Decision support system
Expert system
Image processing
Data Mining
10
Scopus Publications
867
Scholar Citations
16
Scholar h-index
23
Scholar i10-index
Scopus Publications
DEVELOPMENT OF COST-SENSITIVE ARTIFICIAL NEURAL NETWORK OPTIMIZATION IN SOLVING IMBALANCED MULTICLASS CLASSIFICATION PROBLEMS Bosker Sinaga, Yuhandri Yuhandri, Gunadi Widi Nurcahyo Eastern European Journal of Enterprise Technologies, 2026 The object of the study is the classification process of imbalanced multi-class data in air quality analysis based on the air pollution standard index (ISPU), which involves numerical environmental features and categorical output classes. This study addresses the problem of imbalanced multi-class classification in air quality data based on the air pollution standard index (ISPU), where conventional classification techniques tend to be biased toward majority classes and fail to accurately identify minority classes. To overcome this limitation, a cost-sensitive learning strategy combined with adaptive error weighting, grid search with k-fold cross-validation, and principal component analysis (PCA) is applied. The dataset consists of 1,147 samples with an imbalanced distribution across three classes. The results demonstrate that the proposed method achieves an accuracy and F1-score of 98.55% and an area under the ROC curve (AUC) of 0.999, while significantly improving minority class sensitivity. This performance is explained by the cost-sensitive method that increases the penalty for minority class errors and by PCA, which enhances feature representation and learning stability. Compared to existing methods, the proposed method provides a more balanced and robust classification performance without modifying the original data distribution. This method can be effectively applied to ISPU-based air quality classification results and other imbalanced multi-class classification problems, although it requires careful parameter optimization for different data characteristics.
Expert System to Diagnose Dental and Oral Disease Using Naive Bayes Method Jonson Manurung, Yuda Perwira, Bosker Sinaga Icosnikom 2022 2022 IEEE International Conference of Computer Science and Information Technology Boundary Free Preparing Indonesia for Metaverse Society, 2022 The high cost of consulting and checking teeth or mouth makes residents reluctant to go to the doctor. In order to facilitate the consultation, a system is needed that can predict the dental and oral diseases that he is suffering from without having to go to the doctor for consultation on the disease. An expert system is a system that transmits human knowledge to a computer, so that computers can solve problems such as those that are usually tried by experts. Experts defined here are people who have special abilities who can solve problems that ordinary people cannot solve. Research on dental and oral disease expert systems for the manufacture of this expert system used the Naive Bayes method. The decision to diagnose dental and oral disease is carried out through a consultation process between the system and the user, If the answers entered match the applicable regulations, then the system will share the results of the diagnosis of dental and oral diseases that he suffers from. We recommend that the procedures for collecting data in conducting this research are: interviews and literature review. In making this expert system using the Naive Bayes method, it is hoped that it can help residents identify diseases, or share solutions to problems with their teeth and mouth without going to the doctor first.
Development Of Scholarship Sustainability Analysis Application Every Semester On STMIK Pelita Nusantara Students Nera Mayana Br Tarigan, Bosker Sinaga, Erwin Panggabean, Jijon Raphita Sagala Icosnikom 2022 2022 IEEE International Conference of Computer Science and Information Technology Boundary Free Preparing Indonesia for Metaverse Society, 2022 Decision making in an organization is needed a system. Decision support system is a system that helps company management and education in decision making that provides information, modeling and analyzing data with the application of a method. The management, especially higher education, must maximize sophisticated technology. For example, to analyze scholarship data. Problems are found in manual data analysis so that human errors often occur in addition to using more time than the target, losing old data, resulting in inaccurate analysis of scholarship sustainability every semester. The research was conducted to overcome the problems that have been found by analyzing the existing data with the simple additive weighting method, building a system by applying the method and testing the system. The result of this research is to produce an application for the development of a decision support system in managing student data to determine the sustainability of the scholarship every semester. Applications that are built can help the management in managing scholarships.
Decision Support System for Employee Performance Using AHP Method (Case Study: PT. Andhy Putra) Bedizatulo Laia, Bosker Sinaga International Journal of Basic and Applied Science, 2021 The system supports the company's performance appraisal using the AHP (Case Study: PT. Andhy Putra) method, one of which is to find, select, assess and determine the best employees every year to match the abilities and assessment criteria applied so far. PT. Andhy Putra while assessing employee performance, especially in CME and OSP, still experiences shortcomings and weaknesses in determining qualified employees. This employee performance system has problems in assessing the performance appraisal data that is less accurate, which is carried out on a paper-based basis and requires less efficient time and large costs. For that, we need a decision support system in helping PT. Andhy Putra to conduct a performance appraisal every year. The method used in this employee assessment is AHP (Analytical Hierarchy Process), which is often also known as the weighting method. The process hierarchy analytical method is one of the methods used to find weight values based on existing criteria and helps facilitate the ranking of alternatives based on the distance between the positive ideal solution and the negative ideal solution. There are 5 (five) criteria as a tool to assess employee performance, namely commitment to the company, desire for achievement, cooperation, leadership and discipline accompanied by the results of the implementation of this process hierarchy method in the form of ranking the alternatives used. This decision support system is built using the PHP programming language and MySQL database
Big data technology for village status classification based on village index building involving k-means algorithm in programs to support the work of the ministry of the village Journal of Theoretical and Applied Information Technology, 2021
Review the Utilization of Big Data and K-Means Algorithm in Supporting the Determination of Village Status As Support to the Ministry of Village PDTT Paska Marto Hasugian, Harvei Desmon Hutahaean, Bosker Sinaga, Sriadhi, Saronom Silaban Journal of Physics Conference Series, 2021 Abstract Big data refers to big data, fast data processing, diversity of data structures, and data values so that it is not possible to be processed with outdated methods. Big data technology is used in various industrial sectors. Big data technology is the whole technology that can handle Big Data. Some of the uses of big data are based on the largest significant data traffic sources such as social media, financial transactions, public data, sensor data, and corporate data. The same is the case with the status of so many villages in Indonesia, so it is better to use big data for the classification of village status based on the village index build by involving an algorithm process. This research aims to produce a description of the role of big data in supporting activities in a grouping. The method used is a qualitative approach related to data collection based on scientific work with the source of data information needed to study literature techniques from various studies that have been published in national and international journals. A decision is made that big data has been widely used in different circles to facilitate performance and speed up the decision-making process.
Design of big data technology prototype for classification of village status based on village development index involves k-means algorithm to support village ministry Pdtt work programs Paska Marto Hasugian, Harvei Desmon Hutahaean, Bosker Sinaga, Sriadhi, Saronom Silaban Journal of Physics Conference Series, 2021 Abstract Big data technology is the overall technology that can handle the processing associated with analyzing the data to explore the potential that is in it. Some of the uses of big data are based on the biggest data traffic sources, such as social media, financial transactions, public data, censorship data, and company data. The problem found in the accumulation of village status data that has not been utilized in the decision-making process to determine the status of the next village and the absence of an application to process the data stored in the data database so that a tool is developed to analyze the buildup. The results of this study are to produce a prototype design that is Unified Modeling Language (UML) design, Form Design, and Database Design that will be used to develop Big Data Technology in determining the classification of village status based on the Village Build index.
Villages Status Classification Analysis Involving K-Means Algorithm to Support Kementerian Desa Pembangunan Daerah Tertinggal dan Transmigrasi Work Programs Paska Marto Hasugian, Harvei Desmon Hutahaean, Bosker Sinaga, Sriadhi, Saranom Silaban Journal of Physics Conference Series, 2020 Abstract Data mining is a technique of extracting information that has not been known before in a collection of data in the database. Data mining has been applied in various fields that require extracting information, some of the work that can be generated with data mining is classification, prediction, and data grouping. In this study, an analysis of village data collection was carried out to explore the potential or knowledge of the data that has been presented with the main objective of producing a grouping of village status. To support clustering or grouping activities the K-means algorithm used with the general process is to carry out the modeling process without supervision and is one of the methods for grouping data with a system partition, with the principle of allocating each data to the centroid or the closest average, work steps conducted in support of this research is to collect data related to the analysis of data grouping and proceed with the calculation process in accordance with the work steps of the K-means algorithm, the amount of data used as a test of 303 villages scattered in the old Padang regency. The results of calculations by displaying a new group of Cluster 0 is occupied by 120 villages, cluster 1 with a total data of 123 villages, Cluster 2 with a total of 6 villages, cluster 3 with a total of 33 villages while cluster 4 with a total of 21.
Effective methods of pyridoxine supplementation in laying hens to albumin and globulin levels S. Silaban, B. Sinaga, M. Damanik, P. M. Silitonga Rasayan Journal of Chemistry, 2020 This research investigates the effective methods of pyridoxine supplementation to enhance the protein (albumin and globulin) level of chicken egg. 12 laying hens that been ready to produce eggs were categorized into three groups based on pyridoxine supplementation methods (via drinking water, ration, and intravenous injection). Each group received supplementation pyridoxine treatment with dosage of 3 mg/kg ransoms for 68 days. The albumin and globulin levels were analyzed using Folin’s Fenol technique and compared to the standard egg. We found that only albumin level could be enhanced. The intravenous injection was the most effective method to significantly increase the albumin levels compared.
Implementation of Apriori Algorithm for Analysis of Consumer Purchase Patterns Suprianto Panjaitan, Sulindawaty, Muhammad Amin, Sri Lindawati, Ronal Watrianthos, Hengki Tamando Sihotang, Bosker Sinaga Journal of Physics Conference Series, 2019 Abstract Consumer purchasing patterns are a form of purchases made by consumers, whether someone or a lot of people to get the desired item by making a purchase transaction. One characteristic of the purchase pattern is the existence of acquiring something through exchanging money. This study aims to create an application that is used in determining consumer purchasing patterns by applying a priori algorithms and using Visual Basic 2010 as a tool for determining consumer purchase patterns. This application uses a priori algorithm calculation method where the sample consumer purchase data will be sorted and calculated by providing the value of the minium support and configuration parameters and based on the results of confidence the largest number of conclusions such as: can be used as information for determining sales, the application of a priori algorithms can provide information pattern combination item set from consumer purchase data that is with support above 15% and confidence above 50% on item set.
RECENT SCHOLAR PUBLICATIONS
Crop Yield Prediction Using Artificial Neural Network with Principal Component Analysis Dimensionality Reduction B Sinaga, AML Harefa, A Pandia, A Alfarezi Jurnal Sistem Informasi dan Teknologi Jaringan 7 (1), 28-34 , 2026 2026
Multivariate Data Analysis for Customer Segmentation Using Principal Component Analysis and K-Means Clustering B Sinaga, AML Harefa Proceeding of International Conference on Business, Economics, Finance and … , 2025 2025 Citations: 3
Pengenalan dan Implementasi Teknologi Cloud Computing untuk Optimalisasi Manajemen Data B Sinaga, JR Sagala, NMB Tarigan, AML Harefa Jurnal Pengabdian Kepada Masyarakat Teknologi Informasi dan Komunikasi 2 (3 … , 2025 2025 Citations: 1
Implementasi Metode Thresholding Dalam Mengenali Bentuk Citra Buah Salak P Marpaung, M Jannah, B Sinaga Jurnal Media Informatika 6 (3), 2227-2235 , 2025 2025
Prediksi Kebutuhan Barang Laris Dan Meminimalisir Barang Expired Dengan Algoritma Apriori Pada Pt. Sumber Trijaya Lestari Cabang Lubuk Pakam A Tarigan, B Sinaga Journal Data Science Penusa (JDSP) 2 (2), 741-747 , 2025 2025
PKM Pembuatan Dan Pelatihan Aplikasi Pemilihan Bibit Lele Terbaik NMB Tarigan, EB Barus, B Sinaga, AA Sembiring, NS Siregar ULEAD: Jurnal E-Pengabdian, 96-104 , 2025 2025
Penerapan Metode Multiple Linier Regression Untuk Memprediksi Stok Sepeda Motor Pada PT. Indako Trading Coy SK Halawa, B Sinaga Jurnal Sistem Informasi dan Teknologi Jaringan 6 (1), 6-12 , 2025 2025
Penerapan Metode Profile Matching Dalam Menentukan Siswa Yang Layak Mendapatkan Beasiswa (Studi Kasus: Smk Swasta Jaya Krama) J Juanda, B Sinaga Journal Data Science Penusa (JDSP) 2 (1), 363-369 , 2025 2025
Implementasi Data Mining Dalam Prediksi Like Comment View Media Sosial Instagram Pemkab Deli Serdang Menggunakan Metode K-Nearest Neighbor (K-Nn) HN Hasugian, B Sinaga Journal Data Science Penusa (JDSP) 2 (1), 221-231 , 2025 2025
Performance Analysis of Ujung Serdang Village Office Employees Using the Multi Factor Evaluation Process Method NMB Tarigan, B Sinaga, NS Siregar, D Parastia Jurnal Multimedia dan Teknologi Informasi (Jatilima) 7 (01), 93-102 , 2025 2025
Analysis of Detergent Inventory Stock at Luch Laundry Using the Linear Regression Method B Sinaga, NMB Tarigan, R Marpaung, KR Zamili Journal of Computer Networks, Architecture and High Performance Computing 7 … , 2025 2025
PENERAPAN METODE CSI (CUSTOMER SATISFACTION INDEX) UNTUK MENGUKUR TINGKAT KEPUASAN KLIEN TERHADAP PT. CAREFASTINDO K Lahagu, B Sinaga Journal Data Science Penusa (JDSP) 1 (2), 628-635 , 2024 2024
Penerapan Data Mining Untuk Menganalisa Penjualan Barang Pada Utama Jaya Komputer Menggunakan Algoritma Apriori D Andrian, B Sinaga Journal Data Science Penusa (JDSP) 1 (2), 585-596 , 2024 2024
Penerapan Metode Profile Matching Dalam Menentukan Penempatan Karyawan Baru Di Pdam Tirta Deli AH Affandy, B Sinaga Journal Data Science Penusa (JDSP) 1 (2), 1006-1015 , 2024 2024
SISTEM PENDUKUNG KEPUTUSAN PENETUAN PENERIMA KIP KULIAH DENGAN METODE WEIGHTED PRODUCT (STUDI KASUS STMIK PELITA NUSANTARA) F Ginting, B Sinaga Journal Data Science Penusa (JDSP) 1 (2), 740-751 , 2024 2024
Penerapan Metode Multiple Linier Regression Untuk Memprediksi Stok Sepeda Motor Pada PT. Indako Trading Coy SK Halawa Journal Data Science Penusa (JDSP) 1 (1), 318-329 , 2024 2024
Penerapan Metode MOORA Dalam Pemilihan Bibit Lele Terbaik NMB Tarigan, B Sinaga, R Amelia, Y Krisswanti Jurnal Media Informatika 5 (3), 161-169 , 2024 2024
Penerapan Metode Smart Dalam Pemilihan Ketua RT Pada Desa Sei Mencirim B Sinaga, NMB Tarigan, ES Simamora, H Hasanah Jurnal Media Informatika 5 (3), 170-177 , 2024 2024 Citations: 1
PKM PEMBUATAN APLIKASI DAN PELATIHANPENGGUNAAN APLIKASI PENILAIAN KINERJA GURU SMK 2 DELIMA SARI TIGA JUHAR EB Tarigan, NMB Tarigan, B Sinaga, ES Simamora Jurnal Pengabdian Kepada Masyarakat Bersinergi Inovatif 2 (1), 330-337 , 2024 2024
PKM Pembangunan Website Desa Ujung Serdang B Sinaga, NMB Tarigan, M Marpaung, FWB Ginting, O Tumangger Jurnal Pengabdian Kepada Masyarakat Pelita Nusantara 2 (2), 52-57 , 2024 2024
MOST CITED SCHOLAR PUBLICATIONS
Buku Ajar Sistem Pendukung Keputusan Penilaian Hasil Belajar Dengan Metode Topsis M Marbun, B Sinaga Medan: CV. Rudang Mayang , 2018 2018 Citations: 116
Implementation of apriori algorithm for analysis of consumer purchase patterns S Panjaitan, Sulindawaty, M Amin, S Lindawati, R Watrianthos, ... Journal of Physics: Conference Series 1255 (1), 012057 , 2019 2019 Citations: 62
Fuzzy Multiple Attribute Decisison Macking Dengan Metode Oreste Untuk Menentukan Lokasi Promosi FA Sianturi, B Sinaga, PM Hasugian, T Informatika, S Utara Journal Of Informatic Pelita Nusantara 3 (1), 63-68 , 2018 2018 Citations: 49
Penerapan Metode MOORA pada Sistem Pendukung Keputusan untuk Menentukan Siswa Penerima Bantuan Miskin T Shabrina, B Sinaga Jurnal Ilmu Komputer dan Bisnis 12 (2a), 161-172 , 2021 2021 Citations: 47
Sistem Pakar Mendiagnosa Kerusakansmartphone Android Menggunakan Metode Certainty Factor B Sinaga, PM Hasugian, AM Manurung Journal Of Informatic Pelita Nusantara 3 (1) , 2018 2018 Citations: 38
Sistem Pendukung Keputusan Siswa Berprestasi Menggunakan Metode Analytic Hierarchy Process (AHP) Pada SMK Singosari Delitua B Sinaga, HM Zabua Jurnal Mantik Penusa 16 (2), 1-11 , 2014 2014 Citations: 34
Sistem Pendukung Keputusan Penilaian Hasil Belajar Mahasiswa Dengan Metode Topsis Di STMIK Pelita Nusantara Medan M Marbun, B Sinaga Jurnal Mantik Penusa 1 (2), 9-15 , 2017 2017 Citations: 31
Buku Ajar Sistem Pendukung Keputusan Penilaian Hasil Belajar| 1 STMIK Pelita Nusantara Medan M Marbun, B Sinaga Naetty Siahaan and Tince Flora Manurung, Medan, CV. Rudang Mayang , 2018 2018 Citations: 30
Sistem Pendukung Keputusan Penentuan Kesesuaian Lahan Tanaman Cengkeh Dengan Metode Profile Matching DS Simbolon, B Sinaga Jurnal Nasional Komputasi dan Teknologi Informasi 4 (5), 370-376 , 2021 2021 Citations: 29
Analisa Dan Perancangan Aplikasi Algoritma Apriori Untuk Korelasi Penjualan Produk (Studi Kasus: Apotik Diory Farma) HD Hutahaean, B Sinaga, AA Rajagukguk Journal Of Informatic Pelita Nusantara 1 (1) , 2016 2016 Citations: 27
Perancangan Dan Pembuatan Sistem Informasi Forum Diskusi Mahasiswa/I Berbasis Web Di STMIK Pelita Nusantara Medan B Sinaga Jurnal Mantik Penusa 18 (2) , 2015 2015 Citations: 26
Penerapan metode ServQual dalam menentukan tingkat kepuasan masyarakat terhadap pelayanan pengurusan surat izin usaha mikro dan kecil pada Kantor Camat Dolat Rayat Kabupaten Karo J Sembiring, B Sinaga Jurnal Nasional Komputasi Dan Teknologi Informasi 4 (2), 165-170 , 2021 2021 Citations: 25
Best cluster optimization with combination of K-means algorithm and elbow method towards rice production status determination PM Hasugian, B Sinaga, J Manurung, SA Al Hashim International Journal of Artificial Intelligence Research 5 (1) , 2021 2021 Citations: 20
Perancangan Aplikasi Peramalan Penjualan Handphone Dengan Metode Triple Exponential Smoothing B Sinaga, JR Sagala, S Sijabat Jurnal Mantik Penusa 20 (1) , 2016 2016 Citations: 20
Pelatihan Microsoft Office Untuk Guru-Guru Se-Kecamatan Namorambe FA Sianturi, PM Hasugian, B Sinaga Jurnal Pengabdian Kepada Masyarakat Nusantara 1 (1 Maret), 1-7 , 2019 2019 Citations: 17
Deteksi tepi citra dengan metode Laplacian of Gaussian dan metode Canny B Sinaga, J Manurung, MH Silalahi, S Ramen vol 5, 1066-1084 , 2021 2021 Citations: 16
Sistem Pendukung Keputusan Penentuan Dosen Pembimbing Skripsi Menggunakan Metode Profile Matching (Studi Kasus: STMIK Pelita Nusantara Medan) B Sinaga, Y Utami Jurnal Mantik Penusa 2 (2) , 2018 2018 Citations: 16
Sulindawaty, and I B Sinaga Siagian,“Sistem Pendukung Keputusan Pemilihan Asuransi Dengan Metode … , 2017 2017 Citations: 14
Penerapan Algoritma Hill Cipher Dan Least Significant Bit (LSB) Untuk Pengamanan Pesan Pada Citra Digital D Laoli, B Sinaga, ASRM Sinaga JISKA (Jurnal Informatika Sunan Kalijaga) 4 (3), 138-148 , 2020 2020 Citations: 13
Sistem Pakar Mendiagnosa Penyakit Pada Ayam Ternak Menggunakan Metode Certainty Faktor O Nansia, B Sinag Journal Of Informatic Pelita Nusantara 4 (2), 14-18 , 2019 2019 Citations: 13
