instructors from class X to class XII. The selection of the best teachers is done once a month to motivate the teacher in conducting teaching and learning activities. Schools in making decisions are often influenced by subjectivity and are done manually. Resulting in social jealousy among teachers and inaccurate decision results. Therefore, in assessing the best teachers a decision support system is needed in order to obtain accurate results. Decision Support System methods used in this study is Profile Matching. The method determines the value of weights on each criterion, which is to be present on time, responsibility, dress neatly and politely, participate and contribute, be active and productive, and help fellow teachers, which is followed by a ranking process. The result of the comparison of the two methods above is to produce the same chosen alternative, so that both methods can be applied to help the school's decision making.
Rekomendasi Pemilihan Mitra Kerja Proyek Dengan Menggunakan Metode Electre Pada Perusahaan Industri Susliansyah, S; Kusnadi, Yahdi; Irfiani, Eni; Indriyani, Fintri
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v5i1.340

Abstract

Industrial companies, which are one of the players in the economy, are currently experiencing increasingly fast and rapid competition in industrial development. Industrial companies in selecting partners are still using the conventional way of recording partner data and assessing each partner, but some of these records are missing, making it difficult for the company to choose which one has a good performance. In addition, the company still applies subjective methods, namely based on the experience of being partners and being close to people who have power, in the end the company is unable to recommend which partners to accept or which are not accepted. The method that will be used to solve problems is by using the ELECTRE method, which has seven stages, namely Normalization of the Decision Matrix, Weighting the Normalized Matrix, Determining Concordance and Discordance Sets on the Index, Calculating Concordance and Discordance Matrices, Calculating Dominant Concordance and Discordance Matrices, Determine, Aggregate Dominance Matrix and Elimination of Less Favorable Alternatives. The results show that A2, A8 and A4 are the best alternatives from the other 12 alternatives. While the lowest alternatives are A1, A3, A5, A6, A7, A9, A10, A11 and A12.
Pengelompokkan Data Pembelian Tinta Dengan Menggunakan Metode K-Means Susliansyah, Susliansyah; Sumarno, Heny; Priyono, Hendro; Hikmah, Noer
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 3, No 2 (2019): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v3i2.156

Abstract

PT. Mayer Indah Indonesia is engaged in the production of goods, where the most important part to prepare the needs for production needs is the purchasing department, but in the purchasing section it is difficult to determine which items must be bought a lot, are and few in meeting the demand requirements of each part because of the needs goods for production are very unpredictable, eventually causing some goods demand not to be fulfilled because the goods are out of stock. To solve the problems experienced by the purchasing part, datamining using clustering algorithm is k-means method, where the initial stages determine the centroid randomly and do the first iteration calculation and determine the new centroid from the first iteration, then the second iteration calculation is done, because the results of the first and second iterations in the smallest layout of the three groups, the calculation stops. The results obtained by using the ink purchase data seen from the three attributes of incoming goods, items purchased and stock of goods, making it easier and help the purchasing department in classifying items that must be purchased a lot, medium and little.
USE OF UI/X ON WEBSITE RECOMMENDATION OF LAPTOP SPECIFICATIONS WITH K-MEANS ALGORITHM Susliansyah, Susliansyah; Sumarno, Heny; Priyono, Hendro; Maulida, Linda; Indriyani, Fintri
J-Icon : Jurnal Komputer dan Informatika Vol 13 No 1 (2025): March 2025
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v13i1.20552

Abstract

The process of choosing a laptop that suits their needs is often a challenge for consumers because of the variety of specifications and features offered. Many consumers find it difficult to make the right choice, especially because the information available is often not well structured. In addition, each individual's needs vary, ranging from use for daily productivity to special needs such as gaming or graphic design. Therefore, this study aims to develop a prototype design of a laptop recommendation system using the K-Means clustering algorithm, which is able to group laptop specification data into certain clusters based on the similarity of features. A total of 25 laptop specification data were used in this analysis, with the main parameters being RAM capacity and SSD capacity. The data was processed using the data mining method, and the K-Means algorithm was applied to perform grouping. The optimal number of clusters is determined using the elbow method to ensure accurate and relevant results. The results of the grouping show that laptops can be classified into specific groups that represent consumer needs, such as use for daily productivity or high-load work. The prototype design of this system was created using Figma to visualize an intuitive and easy-to-use user interface (UI). With this prototype design, it is hoped that it can be a reference in the development of a system that makes it easier for consumers to choose a laptop that suits their preferences and needs.
IMPLEMENTASI METODE K-MEANS UNTUK PENGELOMPOKKAN KATA BERINDIKASI CYBERBULLYING PADA KOMENTAR TIKTOK Syawal, Muhamad Akmal; Rayhan, Cahya Muhammad; Pradhana, Bintang Arfiandi; Richardo, Yusuf Jordi; Rizal, Khairul; Susliansyah, Susliansyah
Journal of Information System, Informatics and Computing Vol 9 No 2 (2025): JISICOM (December 2025)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisicom.v9i2.2163

Abstract

Perkembangan pesat media sosial seperti TikTok membawa peningkatan kasus cyberbullying yang berdampak negatif pada korban, termasuk tekanan mental. Penelitian ini bertujuan mengimplementasikan metode clustering sebagai pendekatan pembelajaran tanpa pengawasan untuk mengelompokkan kata-kata indikasi cyberbullying dalam komentar TikTok. Dataset komentar TikTok diolah melalui pra-pemrosesan teks seperti tokenisasi dan normalisasi. Metode clustering digunakan untuk mengelompokkan komentar berdasarkan kemiripan pola kata tanpa memerlukan data berlabel. Hasil pengelompokan mengidentifikasi pola kata konsisten yang menjadi indikasi cyberbullying, mendukung deteksi otomatis tindakan bullying di media sosial. Penelitian ini menyimpulkan bahwa pendekatan clustering efektif dalam mengenali ciri cyberbullying dan direkomendasikan untuk pengembangan sistem moderasi konten di TikTok guna mengurangi dampak negatif cyberbullying.
Sistem Deteksi Warna Real-Time untuk Aksesibilitas Penderita Buta Warna Marbun, Stephanie Rotua Uli; Rizal, Khairul; Susliansyah, Susliansyah; Hidayat, Rahmat
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 4 No. 4 (2026): November - January
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v4i4.5155

Abstract

Penelitian ini mengembangkan sistem deteksi warna real-time berbasis computer vision yang bertujuan untuk mendukung aksesibilitas bagi penderita buta warna dalam mengenali warna objek secara cepat dan akurat. Warna merupakan elemen penting dalam penyampaian informasi visual, namun keterbatasan persepsi warna dapat menyebabkan kesalahan interpretasi pada aktivitas sehari-hari. Oleh karena itu, diperlukan solusi berbasis teknologi yang mampu membantu pengguna dalam mengidentifikasi warna secara mandiri melalui perangkat mobile. Sistem yang dikembangkan mengintegrasikan model deteksi objek YOLOv11 dengan metode klasifikasi warna menggunakan OpenCV berbasis ruang warna HSV. Dataset yang digunakan merupakan data primer yang dikumpulkan secara mandiri melalui pengambilan citra objek berwarna pink, hijau, dan kuning dengan variasi kondisi pencahayaan, jarak, dan sudut pengambilan. Tahapan penelitian meliputi pengumpulan data, preprocessing citra, pelatihan model, integrasi sistem ke aplikasi Android, serta evaluasi performa. Hasil pengujian menunjukkan bahwa sistem mampu mendeteksi dan mengklasifikasikan warna secara real-time dengan tingkat akurasi rata-rata sebesar 92% dan waktu respons di bawah 0,5 detik per frame. Implementasi pada aplikasi Android menunjukkan performa yang stabil pada kondisi pencahayaan normal dan latar belakang yang bervariasi. Dengan demikian, penelitian ini membuktikan bahwa pemanfaatan teknologi deep learning dan pengolahan citra digital dapat memberikan solusi praktis dan efektif dalam meningkatkan aksesibilitas bagi penderita buta warna serta berpotensi dikembangkan lebih lanjut pada skala penggunaan yang lebih luas.
Rancangan Aplikasi Algoritma C4.5 pada Stunting Balita Menggunakan Bahasa Phyton Susliansyah Susliansyah; Sigit Yugi Wargiyo; Heny Sumarno; Hendro Priyono; Linda Maulida
REMIK: Riset dan E-Jurnal Manajemen Informatika Komputer Vol. 9 No. 1 (2025): Volume 9 Nomor 1 Januari 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/remik.v9i1.14426

Abstract

Stunting pada balita merupakan salah satu masalah kesehatan serius di Indonesia, yang memengaruhi pertumbuhan fisik dan kognitif anak. Dalam upaya memahami dan memprediksi faktor-faktor risiko yang berkaitan dengan stunting pada balita, digunakan teknologi data mining. Penelitian ini bertujuan mengembangkan aplikasi berbasis algoritma C4.5 untuk memprediksi status gizi balita, menggunakan bahasa pemrograman Python dan aplikasi Orange. Data yang berasal dari dataset "Stunting Toddler Detection" di Kaggle, dengan fokus pada variabel umur, tinggi badan, dan status gizi. Data tersebut digunakan sebagai bahan analisis, dengan tahapan preprocessing, integrasi data, hingga penerapan algoritma C4.5. Metode penelitian melibatkan pengolahan data menggunakan Python untuk analisis awal, sementara Orange dimanfaatkan untuk membangun pohon keputusan dan evaluasi model. Hasil pengujian menunjukkan algoritma C4.5 menghasilkan akurasi sebesar 36% di Orange dan 40% di Python, dengan faktor utama yang memengaruhi status gizi balita adalah tinggi badan. Aplikasi yang dikembangkan juga dilengkapi antarmuka visual untuk mempermudah tenaga kesehatan dan pemangku kebijakan dalam menganalisis risiko stunting.